# Pathologist Attention-Aligned Report Generation for Prostate Histopathology

arXiv: https://arxiv.org/abs/2607.19624 · HTML: https://mlsanity.com/paper/2607.19624/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction](https://mlsanity.com/paper/2403.05396/) (2024)
- [WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image](https://mlsanity.com/paper/2412.02141/) (2024)
- [WsiCaption: Multiple Instance Generation of Pathology Reports for Gigapixel Whole-Slide Images](https://mlsanity.com/paper/2311.16480/) (2023)
- [CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic](https://mlsanity.com/paper/2505.20510/) (2025)
- [Evidence-based diagnostic reasoning with multi-agent copilot for human pathology](https://mlsanity.com/paper/2506.20964/) (2025)
- [Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding](https://mlsanity.com/paper/2510.21356/) (2025)
- [Historical Report Guided Bi-modal Concurrent Learning for Pathology Report Generation](https://mlsanity.com/paper/2506.18658/) (2025)
- [RadGazeGen: Radiomics and Gaze-guided Medical Image Generation using Diffusion Models](https://mlsanity.com/paper/2410.00307/) (2024)
- [Measuring and Predicting Where and When Pathologists Focus their Visual Attention while Grading Whole Slide Images of Cancer](https://mlsanity.com/paper/2508.01668/) (2025)
- [Decoding the visual attention of pathologists to reveal their level of expertise](https://mlsanity.com/paper/2403.17255/) (2024)
- [Personalized Image Descriptions from Attention Sequences](https://mlsanity.com/paper/2512.06662/) (2025)
- [GazeLT: Visual attention-guided long-tailed disease classification in chest radiographs](https://mlsanity.com/paper/2508.09478/) (2025)
- [Eye-Tracking, Mouse Tracking, Stimulus Tracking,and Decision-Making Datasets in Digital Pathology](https://mlsanity.com/paper/2510.24653/) (2025)

## Abstract (arXiv)

The allocation of visual attention by pathologists during cancer diagnosis is a highly selective process that critically shapes the information extracted from whole-slide images (WSIs). Human attention helps medical imaging tasks such as classification and segmentation, and becomes a strong semantic cue for identifying diagnostically informative regions for report generation. In this paper, we introduce human attention into the training of pathologist report generation models. To this end, we collected a multimodal human-attention dataset of 121 prostate WSIs annotated with pathologists' multi-scale viewport trajectories synchronized with the pathologists' verbal descriptions and cursor movements for five clinically relevant components (e.g., Gleason patterns). Using this dataset, we finetune two report generation models with an attention-alignment loss that regularizes the model attention over image patches to match the distribution of pathologist attention. We evaluate our approach on prostate cancer report generation and visual question answering using two models with different internal attention mechanisms (i.e., how image tokens are integrated into the language decoder). Experiments show average gains of 10.9% on NLP-based metrics and 19.3% in accuracy across five clinically relevant report components. Further, model attention maps extracted at inference time, with minimal computational overhead, align more closely with pathologist attention, providing stronger visual support for the generated reports by highlighting the regions that most influence the output.