Nothing Special   »   [go: up one dir, main page]

You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (390)

Search Parameters:
Keywords = PRISMA image

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
16 pages, 1192 KiB  
Systematic Review
Retinal Displacement Following Vitrectomy for Rhegmatogenous Retinal Detachment: A Systematic Review of Surgical Techniques, Tamponade Agents, and Outcomes
by Paulina Siwik, Tomasz Chudoba and Sławomir Cisiecki
J. Clin. Med. 2025, 14(1), 250; https://doi.org/10.3390/jcm14010250 - 3 Jan 2025
Viewed by 332
Abstract
Background: Rhegmatogenous retinal detachment (RRD) is a severe condition that may lead to permanent vision loss if untreated. Pars plana vitrectomy (PPV) has become a preferred surgical intervention, particularly in complex cases. Objective: Retinal displacement (RD) following PPV for RRD can lead to [...] Read more.
Background: Rhegmatogenous retinal detachment (RRD) is a severe condition that may lead to permanent vision loss if untreated. Pars plana vitrectomy (PPV) has become a preferred surgical intervention, particularly in complex cases. Objective: Retinal displacement (RD) following PPV for RRD can lead to visual distortions and can negatively impact patient quality of life. This review examines surgical techniques, tamponade choices, and postoperative strategies to mitigate displacement risks and their clinical implications. Methods: A systemic review of studies from 2010 to 2024 was conducted using PubMed, MEDLINE, and Ovid. The search included terms such as “retinal displacement, “tamponade agents”, and postoperative positioning”. Inclusion criteria focused on studies addressing PPV outcomes, retinal alignment, and visual distortions. Methodological quality was assessed using PRISMA guidelines. Results: Gas tamponades were associated with lower RD rates compared to silicone oil. Intraoperative use of perfluorocarbon liquid (PFCL) improved retinal stability. Postoperative positioning strategies significantly reduced visual distortions. Conclusions: Surgical and postoperative techniques substantially influence RD risk. Advances in imaging and tamponade agents offer promising avenues to improve patient outcomes and minimize RD. Full article
(This article belongs to the Special Issue Vitreoretinal Diseases: Latest Advance in Diagnosis and Management)
Show Figures

Figure 1

Figure 1
<p>Retinal vessel printings on fundus autofluorescence examination (white arrow).</p>
Full article ">Figure 2
<p>PRISMA 2020 flow diagram.</p>
Full article ">Figure 3
<p>The diagram of primary outcomes with the characteristic of tamponade used [<a href="#B3-jcm-14-00250" class="html-bibr">3</a>,<a href="#B4-jcm-14-00250" class="html-bibr">4</a>,<a href="#B5-jcm-14-00250" class="html-bibr">5</a>,<a href="#B7-jcm-14-00250" class="html-bibr">7</a>,<a href="#B8-jcm-14-00250" class="html-bibr">8</a>,<a href="#B14-jcm-14-00250" class="html-bibr">14</a>,<a href="#B15-jcm-14-00250" class="html-bibr">15</a>,<a href="#B16-jcm-14-00250" class="html-bibr">16</a>,<a href="#B17-jcm-14-00250" class="html-bibr">17</a>,<a href="#B18-jcm-14-00250" class="html-bibr">18</a>,<a href="#B19-jcm-14-00250" class="html-bibr">19</a>].</p>
Full article ">
32 pages, 2920 KiB  
Review
EEG in Education: A Scoping Review of Hardware, Software, and Methodological Aspects
by Christos Orovas, Theodosios Sapounidis, Christina Volioti and Euclid Keramopoulos
Sensors 2025, 25(1), 182; https://doi.org/10.3390/s25010182 - 31 Dec 2024
Viewed by 546
Abstract
Education is an activity that involves great cognitive load for learning, understanding, concentrating, and other high-level cognitive tasks. The use of the electroencephalogram (EEG) and other brain imaging techniques in education has opened the scientific field of neuroeducation. Insights about the brain mechanisms [...] Read more.
Education is an activity that involves great cognitive load for learning, understanding, concentrating, and other high-level cognitive tasks. The use of the electroencephalogram (EEG) and other brain imaging techniques in education has opened the scientific field of neuroeducation. Insights about the brain mechanisms involved in learning and assistance in the evaluation and optimization of education methodologies according to student brain responses is the main target of this field. Being a multidisciplinary field, neuroeducation requires expertise in various fields such as education, neuroinformatics, psychology, cognitive science, and neuroscience. The need for a comprehensive guide where various important issues are presented and examples of their application in neuroeducation research projects are given is apparent. This paper presents an overview of the current hardware and software options, discusses methodological issues, and gives examples of best practices as found in the recent literature. These were selected by applying the PRISMA statement to results returned by searching PubMed, Scopus, and Google Scholar with the keywords “EEG and neuroeducation” for projects published in the last six years (2018–2024). Apart from the basic background knowledge, two research questions regarding methodological aspects (experimental settings and hardware and software used) and the subject of the research and type of information used from the EEG signals are addressed and discussed. Full article
(This article belongs to the Special Issue Smart Educational Systems: Hardware and Software Aspects)
Show Figures

