← Back to all news
arXiv Computer Vision By Greta Hasko, Rachit Saluja, Tianyu Shi, Leiyue Zhao, Yuechen Yang, Daniel Reisenbuechler, Tianyuan Yao, Zhenhao Guo, John Cannon, Haichun Yang, Yuankai Huo, Yuling Chi, Lorraine Gudas, Mert R. Sabuncu, Yihe Yang, Ruining Deng

Seeing Abnormal from Normal: Glomerular Abnormality in Representations of Normal Renal Morphology

Read the original on arXiv Computer Vision →

The paper introduces NoRDeC, a one‑class anomaly detection framework that uses a frozen residual U‑Net backbone pretrained on normal renal morphology to identify and characterize glomerular abnormalities. By combining Mahalanobis normal‑reference scoring with layer‑wise representation analysis and centered kernel alignment, NoRDeC achieves high AUROC scores across multiple abnormality categories, outperforming existing methods such as PaDiM and PatchCore. The study demonstrates that a model trained solely on normal glomeruli can detect unseen pathological subtypes and reveal subtype‑dependent changes in inter‑layer relationships without requiring abnormal training examples.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Jun 9

Robust Renal Mass Segmentation on CT: A Validation Study of an AI-Based Framework

arXiv:2505. 07573v2 Announce Type: replace-cross Abstract: Renal mass segmentation has important potential to enhance the clinical workflow, especially in settings requiring quantitative assessments.

By Sarah de Boer, Hartmut H\"antze, Kiran Vaidhya Venkadesh, Myrthe A. D. Buser, Gabriel E. Humpire Mamani, Lina Xu, Lisa C. Adams, Jawed Nawabi, Keno K. Bressem, Bram van Ginneken, Mathias Prokop, Alessa Hering
computer-visionbenchmarks
More like this →
arXiv Machine Learning
Jul 15

From Many to Meaningful: Feature-Guided Zero-Shot Chronic Kidney Disease Screening Using Large Language Models

arXiv:2607. 12260v1 Announce Type: new Abstract: Early screening of chronic kidney disease (CKD) is essential for preventing irreversible progression; however, many machine learning (ML)-based screening methods remain difficult to deploy in community and resource-limited screening settings due to their reliance on large labeled datasets, resource-intensive pathology tests, or high-dimensional clinical features, and limited robustness to population and distributional shifts.

By Muhammad Ashad Kabir, Sirajam Munira
llms
More like this →
arXiv AI
Jun 30

Towards Modality-Agnostic Medical Image Anomaly Detection: A Training-Free Manifold Refinement Approach

arXiv:2604. 19191v2 Announce Type: replace-cross Abstract: Deploying AI-based anomaly detection across diverse clinical imaging settings remains challenging because most existing methods rely on modality-specific architectures, anatomical priors, or extensive retraining, limiting their use as general-purpose screening tools.

By Pritam Kar, Gouri Lakshmi S, Saptarshi Bej
ragdiffusionbenchmarks
More like this →
arXiv Machine Learning
Aug 4

Development and Validation of a Dynamic Kidney Failure Prediction Model based on Deep Learning: A Real-World Study with External Validation

arXiv:2501. 16388v3 Announce Type: replace Abstract: Background: Chronic kidney disease (CKD), a progressive disease with high morbidity and mortality, has become a significant global public health problem.

By Jingying Ma, Jinwei Wang, Lanlan Lu, Zhiqin Jiang, Mengling Feng, Feifei Zhang, Peng Shen, Yexiang Sun, Shenda Hong, Luxia Zhang
safety
More like this →