Organizations: Vanderbilt University, Tennessee, USA · Vanderbilt University Medical Center, Tennessee, USA · Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan · School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
Quantifying disease-associated renal tubular remodeling is challenging because tubular appearances are heterogeneous. We introduce TuMAP (Tubular Morphotype-Aware Pathomics), a pipeline combining (1) dual-view foundation-model representations and provisional morphotype annotation, (2) compositional and within-morphotype pathomics, and (3) patient-level statistical inference. From 456,158 tubules in 358 PAS-stained kidney biopsy slides, TuMAP identified eight image-based morphotypes, seven of which showed stable subsampling assignments. Across 219 patients in six diagnostic groups, diabetic nephropathy (DN) and tubulointerstitial nephritis/acute tubular injury (TIN/ATI) each differed from minimal change disease in seven morphotype proportions, while IgA nephropathy differed in six. DN showed reduced nuclear solidity and increased eccentricity across all eight morphotypes. Area-normalized nuclear density exposed additional within-morphotype differences. TuMAP provides a framework for separating changes in tubular morphotype composition from phenotypic differences within morphotypes.
Figures & tables
Figure 1: Overview of the TuMAP pipeline. (1) Dual-view tubular representation: Texture and shape views encoded with frozen UNI2-h are harmonized and clustered into provisional M1–M8 morphotypes. (2) Dual-level morphotype-aware pathomics: Composition and within-morphotype phenotypes are quantified. (3) Patient-level statistical inference: Measurements are aggregated per patient and morphotype (red circle: M1 median solidity in one DN biopsy; note different y-axis scales), followed by regression with HC3 robust standard errors and FDR control.
Diagnosis
Patients
Tubules
Tubules/patient
GS (%)
MCD
23
33,486
1446 [1156-1722]
4.3 [0.0–13.4]
MN
37
53,603
1426 [1154-1714]
4.6 [0.0–15.6]
LN
28
43,628
1418 [1197-1980]
9.4 [2.9–23.6]
IgAN
39
43,228
1049 [879-1234]
22.2 [10.0–50.0]
TIN/ATI
28
30,931
1070 [805-1402]
20.0 [0.0–34.4]
DN
64
78,236
1164 [1008-1388]
52.7 [33.3–64.6]
Table 1: Comparison cohort (219 patients). Tubules: total on analyzed sections; tubules/patient: median [IQR]. GS: globally sclerosed glomeruli (%), median [IQR] (190 patients with available GS%).
Figure 2: Eight provisional morphotypes (456,158 tubules; 358 slides). Left: UMAP (200,000 points). Right: M1–M8 counts, median area/circularity, and representative tubules (20-µm bars). Segment-like names are not immunohistochemically confirmed.
Figure 3: Patient-level comparisons vs. MCD ( n=219 ). (a) Mean morphotype shares (%) with adjusted logit-share effects (SD). (b,c) Tubular/nuclear effects (SD), labeled by M number; dots mark FDR q<0.05 . (d–f) M1 tubular solidity, nuclear minor axis, and assigned nuclei per 10,000 µm 2 of contour area (including lumen). Points represent patients; asterisks mark FDR q<0.05 .
Chronic kidney disease is characterized by structural alterations in renal tissue and progressive loss of kidney function. While glomerular subtype ratios provide a compact and clinically meaningful summary of glomerular composition, representing pathomic information using whole-slide image (WSI)-level mean values diminishes glomerulus-level heterogeneity and the contribution of less prevalent patterns. In this proof-of-concept study, we investigated whether modeling individual glomeruli using multiple-instance learning (MIL) could provide complementary information to conventional subtype ratios for estimated glomerular filtration rate (eGFR) classification. We analyzed 162 kidney-biopsy WSIs from 162 patients, categorizing renal function as eGFR < 60 or >= 60 mL/min/1.73 m^2. Quantitative size, shape, intensity, and texture features were extracted from segmented glomeruli, representing each patient as a bag of glomerular instances. An attention-based MIL model was trained to aggregate these heterogeneous pathomic profiles. We evaluated subtype ratios, pathomics, and their combination using ABMIL, with a mean-pooled multilayer perceptron baseline. In five-fold cross-validation, the subtype-ratio-only model achieved an AUC of 0.7262 +/- 0.0596. MIL using pathomics alone achieved an AUC of 0.7362 +/- 0.0788, whereas integrating pathomics with subtype ratios produced the highest mean AUC of 0.7630 +/- 0.0665. SHapley Additive exPlanations (SHAP) were used to examine individual feature contributions. These results demonstrate that MIL-based pathomics can complement established glomerular subtype ratios by capturing additional glomerulus-level information for quantitative kidney-biopsy analysis.
