Deep Learning-Based Artificial Intelligence System for Automatic Assessment of Glomerular Pathological Findings in Lupus Nephritis
Accurate assessment of renal histopathology is crucial for the clinical management of patients with lupus nephritis (LN). However, the current classification system has poor interpathologist agreement. This paper proposes a deep convolutional neural network (CNN)-based system that detects and classi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/11/1983 |
| _version_ | 1827676864077889536 |
|---|---|
| author | Zhaohui Zheng Xiangsen Zhang Jin Ding Dingwen Zhang Jihong Cui Xianghui Fu Junwei Han Ping Zhu |
| author_facet | Zhaohui Zheng Xiangsen Zhang Jin Ding Dingwen Zhang Jihong Cui Xianghui Fu Junwei Han Ping Zhu |
| author_sort | Zhaohui Zheng |
| collection | DOAJ |
| description | Accurate assessment of renal histopathology is crucial for the clinical management of patients with lupus nephritis (LN). However, the current classification system has poor interpathologist agreement. This paper proposes a deep convolutional neural network (CNN)-based system that detects and classifies glomerular pathological findings in LN. A dataset of 349 renal biopsy whole-slide images (WSIs) (163 patients with LN, periodic acid-Schiff stain, 3906 glomeruli) annotated by three expert nephropathologists was used. The CNN models YOLOv4 and VGG16 were employed to localise the glomeruli and classify glomerular lesions (slight/severe impairments or sclerotic lesions). An additional 321 unannotated WSIs from 161 patients were used for performance evaluation at the per-patient kidney level. The proposed model achieved an accuracy of 0.951 and Cohen’s kappa of 0.932 (95% CI 0.915–0.949) for the entire test set for classifying the glomerular lesions. For multiclass detection at the glomerular level, the mean average precision of the CNN was 0.807, with ‘slight’ and ‘severe’ glomerular lesions being easily identified (F1: 0.924 and 0.952, respectively). At the per-patient kidney level, the model achieved a high agreement with nephropathologist (linear weighted kappa: 0.855, 95% CI: 0.795–0.916, <i>p</i> < 0.001; quadratic weighted kappa: 0.906, 95% CI: 0.873–0.938, <i>p</i> < 0.001). The results suggest that deep learning is a feasible assistive tool for the objective and automatic assessment of pathological LN lesions. |
| first_indexed | 2024-03-10T05:34:15Z |
| format | Article |
| id | doaj.art-36a7fad20db24340aca6e81348af65c3 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T05:34:15Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-36a7fad20db24340aca6e81348af65c32023-11-22T23:00:38ZengMDPI AGDiagnostics2075-44182021-10-011111198310.3390/diagnostics11111983Deep Learning-Based Artificial Intelligence System for Automatic Assessment of Glomerular Pathological Findings in Lupus NephritisZhaohui Zheng0Xiangsen Zhang1Jin Ding2Dingwen Zhang3Jihong Cui4Xianghui Fu5Junwei Han6Ping Zhu7Department of Clinical Immunology, Xijing Hospital, Fourth Military Medical University, Xi’an 710032, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an 710072, ChinaDepartment of Clinical Immunology, Xijing Hospital, Fourth Military Medical University, Xi’an 710032, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an 710072, ChinaLab of Tissue Engineering, College of Life Sciences, Northwest University, Xi’an 710069, ChinaDepartment of Clinical Immunology, Xijing Hospital, Fourth Military Medical University, Xi’an 710032, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an 710072, ChinaDepartment of Clinical Immunology, Xijing Hospital, Fourth Military Medical University, Xi’an 710032, ChinaAccurate assessment of renal histopathology is crucial for the clinical management of patients with lupus nephritis (LN). However, the current classification system has poor interpathologist agreement. This paper proposes