Figure 1

Figure 1
<p>Example of 5 s EEG recording (source: sample data plot from EEGLAB [<a href="#B14-sensors-25-00182" class="html-bibr">14</a>]). There are 32 channels, with their naming derived from the 10–20 system, and the scale refers to microvolts (μV).</p>
Full article ">Figure 2
<p>The conceptual framework for the usage of software in EEG applications.</p>
Full article ">Figure 3
<p>The PRISMA flow diagram.</p>
Full article ">Figure 4
<p>Counts of the sample sizes in groups of ten.</p>
Full article ">Figure 5
<p>Counts of wired and wireless EEG recordings in each group of sample sizes.</p>
Full article ">Figure 6
<p>Counts of use of EEG devices and configurations (amplifier and caps).</p>
Full article ">Figure 7
<p>The way in which EEG signals were used in the presented projects.</p>
Full article ">
18 pages, 2023 KiB  
Systematic Review
Vulvar Epidermolytic Hyperkeratosis: A Comprehensive Systematic Review of Case Reports and Series
by Miruna Ioana Cristescu, Elena Codruța Cozma, Cristina Beiu, Irina Tudose, Selda Ali, Anca Bobircă and Liliana Gabriela Popa
J. Clin. Med. 2025, 14(1), 94; https://doi.org/10.3390/jcm14010094 - 27 Dec 2024
Viewed by 366
Abstract
Background: Vulvar epidermolytic hyperkeratosis (EHK) is an exceedingly rare dermatological condition, often presenting as solitary or multiple lesions in the vulvar region. Due to its clinical resemblance to other vulvar disorders, such as condyloma acuminatum, Bowenoid papulosis, and squamous cell carcinoma, vulvar [...] Read more.
Background: Vulvar epidermolytic hyperkeratosis (EHK) is an exceedingly rare dermatological condition, often presenting as solitary or multiple lesions in the vulvar region. Due to its clinical resemblance to other vulvar disorders, such as condyloma acuminatum, Bowenoid papulosis, and squamous cell carcinoma, vulvar EHK poses significant diagnostic challenges. While individual case reports and small case series have documented instances of vulvar EHK, comprehensive studies systematically consolidating the clinical, histopathological, and therapeutic aspects of this condition remain lacking. Objectives: To address this gap, this systematic review consolidates all available case reports and case series on vulvar EHK. The review aims to provide a comprehensive analysis of clinical presentations, histopathological features, diagnostic challenges, treatment approaches, and patient outcomes. Methods: We conducted a systematic review following the PRISMA guidelines. We searched multiple databases (PubMed, Web of Science, Scopus) for studies published up to 30 September 2024. Only case reports and case series with histopathologically confirmed vulvar EHK were included, as no higher-level studies (e.g., randomized controlled trials or cohort studies) were available due to the rarity of this condition. Exclusion criteria were male cases, oral EHK or other unrelated conditions, and literature reviews. We extracted and analyzed data on: patient demographics, time to diagnosis, anatomical distribution, clinical presentation, associated symptoms, histopathological features, patient history, risk factors, HPV status, treatment, and outcomes. Risk of bias was assessed using the CARE checklist and JBI Checklist for Case Series. Additionally, original clinical and histopathological images from our department were included to enhance the review. Results: A total of 19 studies, encompassing 30 cases of histopathologically confirmed vulvar EHK, were identified. Most cases presented with hyperkeratotic plaques and papules localized on the labia majora. Histopathological analysis consistently revealed hyperkeratosis, acanthosis, and vacuolar degeneration in the granular and spinous layers. Misdiagnosis was common, with lesions frequently mistaken for condyloma acuminatum or other vulvar neoplasms. Conservative management, including observation and topical therapies, was associated with disease stability in asymptomatic cases, while surgical excision demonstrated complete remission in all cases where it was employed. The rarity of vulvar EHK and reliance on case reports and series limit the generalizability of findings. Conclusions: Vulvar EHK is often misdiagnosed due to its similarity to malignancies and sexually transmitted infections. This review, the first of its kind, highlights the importance of prompt histopathological diagnosis to avoid the psychological impact of a cancer or sexually transmitted disease diagnosis and unnecessary, distressing, or aggressive treatments. Further research is needed to explore the role of HPV in vulvar EHK and to establish standardized diagnostic and treatment guidelines. Full article
(This article belongs to the Section Dermatology)
Show Figures

Figure 1

Figure 1
<p>PRISMA flow diagram: Nineteen relevant publications were identified through database searching and were all included in the qualitative and quantitative synthesis. * records excluded based on title and abstract screening for not meeting inclusion criteria; ** records excluded during full-text review due to irrelevance or lack of histopathological confirmation.</p>
Full article ">Figure 2
<p>Representative clinical image of a patient with vulvar EHK, showing multiple grey-colored, hyperkeratotic papules coalescing into plaques located bilaterally on the labia majora (clinical photograph taken at Elias Emergency University Hospital, Bucharest, Romania).</p>
Full article ">Figure 3
<p>Hematoxylin–eosin stain showing hyperorthokeratosis, focal hypergranulosis, and the presence of irregular keratohyalin granules, along with vacuolar degeneration of the granular and superficial spinous layers, and a minimal lymphocytic inflammatory infiltrate in the superficial dermis ((<b>A</b>): 50×; (<b>B</b>): 100×; (<b>C</b>): 200×; (<b>D</b>): 400×) (histopathology images from the Pathology Department at Elias Emergency University Hospital, Bucharest, Romania).</p>
Full article ">
29 pages, 2570 KiB  
Systematic Review
The Challenge of Deep Learning for the Prevention and Automatic Diagnosis of Breast Cancer: A Systematic Review
by Jhelly-Reynaluz Pérez-Núñez, Ciro Rodríguez, Luis-Javier Vásquez-Serpa and Carlos Navarro
Diagnostics 2024, 14(24), 2896; https://doi.org/10.3390/diagnostics14242896 - 23 Dec 2024
Viewed by 532
Abstract
Objectives: This review aims to evaluate several convolutional neural network (CNN) models applied to breast cancer detection, to identify and categorize CNN variants in recent studies, and to analyze their specific strengths, limitations, and challenges. Methods: Using PRISMA methodology, this review examines studies [...] Read more.
Objectives: This review aims to evaluate several convolutional neural network (CNN) models applied to breast cancer detection, to identify and categorize CNN variants in recent studies, and to analyze their specific strengths, limitations, and challenges. Methods: Using PRISMA methodology, this review examines studies that focus on deep learning techniques, specifically CNN, for breast cancer detection. Inclusion criteria encompassed studies from the past five years, with duplicates and those unrelated to breast cancer excluded. A total of 62 articles from the IEEE, SCOPUS, and PubMed databases were analyzed, exploring CNN architectures and their applicability in detecting this pathology. Results: The review found that CNN models with advanced architecture and greater depth exhibit high accuracy and sensitivity in image processing and feature extraction for breast cancer detection. CNN variants that integrate transfer learning proved particularly effective, allowing the use of pre-trained models with less training data required. However, challenges include the need for large, labeled datasets and significant computational resources. Conclusions: CNNs represent a promising tool in breast cancer detection, although future research should aim to create models that are more resource-efficient and maintain accuracy while reducing data requirements, thus improving clinical applicability. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
Show Figures

Figure 1

Figure 1
<p>Overview of imaging modalities in breast cancer detection (created with <a href="http://BioRender.com" target="_blank">BioRender.com</a>).</p>
Full article ">Figure 2
<p>Medical image classification process using a convolutional neural network (CNN).</p>
Full article ">Figure 3
<p>CNN-based diagnostic workflow for breast cancer image classification.</p>
Full article ">Figure 4
<p>PRISMA 2020 flow diagram for systematic reviews.</p>
Full article ">Figure 5
<p>Average accuracy comparison by dataset in cancer detection methods.</p>
Full article ">Figure 6
<p>Frequency of breast cancer image dataset usage in research studies.</p>
Full article ">
22 pages, 2819 KiB  
Systematic Review
Functional Magnetic Resonance Imaging in Research on Dog Cognition: A Systematic Review
by Katarzyna Skierbiszewska, Marta Borowska, Joanna Bonecka, Bernard Turek, Tomasz Jasiński and Małgorzata Domino
Appl. Sci. 2024, 14(24), 12028; https://doi.org/10.3390/app142412028 - 23 Dec 2024
Viewed by 373
Abstract
Canine functional magnetic resonance imaging (fMRI) neurocognitive studies represent an emerging field that is advancing more gradually compared to progress in human fMRI research. Given the potential benefits of canine fMRI for veterinary, comparative, and translational research, this systematic review highlights significant findings, [...] Read more.
Canine functional magnetic resonance imaging (fMRI) neurocognitive studies represent an emerging field that is advancing more gradually compared to progress in human fMRI research. Given the potential benefits of canine fMRI for veterinary, comparative, and translational research, this systematic review highlights significant findings, focusing on specific brain areas activated during task-related and resting state conditions in dogs. The review addresses the following question: “What brain areas in dogs are activated in response to various stimuli?”. Following PRISMA 2020 guidelines, a comprehensive search of PUBMED, Scopus, and Web of Knowledge databases identified 1833 studies, of which 46 met the inclusion criteria. The studies were categorized into themes concerning resting state networks and visual, auditory, olfactory, somatosensory, and multi-stimulations studies. In dogs, resting state networks and stimulus-specific functional patterns were confirmed as vital for brain function. These findings reveal both similarities and differences in the neurological mechanisms underlying canine and human cognition, enhance the understanding of neural activation pathways in dogs, expand the knowledge of social bonding patterns, and highlight the potential use of fMRI in predicting the suitability of dogs for assistance roles. Further studies are needed to further map human–canine similarities and identify the unique features of canine brain function. Additionally, implementing innovative human methods, such as combined fMRI–magnetic resonance spectroscopy (MRS), into canine neurocognitive research could significantly advance the field. Full article
Show Figures

