Application of deep learning in the real-time diagnosis of gastric lesion based on magnifying optical enhancement videos

Mingjun Ma; Zhen Li; Tao Yu; Guanqun Liu; Rui Ji; Guangchao Li; Zhuang Guo; Limei Wang; Qingqing Qi; Xiaoxiao Yang; Junyan Qu; Xiao Wang; Xiuli Zuo; Hongliang Ren; Yanqing Li

doi:10.3389/fonc.2022.945904

Application of deep learning in the real-time diagnosis of gastric lesion based on magnifying optical enhancement videos

Front Oncol. 2022 Aug 5:12:945904. doi: 10.3389/fonc.2022.945904. eCollection 2022.

Authors

Mingjun Ma^{1

2

3}, Zhen Li^{1

2

3}, Tao Yu^{1

2

3}, Guanqun Liu^{1

2

3}, Rui Ji^{1

2

3}, Guangchao Li^{1

2

3}, Zhuang Guo⁴, Limei Wang^{1

2

3}, Qingqing Qi^{1

2

3}, Xiaoxiao Yang^{1

2

3}, Junyan Qu^{1

2

3}, Xiao Wang⁵, Xiuli Zuo^{1

2

3}, Hongliang Ren^{6

7}, Yanqing Li^{1

2

3}

Affiliations

¹ Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China.
² Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China.
³ Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China.
⁴ Department of Gastroenterology, Shengli Oilfield Central Hospital, Dongying, China.
⁵ Department of Pathology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China.
⁶ Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China.
⁷ Department of Biomedical Engineering, National University of Singapore, Singapore, Singapore.

Abstract

Background and aim: Magnifying image-enhanced endoscopy was demonstrated to have higher diagnostic accuracy than white-light endoscopy. However, differentiating early gastric cancers (EGCs) from benign lesions is difficult for beginners. We aimed to determine whether the computer-aided model for the diagnosis of gastric lesions can be applied to videos rather than still images.

Methods: A total of 719 magnifying optical enhancement images of EGCs, 1,490 optical enhancement images of the benign gastric lesions, and 1,514 images of background mucosa were retrospectively collected to train and develop a computer-aided diagnostic model. Subsequently, 101 video segments and 671 independent images were used for validation, and error frames were labeled to retrain the model. Finally, a total of 117 unaltered full-length videos were utilized to test the model and compared with those diagnostic results made by independent endoscopists.

Results: Except for atrophy combined with intestinal metaplasia (IM) and low-grade neoplasia, the diagnostic accuracy was 0.90 (85/94). The sensitivity, specificity, PLR, NLR, and overall accuracy of the model to distinguish EGC from non-cancerous lesions were 0.91 (48/53), 0.78 (50/64), 4.14, 0.12, and 0.84 (98/117), respectively. No significant difference was observed in the overall diagnostic accuracy between the computer-aided model and experts. A good level of kappa values was found between the model and experts, which meant that the kappa value was 0.63.

Conclusions: The performance of the computer-aided model for the diagnosis of EGC is comparable to that of experts. Magnifying the optical enhancement model alone may not be able to deal with all lesions in the stomach, especially when near the focus on severe atrophy with IM. These results warrant further validation in prospective studies with more patients. A ClinicalTrials.gov registration was obtained (identifier number: NCT04563416).

Clinical trial registration: ClinicalTrials.gov, identifier NCT04563416.

Keywords: convolutional neural network; deep learning; early gastric cancer; image-enhanced endoscopy; tumor diagnosis.

Associated data

ClinicalTrials.gov/NCT04563416