LEAF-Mamba is a new framework for whole slide image analysis that jointly adapts and fuses frozen pretrained features. It uses a reconstruction‑regularized adapter to learn compact, task‑specific representations and combines parallel Mamba and convolutional streams to capture both long‑range dependencies and local interactions, with a gate that modulates their joint output before slide‑level pooling. Experiments show that this approach improves diagnostic classification and survival prediction over strong multiple‑instance learning baselines, and component analyses confirm the benefits of the adaptation and fusion modules.
arXiv:2609.00396v1 Announce Type: new Abstract: Histopathological whole slide images (WSIs) are central to cancer diagnosis, but their gigapixel scale, tissue heterogeneity, weak slide-level supervis...
arXiv:2609.24894v1 Announce Type: cross Abstract: Whole-slide pathology images (WSIs) contain gigapixel-scale visual content, creating a major scalability challenge for slide-level multimodal large l...
arXiv:2607. 14703v1 Announce Type: cross Abstract: Multiple instance learning (MIL) has become the main paradigm for whole-slide image (WSI) analysis in computational pathology.
arXiv:2510.06113v2 Announce Type: replace Abstract: Survival analysis plays a vital role in making clinical decisions. However, the models currently in use are often difficult to interpret, which red...
Multimodal fusion learning (MFL) has shown great potential in the medical domain, where we are faced with disparate data modalities such as imaging, clinical records, and omics. However, existing MFL strategies face several major challenges.
The paper introduces Locked Image Multiple Instance PreTraining (LIMIT), a method that aligns slide‑level pathology reports with patch‑level visual features by freezing a vision encoder and fine‑tuning a text encoder. LIMIT uses report embeddings as cross‑attention queries over bags of patch features, optimizing slide representations via InfoNCE. Applying LIMIT, the authors create CONCH‑Z, which achieves state‑of‑the‑art zero‑shot performance on 22 pathology tasks, outperforming vision‑language encoders trained on curated caption datasets and narrowing the gap with larger slide‑level foundation models.
arXiv:2610.07913v1 Announce Type: cross Abstract: Gastric adenocarcinoma (GA) is a leading cause of cancer-related mortality worldwide, and accurate histopathological subtype classification from whol...
arXiv:2607. 16260v1 Announce Type: cross Abstract: Multimodal survival analysis utilizing whole slide images (WSIs) and genomic profiles is fundamental for cancer prognosis.
arXiv:2606. 06864v1 Announce Type: cross Abstract: Multiple instance learning (MIL) has become a standard paradigm for whole slide image (WSI) analysis in digital pathology, as it enables slide-level prediction without dense annotations.
LanGuSTE is a patch‑selection framework for whole slide image analysis that uses vision‑language models and large language model knowledge. It introduces Cross‑Scale Visual Prompt Tuning to align low‑resolution and high‑resolution patches, and a coarse‑to‑fine selection module that encodes only informative high‑resolution patches. Experiments show LanGuSTE cuts overall processing time to about one‑third of the baseline while matching or surpassing diagnostic performance of exhaustive and state‑of‑the‑art methods.
arXiv:2507. 05077v5 Announce Type: replace-cross Abstract: Deep neural networks are increasingly applied in automated histopathology.
The paper introduces GPF‑Net, a Gated Progressive Fusion Network designed for colonoscopic polyp re‑identification. It fuses multimodal features from multiple levels using fully connected gating mechanisms, allowing layer‑wise refinement of semantic information. Experiments on standard benchmarks show that this multimodal, progressive fusion approach outperforms state‑of‑the‑art unimodal ReID models, especially for small polyps where fine‑grained details are crucial.