Figure 1

Figure 1
<p>PRISMA flow diagram depicting research articles on dog cognition investigated using functional magnetic resonance imaging (fMRI) included and excluded from this systematic review.</p>
Full article ">Figure 2
<p>Traffic light plot of risk of bias in randomized controlled trials on (<b>A</b>) visual stimuli, (<b>B</b>) auditory stimuli, (<b>C</b>) olfactory stimuli, and (<b>D</b>) somatosensory stimuli and multi-stimuli.</p>
Full article ">Figure 3
<p>Traffic light plot of risk of bias in non-randomized trials and observational studies on (<b>A</b>) resting state networks, (<b>B</b>) visual stimuli, (<b>C</b>) auditory stimuli, and (<b>D</b>) somatosensory stimuli and multi–stimuli.</p>
Full article ">
9 pages, 618 KiB  
Systematic Review
Systematic Review of Acute Isolated Distal Radioulnar Joint Dislocation: Treatment Options
by Konstantinos Zampetakis, Ioannis M. Stavrakakis, Kalliopi Alpantaki, Grigorios Kastanis, Ioannis Ktistakis, Alexandros Tsioupros, Nikolaos Ritzakis and Constantinos Chaniotakis
J. Clin. Med. 2024, 13(24), 7817; https://doi.org/10.3390/jcm13247817 - 21 Dec 2024
Viewed by 550
Abstract
Background/Objectives: Acute isolated distal radioulnar joint (DRUJ) dislocations are rare and often misdiagnosed during initial evaluation due to subtle clinical presentation, low index of suspicion, and imaging barriers. Prompt diagnosis and treatment are critical to avoid chronic instability, limited wrist mobility, and [...] Read more.
Background/Objectives: Acute isolated distal radioulnar joint (DRUJ) dislocations are rare and often misdiagnosed during initial evaluation due to subtle clinical presentation, low index of suspicion, and imaging barriers. Prompt diagnosis and treatment are critical to avoid chronic instability, limited wrist mobility, and osteoarthritis. This systematic review evaluates the functional outcomes of conservative and surgical treatment protocols for acute isolated DRUJ dislocations. Methods: A systematic search of PubMed, Scopus, and Mendeley databases (2000–2024) was conducted following PRISMA guidelines. Inclusion criteria involved adult patients with isolated DRUJ dislocations diagnosed and managed within one week of injury. Studies reporting on underage patients, associated fractures, delayed management, and open injuries were excluded. Data on demographics, injury mechanism, diagnostic methods, treatment protocols, and functional outcomes were extracted and analyzed. Results: In total, 22 cases across 20 studies were included. The majority (90.9%) were males, with a mean age of 37.9 years (range: 20–70 years). Falls and sports injuries were the major causes, with volar dislocations predominating (18/22). The misdiagnosis rate was equal to 18%. Most cases were treated conservatively with closed reduction and immobilization for an average of 4.9 weeks. Operative treatment was performed in 6 cases, mainly following failed closed reductions. Functional outcomes were generally favorable, although the same parameters were not consistently studied in all patients. Overall, 82% (14 of 17 patients) achieved a full range of motion; 88% (14 of 16 patients) reported no pain, and all assessed cases had stable DRUJs at follow-up. Conclusions: This review highlights the rarity and diagnostic challenges of this injury. The functional outcomes of both conservative and operative treatment are generally satisfactory. Conservative treatment should be the first-line approach, with surgery reserved for irreducible or unstable cases. Future research using standardized outcome measures is needed to provide guidance for clinicians. Full article
(This article belongs to the Special Issue Advances in Trauma and Orthopedic Surgery: 2nd Edition)
Show Figures

Figure 1

Figure 1
<p>PRISMA 2020 flow diagram for the search protocol used to review treatment of acute isolated DRUJ dislocations. DRUJ: Distal Radioulnar Joint.</p>
Full article ">
12 pages, 5281 KiB  
Systematic Review
Multiple Sclerosis-like Lesions Induced by Radiation: A Case Report and Systematic Review of the Literature
by Angeliki-Erato Sterpi, Alexandros-Stavros Triantafyllou, Dimitrios Tzanetakos, Eleni Ampantzi, Dimitrios Kitsos, Aikaterini Theodorou, Effrosyni Koutsouraki, Maria Maili, Maria Ioanna Stefanou, Christos Moschovos, Lina Palaiodimou, John Tzartos, Sotirios Giannopoulos and Georgios Tsivgoulis
J. Clin. Med. 2024, 13(24), 7554; https://doi.org/10.3390/jcm13247554 - 12 Dec 2024
Viewed by 415
Abstract
Background/Objectives: Radiotherapy (RT) remains crucial in treating both primary and metastatic central nervous system cancer. Despite advancements in modern techniques that mitigate some toxic adverse effects, magnetic resonance imaging (MRI) scans still reveal a wide range of radiation-induced changes. Radiation can adversely affect [...] Read more.
Background/Objectives: Radiotherapy (RT) remains crucial in treating both primary and metastatic central nervous system cancer. Despite advancements in modern techniques that mitigate some toxic adverse effects, magnetic resonance imaging (MRI) scans still reveal a wide range of radiation-induced changes. Radiation can adversely affect neuroglial cells and their precursors, potentially triggering a demyelinating pattern similar to multiple sclerosis (MS). The aim of the current review is to investigate the occurrence and characteristics of such cases presented in the literature. Methods: We present the case of a 37-year-old female patient with multiple white matter lesions on a brain MRI, mimicking MS, after the completion of RT sessions. Additionally, a systematic review of the literature (PROSPERO id: CRD42024624053) was performed on 4 January 2024. The databases of MEDLINE and SCOPUS were searched. Case reports or case series of adult patients with white matter lesions in a brain MRI, consistent with the MAGNIMS criteria for MS plaques, after RT, were included in our final synthesis. The PRISMA guidelines were applied. Results: The systematic search of the literature revealed 1723 studies, 7 of which conformed to our inclusion criteria, including seven patients in our final analysis. Four of them were female and the mean age was 39 ± 11 years. Several intracranial and extracranial RT types were performed. The symptoms occurred 3 ± 0.8 months after the completion of RT. Lesions were revealed in infratentorial, periventricular and subcortical white matter regions, but not in the spinal cord. All patients who received corticosteroids (83%) showed clinical improvement. Clinical and radiological recurrence occurred in two of the patients during the follow-up period. Fingolimod and Interferon beta-1a were administered to these two patients. Conclusions: Radiation-induced demyelination is a critical clinical and radiological entity that requires attention from both oncologists and neurologists. Comprehensive follow-up is essential to identify patients who may benefit from disease-modifying therapies and to distinguish them from those with pre-existing demyelinating conditions. Full article
(This article belongs to the Section Immunology)
Show Figures

