Diagnosis of Esophageal Lesions by Multi-Classification and Segmentation Using an Improved Multi-Task Deep Learning Model

Sensors

Tong Fang¹  Suigu Tang¹  Chak-Fong Cheang¹  Zeming Hu¹  Xiaoyuan Yu¹  Hon-Ho Yu²  I-Cheong Choi² 

[1] Faculty of Information Technology, Macau University of Science and Technology, Macau 999078, China;Kiang Wu Hospital, Macau 999078, China;

关键词: classification;    deep learning;    esophageal lesions;    gastrointestinal endoscopy;    multi-task;    segmentation;   

DOI  :  10.3390/s22041492

来源: DOAJ

【 摘 要 】

It is challenging for endoscopists to accurately detect esophageal lesions during gastrointestinal endoscopic screening due to visual similarities among different lesions in terms of shape, size, and texture among patients. Additionally, endoscopists are busy fighting esophageal lesions every day, hence the need to develop a computer-aided diagnostic tool to classify and segment the lesions at endoscopic images to reduce their burden. Therefore, we propose a multi-task classification and segmentation (MTCS) model, including the Esophageal Lesions Classification Network (ELCNet) and Esophageal Lesions Segmentation Network (ELSNet). The ELCNet was used to classify types of esophageal lesions, and the ELSNet was used to identify lesion regions. We created a dataset by collecting 805 esophageal images from 255 patients and 198 images from 64 patients to train and evaluate the MTCS model. Compared with other methods, the proposed not only achieved a high accuracy (93.43%) in classification but achieved a dice similarity coefficient (77.84%) in segmentation. In conclusion, the MTCS model can boost the performance of endoscopists in the detection of esophageal lesions as it can accurately multi-classify and segment the lesions and is a potential assistant for endoscopists to reduce the risk of oversight.

【 授权许可】

Unknown