AI and Rare Diseases ── Kidney, liver and gut ── 2026-10-16

Input is PAS-stained biopsy images. Because MEST-C assessment relies on pathologist interpretation, DU-KAN, a dual-branch encoder framework, segments the images with mean Dice 69.58%, then aggregates outputs into case-level MEST-C-related indicators. In 40 exploratory cases, full agreement was 65.00% and sensitivity for E was 37.50%, so it serves only as an auxiliary reference. — Image abstract — the whole article on one page (click to enlarge)

1 Kidney, liver and gut papers. Lead: DU-KAN: A Dual-Domain Enhanced Deep-Learning Framework for Digital Pathology-Based Oxford MEST-C Assessment in Pediatric IgA Nephropathy

Journals covered and how papers are chosen: see the index

Rare kidney, liver and gastrointestinal diseases: treatment, trials and AI

DU-KAN: A Dual-Domain Enhanced Deep-Learning Framework for Digital Pathology-Based Oxford MEST-C Assessment in Pediatric IgA Nephropathy
Bioengineering · 2026-10-13 · Evidence: Single-center model development with internal validation (exploratory 40-case evaluation; no external validation)
Abstract
Oxford MEST-C assessment of pediatric immunoglobulin A nephropathy (IgAN) relies on pathologists’ interpretation of complex renal biopsy structures. Automated segmentation may support standardized quantification but is challenged by scale variation, weak boundaries, and small lesions. We developed DU-KAN, a stage-adapted U-KAN framework combining a shallow convolution–MaxViT dual-branch encoder with adapted heterogeneous feature fusion and wavelet–prototype skip enhancement. A single-center dataset of 532 periodic acid–Schiff-stained images from 278 children was partitioned at the patient level. On the held-out test set of 55 patients, DU-KAN achieved a mean Dice of 69.58% across eight classes, including background (95% patient-level bootstrap CI, 66.23–71.91), exceeding U-KAN by 3.56 percentage points (95% CI, 1.90–5.26). Foreground mean Dice was 65.42%. On the Synapse abdominal CT benchmark, mean Dice across eight organs was 87.21%, supporting cross-task architectural generalization, rather than external validation in pediatric IgAN. Segmentation outputs were further aggregated into case-level MEST-C-related indicators. In an exploratory 40-case evaluation, complete agreement across the five assessed indicators was 65.00% (26/40), while sensitivity was 37.50% for E (3/8) and 50.00% for T (1/2). The 97.50% agreement for T largely reflected the predominance of negative cases and did not establish reliable positive-case detection. DU-KAN improves the internal segmentation performance and achieves structured pathological quantification, which can provide auxiliary reference for clinical judgment of renal pathologists.
Journal IF-equivalent: 5.4 (OpenAlex 2-year mean citedness, value as of 2026-10-15, retrieved 2026-10-16; not the official Clarivate IF)
Reference: Fu J, Cui H, Zhu Y, Gao T, Zhang P, Gao C. DU-KAN: A Dual-Domain Enhanced Deep-Learning Framework for Digital Pathology-Based Oxford MEST-C Assessment in Pediatric IgA Nephropathy. Bioengineering. 2026 Oct 13;13(10):1191. doi:10.3390/bioengineering13101191.
Checked: Abstract only

← Back to this issue