Upper Gastronintestinal Ulcer Segmentation Model of Endoscopic Images
Using DeepLab V3+ Network Framework
XUE Yuhan1,2, ZHOU Yijia1,2, HE Yu1,2, LIN Jiaxi1,3, ZHU Jinzhou1,3, LIU Xiaolin1,3,
WANG Yu4, XU Chunfang1,3, YIN Minyue1,3
1. Department of Gastroenterology, The First Affiliated Hospital of Soochow University, Suzhou Jiangsu 215006, China;
2. Suzhou Medical College of Soochow University, Suzhou Jiangsu 215123, China; 3. Suzhou Clinical Center of Digestive Diseases,
Suzhou Jiangsu 215006, China; 4. Department of General Surgery, Jintan Hospital Affiliated to Jiangsu University,
Changzhou Jiangsu 213200, China
Abstract:Objective Based on DeepLab V3+ network framework, to construct a deep learning computer vision model to achieve
more accurate semantic segmentation of upper gastrointestinal ulcer endoscopic images. Methods The encoder of the DeepLab
V3+ network framework initially extracted features from images using multiple parallel dilated convolutional layers with varying
sampling rates, followed by global average pooling to achieve multi-scale feature extraction. In the decoder section, the deep feature
layer was up-sampled four times while the shallow feature layer was stacked and adjusted in size to match that of the input image
before generating predictions. The prediction results of the model were obtained. Results In the internal validation set, the accuracy
(ACC) of the model was 0.963, and the mean intersection over union (mIoU) was 0.927. In the external test set, the ACC and mIoU
were 0.958 and 0.915. All of them were better than the traditional algorithm U-Net (internal validation set ACC was 0.810, mIoU
was 0.785; the external test set ACC was 0.779 and mIoU was 0.732). Conclusion The DeepLab V3+ network framework has high
accuracy in identifying lesions, and has good clinical practice.
薛雨涵1,2,周亦佳1,2,何宇1,2,林嘉希1,3,朱锦舟1,3,刘晓琳1,3,王玉4,许春芳1,3,殷民月1,3. 基于DeepLab V3+网络框架的上消化道
溃疡内镜图像分割模型[J]. 中国医疗设备, 2023, 38(11): 22-26.
XUE Yuhan1,2, ZHOU Yijia1,2, HE Yu1,2, LIN Jiaxi1,3, ZHU Jinzhou1,3, LIU Xiaolin1,3,
WANG Yu4, XU Chunfang1,3, YIN Minyue1,3. Upper Gastronintestinal Ulcer Segmentation Model of Endoscopic Images
Using DeepLab V3+ Network Framework. China Medical Devices, 2023, 38(11): 22-26.