Cascade-EC Network: Recognition of Gastrointestinal Multiple Lesions Based on EfficientNet and CA_stm_Retinanet

Xudong Guo; Lei Xu; Shengnan Li; Meidong Xu; Yuan Chu; Qinfen Jiang

doi:10.1007/s10278-024-01096-9

Cascade-EC Network: Recognition of Gastrointestinal Multiple Lesions Based on EfficientNet and CA_stm_Retinanet

J Imaging Inform Med. 2024 Apr 8. doi: 10.1007/s10278-024-01096-9. Online ahead of print.

Authors

Xudong Guo¹, Lei Xu², Shengnan Li², Meidong Xu³, Yuan Chu⁴, Qinfen Jiang⁵

Affiliations

¹ School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China. guoxd@usst.edu.cn.
² School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China.
³ Endoscopy Center, Department of Gastroenterology, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, 200120, China. 1800512@tongji.edu.cn.
⁴ Endoscopy Center, Department of Gastroenterology, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, 200120, China.
⁵ Department of Information Management, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, 200120, China.

PMID: 38587768
DOI: 10.1007/s10278-024-01096-9

Abstract

Capsule endoscopy (CE) is non-invasive and painless during gastrointestinal examination. However, capsule endoscopy can increase the workload of image reviewing for clinicians, making it prone to missed and misdiagnosed diagnoses. Current researches primarily concentrated on binary classifiers, multiple classifiers targeting fewer than four abnormality types and detectors within a specific segment of the digestive tract, and segmenters for a single type of anomaly. Due to intra-class variations, the task of creating a unified scheme for detecting multiple gastrointestinal diseases is particularly challenging. A cascade neural network designed in this study, Cascade-EC, can automatically identify and localize four types of gastrointestinal lesions in CE images: angiectasis, bleeding, erosion, and polyp. Cascade-EC consists of EfficientNet for image classification and CA_stm_Retinanet for lesion detection and location. As the first layer of Cascade-EC, the EfficientNet network classifies CE images. CA_stm_Retinanet, as the second layer, performs the target detection and location task on the classified image. CA_stm_Retinanet adopts the general architecture of Retinanet. Its feature extraction module is the CA_stm_Backbone from the stack of CA_stm Block. CA_stm Block adopts the split-transform-merge strategy and introduces the coordinate attention. The dataset in this study is from Shanghai East Hospital, collected by PillCam SB3 and AnKon capsule endoscopes, which contains a total of 7936 images of 317 patients from the years 2017 to 2021. In the testing set, the average precision of Cascade-EC in the multi-lesions classification task was 94.55%, the average recall was 90.60%, and the average F1 score was 92.26%. The mean mAP@ 0.5 of Cascade-EC for detecting the four types of diseases is 85.88%. The experimental results show that compared with a single target detection network, Cascade-EC has better performance and can effectively assist clinicians to classify and detect multiple lesions in CE images.

Keywords: Capsule endoscopy; Cascade-EC; Lesion detection and location; Split-transform-merge strategy.

Abstract

Grants and funding