Figure 1

Figure 1
<p>Mechanisms of early delayed CNS injury induced by radiation. Abbreviations: BBB: blood–brain barrier; OPCs: Oligodendrocyte type-2 astrocytes; ROS: reactive oxygen species.</p>
Full article ">Figure 2
<p>Brain MRI prior to radiation therapy. Metastatic lesions in the gray–white matter junction are indicated by arrows on axial FLAIR (<b>D</b>) and axial post-gadolinium T1-MPRAGE images (<b>E</b>–<b>H</b>). (<b>A</b>–<b>H</b>). Abbreviations: FLAIR: fluid-attenuated inversion recover; MPRAGE: magnetization prepared rapid gradient echo.</p>
Full article ">Figure 3
<p>Brain MRI following radiation therapy. FLAIR images showed several hyperintense ovoid lesions in both infratentorial (<b>A</b>) and supratentorial regions (periventricular and subcortical/juxtacortical) (<b>B</b>,<b>C</b>). Several of these lesions are oriented perpendicular to the long axis of the lateral ventricles ((<b>C</b>), arrows). A few hypointense lesions on T1-MPRAGE images, consistent with “black holes”, are depicted in image (<b>D</b>) (arrows). On T1-weighted post-contrast imaging (<b>E</b>,<b>F</b>), there is no evidence of gadolinium enhancement. Abbreviations: FLAIR: fluid-attenuated inversion recover; MPRAGE: magnetization prepared rapid gradient echo.</p>
Full article ">Figure 4
<p>Flowchart of systematic review. Abbreviations: n: number.</p>
Full article ">
35 pages, 528 KiB  
Systematic Review
Comprehensive Insights into Artificial Intelligence for Dental Lesion Detection: A Systematic Review
by Kubra Demir, Ozlem Sokmen, Isil Karabey Aksakalli and Kubra Torenek-Agirman
Diagnostics 2024, 14(23), 2768; https://doi.org/10.3390/diagnostics14232768 - 9 Dec 2024
Viewed by 633
Abstract
Background/Objectives: The growing demand for artificial intelligence (AI) in healthcare is driven by the need for more robust and automated diagnostic systems. These methods not only provide accurate diagnoses but also promise to enhance operational efficiency and optimize resource utilization in clinical workflows. [...] Read more.
Background/Objectives: The growing demand for artificial intelligence (AI) in healthcare is driven by the need for more robust and automated diagnostic systems. These methods not only provide accurate diagnoses but also promise to enhance operational efficiency and optimize resource utilization in clinical workflows. In the field of dental lesion detection, the application of deep learning models to various imaging techniques has gained significant prominence. This study presents a comprehensive systematic review of the utilization of deep learning methods for detecting dental lesions across different imaging modalities, including panoramic imaging, periapical radiographs, and cone-beam computed tomography (CBCT). A systematic search was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to ensure a structured and transparent review process. Methods: This study addresses four key research questions related to the types of objects used for AI in dental images, state-of-the-art approaches for detecting lesions in dental images, data augmentation methods, and challenges and possible solutions to the existing AI-based dental lesion detection. Furthermore, this systematic review was performed on 29 primary studies identified from multiple electronic databases. This review focused on studies published between 2019 and 2024, sourced from IEEE, Web of Knowledge, Springer, ScienceDirect, PubMed, and Google Scholar. Results: We identified five types of lesions in dental images as periapical lesions, cyst lesions, jawbone lesions, dental caries, and apical lesions. Among the fourteen state-of-the-art deep learning approaches, the results demonstrate that deep learning models, such as U-Net, AlexNet, and You Only Look Once (YOLO) version 8 (YOLOv8) are commonly employed for dental lesion detection. These deep learning models have the potential to serve as integral components of decision-making processes by improving detection accuracy and supporting clinical workflows. Furthermore, we found that among twelve types of data augmentation techniques, flipping, rotation, and reflection methods played an important role in increasing the diversity of the datasets. We also identified six challenges for dental lesion detection, and the main issues were identified as data integration, poor data quality, limited model generalization, and overfitting. Proposed solutions against the aforementioned challenges include the integration of larger datasets, model optimization, and diversification of data sources. Conclusions: This study provides a comprehensive overview of current methodologies and potential advancements in dental lesion detection using deep learning. The findings indicate that possible solutions against the challenges of AI-based diagnostic methods in dental lesion detection need to be more generalizable regardless of image type, the number of data, and data quality. Full article
(This article belongs to the Special Issue Artificial Intelligence in Biomedical Diagnostics and Analysis 2024)
Show Figures

Figure 1

Figure 1
<p>Radiographic methods used in radiology practice for dental lesion detection (white arrows indicate the lesion area in the relevant images): (<b>a</b>) a chronic apical periodontitis on panoramic radiography; (<b>b</b>) a chronic apical periodontitis on periapical radiography; (<b>c</b>) a radicular cyst on CBCT.</p>
Full article ">Figure 2
<p>The PRISMA flowchart diagram of study selection process [<a href="#B4-diagnostics-14-02768" class="html-bibr">4</a>].</p>
Full article ">Figure 3
<p>The number of primary studies according to publication type and publication year.</p>
Full article ">Figure 4
<p>Overall quality scores of the primary studies.</p>
Full article ">Figure 5
<p>Reference reporting quality scores of the primary studies.</p>
Full article ">Figure 6
<p>Rigor quality scores of the primary studies.</p>
Full article ">Figure 7
<p>Credibility of evidence scores of the primary studies.</p>
Full article ">Figure 8
<p>Relevance quality scores of the primary studies.</p>
Full article ">
13 pages, 1722 KiB  
Systematic Review
Exploring the Role of Large Language Models in Melanoma: A Systematic Review
by Mor Zarfati, Girish N. Nadkarni, Benjamin S. Glicksberg, Moti Harats, Shoshana Greenberger, Eyal Klang and Shelly Soffer
J. Clin. Med. 2024, 13(23), 7480; https://doi.org/10.3390/jcm13237480 - 9 Dec 2024
Viewed by 935
Abstract
Objective: This systematic review evaluates the current applications, advantages, and challenges of large language models (LLMs) in melanoma care. Methods: A systematic search was conducted in PubMed and Scopus databases for studies published up to 23 July 2024, focusing on the application [...] Read more.
Objective: This systematic review evaluates the current applications, advantages, and challenges of large language models (LLMs) in melanoma care. Methods: A systematic search was conducted in PubMed and Scopus databases for studies published up to 23 July 2024, focusing on the application of LLMs in melanoma. The review adhered to PRISMA guidelines, and the risk of bias was assessed using the modified QUADAS-2 tool. Results: Nine studies were included, categorized into subgroups: patient education, diagnosis, and clinical management. In patient education, LLMs demonstrated high accuracy, though readability often exceeded recommended levels. For diagnosis, multimodal LLMs like GPT-4V showed capabilities in distinguishing melanoma from benign lesions, but accuracy varied, influenced by factors such as image quality and integration of clinical context. Regarding management advice, ChatGPT provided more reliable recommendations compared to other LLMs, but all models lacked depth for individualized decision-making. Conclusions: LLMs, particularly multimodal models, show potential in improving melanoma care. However, current applications require further refinement and validation. Future studies should explore fine-tuning these models on large, diverse dermatological databases and incorporate expert knowledge to address limitations such as generalizability across different populations and skin types. Full article
(This article belongs to the Section Dermatology)
Show Figures

