PRISM2: Unlocking Multi-Modal General Pathology AI with Clinical Dialogue

• URL: http://arxiv.org/abs/2506.13063v2
• Date: Fri, 31 Oct 2025 20:56:23 GMT
• Title: PRISM2: Unlocking Multi-Modal General Pathology AI with Clinical Dialogue
• Authors: Eugene Vorontsov, George Shaikovski, Adam Casson, Julian Viret, Eric Zimmermann, Neil Tenenholtz, Yi Kan Wang, Jan H. Bernhard, Ran A. Godrich, Juan A. Retamero, Jinru Shia, Mithat Gonen, Martin R. Weiser, David S. Klimstra, Razik Yousfi, Nicolo Fusi, Thomas J. Fuchs, Kristen Severson, Siqi Liu,
• Abstract summary: We present PRISM2, a multimodal slide-level foundation model trained on data from 700,000 diagnostic specimen-report pairs.<n>PRISM2 aligns histomorphologic features with the language of diagnostic reasoning, producing slide-level representations.<n>Results demonstrate how language-supervised pretraining provides a scalable, clinically grounded signal for learning generalizable pathology representations.
• Score: 2.578328028000588
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent rapid progress in the field of computational pathology has been enabled by foundation models. These models are beginning to move beyond encoding image patches towards whole-slide understanding but their clinical utility remains limited. In this work, we present PRISM2, a multimodal slide-level foundation model trained on data from 700,000 diagnostic specimen-report pairs, the largest vision (2.3 million whole slide images) and language (14M question-answer pairs) histopathology dataset to date. By learning through clinical-dialogue supervision, PRISM2 aligns histomorphologic features with the language of diagnostic reasoning, producing slide-level representations that support both direct diagnostic question-answering and transferable embeddings for downstream tasks. Without additional training, PRISM2 matches or exceeds the cancer-detection performance of clinical-grade products. This is observed without loss of generality on other tasks, where PRISM2 achieves top performance. Finally, using survival prediction as the example, we show that task-specific finetuning with a large dataset can outperform task-specific models, further improving performance. These results demonstrate how language-supervised pretraining provides a scalable, clinically grounded signal for learning generalizable pathology representations, bridging human diagnostic reasoning and foundation-model performance.

