Intrapapillary capillary loop classification in magnification endoscopy: open dataset and baseline methodology

Autor: Wen-Lun Wang, Martin Everson, Tom Vercauteren, Hsiu-Po Wang, Rehan Haidry, Danail Stoyanov, Laurence Lovat, Sebastien Ourselin, Luis C. Garcia-Peraza-Herrera
Jazyk: angličtina
Rok vydání: 2020
Předmět:
FOS: Computer and information sciences
Technology
Esophageal Neoplasms
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
0302 clinical medicine
Engineering
Intrapapillary capillary loop (IPCL)
Image and Video Processing (eess.IV)
Radiology
Nuclear Medicine & Medical Imaging
General Medicine
Computer Graphics and Computer-Aided Design
3. Good health
Computer Science Applications
030220 oncology & carcinogenesis
Benchmark (computing)
030211 gastroenterology & hepatology
Original Article
Computer Vision and Pattern Recognition
SQUAMOUS-CELL CARCINOMA
Abnormality
Life Sciences & Biomedicine
medicine.medical_specialty
Loop (graph theory)
Class activation map (CAM)
Biomedical Engineering
Health Informatics
Context (language use)
03 medical and health sciences
Esophagus
medicine
FOS: Electrical engineering
electronic engineering
information engineering
Humans
Radiology
Nuclear Medicine and imaging
Neoplasms
Squamous Cell
Engineering
Biomedical
Science & Technology
ESOPHAGEAL
business.industry
Frame (networking)
Pattern recognition
Endoscopy
Electrical Engineering and Systems Science - Image and Video Processing
Magnification endoscopy
DEPTH
Histopathology
Surgery
Artificial intelligence
business
Early squamous cell neoplasia (ESCN)
Zdroj: International Journal of Computer Assisted Radiology and Surgery
García-Peraza-Herrera, L C, Everson, M, Lovat, L, Wang, H-P, Wang, W L, Haidry, R, Stoyanov, D, Ourselin, S & Vercauteren, T 2020, ' Intrapapillary capillary loop classification in magnification endoscopy : open dataset and baseline methodology ', International Journal of Computer Assisted Radiology and Surgery, vol. 15, no. 4, pp. 651-659 . https://doi.org/10.1007/s11548-020-02127-w
ISSN: 1861-6429
1861-6410
DOI: 10.1007/s11548-020-02127-w
Popis: Purpose. Early squamous cell neoplasia (ESCN) in the oesophagus is a highly treatable condition. Lesions confined to the mucosal layer can be curatively treated endoscopically. We build a computer-assisted detection (CADe) system that can classify still images or video frames as normal or abnormal with high diagnostic accuracy. Methods. We present a new benchmark dataset containing 68K binary labeled frames extracted from 114 patient videos whose imaged areas have been resected and correlated to histopathology. Our novel convolutional network (CNN) architecture solves the binary classification task and explains what features of the input domain drive the decision-making process of the network. Results. The proposed method achieved an average accuracy of 91.7 % compared to the 94.7 % achieved by a group of 12 senior clinicians. Our novel network architecture produces deeply supervised activation heatmaps that suggest the network is looking at intrapapillary capillary loop (IPCL) patterns when predicting abnormality. Conclusion. We believe that this dataset and baseline method may serve as a reference for future benchmarks on both video frame classification and explainability in the context of ESCN detection. A future work path of high clinical relevance is the extension of the classification to ESCN types.
Accepted by IJCARS
Databáze: OpenAIRE
Externí odkaz: