Evaluating tubulointerstitial compartments in renal biopsy specimens using a deep learning-based approach for classifying normal and abnormal tubules

Abstract

Renal pathology is essential for diagnosing and assessing the severity and prognosis of kidney diseases. Deep learning-based approaches have developed rapidly and have been applied in renal pathology. However, methods for the automated classification of normal and abnormal renal tubules remain scarce. Using a deep learning-based method, we aimed to classify normal and abnormal renal tubules, thereby assisting renal pathologists in the evaluation of renal biopsy specimens. Consequently, we developed a U-Net-based segmentation model using randomly selected regions obtained from 21 renal biopsy specimens. Further, we verified its performance in multiclass segmentation by calculating the Dice coefficients (DCs). We used 15 cases of tubulointerstitial nephritis to assess its applicability in aiding routine diagnoses conducted by renal pathologists and calculated the agreement ratio between diagnoses conducted by two renal pathologists and the time taken for evaluation. We also determined whether such diagnoses were improved when the output of segmentation was considered. The glomeruli and interstitium had the highest DCs, whereas the normal and abnormal renal tubules had intermediate DCs. Following the detailed evaluation of the tubulointerstitial compartments, the proximal, distal, atrophied, and degenerated tubules had intermediate DCs, whereas the arteries and inflamed tubules had low DCs. The annotation and output areas involving normal and abnormal tubules were strongly correlated in each class. The pathological concordance for the glomerular count, t, ct, and ci scores of the Banff classification of renal allograft pathology remained high with or without the segmented images. However, in terms of time consumption, the quantitative assessment of tubulitis, tubular atrophy, degenerated tubules, and the interstitium was improved significantly when renal pathologists considered the segmentation output. Deep learning algorithms can assist renal pathologists in the classification of normal and abnormal tubules in renal biopsy specimens, thereby facilitating the enhancement of renal pathology and ensuring appropriate clinical decisions.

Tubular and Glomerular Size by Cortex Depth as Predictor of Progressive CKD after Radical Nephrectomy for Tumor

“…More refined assessment of tubular size using digital pathology with deep learning models to quantify the size of glomeruli and tubules at different depths may be needed to make the morphometric evaluation of kidney biopsies practical. [53][54][55][56][57][58] Assessment of morphometry by depth is a challenge with commonly used needle core biopsies. However, the presence of a capsule can be used to identify superficial cortical depths where distal tubule diameter is more prognostic for progressive CKD.…”

High-throughput image analysis with deep learning captures heterogeneity and spatial relationships after kidney injury

“…For example, periodic acid-Schiff (PAS) staining is used routinely to study kidney disease. Recently, U-Net-based architectures have been reported for the segmentation of tissue compartments in PAS-stained kidney sections 16 , 19 , 20 . These tools use a large set of training data to produce remarkably accurate results.…”

Artificial Intelligence Reporting Guidelines’ Adherence in Nephrology for Improved Research and Clinical Outcomes

“…Diagnostic accuracy study : The application of diagnostic and prognostic AI algorithms is becoming more popular in nephrology and urology, such as in kidney transplant pathology [ 39 , 40 , 41 ], delayed graft function prediction [ 42 , 43 , 44 ], kidney transplant survival [ 45 ], and medical image analysis to detect glomerulosclerosis [ 46 , 47 , 48 ]. Interestingly, AI-provided diagnostic accuracies are similar to those provided by expert clinicians, which might significantly save healthcare resource use [ 32 , 49 ].…”