Related papers

• DermoGPT: Open Weights and Open Data for Morphology-Grounded Dermatological Reasoning MLLMs [54.8829900010621]
  Multimodal Large Language Models (MLLMs) show promise for medical applications, yet progress in dermatology lags due to limited training data, narrow task coverage, and lack of clinically-grounded supervision.<n>We present a comprehensive framework to address these gaps.<n>First, we introduce DermoInstruct, a large-scale morphology-anchored instruction corpus comprising 211,243 images and 772,675 trajectories across five task formats.<n>Second, we establish DermoBench, a rigorous benchmark evaluating 11 tasks across four clinical axes: Morphology, Diagnosis, Reasoning, and Fairness, including a challenging subset of 3,600
  arXiv  Detail & Related papers  (2026-01-05T07:55:36Z)
• Multimodal Causal-Driven Representation Learning for Generalizable Medical Image Segmentation [56.52520416420957]
  We propose Multimodal Causal-Driven Representation Learning (MCDRL) to tackle domain generalization in medical image segmentation.<n>MCDRL consistently outperforms competing methods, yielding superior segmentation accuracy and exhibiting robust generalizability.
  arXiv  Detail & Related papers  (2025-08-07T03:41:41Z)
• Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language Reasoning [37.37330596550283]
  We introduce a framework for reliable medical image diagnosis using vision-language models.<n>A test-time scaling strategy consolidates multiple candidate outputs into a reliable final diagnosis.<n>We evaluate our approach across various medical imaging modalities.
  arXiv  Detail & Related papers  (2025-06-11T22:23:38Z)
• A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis [37.59267835101216]
  EndoBench is the first comprehensive benchmark specifically designed to assess MLLMs across the full spectrum of endoscopic practice.<n>We benchmark 23 state-of-the-art models, including general-purpose, medical-specialized, and proprietary MLLMs.<n>Our experiments reveal: proprietary MLLMs outperform open-source and medical-specialized models overall, but still trail human experts.
  arXiv  Detail & Related papers  (2025-05-29T16:14:34Z)
• MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment [12.665019147690975]
  MAKE is a vision-language pretraining framework for zero-shot dermatological tasks.<n>It decomposes clinical narratives into knowledge-enhanced sub-texts.<n>It prioritizes different sub-captions based on clinical significance prior.
  arXiv  Detail & Related papers  (2025-05-14T13:24:08Z)
• Towards Accurate and Interpretable Neuroblastoma Diagnosis via Contrastive Multi-scale Pathological Image Analysis [16.268045905735818]
  We propose CMSwinKAN, a contrastive-learning-based multi-scale feature fusion model tailored for pathological image classification.<n>By fusing multi-scale features and leveraging contrastive learning strategies, CMSwinKAN mimics clinicians' comprehensive approach.<n>Results demonstrate that CMSwinKAN performs better than existing state-of-the-art pathology-specific models pre-trained on large datasets.
  arXiv  Detail & Related papers  (2025-04-18T15:39:46Z)
• CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models [27.726366396356763]
  We introduce Clinical Large-Scale Integrative Multimodal Benchmark ( CLIMB)<n> CLIMB is a comprehensive benchmark unifying diverse clinical data across imaging, language, temporal, and graph modalities.<n>Pretraining on CLIMB effectively improves models' generalization capability to new tasks, and strong unimodal encoder performance translates well to multimodal performance when paired with task-appropriate fusion strategies.
  arXiv  Detail & Related papers  (2025-03-09T01:45:05Z)
• Continually Evolved Multimodal Foundation Models for Cancer Prognosis [50.43145292874533]
  Cancer prognosis is a critical task that involves predicting patient outcomes and survival rates.<n>Previous studies have integrated diverse data modalities, such as clinical notes, medical images, and genomic data, leveraging their complementary information.<n>Existing approaches face two major limitations. First, they struggle to incorporate newly arrived data with varying distributions into training, such as patient records from different hospitals.<n>Second, most multimodal integration methods rely on simplistic concatenation or task-specific pipelines, which fail to capture the complex interdependencies across modalities.
  arXiv  Detail & Related papers  (2025-01-30T06:49:57Z)
• Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective [32.93871326428446]
  Recent advances in artificial intelligence (AI) are revolutionizing medical imaging and computational pathology.<n>A constant challenge in the analysis of digital Whole Slide Images (WSIs) is the problem of aggregating tens of thousands of tile-level image embeddings to a slide-level representation.<n>This study conducts a benchmarking analysis of ten slide-level aggregation techniques across nine clinically relevant tasks.
  arXiv  Detail & Related papers  (2024-07-10T17:00:57Z)
• RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports [19.915033191502328]
  The Vision-Language Foundation model is increasingly investigated in the fields of computer vision and natural language processing. To handle this issue, a CLIP-style retinal image foundation model is developed in this paper. Our foundation model, RET-CLIP, is specifically trained on a dataset of 193,865 patients to extract general features of color fundus photographs.
  arXiv  Detail & Related papers  (2024-05-23T03:20:51Z)
• Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction [0.6291443816903801]
  We introduce a novel training strategy for our foundation model. We demonstrate that the proposed strategy significantly improves task performance on small-scale clinical datasets. Results further demonstrated the enhanced generalizability of our foundation model.
  arXiv  Detail & Related papers  (2023-12-21T07:42:49Z)
• CLIP in Medical Imaging: A Survey [59.429714742927956]
  Contrastive Language-Image Pre-training successfully introduces text supervision to vision models.<n>The use of CLIP has recently gained increasing interest in the medical imaging domain.
  arXiv  Detail & Related papers  (2023-12-12T15:21:57Z)
• Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models [49.95603725998561]
  We propose a new paradigm to build robust and interpretable medical image classifiers with natural language concepts. Specifically, we first query clinical concepts from GPT-4, then transform latent image features into explicit concepts with a vision-language model.
  arXiv  Detail & Related papers  (2023-10-04T21:57:09Z)
• A Transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics [63.106382317917344]
  We report a Transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary diseases.
  arXiv  Detail & Related papers  (2023-06-01T16:23:47Z)
• Hierarchical discriminative learning improves visual representations of biomedical microscopy [35.521563469534264]
  HiDisc is a data-driven method that implicitly learns features of the underlying cancer diagnosis. HiDisc pretraining outperforms current state-of-the-art self-supervised pretraining methods for cancer diagnosis and genetic mutation prediction.
  arXiv  Detail & Related papers  (2023-03-02T22:04:42Z)
• Dissecting Self-Supervised Learning Methods for Surgical Computer Vision [51.370873913181605]
  Self-Supervised Learning (SSL) methods have begun to gain traction in the general computer vision community. The effectiveness of SSL methods in more complex and impactful domains, such as medicine and surgery, remains limited and unexplored. We present an extensive analysis of the performance of these methods on the Cholec80 dataset for two fundamental and popular tasks in surgical context understanding, phase recognition and tool presence detection.
  arXiv  Detail & Related papers  (2022-07-01T14:17:11Z)
• Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation [116.87918100031153]
  We propose a Cross-modal clinical Graph Transformer (CGT) for ophthalmic report generation (ORG) CGT injects clinical relation triples into the visual features as prior knowledge to drive the decoding procedure. Experiments on the large-scale FFA-IR benchmark demonstrate that the proposed CGT is able to outperform previous benchmark methods.
  arXiv  Detail & Related papers  (2022-06-04T13:16:30Z)
• MIMO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning [49.57261599776167]
  We propose an end-to-end robust Transformer-based solution, Mutual Integration of patient journey and Medical Ontology (MIMO) for healthcare representation learning and predictive analytics.
  arXiv  Detail & Related papers  (2021-07-20T07:04:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.