a deep convolutional neural network (CNN)-based system that detects and classifies glomerular pathological findings in LN. A dataset of 349 renal biopsy whole-slide images (WSIs) (163 patients with LN, periodic acid-Schiff stain, 3906 glomeruli) annotated by three expert nephropathologists was used. The CNN models YOLOv4 and VGG16 were employed to localise the glomeruli and classify glomerular lesions (slight/severe impairments or sclerotic lesions). An additional 321 unannotated WSIs from 161 patients were used for performance evaluation at the per-patient kidney level. The proposed model achieved an accuracy of 0.951 and Cohen’s kappa of 0.932 (95% CI 0.915–0.949) for the entire test set for classifying the glomerular lesions. For multiclass detection at the glomerular level, the mean average precision of the CNN was 0.807, with ‘slight’ and ‘severe’ glomerular lesions being easily identified (F1: 0.924 and 0.952, respectively). At the per-patient kidney level, the model achieved a high agreement with nephropathologist (linear weighted kappa: 0.855, 95% CI: 0.795–0.916, <i>p</i> < 0.001; quadratic weighted kappa: 0.906, 95% CI: 0.873–0.938, <i>p</i> < 0.001). The results suggest that deep learning is a feasible assistive tool for the objective and automatic assessment of pathological LN lesions.https://www.mdpi.com/2075-4418/11/11/1983lupus nephritisrenal biopsyhistopathologydeep learningartificial intelligence |
| spellingShingle | Zhaohui Zheng Xiangsen Zhang Jin Ding Dingwen Zhang Jihong Cui Xianghui Fu Junwei Han Ping Zhu Deep Learning-Based Artificial Intelligence System for Automatic Assessment of Glomerular Pathological Findings in Lupus Nephritis Diagnostics lupus nephritis renal biopsy histopathology deep learning artificial intelligence |
| title | Deep Learning-Based Artificial Intelligence System for Automatic Assessment of Glomerular Pathological Findings in Lupus Nephritis |
| title_full | Deep Learning-Based Artificial Intelligence System for Automatic Assessment of Glomerular Pathological Findings in Lupus Nephritis |
| title_fullStr | Deep Learning-Based Artificial Intelligence System for Automatic Assessment of Glomerular Pathological Findings in Lupus Nephritis |
| title_full_unstemmed | Deep Learning-Based Artificial Intelligence System for Automatic Assessment of Glomerular Pathological Findings in Lupus Nephritis |
| title_short | Deep Learning-Based Artificial Intelligence System for Automatic Assessment of Glomerular Pathological Findings in Lupus Nephritis |
| title_sort | deep learning based artificial intelligence system for automatic assessment of glomerular pathological findings in lupus nephritis |
| topic | lupus nephritis renal biopsy histopathology deep learning artificial intelligence |
| url | https://www.mdpi.com/2075-4418/11/11/1983 |
| work_keys_str_mv | AT zhaohuizheng deeplearningbasedartificialintelligencesystemforautomaticassessmentofglomerularpathologicalfindingsinlupusnephritis AT xiangsenzhang deeplearningbasedartificialintelligencesystemforautomaticassessmentofglomerularpathologicalfindingsinlupusnephritis AT jinding deeplearningbasedartificialintelligencesystemforautomaticassessmentofglomerularpathologicalfindingsinlupusnephritis AT dingwenzhang deeplearningbasedartificialintelligencesystemforautomaticassessmentofglomerularpathologicalfindingsinlupusnephritis AT jihongcui deeplearningbasedartificialintelligencesystemforautomaticassessmentofglomerularpathologicalfindingsinlupusnephritis AT xianghuifu deeplearningbasedartificialintelligencesystemforautomaticassessmentofglomerularpathologicalfindingsinlupusnephritis AT junweihan deeplearningbasedartificialintelligencesystemforautomaticassessmentofglomerularpathologicalfindingsinlupusnephritis AT pingzhu deeplearningbasedartificialintelligencesystemforautomaticassessmentofglomerularpathologicalfindingsinlupusnephritis |