Glomerular pathology is central to the diagnosis and prognosis of renal diseases, yet the heterogeneity of glomerular morphology and fine-grained lesion patterns remain challenging for current AI approaches. We present GloPath, an entity-centric foundation model trained on over one million glomeruli extracted from 14,049 renal biopsy specimens using multi-scale and multi-view self-supervised learning. GloPath addresses two major challenges in nephropathology: glomerular lesion assessment and clinicopathological insights discovery. For lesion assessment, GloPath was benchmarked across three independent cohorts on 52 tasks, including lesion recognition, grading, few-shot classification, and cross-modality diagnosis-outperforming state-of-the-art methods in 42 tasks (80.8%). In the large-scale real-world study, it achieved an ROC-AUC of 91.51% for lesion recognition, demonstrating strong robustness in routine clinical settings. For clinicopathological insights, GloPath systematically revealed statistically significant associations between glomerular morphological parameters and clinical indicators across 224 morphology-clinical variable pairs, demonstrating its capacity to connect tissue-level pathology with patient-level outcomes. Together, these results position GloPath as a scalable and interpretable platform for glomerular lesion assessment and clinicopathological discovery, representing a step toward clinically translatable AI in renal pathology.
Qiming He, Jing Li, Tian Guan +26
Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Interdisciplinary Institute for Medical Engineering, Fuzhou University, Fuzhou, China · Medical Optical Technology R&D Center, Research Institute of Tsinghua, Pearl River Delta, Guangzhou, China +6
Fine-grained evaluation of glomerular pathology must distinguish normal glomeruli from abnormalities such as global and segmental glomerulosclerosis, obsolescent, ischemic, solidified, disappearing, and atubular glomeruli. Supervised classification requires labeled examples of every category, which is impractical when subtypes are rare or absent from the training cohort. One-class anomaly detection offers an alternative by modeling normal data and scoring deviations, allowing previously unseen abnormalities to be detected. We use the frozen residual U-Net backbone of Omni-Seg, pretrained to segment structurally normal renal primitives without abnormal-subtype labels. We propose NoRDeC (Normal-Reference Detection and Characterization), a framework combining Mahalanobis normal-reference scoring with layer-wise representation analysis to determine whether and where glomerular pathology is encoded, how spatial aggregation affects detection, and whether abnormalities alter inter-layer relationships differently. Using glomerular images from two institutions, we evaluate backbone layers and aggregation strategies, compare NoRDeC with PaDiM and PatchCore, and analyze representations using centered kernel alignment (CKA). Layer 4 with Center-70 aggregation achieved a pooled AUROC of 0.926±0.013. NoRDeC achieved the highest AUROC in six of seven abnormality categories and in the pooled analysis, while CKA suggested subtype-dependent changes in inter-layer relationships not captured by anomaly scores alone. The normal-reference model is fitted using only normal glomeruli; abnormality labels are used for configuration selection, evaluation, and grouping in the representation analysis. These results show that a frozen renal feature extractor can support both detection and representation-level characterization of glomerular abnormalities without using abnormal examples to fit the detector.
Greta Hasko, Rachit Saluja, Tianyu Shi +11
Cornell University, Ithaca, NY 14853, USA · Cornell Tech, New York, NY 10044, USA · Sichuan University, Chengdu, 610207, CN +6