cs.CVNov 6, 2026

PathXAI: Evidence-guided structured pathology reporting by transferable tissue segmentation

Authors: Zhaorui Tan, Jun Aun Tan, Weixiang Zhong, Xiaoxi Wang, Tan Pan, Xingdong Xue, Li Liu, Jing Zhang, 

Organizations: Intelligent Digital and Molecular Pathology Lab, Bioinformatics Institute, A∗STAR, Singapore. · Department of Pathology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. · Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China. · School of Big Data and Software Engineering, Chongqing University, Chongqing, China. · 

Abstract

Pathology reporting translates tissue observations across regions and slides into diagnoses and supporting morphological descriptions, yet explicit tissue-composition measurements are rarely used to guide H&E-based report generation. We developed PathXAI, which pairs transferable tissue segmentation with a pretrained vision-language model. Because supplying tissue information directly with H&E images gave limited benefit, PathXAI-Report uses segmentation overlays and tissue statistics in separate steps, selects between candidate diagnoses by fixed rules, acquires further images when evidence is insufficient and records every step for review, without updating model weights. Its segmentation component exceeded baselines in mean Dice on internal and external tests. In automated evaluation on 1,200 public and 151 private cases, PathXAI achieved higher agreement with reference diagnoses and documented morphology than H&E-based comparators. On the public cohort, it exceeded Qwen+H&E by 4.4 percentage points in cancer family match rate and 5.7 percentage points in finding F1.

Figures & tables

Explore similar work

CardsList
  1. HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report Prediction

    Mar 20, 2026Ruicheng Yuan, Zhenxuan Zhang, Anbang Wang +5Computational PathologyMedical Report Generation

  2. PathKGen: Pathology Knowledge Assisted MLLM for Explainable Histopathology

    Oct 24, 2026Nadun Rajapaksha, Sandun Herath, Devnith Wijesinghe +3Medical Report GenerationWhole-Slide Image Analysis