Histopathological Diagnosis System for Gastritis Using Deep Learning Algorithm

Ba Wei; Wang Shuhao; Liu Cancheng; Wang Yuefeng; Shi Huaiyin; Song Zhigang

doi:10.24920/003962

Your Location：

Home >

Browse articles >

Histopathological Diagnosis System for Gastritis Using Deep Learning Algorithm

Chinese Medical Sciences Journal Vol. 36, Issue 3, Pages: 204-209(2021)

ORIGINAL ARTICLE | Updated：2024-04-10

- Histopathological Diagnosis System for Gastritis Using Deep Learning Algorithm
- Affiliations：
  
  1. 1Department of Pathology, Chinese PLA General Hospital & Medical School, Beijing 100853, China
  2. 2Artificial Intelligence Lab, Thorough Images,Beijing 100853, China
- Author bio：
  
  *Tel: 86-13810410643; E-mail: songzhg301@139.com
- Funds：
- DOI：10.24920/003962
  CLC：
- Received：29 June 2021，
  
  Accepted：2021-8-18，
  
  Published Online：31 August 2021，
  
  Published：31 August 2021
- Accepted：
Scan QR Code
Ba Wei, Wang Shuhao, Liu Cancheng, et al. Histopathological Diagnosis System for Gastritis Using Deep Learning Algorithm[J]. Chinese medical sciences journal, 2021, 36(3): 204-209.
DOI：

Ba Wei, Wang Shuhao, Liu Cancheng, et al. Histopathological Diagnosis System for Gastritis Using Deep Learning Algorithm[J]. Chinese medical sciences journal, 2021, 36(3): 204-209. DOI： 10.24920/003962.

摘要

目的

开发一种用于慢性胃炎病理分类的深度学习算法

并使用全切片病理图像（whole slide images

WSI）评估其性能。

方法

回顾性收集解放军总医院胃活检标本1

250例（胃炎1

128例

正常胃黏膜122例）。分别使用1

008张和100张WSIs

基于DeepLab v3（ResNet-50）架构训练和验证深度学习算法

并在142张WSIs的独立测试集上测试该算法对不同胃炎亚型的诊断效能。

结果

模型为测试集中的慢性浅表性胃炎（chronic superficial gastritis

CSuG）、慢性活动性胃炎（chronic active gastritis

CAcG）和慢性萎缩性胃炎（chronic atrophic gastritis

CAtG）作出诊断所生成的受试者工作特征（receiver operating characteristic

ROC）曲线的曲线下面积分别为0.882、0.905和0.910。深度学习算法对CSuG、CAcG和CAtG分类的敏感性和特异性分别为0.790和1.000（准确度0.880）、0.985和0.829（准确度0.901）、0.952和0.992（准确度0.986）。对三种不同类型胃炎诊断的总体准确度为 0.867。通过在 WSI 中标记算法识别的可疑区域

可以生成更为透明和可解释的诊断结果。

结论

深度学习算法使用WSI对慢性胃炎进行病理学分型具有较高的准确性。通过预先标记出不同类型胃炎的区域

深度学习算法可以作为辅助诊断工具

提高病理医生的工作效率。

Abstract

Objective

To develope a deep learning algorithm for pathological classification of chronic gastritis and assess its performance using whole-slide images (WSIs).

Methods

We retrospectively collected 1

250 gastric biopsy specimens (1

128 gastritis

122 normal mucosa) from PLA General Hospital. The deep learning algorithm based on DeepLab v3 (ResNet-50) architecture was trained and validated using 1

008 WSIs and 100 WSIs

respectively. The diagnostic performance of the algorithm was tested on an independent test set of 142 WSIs

with the pathologists’ consensus diagnosis as the gold standard.

Results

The receiver operating characteristic (ROC) curves were generated for chronic superficial gastritis (CSuG)

chronic active gastritis (CAcG)

and chronic atrophic gastritis (CAtG) in the test set

respectively.The areas under the ROC curves (AUCs) of the algorithm for CSuG

CAcG

and CAtG were 0.882

0.905 and 0.910

respectively. The sensitivity and specificity of the deep learning algorithm for the classification of CSuG

CAcG

and CAtG were 0.790 and 1.000 (accuracy 0.880)

0.985 and 0.829 (accuracy 0.901)

0.952 and 0.992 (accuracy 0.986)

respectively. The overall predicted accuracy for three different types of gastritis was 0.867. By flagging the suspicious regions identified by the algorithm in WSI

a more transparent and interpretable diagnosis can be generated.

Conclusion

The deep learning algorithm achieved high accuracy for chronic gastritis classification using WSIs. By pre-highlighting the different gastritis regions

it might be used as an auxiliary diagnostic tool to improve the work efficiency of pathologists.