Graphical abstract

Graphical abstract
Full article ">Figure 1
<p>Hierarchy diagram of artificial intelligence (AI) terms.</p>
Full article ">Figure 2
<p>Flow diagram of the search and inclusion process based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.</p>
Full article ">
24 pages, 830 KiB  
Systematic Review
Evolving Strategies in Machine Learning: A Systematic Review of Concept Drift Detection
by Gurgen Hovakimyan and Jorge Miguel Bravo
Information 2024, 15(12), 786; https://doi.org/10.3390/info15120786 - 7 Dec 2024
Viewed by 1048
Abstract
In this comprehensive literature review, we rigorously adhere to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines for our process and reporting. This review employs an innovative method integrating the advanced natural language processing model T5 (Text-to-Text Transfer Transformer) to [...] Read more.
In this comprehensive literature review, we rigorously adhere to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines for our process and reporting. This review employs an innovative method integrating the advanced natural language processing model T5 (Text-to-Text Transfer Transformer) to enhance the accuracy and efficiency of screening and data extraction processes. We assess strategies for handling the concept drift in machine learning using high-impact publications from notable databases that were made accessible via the IEEE and Science Direct APIs. The chronological analysis covering the past two decades provides a historical perspective on methodological advancements, recognizing their strengths and weaknesses through citation metrics and rankings. This review aims to trace the growth and evolution of concept drift mitigation strategies and to provide a valuable resource that guides future research and deepens our understanding of this rapidly changing field. Key findings highlight the effectiveness of diverse methodologies such as drift detection methods, window-based methods, unsupervised statistical methods, and neural network techniques. However, challenges remain, particularly with imbalanced data, computational efficiency, and the application of concept drift detection to non-tabular data like images. This review aims to trace the growth and evolution of concept drift mitigation strategies and provide a valuable resource that guides future research and deepens our understanding of this rapidly changing field. Full article
(This article belongs to the Topic Decision-Making and Data Mining for Sustainable Computing)
Show Figures

Figure 1

Figure 1
<p>Distribution-based concept drift: The figure shows various concept drift scenarios, where different shapes represent different classes and changes in data distribution and class relationships.</p>
Full article ">Figure 2
<p>Pattern-based concept drift: The figure illustrates different types of concept drift over time, where changes in data distribution occur in sudden, incremental, reoccurring, and gradual patterns.</p>
Full article ">Figure 3
<p>PRISMA flow diagram illustrating the selection process of the studies.</p>
Full article ">
12 pages, 452 KiB  
Systematic Review
Factors Influencing Contrast Enhancement in Abdominal Computed Tomography Angiography in the Dog: A Systematic Review
by Simone Perfetti, Carlo Guglielmini, Nikolina Linta and Alessia Diana
Animals 2024, 14(23), 3521; https://doi.org/10.3390/ani14233521 - 5 Dec 2024
Viewed by 558
Abstract
Multidetector-row computed tomographic angiography (angio-CT) aims to achieve optimal opacification of the vascular compartment of interest. The distribution and quality of vascular opacification are influenced by patient-related factors, contrast medium (CM)-related factors, and scanner-related factors. This systematic review evaluates these factors and their [...] Read more.
Multidetector-row computed tomographic angiography (angio-CT) aims to achieve optimal opacification of the vascular compartment of interest. The distribution and quality of vascular opacification are influenced by patient-related factors, contrast medium (CM)-related factors, and scanner-related factors. This systematic review evaluates these factors and their effects on contrast enhancement. A comprehensive literature search was made in February 2024 across four online bibliographic databases (Web of Science, PubMed, Scopus, and CAB Abstract) in adherence with the PRISMA 2020 guidelines. After screening the 5990 unique published articles initially identified, 20 full-text original studies met the inclusion criteria for the final review. The amount of abdominal adipose tissue was found to significantly affect enhancement, which suggests the possibility of reducing the CM dose to minimize adverse effects or toxicity. The injection rate of the CM, rather than the injection duration, was identified as the most critical factor, with important clinical implications. For scanners with slower acquisition speeds or longer scan durations, maintaining a fixed CM injection duration may optimize vascular phase acquisition. In contrast, faster scanners benefit from bolus tracking, which allows for improved differentiation between vascular phases. Additionally, administering a saline flush post-CM injection enhances arterial opacification while reducing the necessary CM dose. This systematic review highlights essential factors influencing contrast enhancement in angio-CT for dogs and provides a foundation for future research aimed at optimizing imaging protocols in veterinary medicine. Full article
(This article belongs to the Section Companion Animals)
Show Figures

Figure 1

Figure 1
<p>Flow diagram of the literature search strategy.</p>
Full article ">
21 pages, 5901 KiB  
Article
Identification of a Potential Rare Earth Element Deposit at Ivanpah Dry Lake, California Through the Bastnäsite Indices
by Otto C. A. Gadea and Shuhab D. Khan
Remote Sens. 2024, 16(23), 4540; https://doi.org/10.3390/rs16234540 - 4 Dec 2024
Viewed by 548
Abstract
A groundbreaking remote sensing approach that uses three Bastnäsite Indices (BI) to detect rare earth elements (REEs) was initially developed using ore samples from the Sulfide Queen mine in California and later applied to various well-studied ground-based, drone-based, airborne, and spaceborne imaging spectrometers [...] Read more.
A groundbreaking remote sensing approach that uses three Bastnäsite Indices (BI) to detect rare earth elements (REEs) was initially developed using ore samples from the Sulfide Queen mine in California and later applied to various well-studied ground-based, drone-based, airborne, and spaceborne imaging spectrometers across a wide range of scales, from micrometers to tens of meters. In this work, those same innovative techniques have revealed the existence of a potential site for extracting REEs. Data from AVIRIS-NG, AVIRIS-Classic, HISUI, DESIS, EnMAP, EO-1 Hyperion, PRISMA, and EMIT were utilized to map Ivanpah Dry Lake, which is located fourteen kilometers northeast of the Sulfide Queen mine. Although this area was not previously associated with REE deposits, BI maps have indicated the presence of a site that has remained enriched in REEs for decades, suggesting an opportunity for further exploration and mining. Historically, a pipeline transported wastewater from facilities at the Sulfide Queen mine to evaporation ponds on or near Ivanpah Dry Lake, where wastewater may have contained concentrated REEs. This research highlights imaging spectroscopy not only as a valuable tool for rapidly identifying and efficiently extracting REEs, but also as a means of recovering REEs from supposed waste. Full article
(This article belongs to the Section Environmental Remote Sensing)
Show Figures

