The paper introduces a novel framework that aligns single white blood cell images with genetic data (karyotype and somatic mutations) to significantly improve the diagnosis of blood cancers, outperfor…

CodeCytos is a novel coding-based reasoning agent framework that enables dynamic, programmable interaction with spatial molecular imaging data, significantly improving the automation and customization…

This paper introduces TRACE, a model for interpretable 4-class glioblastoma response classification on longitudinal 3D MRI using a structured concept reasoning approach.

The paper proposes GC-MoE, a novel framework that uses a Mixture-of-Experts approach guided by genomics to accurately predict cell-type-specific gene expression for individual cells from histopatholog…

This paper proposes an anatomically aware frequency-and-structure-guided vision transformer (AA-ViT) for accurate and non-invasive contrast enhanced MRI (CEMRI) synthesis using pre-contrast MRI modali…

This paper introduces BBOmix, an open-source benchmark for unsupervised representation learning on real-world biological data.

The paper addresses 'Template Collapse' in 3D CT report generation—where models generate generic reports—by proposing CLarGen, a decoupled framework that significantly improves clinical accuracy and d…

The paper proposes a novel Global Context-aware Squeeze and Excite Residual UNet (GCSER-UNet) network, which significantly enhances brain tumor segmentation accuracy on benchmark MRI datasets.

The paper proposes Alignment-Guided Score Matching (AGSM), a lightweight, reward-free post-training method that integrates contrastive alignment guidance directly into the score-matching objective of…

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reali…

The paper presents a method for training deep learning classifiers on cancer registry data using Attention-Based Multiple Instance Learning (ABMIL), allowing the use of operationally-generated patient…

The paper introduces a simple, token-efficient vision-language model for generating comprehensive pathology synoptic reports from multiple whole-slide images (WSIs), achieving high performance while s…

The paper introduces a histogram-regularized latent diffusion model to synthesize highly realistic and subtype-specific pulmonary nodules in 3D CT volumes, addressing the limitations of existing metho…

A unified high-dimensional k-space reconstruction framework is proposed to enhance diffusion-based solvers for noisy MRI inverse problems through representation lifting.

This paper identifies prediction bias, a failure mode of entropy minimization in test-time adaptation, and proposes Distribution Shift Bias Reduction (DSBR) to stabilize adaptation and prevent model c…