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.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
8.0
4.5
Journals
Cancers
Special Issues
Endoscopic Ultrasound in Cancer Research
share announcement

Endoscopic Ultrasound in Cancer Research

A special issue of Cancers (ISSN 2072-6694). This special issue belongs to the section "Cancer Pathophysiology".

Deadline for manuscript submissions: closed (5 October 2024) | Viewed by 2956

Special Issue Editors

Dr. Enrique Perez-Cuadrado-Robles

E-Mail Website
Guest Editor
Department of Gastroenterology, Georges-Pompidou European Hospital, 75015 Paris, France
Interests: ERCP; pancreatic cancer; bilio-pancreatic endoscopy; endoscopic ultrasound
Dr. Marcus Hollenbach

E-Mail Website
Guest Editor
University of Leipzig Medical Center, Leipzig, Germany
Interests: diagnostic and interventional endoscopy; HBP-endoscopy; acute and chronic pancreatitis; pancreatic cancer; AI in endoscopy; papillectomy; bariatric endoscopy; EUS-guided interventions
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Endoscopic ultrasounds (EUS) are frequently used on patients with oncological conditions for diagnostic and therapeutic purposes. In addition, EUS produce high-quality images and can be used alongside other techniques (e.g., contrast and elastography imaging). In addition, EUS-guided fine needle biopsy (FNB) is the gold standard for the histopathological diagnosis of gastrointestinal tumors. In this technique, many dedicated needles are used.

Therapeutic EUS favors biliopancreatic endoscopy and does not require invasive surgical procedures. Indeed, therapeutic EUS is becoming more popular, with techniques such as EUS-guided biliary drainage, the creation of digestive anastomosis using lumen apposing metal stents (LAMS), fiducial placement, vascular therapies, or radiofrequency. In this issue of Cancers, we will cover all EUS-related topics in cancer research with a focus on new technologies and future perspectives. Multicenter studies and prospective research articles will be prioritized. 

Dr. Enrique Perez-Cuadrado-Robles
Dr. Marcus Hollenbach
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Cancers is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2900 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • endoscopic ultrasound
  • pancreatic cancer
  • LAMS
  • cholangiocarcinoma
  • radiofrequency
  • digestive anastomosis
  • gastric cancer

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Other

14 pages, 10404 KiB  
Article
Deep Learning in Endoscopic Ultrasound: A Breakthrough in Detecting Distal Cholangiocarcinoma
by Rares Ilie Orzan, Delia Santa, Noemi Lorenzovici, Thomas Andrei Zareczky, Cristina Pojoga, Renata Agoston, Eva-Henrietta Dulf and Andrada Seicean
Cancers 2024, 16(22), 3792; https://doi.org/10.3390/cancers16223792 - 11 Nov 2024
Viewed by 348
Abstract
Introduction: Cholangiocarcinoma (CCA) is a highly lethal malignancy originating in the bile ducts, often diagnosed late with poor prognosis. Differentiating benign from malignant biliary tumors remains challenging, necessitating advanced diagnostic techniques. Objective: This study aims to enhance the diagnostic accuracy of endoscopic ultrasound [...] Read more.
Introduction: Cholangiocarcinoma (CCA) is a highly lethal malignancy originating in the bile ducts, often diagnosed late with poor prognosis. Differentiating benign from malignant biliary tumors remains challenging, necessitating advanced diagnostic techniques. Objective: This study aims to enhance the diagnostic accuracy of endoscopic ultrasound (EUS) for distal cholangiocarcinoma (dCCA) using advanced convolutional neural networks (CCNs) for the classification and segmentation of EUS images, specifically targeting dCCAs, the pancreas, and the bile duct. Materials and Methods: In this retrospective study, EUS images from patients diagnosed with dCCA via biopsy and an EUS-identified bile duct tumor were evaluated. A custom CNN was developed for classification, trained on 156 EUS images. To enhance the model’s robustness, image augmentation techniques were applied, generating a total of 1248 images. For tumor and organ segmentation, the DeepLabv3+ network with ResNet50 architecture was utilized, employing Tversky loss to manage unbalanced classes. Performance evaluation included metrics such as accuracy, sensitivity, specificity, and Intersection over Union (IoU). These methods were implemented in collaboration with the ADAPTED Research Group at the Technical University of Cluj-Napoca. Results: The classification model achieved a high accuracy of 97.82%, with precision and specificity both at 100% and sensitivity at 94.44%. The segmentation models for the pancreas and bile duct demonstrated global accuracies of 84% and 90%, respectively, with robust IoU scores indicating good overlap between predicted and actual contours. The application performed better than the UNet model, particularly in generalization and boundary delineation. Conclusions: This study demonstrates the significant potential of AI in EUS imaging for dCCA, presenting a robust tool that enhances diagnostic accuracy and efficiency. The developed MATLAB application serves as a valuable aid for medical professionals, facilitating informed decision-making and improving patient outcomes in the diagnosis of cholangiocarcinoma and related pathologies. Full article
(This article belongs to the Special Issue Endoscopic Ultrasound in Cancer Research)
►▼ Show Figures