关键词

Keywords

references

Correa P , Yardley JH . Grading and classification of chronic gastritis: one American response to the Sydney system . Gastroenterology 1992 ; 102 ( 1 ): 355 - 9 . doi: 10.1016/0016-5085(92)91820-t 1001-9294-36-3-204/0016-5085(92)91820-t . DOI: 10.1016/0016-5085(92)91820-t http://doi.org/10.1016/0016-5085(92)91820-t

Price AB , Misiewicz JJ . Grading and classification of chronic gastritis: the response of the working party . Gastroenterology 1992 ; 103 ( 3 ): 1116 - 7 . doi: 10.1016/0016-5085(92)90066-8 1001-9294-36-3-204/0016-5085(92)90066-8 . DOI: 10.1016/0016-5085(92)90066-8 http://doi.org/10.1016/0016-5085(92)90066-8

Dixon MF , Genta RM , Yardley JH , et al . Classification and grading of gastritis. The updated Sydney System. International Workshop on the Histopathology of Gastritis, Houston 1994 . Am J Surg Pathol 1996 ; 20 ( 10 ): 1161 - 81 . doi: 10.1097/00000478-199610000-00001 1001-9294-36-3-204/00000478-199610000-00001 . DOI: 10.1097/00000478-199610000-00001 http://doi.org/10.1097/00000478-199610000-00001

Stolte M , Meining A . The updated Sydney system: classification and grading of gastritis as the basis of diagnosis and treatment . Can J Gastroenterol 2001 ; 15 ( 9 ): 591 - 8 . doi: 10.1155/2001/367832 1001-9294-36-3-204/2001/367832 . DOI: 10.1155/2001/367832 http://doi.org/10.1155/2001/367832 http://www.hindawi.com/journals/cjgh/2001/367832/abs/ http://www.hindawi.com/journals/cjgh/2001/367832/abs/

Metter DM , Colgan TJ , Leung ST , et al . Trends in the US and Canadian Pathologist Workforces From 2007 to 2017 . JAMA Netw Open 2019 ; 2 ( 5 ): e194337 . doi: 10.1001/jamanetworkopen.2019.4337 1001-9294-36-3-204/jamanetworkopen.2019.4337 . DOI: 10.1001/jamanetworkopen.2019.4337 http://doi.org/10.1001/jamanetworkopen.2019.4337 http://jamanetworkopen.jamanetwork.com/article.aspx?doi=10.1001/jamanetworkopen.2019.4337 http://jamanetworkopen.jamanetwork.com/article.aspx?doi=10.1001/jamanetworkopen.2019.4337

Retamero JA , Aneiros-Fernandez J , Del Moral RG . Complete digital pathology for routine histopathology diagnosis in a multicenter hospital network . Arch Pathol Lab Med 2020 ; 144 ( 2 ): 221 - 8 . doi: 10.5858/arpa.2018-0541-OA 1001-9294-36-3-204/arpa.2018-0541-OA . DOI: 10.5858/arpa.2018-0541-OA http://doi.org/10.5858/arpa.2018-0541-OA

Cruz-Roa A , Gilmore H , Basavanhally A , et al . Accurate and reproducible invasive breast cancer detection in whole-slide images: A deep learning approach for quantifying tumor extent . Sci Rep 2017 ; 7 : 46450 . doi: 10.1038/srep46450 1001-9294-36-3-204/srep46450 . DOI: 10.1038/srep46450 http://doi.org/10.1038/srep46450

Ehteshami Bejnordi B , Veta M , Johannes van Diest P , et al . Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer . JAMA 2017 ; 318 ( 2 ): 2199 - 210 . doi: 10.1001/jama.2017.14585 1001-9294-36-3-204/jama.2017.14585 . DOI: 10.1001/jama.2017.14585 http://doi.org/10.1001/jama.2017.14585 http://jama.jamanetwork.com/article.aspx?doi=10.1001/jama.2017.14585 http://jama.jamanetwork.com/article.aspx?doi=10.1001/jama.2017.14585

Coudray N , Ocampo PS , Sakellaropoulos T , et al . Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning . Nature Medicine 2018 ; 24 ( 10 ): 1559 . doi: 10.1038/s41591-018-0177-5 1001-9294-36-3-204/s41591-018-0177-5 . DOI: 10.1038/s41591-018-0177-5 http://doi.org/10.1038/s41591-018-0177-5 https://doi.org/10.1038/s41591-018-0177-5 https://doi.org/10.1038/s41591-018-0177-5

Khosravi P , Kazemi E , Imielinski M , et al . Deep convolutional neural networks enable discrimination of heterogeneous digital pathology images . EBioMedicine 2018 ; 27 : 317 - 28 . doi: 10.1016/j.ebiom.2017.12.026 1001-9294-36-3-204/j.ebiom.2017.12.026 . DOI: S2352-3964(17)30507-8 http://doi.org/S2352-3964(17)30507-8