Graphical abstract

Graphical abstract
Full article ">Figure 1
<p>The figure displays the location of Ivanpah Dry Lake in the Mojave Desert. The Sulfide Queen Mine is situated southwest in Mountain Pass. A zoomed-in view of Ivanpah Dry Lake is shown in the top left, displaying the region covered in hyperspectral data from various sensors. The background image is from the Maxar Vivid Imagery Basemap Layer. The images for this layer were captured by the WorldView-2 Satellite on 31 March 2023 (ESRI, 2024).</p>
Full article ">Figure 2
<p>Spectra of terrain containing high concentrations of rare earth elements, scanned by airborne and spaceborne imaging spectrometers over the Ivanpah Dry Lake racetrack; the exact year when each dataset was collected is listed beside the name of its corresponding spectrometer.</p>
Full article ">Figure 3
<p>Hyperspectral images of terrain containing high concentrations of rare earth elements, scanned by AVIRIS-NG over the Ivanpah Dry Lake racetrack: (<b>A</b>) true-color RGB composite of the area of interest; rare earth element detection maps of the same area according to Bastnäsite Indices (<b>B</b>) 1, (<b>C</b>) 2, and (<b>D</b>) 3, respectively.</p>
Full article ">Figure 4
<p>Hyperspectral images of terrain containing high concentrations of rare earth elements, scanned by AVIRIS-Classic over the Ivanpah Dry Lake racetrack: (<b>A</b>) true-color RGB composite of the area of interest; rare earth element detection maps of the same area according to Bastnäsite Indices (<b>B</b>) 1, (<b>C</b>) 2, and (<b>D</b>) 3, respectively.</p>
Full article ">Figure 5
<p>Hyperspectral images of terrain containing high concentrations of rare earth elements, scanned by HISUI over the Ivanpah Dry Lake racetrack: (<b>A</b>) true-color RGB composite of the area of interest; rare earth element detection maps of the same area according to Bastnäsite Indices (<b>B</b>) 1, (<b>C</b>) 2, and (<b>D</b>) 3, respectively.</p>
Full article ">Figure 6
<p>Hyperspectral images of terrain containing high concentrations of rare earth elements, scanned by DESIS over the Ivanpah Dry Lake racetrack: (<b>A</b>) true-color RGB composite of the area of interest; rare earth element detection maps of the same area according to Bastnäsite Indices (<b>B</b>) 1, (<b>C</b>) 2, and (<b>D</b>) 3, respectively.</p>
Full article ">Figure 7
<p>Hyperspectral images of terrain containing high concentrations of rare earth elements, scanned by EnMAP over the Ivanpah Dry Lake racetrack: (<b>A</b>) true-color RGB composite of the area of interest; rare earth element detection maps of the same area according to Bastnäsite Indices (<b>B</b>) 1, (<b>C</b>) 2, and (<b>D</b>) 3, respectively.</p>
Full article ">Figure 8
<p>Hyperspectral images of terrain containing high concentrations of rare earth elements, scanned by EO-1 Hyperion over the Ivanpah Dry Lake racetrack: (<b>A</b>) true-color RGB composite of the area of interest; rare earth element detection maps of the same area according to Bastnäsite Indices (<b>B</b>) 1, (<b>C</b>) 2, and (<b>D</b>) 3, respectively.</p>
Full article ">Figure 9
<p>Hyperspectral images of terrain containing high concentrations of rare earth elements, scanned by PRISMA over the Ivanpah Dry Lake racetrack: (<b>A</b>) true-color RGB composite of the area of interest; rare earth element detection maps of the same area according to Bastnäsite Indices (<b>B</b>) 1, (<b>C</b>) 2, and (<b>D</b>) 3, respectively.</p>
Full article ">Figure 10
<p>Hyperspectral images of terrain containing high concentrations of rare earth elements, scanned by EMIT over the Ivanpah Dry Lake racetrack: (<b>A</b>) true-color RGB composite of the area of interest; rare earth element detection maps of the same area according to Bastnäsite Indices (<b>B</b>) 1, (<b>C</b>) 2, and (<b>D</b>) 3, respectively.</p>
Full article ">
16 pages, 3665 KiB  
Systematic Review
Clinical Application of 3D-Assisted Surgery Techniques in Treatment of Intra-Articular Distal Radius Fractures: A Systematic Review in 718 Patients
by Lisanne J. M. Roelofs, Nick Assink, Joep Kraeima, Kaj ten Duis, Job N. Doornberg, Jean-Paul P. M. de Vries, Anne M. L. Meesters and Frank F. A. IJpma
J. Clin. Med. 2024, 13(23), 7296; https://doi.org/10.3390/jcm13237296 - 30 Nov 2024
Viewed by 671
Abstract
Objectives: Three-dimensional (3D) technology is increasingly applied in the surgical treatment of distal radial fractures and may optimize surgical planning, improve fracture reduction, facilitate implant and screw positioning, and thus prevent surgical complications. The main research questions of this review were as [...] Read more.
Objectives: Three-dimensional (3D) technology is increasingly applied in the surgical treatment of distal radial fractures and may optimize surgical planning, improve fracture reduction, facilitate implant and screw positioning, and thus prevent surgical complications. The main research questions of this review were as follows: (1) “How do 3D-assisted versus 2D-assisted distal radius fracture surgery compare in terms of intraoperative metrics (i.e., operation time and fluoroscopy frequency)?”, and (2) ”What are the effects of 3D-assisted versus 2D-assisted surgery on postoperative outcomes (patient-reported outcome measures (PROMs), range of motion (ROM), fracture reduction, complication rate, and screw placement accuracy)?” Methods: This review was performed according to the Preferred Reporting Items for Systematic Reviews (PRISMA) guidelines. In total, 873 articles were found between 1 January 2010 and 1 April 2024, of which 12 (718 patients) were suitable for inclusion. The quality of the studies, assessed using the McMaster quality assessment, ranged from moderate to excellent, although the surgical techniques and outcome measures varied widely. Articles comparing a 3D group to a 2D group (conventional imaging) and reporting on primary or secondary outcomes were included in the analysis, for which weighted means and ranges were calculated. Results: Three different concepts of 3D-assisted surgery techniques were identified: (1) 3D virtual surgical planning (VSP), (2) 3D-printed handheld models, and (3) 3D intraoperative guides. Differences between 3D-assisted and conventional 2D-assisted surgery were evaluated. Regarding intraoperative metrics, 3D-assisted surgery significantly reduced operation time by 6 min (weighted mean 66.9 versus 73.2 min) and reduced the fluoroscopy frequency by 1.1 images (5.8 versus 4.7 times). Regarding postoperative outcomes, the weighted mean of the DASH score differed between the 3D- and 2D-assisted groups (17.8 versus 23.9 points), and no differences in PRWE or VAS score were found. Furthermore, our results showed no significant differences in the ROM and fracture reduction parameters. In terms of complications, the application of 3D-assisted surgery decreased the complication rate from 10.7% to 3.6%, and the use of screws with appropriate lengths improved from 75% to 86%. Conclusions: Applications of 3D-assisted surgery in distal radial fracture surgery can slightly reduce the operation time and fluoroscopy frequency. Evidence for the improvement of fracture reduction and functional outcomes is still lacking, although it likely reduces the complication rate and improves the use of appropriate screw lengths. Full article
(This article belongs to the Section Orthopedics)
Show Figures

