arXiv Computer Vision
Gated Spatial Redundancy Projection for Pathology Transformer Attentions
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 8
DaX: Learning General Pathology Representations Across Scales
arXiv:2606. 06983v1 Announce Type: cross Abstract: Computational pathology requires visual representations that transfer across diverse clinical endpoints and remain robust to variation in magnification, staining, scanner type, slide preparation, and input resolution.
arXiv AI
Jun 2
Aligning Cellular Sheaves with Classifier Attention for Interpretable Weakly-Supervised Pathology Localization
arXiv:2606. 00092v1 Announce Type: cross Abstract: Weakly-supervised classification of whole-slide images with attention-based multiple instance learning (ABMIL) on top of foundation features now reaches near-saturation on Camelyon16 slide-level performance, but the corresponding attention maps are an imperfect localization signal: in clinical interpretation, a model that classifies correctly without firing on the actual lesion is hard to trust.
arXiv AI
Jul 28
Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention
arXiv:2607. 22749v1 Announce Type: cross Abstract: Tracking residual tumor after surgery is essential for catching recurrence early, but automating post-operative glioma segmentation remains a difficult task.
arXiv Computer Vision
Sep 17
Learning Where to Focus: Self-Supervised Multi-Scale ViTs for Histopathology
arXiv:2609.18578v1 Announce Type: new Abstract: Pathologists diagnose diseases by first locating suspicious tissue and then examining it at higher magnification, whereas self-supervised vision transf...
arXiv Computer Vision
Sep 15
Weakly Supervised Spatial Grounding for Discriminative Attention-Based Ultrasound-Histopathology Alignment in Prostate Cancer Grading
arXiv:2609.15150v1 Announce Type: new Abstract: Unpaired cross-modal distillation transfers grade structure from histopathology into a micro-ultrasound (micro-US) encoder by aligning a pooled needle-...
arXiv Machine Learning
Aug 26
RACR-MIL: Rank-aware contextual reasoning for weakly supervised grading of squamous cell carcinoma using whole slide images
RACR-MIL is a weakly‑supervised method for grading squamous cell carcinoma (SCC) from whole‑slide images, using an attention‑based multiple‑instance learning framework. It introduces a hybrid WSI graph to capture local tissue context and non‑local phenotypic dependencies, and applies rank‑ordering constraints on attention to prioritize higher‑grade tumor regions, mirroring pathologists’ diagnostic reasoning. The approach achieves state‑of‑the‑art performance, improving SCC grading accuracy by 3–9% over existing methods and up to 10% in tumor localization, and a pilot study showed pathologists reported increased grading efficiency in 60% of cases.