Ba W , Wang R , Yin G , et al . Diagnostic assessment of deep learning for melanocytic lesions using whole-slide pathological images . Transl Onc 2021 ; 6 ( 1 ): 475 .doi: 10.1016/j.tranon.2021.101161 1001-9294-36-3-204/j.tranon.2021.101161 . DOI: 10.1016/j.tranon.2021.101161 http://doi.org/10.1016/j.tranon.2021.101161

Golden JA . Deep learning algorithms for detection of lymph node metastases from breast cancer: helping artificial intelligence be seen . JAMA 2017 ; 318 ( 22 ): 2184 - 6 . doi: 10.1001/jama.2017.14580 1001-9294-36-3-204/jama.2017.14580 . DOI: 10.1001/jama.2017.14580 http://doi.org/10.1001/jama.2017.14580 http://jama.jamanetwork.com/article.aspx?doi=10.1001/jama.2017.14580 http://jama.jamanetwork.com/article.aspx?doi=10.1001/jama.2017.14580

Pan Y , Sun Z , Wang W , et al . Automatic detection of squamous cell carcinoma metastasis in esophageal lymph nodes using semantic segmentation . Clin Transl Med 2020 ; 10 ( 3 ): e129 . doi: 10.1002/ctm2.129 1001-9294-36-3-204/ctm2.129 . DOI: 10.1002/ctm2.129 http://doi.org/10.1002/ctm2.129

Martin DR , Hanson JA , Gullapalli RR , et al . A deep learning convolutional neural network can recognize common patterns of injury in gastric pathology . Arch Pathol Lab Med 2020 ; 144 ( 3 ): 370 - 8 . doi: 10.5858/arpa.2019-0004-OA 1001-9294-36-3-204/arpa.2019-0004-OA . DOI: 10.5858/arpa.2019-0004-OA http://doi.org/10.5858/arpa.2019-0004-OA

Song Z , Zou S , Zhou W , et al . Clinically applicable histopathological diagnosis system for gastric cancer detection using deep learning . Nat Commun 2020 ; 11 ( 1 ): 4294 . doi: 10.1038/s41467-020-18147-8 1001-9294-36-3-204/s41467-020-18147-8 . DOI: 10.1038/s41467-020-18147-8 http://doi.org/10.1038/s41467-020-18147-8 https://doi.org/10.1038/s41467-020-18147-8 https://doi.org/10.1038/s41467-020-18147-8

Arvaniti E , Fricker KS , Moret M , et al . Automated Gleason grading of prostate cancer tissue microarrays via deep learning . Sci Rep 2018 ; 8 ( 1 ): 12054 . doi: 10.1038/s41598-018-30535-1 1001-9294-36-3-204/s41598-018-30535-1 . DOI: 10.1038/s41598-018-30535-1 http://doi.org/10.1038/s41598-018-30535-1

Topol EJ . High-performance medicine: the convergence of human and artificial intelligence . Nat Med 2019 ; 25 ( 1 ): 44 - 56 . doi: 10.1038/s41591-018-0300-7 1001-9294-36-3-204/s41591-018-0300-7 . DOI: 10.1038/s41591-018-0300-7 http://doi.org/10.1038/s41591-018-0300-7

Tschandl P . Problems and potentials of automated object detection for skin cancer recognition . JAMA Dermatol 2020 ; 156 ( 1 ): 23 - 4 . doi: 10.1001/jamadermatol.2019.3360 1001-9294-36-3-204/jamadermatol.2019.3360 . DOI: 10.1001/jamadermatol.2019.3360 http://doi.org/10.1001/jamadermatol.2019.3360

Views

523

Downloads

CSCD

Alert me when the article has been cited

Submit

Publicity Resources

Advances of Artificial Intelligence Application in Medical Imaging of Ovarian Cancers

Semi-supervised Long-tail Endoscopic Image Classification

External and Internal Validation of a Computer Assisted Diagnostic Model for Detecting Multi-Organ Mass Lesions in CT images

Radiomics in Antineoplastic Agents Development: Application and Challenge in Response Evaluation

An Insight of the First Community Infected COVID-19 Patient in Beijing by Imported Case: Role of Deep Learning-Assisted CT Diagnosis

Related Author

Xu Chen

Xiaofei Huo

Zhe Wu

Jingjing Lu

Runnan Cao

Mengjie Fang

Hailing Li

Jie Tian

Related Institution

Department of Radiology, Beijing United Family Hospital

Department of Radiology, Fushun Central Hospital

School of Artificial Intelligence, University of Chinese Academy of Sciences

CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences

Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University

⁰