Figure 1

Figure 1
<p>(<b>a</b>) EUS aspect of a dCCA; (<b>b</b>) binary mask for tumor.</p> Full article ">Figure 2
<p>Architecture of the CNNs.</p> Full article ">Figure 3
<p>DeepLabv3+ architecture based on Resnet50.</p> Full article ">Figure 4
<p>Evolution of accuracy based on the number of epochs for tumor identification.</p> Full article ">Figure 5
<p>The different stages of tumor segmentation models after repeated training. (<b>A</b>) Tumor detection after the first training; (<b>B</b>) tumor detection after adjusting the brightness and contrast of the images to highlight the contours; (<b>C</b>) final training focusing on the alpha and beta loss parameters within the Tversky Loss function; (<b>a</b>) original image; (<b>b</b>) binary mask; (<b>c</b>) testing image.</p> Full article ">Figure 6
<p>Bile duct pathway segmentation. (<b>a</b>) Original image; (<b>b</b>) binary mask; (<b>c</b>) testing image.</p> Full article ">Figure 7
<p>Comparison of performance metrics between DeepLabv3+ and Unet.</p> Full article ">Figure 8
<p>Results of tumor segmentation using UNet. (<b>a</b>) Original image; (<b>b</b>) binary mask; (<b>c</b>) testing image.</p> Full article ">Figure 9
<p>(<b>a</b>) Main interface of the novel CCN used for dCCA detection; (<b>b</b>) the user interface has various functionalities for analyzing endoscopic ultrasound images.</p> Full article ">Figure 10
<p>View of the segmented regions, with distinct colors assigned to each organ to enhance visibility and differentiation. (<b>a</b>) All contours, including the tumor (red), pancreas (blue), and bile duct (green), are generated automatically by the CNN; (<b>b</b>) contours of the tumor (red) and pancreas (blue) are generated automatically by the CNN, while the bile duct (full red) is drawn manually.</p> Full article ">
11 pages, 2605 KiB  
Article
Application of Deep Learning for Real-Time Ablation Zone Measurement in Ultrasound Imaging
by Corinna Zimmermann, Adrian Michelmann, Yannick Daniel, Markus D. Enderle, Nermin Salkic and Walter Linzenbold
Cancers 2024, 16(9), 1700; https://doi.org/10.3390/cancers16091700 - 27 Apr 2024
Viewed by 1249
Abstract
Background: The accurate delineation of ablation zones (AZs) is crucial for assessing radiofrequency ablation (RFA) therapy’s efficacy. Manual measurement, the current standard, is subject to variability and potential inaccuracies. Aim: This study aims to assess the effectiveness of Artificial Intelligence (AI) in automating [...] Read more.
Background: The accurate delineation of ablation zones (AZs) is crucial for assessing radiofrequency ablation (RFA) therapy’s efficacy. Manual measurement, the current standard, is subject to variability and potential inaccuracies. Aim: This study aims to assess the effectiveness of Artificial Intelligence (AI) in automating AZ measurements in ultrasound images and compare its accuracy with manual measurements in ultrasound images. Methods: An in vitro study was conducted using chicken breast and liver samples subjected to bipolar RFA. Ultrasound images were captured every 15 s, with the AI model Mask2Former trained for AZ segmentation. The measurements were compared across all methods, focusing on short-axis (SA) metrics. Results: We performed 308 RFA procedures, generating 7275 ultrasound images across liver and chicken breast tissues. Manual and AI measurement comparisons for ablation zone diameters revealed no significant differences, with correlation coefficients exceeding 0.96 in both tissues (p < 0.001). Bland–Altman plots and a Deming regression analysis demonstrated a very close alignment between AI predictions and manual measurements, with the average difference between the two methods being −0.259 and −0.243 mm, for bovine liver and chicken breast tissue, respectively. Conclusion: The study validates the Mask2Former model as a promising tool for automating AZ measurement in RFA research, offering a significant step towards reducing manual measurement variability. Full article
(This article belongs to the Special Issue Endoscopic Ultrasound in Cancer Research)
►▼ Show Figures