Figure 1

Figure 1
<p>PRISMA flow diagram.</p>
Full article ">Figure 2
<p>Schematic representation of the 3D applications for distal radius fracture surgery that were found.</p>
Full article ">Figure 3
<p>A step-by-step representation of the workflow of 3D virtual surgical planning, and evaluation of the postoperative results. Explanation of colors: Illustration c: yellow, green and blues: masks of the fracture fragments. Illustrations e-i: oranges and blues: fracture fragments, Illustration K and Y: blue: 3D plate and screws model, derived from the post-operative CT scan.</p>
Full article ">
45 pages, 4261 KiB  
Review
VNIR-SWIR Imaging Spectroscopy for Mining: Insights for Hyperspectral Drone Applications
by Friederike Koerting, Saeid Asadzadeh, Justus Constantin Hildebrand, Ekaterina Savinova, Evlampia Kouzeli, Konstantinos Nikolakopoulos, David Lindblom, Nicole Koellner, Simon J. Buckley, Miranda Lehman, Daniel Schläpfer and Steven Micklethwaite
Mining 2024, 4(4), 1013-1057; https://doi.org/10.3390/mining4040057 - 29 Nov 2024
Viewed by 1592
Abstract
Hyperspectral imaging technology holds great potential for various stages of the mining life cycle, both in active and abandoned mines, from exploration to reclamation. The technology, however, has yet to achieve large-scale industrial implementation and acceptance. While hyperspectral satellite imagery yields high spectral [...] Read more.
Hyperspectral imaging technology holds great potential for various stages of the mining life cycle, both in active and abandoned mines, from exploration to reclamation. The technology, however, has yet to achieve large-scale industrial implementation and acceptance. While hyperspectral satellite imagery yields high spectral resolution, a high signal-to-noise ratio (SNR), and global availability with breakthrough systems like EnMAP, EMIT, GaoFen-5, PRISMA, and Tanager-1, limited spatial and temporal resolution poses challenges for the mining sectors, which require decimetre-to-centimetre-scale spatial resolution for applications such as reconciliation and environmental monitoring and daily temporal revisit times, such as for ore/waste estimates and geotechnical assessments. Hyperspectral imaging from drones (Uncrewed Aerial Systems; UASs) offers high-spatial-resolution data relevant to the pit/mine scale, with the capability for frequent, user-defined re-visit times for areas of limited extent. Areas of interest can be defined by the user and targeted explicitly. Collecting data in the visible to near and shortwave infrared (VNIR-SWIR) wavelength regions offers the detection of different minerals and surface alteration patterns, potentially revealing crucial information for exploration, extraction, re-mining, waste remediation, and rehabilitation. This is related to but not exclusive to detecting deleterious minerals for different processes (e.g., clays, iron oxides, talc), secondary iron oxides indicating the leakage of acid mine drainage for rehabilitation efforts, swelling clays potentially affecting rock integrity and stability, and alteration minerals used to vector toward economic mineralisation (e.g., dickite, jarosite, alunite). In this paper, we review applicable instrumentation, software components, and relevant studies deploying hyperspectral imaging datasets in or appropriate to the mining sector, with a particular focus on hyperspectral VNIR-SWIR UASs. Complementarily, we draw on previous insights from airborne, satellite, and ground-based imaging systems. We also discuss common practises for UAS survey planning and ground sampling considerations to aid in data interpretation. Full article
Show Figures

