Knowledge Distillation with a Class-Aware Loss for Endoscopic Disease Detection
Authors: 
Pedro E. Chavarrias-Solano, Mansoor A. Teevno, Gilberto Ochoa-Ruiz, Sharib AliAuthors Info & Claims
Pages 67 - 76
Abstract
Prevalence of gastrointestinal (GI) cancer is growing alarmingly every year leading to a substantial increase in the mortality rate. Endoscopic detection is providing crucial diagnostic support, however, subtle lesions in upper and lower GI are quite hard to detect and cause considerable missed detection. In this work, we leverage deep learning to develop a framework to improve the localization of difficult to detect lesions and minimize the missed detection rate. We propose an end to end student-teacher learning setup where class probabilities of a trained teacher model on one class with larger dataset are used to penalize multi-class student network. Our model achieves higher performance in terms of mean average precision (mAP) on both endoscopic disease detection (EDD2020) challenge and Kvasir-SEG datasets. Additionally, we show that using such learning paradigm, our model is generalizable to unseen test set giving higher APs for clinically crucial neoplastic and polyp categories.
References
[1]
Ali, S., et al.: Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy. Med. Image Anal. 70, 102002 (2021). arXiv: 2010.06034
[2]
Ali, S., et al.: Endoscopy disease detection challenge 2020. arXiv preprint arXiv:2003.03376 (2020)
[3]
Arnold M et al. Global burden of 5 major types of gastrointestinal cancer Gastroenterology 2020 159 1 335-349.e15
[4]
Badrinarayanan V, Kendall A, and Cipolla R SegNet: a deep convolutional encoder-decoder architecture for image segmentation IEEE Trans. Pattern Anal. Mach. Intell. 2017 39 12 2481-2495
[5]
Chen BL, Wan JJ, Chen TY, Yu YT, and Ji M A self-attention based faster R-CNN for polyp detection from colonoscopy images Biomed. Signal Process. Control 2021 70 103019
[6]
Gjestang, H.L., Hicks, S.A., Thambawita, V., Halvorsen, P., Riegler, M.A.: A self-learning teacher-student framework for gastrointestinal image classification. In: 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS), pp. 539–544. IEEE (2021)
[7]
Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey (2020). https://arxiv.org/abs/2006.05525
[8]
Horie Y et al. Diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks Gastrointest. Endosc. 2019 89 1 25-32
[9]
Hou W, Wang L, Cai S, Lin Z, Yu R, and Qin J Early neoplasia identification in Barrett’s esophagus via attentive hierarchical aggregation and self-distillation Med. Image Anal. 2021 72 102092
[10]
Jha D, et al., et al. Ro YM, et al., et al. Kvasir-SEG: a segmented polyp dataset MultiMedia Modeling 2020 Cham Springer 451-462
[11]
Jia X et al. Automatic polyp recognition in colonoscopy images using deep learning and two-stage pyramidal feature prediction IEEE Trans. Autom. Sci. Eng. 2020 17 3 1570-1584
[12]
Krenzer, A., Hekalo, A., Puppe, F.: Endoscopic detection and segmentation of gastroenterological diseases with deep convolutional neural networks. In: EndoCV@ ISBI, pp. 58–63 (2020)
[13]
Li, X., Liu, R., Li, M., Liu, Y., Jiang, L., Zhou, C.: Real-time polyp detection for colonoscopy video on CPU. In: 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), pp. 890–897. IEEE (2020)
[14]
Niyaz, U., Bathula, D.R.: Augmenting knowledge distillation with peer-to-peer mutual learning for model compression. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), pp. 1–4. IEEE (2022)
[15]
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv:1506.01497, January 2016. http://arxiv.org/abs/1506.01497
[16]
Shin Y, Qadir HA, Aabakken L, Bergsland J, and Balasingham I Automatic colon polyp detection using region based deep CNN and post learning approaches IEEE Access 2018 6 40950-40962
[17]
Turshudzhyan A, Rezaizadeh H, and Tadros M Lessons learned: preventable misses and near-misses of endoscopic procedures World J. Gastrointest. Endosc. 2022 14 5 302-310
[18]
Urban G et al. Deep learning localizes and identifies polyps in real time with 96% accuracy in screening colonoscopy Gastroenterology 2018 155 4 1069-1078
[19]
Wang, D., et al.: AFP-Net: realtime anchor-free polyp detection in colonoscopy. In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), pp. 636–643. IEEE (2019)
[20]
Wang P et al. Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy Nat. Biomed. Eng. 2018 2 10 741-748
[21]
Yamada M et al. Development of a real-time endoscopic image diagnosis support system using deep learning technology in colonoscopy Sci. Rep. 2019 9 1 1-9
[22]
Zhang R, Zheng Y, Poon CC, Shen D, and Lau JY Polyp detection during colonoscopy using a regression-based convolutional neural network with a tracker Pattern Recogn. 2018 83 209-219
[23]
Zhang X et al. Real-time gastric polyp detection using convolutional neural networks PLoS ONE 2019 14 3 e0214133
Recommendations
A novel method for reducing arrhythmia classification from 12-lead ECG signals to single-lead ECG with minimal loss of accuracy through teacher-student knowledge distillation
Highlights- Introducing a method for arrhythmia classification of 12-lead electrocardiogram(ECG).
AbstractDeep learning models developed through multi-lead electrocardiogram (ECG) signals are considered the leading methods for the automated detection of arrhythmia on computer systems. However, due to the amplitudes of input signals, these ...
An Accurate Urine Erythrocytes Detection Model Coupled Faster RCNN with VggNet
CAIH2020: Proceedings of the 2020 Conference on Artificial Intelligence and HealthcareIn the process of kidney disease diagnosis, it is particularly important to screen the morphology of erythrocytes in urine. Because of the small and similar morphology of erythrocytes in urine, manual labeling and observation is time-consuming and labor-...
CASMatching strategy for automated detection and quantification of carotid artery stenosis based on digital subtraction angiography
Highlights- A novel solution to accurately predict morphological indices of carotid artery stenosis based on digital subtraction angiography, improving interpretability and accuracy.
- A customized detection strategy named CASMatching to model the ...
Abstract Background and objectiveAutomated detection and quantification of carotid artery stenosis is a crucial task in establishing a computer-aided diagnostic system for brain diseases. Digital subtraction angiography (DSA) is known as the "gold ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Sep 2022
174 pages
ISBN:978-3-031-17978-5
DOI:10.1007/978-3-031-17979-2
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 22 September 2022
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 21 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in