Nephrology

Unsupervised Anatomical Feature Learning via Diffusion Models: Enhanced Medical Image Segmentation with Denoising Diffusion Probabilistic Models

Acquiring pixel-level annotations for medical image segmentation is a severe bottleneck. Traditional U-Net architectures, while effective, learn local texture patterns and lack awareness of global anatomical structures, leading to boundary delineation failures in low-data regimes. This research paper proposes utilizing unsupervised Denoising Diffusion Probabilistic Models (DDPMs) to extract anatom...

Deep learning-mediated detection of accelerated water drinking after aquaresis in V1b vasopressin receptor knockout mice

How water intake is initiated and maintained following V2 vasopressin receptor antagonism remains poorly understood. To elucidate the role of the V1b receptor in managing dehydration stress induced by V2 antagonism, we used deep learning-based computer vision to analyze drinking behavior in V1b knockout (V1bKO) and wild-type (WT) mice. While total water access and intake volume were comparable bet...

Benchmarking Graph Neural Networks for Multi-Omics Cancer Subtyping using Methylation and Gene Expression Profiles

Motivation: Graph Neural Networks (GNNs) have gained increasing interest in the biomedical domain, as the integration of prior knowledge and deep neur...

Glucagon-like peptide-1 receptor agonist initiation and risk of clinically recorded Alzheimer's disease-type dementia in older adults with type 2 diabetes: a target trial emulation using causal machine learning

Background Glucagon-like peptide-1 (GLP-1) receptor agonists and sodium-glucose cotransporter-2 (SGLT2) inhibitors are increasingly used for type 2 di...

Can GPT Be Used as an Alternative Prediction Model to Traditional Machine Learning and Neural Networks on Low-Volume Clinical Data?

Background and Objective: Early and reliable disease prediction from structured clinical data remains challenging when datasets are small, highly imba...

Development and multi-dataset evaluation of a unified single-view deep-learning model for the right heart: four-chamber segmentation, biventricular ejection fraction, deformation, and pulmonary-hypertension prediction from the apical four-chamber echocardiogram

Background: Right ventricular (RV) function predicts survival in pulmonary hypertension (PH) and other cardiovascular diseases, yet echocardiographic ...

Anatomy-Informed Neural Networks: Encoding Anatomic Priors in Loss and Architecture, with an SE(3) Formulation of Guidewire-Induced Aortoiliac Deformation

Deep-learning models of anatomy can be numerically plausible yet anatomically impossible, and they generalize poorly when data are scarce. We introduc...

Explainable Clinician-Supervised Artificial Intelligence as an Implementation Framework for Cardiovascular-Kidney-Metabolic Population Health: Synthetic Data Validation of the CHAPERONE-CKM Framework

Abstract Background: Cardiovascular-kidney-metabolic (CKM) syndrome is an increasingly prevalent multisystem condition associated with morbidity, frag...

Robustness Gap of Large Language Models in Nephrology

Background: Whether benchmark performance reflects robust clinical reasoning rather than surface-level pattern recognition remains uncertain. We evalu...

PolypVision: A Three-Stage Hierarchical Deep Learning Framework for Classification and Segmentation of Colorectal Polyps

Colorectal cancer (CRC) remains one of the leading causes of cancer-related mortality worldwide, predominantly arising from precancerous polyps. Accur...

PET/CT Radiogenomic Mutation Prediction in Non-Small Cell Lung Cancer Using Multi-Label Learning

Lung cancer remains one of the leading causes of cancer- related mortality worldwide. Although targeted therapies have improved outcomes for patients ...

Explainable machine learning relates histological to genomic pathology

Background & Aims: Haematoxylin and eosin (H&E) staining remains the diagnostic gold standard for solid cancers, including hepatocellular carcinoma, a...

Multi-scale modeling of human tissues from spatial transcriptomics with TERRA

Spatial transcriptomics maps gene expression at cellular resolution, revealing how cells organize into multicellular niches. Yet computational analyse...

Paired Recipient-based Evaluation of Survival Prediction for Deceased Donor Kidney Transplants

There has been significant interest in using machine learning algorithms to predict kidney transplant outcomes, such as the number of years until a gr...

IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images

Most in-generation diffusion watermarks embed patterns independent of the image that carries them, and attackers transplant the marks onto images the ...

Architectural Safety Mechanisms for Multi-Agent Clinical LLM Systems Under Knowledge Base Distribution Shift

Objective: To evaluate whether multi-agent LLM architectures with explicit safety verification maintain guideline compliance when their clinical knowl...

Clinical characteristics and associated factors of de novo and recurrent prostate cancer after kidney transplantation

Kidney transplant recipients experience a higher burden of several malignancies, yet the factors associated with prostate cancer presentation after tr...

Interpretable Machine Learning to Improve Donor-Recipient Matching at Time of Heart Transplantation

BACKGROUND: Machine learning (ML) models have been used to evaluate one-year post-transplant mortality in donor-recipient pairs. Previous modeling uti...

Agentic-TimesFM-AKI: A Dual LLM-Time Series Framework for Predicting Drug-Induced Acute Kidney Injury with Privacy-Preserving Synthetic Data

Background: Acute kidney injury (AKI) is a severe complication in intensive care units, frequently exacerbated by synergistic nephrotoxicity from drug...

Explainable AI for Chronic Kidney Disease Prediction Using Simulated Federated Learning

Chronic Kidney Disease (CKD), characterized by the gradual loss of kidney function, remains a significant public health challenge. Early detection is ...