Figure 1

Figure 1
<p>Outcrop-scale mineral map using HSI data collected by U.S. Geological Survey personnel in the Cresson pit. Regions excluded from the analysis (i.e., leach pad and dump piles) are outlined in red. Red circles labeled a, b, and c indicate locations of 3 × 3 pixels averages used to generate the endmember spectral library and to track shifts in white mica wavelength positions. Figure from [<a href="#B117-mining-04-00057" class="html-bibr">117</a>], published as open access (<a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a>, accessed on 1 March 2024).</p>
Full article ">Figure 2
<p>Fe (III) iron band ratio indices for simulated Sentinel-2 (a), PlanetScope 2.SD (b), UAV (c), and ASD Halo handheld spectrometer (d) and a natural RGB image of Wheal Maid (e). Red areas indicate high Fe (III) iron pixel distribution, dark green areas denote vegetated areas. A model for the handheld point spectrometer was created via kriging (d). Figure modified from [<a href="#B143-mining-04-00057" class="html-bibr">143</a>], published as open access (<a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a>; accessed on 1 March 2024). The originally published graphs (f–h) were clipped.</p>
Full article ">Figure 3
<p>The spatial distribution of Fe (III) iron oxides surrounding the Chuquicamata porphyry copper mine in Chile using EnMAP hyperspectral satellite data acquired on 30 April 2023. The left panel displays natural colour composite imagery, the middle panel illustrates the relative abundance of ferric iron oxides, and the right panel shows the minimum wavelength of the ferric feature from 875 nm to 955 nm. This wavelength range indicates the prevalence of jarosite (blueish) and goethite (reddish) within the regions. These data were prepared within the M4Mining project to demonstrate EnMap mapping capabilities at a large scale for the mining industry. Mapped patterns are based on satellite data only and have not been validated on-site.</p>
Full article ">Figure 4
<p>Graphical abstract from [<a href="#B124-mining-04-00057" class="html-bibr">124</a>], showing results of the random forest regression prediction for pH values in the river water of Tintillo River (Spain), which collects the drainage from the western part of Rio Tinto’s massive sulphide deposit. Figure available via CC BY 4.0 licencing (<a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a>; accessed on 1 March 2024).</p>
Full article ">Figure 5
<p>Secondary iron mineral maps from the Skouriotissa mine monitoring for acid-forming potential. Left: mineral mapping based on WorldView-2 data provided by European Space Imaging<sup>®</sup> within the ESA TPM project 61058 (4 m × 4 m pixels); right: mineral map based on Copernicus Sentinel-2 data (20 m × 20 m pixels). From [<a href="#B146-mining-04-00057" class="html-bibr">146</a>], licenced under CC BY 4.0 (<a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a>; accessed on 1 March 2024).</p>
Full article ">Figure 6
<p>Overview of an exemplary UAS, including the octocopter platform, gimbal, and camera payload. Specifically, this is the HySpex Mjolnir VS-620 camera (by NEO, Oslo, Norway) and LiDAR from Velodyne VLC-32 (by Mapix Technologies, Edinburgh, UK) mounted on a BFD SE8 octocopter (by BFD Systems, Pennsauken, NJ, USA). While not listed in the image, the INS is hard-mounted in the chassis of the hyperspectral camera.</p>
Full article ">Figure 7
<p>Example of sampling points from a M4Mining (<a href="http://www.m4mining.eu" target="_blank">www.m4mining.eu</a>; accessed on 1 April 2024) UAV campaign in Queensland, Australia, in September 2023. Right: sampling areas are marked via 50 cm × 50 cm outline using white chalk spray. Only the sample’s immediate surface is sampled. Left: location of the 50 cm × 50 cm markers in the ca. 12 cm × 12 cm pixel resolution UAS data captured using HySpex Mjolnir-VS620. Red arrows point to and highlight the location and the small size of the sampling areas in relation to the entire survey area. This is an RGB true colour image based on the native spatial resolution of the UAS-collected HSI.</p>
Full article ">
35 pages, 4458 KiB  
Systematic Review
Schizophrenia Detection and Classification: A Systematic Review of the Last Decade
by Arghyasree Saha, Seungmin Park, Zong Woo Geem and Pawan Kumar Singh
Diagnostics 2024, 14(23), 2698; https://doi.org/10.3390/diagnostics14232698 - 29 Nov 2024
Viewed by 1169
Abstract
Background/Objectives: Artificial Intelligence (AI) in healthcare employs advanced algorithms to analyze complex and large-scale datasets, mimicking aspects of human cognition. By automating decision-making processes based on predefined thresholds, AI enhances the accuracy and reliability of healthcare data analysis, reducing the need for human [...] Read more.
Background/Objectives: Artificial Intelligence (AI) in healthcare employs advanced algorithms to analyze complex and large-scale datasets, mimicking aspects of human cognition. By automating decision-making processes based on predefined thresholds, AI enhances the accuracy and reliability of healthcare data analysis, reducing the need for human intervention. Schizophrenia (SZ), a chronic mental health disorder affecting millions globally, is characterized by symptoms such as auditory hallucinations, paranoia, and disruptions in thought, behavior, and perception. The SZ symptoms can significantly impair daily functioning, underscoring the need for advanced diagnostic tools. Methods: This systematic review has been conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines and examines peer-reviewed studies from the last decade (2015–2024) on AI applications in SZ detection as well as classification. The review protocol has been registered in the International Prospective Register of Systematic Reviews (PROSPERO) under registration number: CRD42024612364. Research has been sourced from multiple databases and screened using predefined inclusion criteria. The review evaluates the use of both Machine Learning (ML) and Deep Learning (DL) methods across multiple modalities, including Electroencephalography (EEG), Structural Magnetic Resonance Imaging (sMRI), and Functional Magnetic Resonance Imaging (fMRI). The key aspects reviewed include datasets, preprocessing techniques, and AI models. Results: The review identifies significant advancements in AI methods for SZ diagnosis, particularly in the efficacy of ML and DL models for feature extraction, classification, and multi-modal data integration. It highlights state-of-the-art AI techniques and synthesizes insights into their potential to improve diagnostic outcomes. Additionally, the analysis underscores common challenges, including dataset limitations, variability in preprocessing approaches, and the need for more interpretable models. Conclusions: This study provides a comprehensive evaluation of AI-based methods in SZ prognosis, emphasizing the strengths and limitations of current approaches. By identifying unresolved gaps, it offers valuable directions for future research in the application of AI for SZ detection and diagnosis. Full article
Show Figures

Figure 1

Figure 1
<p>The projected rate of schizophrenia among a population of 100 individuals, adjusted for age, in the year 2021 (taken from [<a href="#B17-diagnostics-14-02698" class="html-bibr">17</a>]).</p>
Full article ">Figure 2
<p>SZ diagnosis utilizing ML and DL techniques.</p>
Full article ">Figure 3
<p>Flow chart of the proposed survey on the automatic detection of SZ.</p>
Full article ">Figure 4
<p>PRISMA 2020 flow diagram for selecting appropriate literature on the automatic detection of SZ.</p>
Full article ">Figure 5
<p>A bar graph depicting the number of articles related to the diagnosis of SZ with ML and DL methodologies published during the past decade. This is a non-exhaustive list of publications.</p>
Full article ">Figure 6
<p>Data statistics of the COBRE dataset [<a href="#B55-diagnostics-14-02698" class="html-bibr">55</a>].</p>
Full article ">Figure 7
<p>Data statistics of the RepOD dataset [<a href="#B57-diagnostics-14-02698" class="html-bibr">57</a>].</p>
Full article ">Figure 8
<p>Data statistics of the NUSDAST dataset [<a href="#B58-diagnostics-14-02698" class="html-bibr">58</a>].</p>
Full article ">Figure 9
<p>Data statistics of the UCLA dataset [<a href="#B59-diagnostics-14-02698" class="html-bibr">59</a>].</p>
Full article ">Figure 10
<p>Data statistics of the SchizConnect dataset [<a href="#B60-diagnostics-14-02698" class="html-bibr">60</a>].</p>
Full article ">Figure 11
<p>Data statistics of the MCIC dataset [<a href="#B61-diagnostics-14-02698" class="html-bibr">61</a>].</p>
Full article ">Figure 12
<p>Data statistics of the MLSP2014 dataset [<a href="#B62-diagnostics-14-02698" class="html-bibr">62</a>].</p>
Full article ">Figure 13
<p>(<b>a</b>) Data statistics of the MSU EEG dataset. (<b>b</b>) Topographical positions of channel numbers [<a href="#B63-diagnostics-14-02698" class="html-bibr">63</a>].</p>
Full article ">Figure 14
<p>Data statistics of the FBIRN dataset: (<b>a</b>) Phase II and (<b>b</b>) Phase III [<a href="#B64-diagnostics-14-02698" class="html-bibr">64</a>].</p>
Full article ">Figure 15
<p>Taxonomy of neuroimaging modalities for SZ detection and classification.</p>
Full article ">Figure 16
<p>EEG signals of an HC and an SZ patient (obtained from [<a href="#B67-diagnostics-14-02698" class="html-bibr">67</a>]).</p>
Full article ">Figure 17
<p>Flowchart of the CAD approach for automatic SZ detection with EEG signals developed by Aslan et al. [<a href="#B1-diagnostics-14-02698" class="html-bibr">1</a>].</p>
Full article ">Figure 18
<p>SZ diagnosis utilizing sMRI ((<b>Left</b>): enlarged ventricles indicate SZ. (<b>Right</b>): typical ventricles indicate a healthy condition) [<a href="#B29-diagnostics-14-02698" class="html-bibr">29</a>].</p>
Full article ">Figure 19
<p>Snapshots of various categories within the NAMIC dataset: (<b>a</b>) HCs and (<b>b</b>) patients with SZ [<a href="#B104-diagnostics-14-02698" class="html-bibr">104</a>].</p>
Full article ">Figure 20
<p>SZ diagnosis utilizing fMRI [<a href="#B29-diagnostics-14-02698" class="html-bibr">29</a>].</p>
Full article ">Figure 21
<p>Architecture diagram of the study proposed by Nallusamy et al. [<a href="#B114-diagnostics-14-02698" class="html-bibr">114</a>].</p>
Full article ">
Back to TopTop