A Multitask Network for the Diagnosis of Autoimmune Gastritis

Autoimmune gastritis (AIG) has a strong correlation with gastric neuroendocrine tumors (NETs) and gastric cancer, making its timely and accurate diagnosis crucial for tumor prevention. The endoscopic manifestations of AIG differ from those of gastritis caused by <i>Helicobacter pylori</i>...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuqi Cao, Yining Zhao, Xinao Jin, Jiayuan Zhang, Gangzhi Zhang, Pingjie Huang, Guangxin Zhang, Yuehua Han
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Journal of Imaging
Subjects:
Online Access:https://www.mdpi.com/2313-433X/11/5/154
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327014873399296
author Yuqi Cao
Yining Zhao
Xinao Jin
Jiayuan Zhang
Gangzhi Zhang
Pingjie Huang
Guangxin Zhang
Yuehua Han
author_facet Yuqi Cao
Yining Zhao
Xinao Jin
Jiayuan Zhang
Gangzhi Zhang
Pingjie Huang
Guangxin Zhang
Yuehua Han
author_sort Yuqi Cao
collection DOAJ
description Autoimmune gastritis (AIG) has a strong correlation with gastric neuroendocrine tumors (NETs) and gastric cancer, making its timely and accurate diagnosis crucial for tumor prevention. The endoscopic manifestations of AIG differ from those of gastritis caused by <i>Helicobacter pylori</i> (<i>H. pylori</i>) infection in terms of the affected gastric anatomical regions and the pathological characteristics observed in biopsy samples. Therefore, when diagnosing AIG based on endoscopic images, it is essential not only to distinguish between normal and atrophic gastric mucosa but also to accurately identify the anatomical region in which the atrophic mucosa is located. In this study, we propose a patient-based multitask gastroscopy image classification network that analyzes all images obtained during the endoscopic procedure. First, we employ the Scale-Invariant Feature Transform (SIFT) algorithm for image registration, generating an image similarity matrix. Next, we use a hierarchical clustering algorithm to group images based on this matrix. Finally, we apply the RepLKNet model, which utilizes large-kernel convolution, to each image group to perform two tasks: anatomical region classification and lesion recognition. Our method achieves an accuracy of 93.4 ± 0.5% (95% CI) and a precision of 92.6 ± 0.4% (95% CI) in the anatomical region classification task, which categorizes images into the fundus, body, and antrum. Additionally, it attains an accuracy of 90.2 ± 1.0% (95% CI) and a precision of 90.5 ± 0.8% (95% CI) in the lesion recognition task, which identifies the presence of gastric mucosal atrophic lesions in gastroscopy images. These results demonstrate that the proposed multitask patient-based gastroscopy image analysis method holds significant practical value for advancing computer-aided diagnosis systems for atrophic gastritis and enhancing the diagnostic accuracy and efficiency of AIG.
