1. Computer aided detection for laterally spreading tumors and sessile serrated adenomas during colonoscopy
- Author
-
Shan Lei, Guanyu Zhou, Liangping Li, Ren-yi Zhang, Pu Wang, Mengtian Tu, Dan Yang, Han Wang, Xiaogang Liu, Xun Xiao, Peixi Liu, and Yan Song
- Subjects
Adenoma ,Computer and Information Sciences ,Histology ,Colon ,Science ,Colonoscopy ,Colonic Polyps ,Surgical and Invasive Medical Procedures ,Pathology and Laboratory Medicine ,03 medical and health sciences ,Digestive System Procedures ,0302 clinical medicine ,Deep Learning ,Signs and Symptoms ,Diagnostic Medicine ,medicine ,Image Processing, Computer-Assisted ,Medicine and Health Sciences ,Humans ,Miss rate ,Colorectal Cancer ,Multidisciplinary ,medicine.diagnostic_test ,business.industry ,Cancers and Neoplasms ,Biology and Life Sciences ,Endoscopy ,Adenomas ,Computer aided detection ,Gastrointestinal Tract ,Data Acquisition ,Oncology ,030220 oncology & carcinogenesis ,Lesions ,Detection performance ,Medicine ,030211 gastroenterology & hepatology ,Anatomy ,Nuclear medicine ,business ,Colorectal Neoplasms ,Digestive System ,Research Article - Abstract
BackgroundEvidence has shown that deep learning computer aided detection (CADe) system achieved high overall detection accuracy for polyp detection during colonoscopy.AimThe detection performance of CADe system on non-polypoid laterally spreading tumors (LSTs) and sessile serrated adenomas/polyps (SSA/Ps), with higher risk for malignancy transformation and miss rate, has not been exclusively investigated.MethodsA previously validated deep learning CADe system for polyp detection was tested exclusively on LSTs and SSA/Ps. 1451 LST images from 184 patients were collected between July 2015 and January 2019, 82 SSA/Ps videos from 26 patients were collected between September 2018 and January 2019. The per-frame sensitivity and per-lesion sensitivity were calculated.Results(1) For LSTs image dataset, the system achieved an overall per-image sensitivity and per-lesion sensitivity of 94.07% (1365/1451) and 98.99% (197/199) respectively. The per-frame sensitivity for LST-G(H), LST-G(M), LST-NG(F), LST-NG(PD) was 93.97% (343/365), 98.72% (692/701), 85.71% (324/378) and 85.71% (6/7) respectively. The per-lesion sensitivity of each subgroup was 100.00% (71/71), 100.00% (64/64), 98.31% (58/59) and 80.00% (4/5). (2) For SSA/Ps video dataset, the system achieved an overall per-frame sensitivity and per-lesion sensitivity of 84.10% (15883/18885) and 100.00% (42/42), respectively.ConclusionsThis study demonstrated that a local-feature-prioritized automatic CADe system could detect LSTs and SSA/Ps with high sensitivity. The per-frame sensitivity for non-granular LSTs and small SSA/Ps should be further improved.
- Published
- 2020