Abstract
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, p < 0.001; quadratic weighted kappa: 0.906, 95% CI: 0.873–0.938, p < 0.001). The results suggest that deep learning is a feasible assistive tool for the objective and automatic assessment of pathological LN lesions.
Highlights
Lupus nephritis (LN) affects up to 40% of adults and 80% of children with systemic lupus erythematosus and is a major cause of morbidity and mortality [1]
Accurate renal impairment evaluation is vital for guiding treatment and improving the prognosis of LN [4,5] and to date, renal biopsy is the gold standard for LN diagnosis
Specimens stained by periodic acid-Schiff (PAS) were employed because PAS-stained kidney wholeslide images (WSIs) can yield the best concordance between pathologists and deep learning segmentation across all structures [18,19]
Summary
Lupus nephritis (LN) affects up to 40% of adults and 80% of children with systemic lupus erythematosus and is a major cause of morbidity and mortality [1]. The International Society of Nephrology and the Renal Pathology Society (ISN/RPS) categorised glomerular lesions in LN from class I to VI and the activity of renal involvement in terms of active and chronic indices [6,7]. The current ISN/RPS classification system has been recognised and adopted by renal pathologists worldwide, obstacles to its application remain, in that it is highly subjective and depends on the experience of the pathologist. Wilhelmus et al showed that the global interobserver agreement regarding the recognition of class III and IV lesions was very poor, and highly experienced pathologists had higher agreement than less experienced pathologists [10]. A systemic review by Dasari et al indicated that the interpathologist agreement in assessing the LN ISN/RPS class, active indices, and chronic indices was poor to moderate overall [11]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