format Article
id doaj-art-b91b0ebb253f474aacae70c20d36d4e9
institution Kabale University
issn 2313-433X
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Journal of Imaging
spelling doaj-art-b91b0ebb253f474aacae70c20d36d4e92025-08-20T03:47:59ZengMDPI AGJournal of Imaging2313-433X2025-05-0111515410.3390/jimaging11050154A Multitask Network for the Diagnosis of Autoimmune GastritisYuqi Cao0Yining Zhao1Xinao Jin2Jiayuan Zhang3Gangzhi Zhang4Pingjie Huang5Guangxin Zhang6Yuehua Han7State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, ChinaDepartment of Gastroenterology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310000, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, ChinaDepartment of Gastroenterology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310000, ChinaAutoimmune gastritis (AIG) has a strong correlation with gastric neuroendocrine tumors (NETs) and gastric cancer, making its timely and accurate diagnosis crucial for tumor prevention. The endoscopic manifestations of AIG differ from those of gastritis caused by <i>Helicobacter pylori</i> (<i>H. pylori</i>) infection in terms of the affected gastric anatomical regions and the pathological characteristics observed in biopsy samples. Therefore, when diagnosing AIG based on endoscopic images, it is essential not only to distinguish between normal and atrophic gastric mucosa but also to accurately identify the anatomical region in which the atrophic mucosa is located. In this study, we propose a patient-based multitask gastroscopy image classification network that analyzes all images obtained during the endoscopic procedure. First, we employ the Scale-Invariant Feature Transform (SIFT) algorithm for image registration, generating an image similarity matrix. Next, we use a hierarchical clustering algorithm to group images based on this matrix. Finally, we apply the RepLKNet model, which utilizes large-kernel convolution, to each image group to perform two tasks: anatomical region classification and lesion recognition. Our method achieves an accuracy of 93.4 ± 0.5% (95% CI) and a precision of 92.6 ± 0.4% (95% CI) in the anatomical region classification task, which categorizes images into the fundus, body, and antrum. Additionally, it attains an accuracy of 90.2 ± 1.0% (95% CI) and a precision of 90.5 ± 0.8% (95% CI) in the lesion recognition task, which identifies the presence of gastric mucosal atrophic lesions in gastroscopy images. These results demonstrate that the proposed multitask patient-based gastroscopy image analysis method holds significant practical value for advancing computer-aided diagnosis systems for atrophic gastritis and enhancing the diagnostic accuracy and efficiency of AIG.https://www.mdpi.com/2313-433X/11/5/154autoimmune gastritisgastrointestinal endoscopy imagedeep learningmultitask networkclassificationimage registration
spellingShingle Yuqi Cao
Yining Zhao
Xinao Jin
Jiayuan Zhang
Gangzhi Zhang
Pingjie Huang
Guangxin Zhang
Yuehua Han
A Multitask Network for the Diagnosis of Autoimmune Gastritis
Journal of Imaging
autoimmune gastritis
gastrointestinal endoscopy image
deep learning
multitask network
classification
image registration
title A Multitask Network for the Diagnosis of Autoimmune Gastritis
title_full A Multitask Network for the Diagnosis of Autoimmune Gastritis
title_fullStr A Multitask Network for the Diagnosis of Autoimmune Gastritis
title_full_unstemmed A Multitask Network for the Diagnosis of Autoimmune Gastritis
title_short A Multitask Network for the Diagnosis of Autoimmune Gastritis
title_sort multitask network for the diagnosis of autoimmune gastritis
topic autoimmune gastritis
gastrointestinal endoscopy image
deep learning
multitask network
classification
image registration
url https://www.mdpi.com/2313-433X/11/5/154
work_keys_str_mv AT yuqicao amultitasknetworkforthediagnosisofautoimmunegastritis
AT yiningzhao amultitasknetworkforthediagnosisofautoimmunegastritis
AT xinaojin amultitasknetworkforthediagnosisofautoimmunegastritis
AT jiayuanzhang amultitasknetworkforthediagnosisofautoimmunegastritis
AT gangzhizhang amultitasknetworkforthediagnosisofautoimmunegastritis
AT pingjiehuang amultitasknetworkforthediagnosisofautoimmunegastritis
AT guangxinzhang amultitasknetworkforthediagnosisofautoimmunegastritis
AT yuehuahan amultitasknetworkforthediagnosisofautoimmunegastritis
AT yuqicao multitasknetworkforthediagnosisofautoimmunegastritis
AT yiningzhao multitasknetworkforthediagnosisofautoimmunegastritis
AT xinaojin multitasknetworkforthediagnosisofautoimmunegastritis
AT jiayuanzhang multitasknetworkforthediagnosisofautoimmunegastritis
AT gangzhizhang multitasknetworkforthediagnosisofautoimmunegastritis
AT pingjiehuang multitasknetworkforthediagnosisofautoimmunegastritis
AT guangxinzhang multitasknetworkforthediagnosisofautoimmunegastritis
AT yuehuahan multitasknetworkforthediagnosisofautoimmunegastritis