Figure 1

Figure 1
<p>Self-designed test stand with liver tissue. The RFA probe (1) was horizontally introduced in the tissue which was placed in the tissue cup (3). The US transducer (2) was placed horizontally and perpendicular to the RFA probe at the location of the separator, as shown in the schematic on the right. For the adjustment the US transducer could be moved in three dimensions indicated by the white arrows.</p> Full article ">Figure 2
<p>Representation of AZ in US images of liver (first row) and chicken tissue (second row) and the labelled mask (green) and predicted mask (orange). The AZ is less hyperechoic represented in chicken breast tissue as in liver tissue. Larger image artifacts can be observed underneath the AZ in liver tissue with ongoing RFA, making the assessment of the under AZ contour difficult. An acoustic shadow can be observed in the case of chicken breast.</p> Full article ">Figure 3
<p>Box-plot diagrams comparing the mean values of AI predicted and US manual measured diameter of RFA ablation zones in bovine liver tissue (<b>left</b>) and chicken breast tissue (<b>right</b>).</p> Full article ">Figure 4
<p>Bland - Altman plots (<b>left</b>) for chicken breast tissue (red) and bovine liver (blue) depicting the reliability of AI predicted diameter in comparison with US manual measurement as ground truth. Deming regression plots (<b>right</b>) for chicken breast tissue (red) and bovine liver (blue), demonstrating the reliability of AI−predicted diameter in comparison with US manual measurement as ground truth.</p> Full article ">

Other

Jump to: Research

14 pages, 1422 KiB  
Systematic Review
Endoscopic Contrast-Enhanced Ultrasound and Fine-Needle Aspiration or Biopsy for the Diagnosis of Pancreatic Solid Lesions: A Systematic Review and Meta-Analysis
by Giorgio Esposto, Giuseppe Massimiani, Linda Galasso, Paolo Santini, Raffaele Borriello, Irene Mignini, Maria Elena Ainora, Alberto Nicoletti, Lorenzo Zileri Dal Verme, Antonio Gasbarrini, Sergio Alfieri, Giuseppe Quero and Maria Assunta Zocco
Cancers 2024, 16(9), 1658; https://doi.org/10.3390/cancers16091658 - 25 Apr 2024
Viewed by 841
Abstract
Introduction: Endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) and endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) are currently recommended for the pathologic diagnosis of pancreatic solid lesions (PSLs). The application of contrast-enhanced endoscopic ultrasound (ECEUS) could aid the endoscopist during an FNA and/or FNB procedure. CEUS is [...] Read more.
Introduction: Endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) and endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) are currently recommended for the pathologic diagnosis of pancreatic solid lesions (PSLs). The application of contrast-enhanced endoscopic ultrasound (ECEUS) could aid the endoscopist during an FNA and/or FNB procedure. CEUS is indeed able to better differentiate the pathologic tissue from the surrounding healthy pancreatic parenchyma and to detect necrotic areas and vessels. Objectives: Our objective was to evaluate if ECEUS could reduce the number of needle passes and side effects and increase the diagnostic efficacy of FNA and/or FNB. Methods: A comprehensive literature search of clinical studies was performed to explore if ECEUS-FNA or FNB could increase diagnostic accuracy and reduce the number of needle passes and adverse effects compared to standard EUS-FNA or FNB. In accordance with the study protocol, a qualitative and quantitative analysis of the evidence was planned. Results: The proportion of established diagnoses of ECEUS was 90.9% compared to 88.3% of EUS, with no statistically significant difference (p = 0.14). The diagnosis was made through a single step in 70.9% of ECEUS patients and in 65.3% of EUS patients, without statistical significance (p = 0.24). The incidence of adverse reactions was substantially comparable across both groups (p = 0.89). Conclusion: ECEUS-FNA and FNB do not appear superior to standard EUS-FNA and FNB for the diagnosis of pancreatic lesions. Full article
(This article belongs to the Special Issue Endoscopic Ultrasound in Cancer Research)
►▼ Show Figures

Figure 1

Figure 1
<p>PRISMA study selection flow diagram. PRISMA: preferred reporting items for systematic reviews and meta-analyses.</p> Full article ">Figure 2
<p>Risk-of-bias assessment according to RoB2 tool for quality assessment of randomized studies. RoB2: a revised Cochrane risk-of-bias tool for randomized trials [<a href="#B15-cancers-16-01658" class="html-bibr">15</a>,<a href="#B16-cancers-16-01658" class="html-bibr">16</a>,<a href="#B17-cancers-16-01658" class="html-bibr">17</a>,<a href="#B18-cancers-16-01658" class="html-bibr">18</a>].</p> Full article ">Figure 3
<p>Risk of bias assessment according to ROBINS-I tool for quality assessment of non-randomized interventional studies. ROBINS-I: a tool for assessing risk of bias in non-randomized studies of interventions [<a href="#B17-cancers-16-01658" class="html-bibr">17</a>,<a href="#B19-cancers-16-01658" class="html-bibr">19</a>,<a href="#B21-cancers-16-01658" class="html-bibr">21</a>,<a href="#B22-cancers-16-01658" class="html-bibr">22</a>,<a href="#B23-cancers-16-01658" class="html-bibr">23</a>].</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop