Modern medicine generates vast multimodal data across siloed systems, yet no existing model integrates the full breadth and temporal depth of the clinical record into a unified patient representation. We introduce Apollo, a multimodal temporal foundation model trained and evaluated on over three decades of longitudinal hospital records from a major US hospital system, composed of 25 billion records from 7.2 million patients, representing 28 distinct medical modalities and 12 major medical specialties. Apollo learns a unified representation space integrating over 100 thousand unique medical events in our clinical vocabulary as well as images and clinical text. This "atlas of medical concepts" forms a computational substrate for modeling entire patient care journeys comprised of sequences of structured and unstructured events, which are compressed by Apollo into virtual patient representations. To assess the potential of these whole-patient representations, we created 322 prognosis and retrieval tasks from a held-out test set of 1.4 million patients. We demonstrate the generalized clinical forecasting potential of Apollo embeddings, including predicting new disease onset risk up to five years in advance (95 tasks), disease progression (78 tasks), treatment response (59 tasks), risk of treatment-related adverse events (17 tasks), and hospital operations endpoints (12 tasks). Using feature attribution techniques, we show that model predictions align with clinically-interpretable multimodal biomarkers. We evaluate semantic similarity search on 61 retrieval tasks, and moreover demonstrate the potential of Apollo as a multimodal medical search engine using text and image queries. Together, these modeling capabilities establish the foundation for computable medicine, where the full context of patient care becomes accessible to computational reasoning.

A comprehensive three-dimensional (3D) map of tissue architecture and gene expression is crucial for illuminating the complexity and heterogeneity of tissues across diverse biomedical applications. However, most spatial transcriptomics (ST) approaches remain limited to two-dimensional (2D) sections of tissue. Although current 3D ST methods hold promise, they typically require extensive tissue sectioning, are complex, are not compatible with non-destructive 3D tissue imaging technologies, and often lack scalability. Here, we present VOlumetrically Resolved Transcriptomics EXpression (VORTEX), an AI framework that leverages 3D tissue morphology and minimal 2D ST to predict volumetric 3D ST. By pretraining on diverse 3D morphology-transcriptomic pairs from heterogeneous tissue samples and then fine-tuning on minimal 2D ST data from a specific volume of interest, VORTEX learns both generic tissue-related and sample-specific morphological correlates of gene expression. This approach enables dense, high-throughput, and fast 3D ST, scaling seamlessly to large tissue volumes far beyond the reach of existing 3D ST techniques. By offering a cost-effective and minimally destructive route to obtaining volumetric molecular insights, we anticipate that VORTEX will accelerate biomarker discovery and our understanding of morphomolecular associations and cell states in complex tissues. Interactive 3D ST volumes can be viewed at https://vortex-demo.github.io/

Foundation models have begun to transform image analysis by acting as pretrained generalist backbones that can be adapted to many tasks even when post-training data are limited, yet their impact on spatial proteomics, imaging that maps proteins at single-cell resolution, remains limited. Here, we introduce KRONOS, a foundation model built for spatial proteomics. KRONOS was trained in a self-supervised manner on over 47 million image patches covering 175 protein markers, 16 tissue types, and 8 fluorescence-based imaging platforms. We introduce key architectural adaptations to address the high-dimensional, multi-channel, and heterogeneous nature of multiplex imaging. We demonstrate that KRONOS learns biologically meaningful representations across multiple scales, ranging from cellular and microenvironment to tissue levels, enabling it to address diverse downstream tasks, including cell phenotyping, region classification, and patient stratification. Evaluated across 11 independent cohorts, KRONOS achieves state-of-the-art performance across cell phenotyping, treatment response prediction, and retrieval tasks, and is highly data-efficient. KRONOS also introduces the paradigm of segmentation-free patch-level processing for efficient and scalable spatial proteomics analysis, allowing cross-institutional comparisons, and as an image reverse search engine for spatial patterns. Together, these results position KRONOS as a flexible and scalable tool for spatial proteomics. The model is publicly accessible at https://github.com/mahmoodlab/KRONOS.

Foundation models are reshaping computational pathology by enabling transfer learning, where models pre-trained on vast datasets can be adapted for downstream diagnostic, prognostic, and therapeutic response tasks. Despite these advances, foundation models are still limited in their ability to encode the entire gigapixel whole-slide images without additional training and often lack complementary multimodal data. Here, we introduce Threads, a slide-level foundation model capable of generating universal representations of whole-slide images of any size. Threads was pre-trained using a multimodal learning approach on a diverse cohort of 47,171 hematoxylin and eosin (H&E)-stained tissue sections, paired with corresponding genomic and transcriptomic profiles - the largest such paired dataset to be used for foundation model development to date. This unique training paradigm enables Threads to capture the tissue's underlying molecular composition, yielding powerful representations applicable to a wide array of downstream tasks. In extensive benchmarking across 54 oncology tasks, including clinical subtyping, grading, mutation prediction, immunohistochemistry status determination, treatment response prediction, and survival prediction, Threads outperformed all baselines while demonstrating remarkable generalizability and label efficiency. It is particularly well suited for predicting rare events, further emphasizing its clinical utility. We intend to make the model publicly available for the broader community.

Pathology is experiencing rapid digital transformation driven by whole-slide imaging and artificial intelligence (AI). While deep learning-based computational pathology has achieved notable success, traditional models primarily focus on image analysis without integrating natural language instruction or rich, text-based context. Current multimodal large language models (MLLMs) in computational pathology face limitations, including insufficient training data, inadequate support and evaluation for multi-image understanding, and a lack of autonomous, diagnostic reasoning capabilities. To address these limitations, we introduce PathChat+, a new MLLM specifically designed for human pathology, trained on over 1 million diverse, pathology-specific instruction samples and nearly 5.5 million question answer turns. Extensive evaluations across diverse pathology benchmarks demonstrated that PathChat+ substantially outperforms the prior PathChat copilot, as well as both state-of-the-art (SOTA) general-purpose and other pathology-specific models. Furthermore, we present SlideSeek, a reasoning-enabled multi-agent AI system leveraging PathChat+ to autonomously evaluate gigapixel whole-slide images (WSIs) through iterative, hierarchical diagnostic reasoning, reaching high accuracy on DDxBench, a challenging open-ended differential diagnosis benchmark, while also capable of generating visually grounded, humanly-interpretable summary reports.

The field of computational pathology has been transformed with recent advances in foundation models that encode histopathology region-of-interests (ROIs) into versatile and transferable feature representations via self-supervised learning (SSL). However, translating these advancements to address complex clinical challenges at the patient and slide level remains constrained by limited clinical data in disease-specific cohorts, especially for rare clinical conditions. We propose TITAN, a multimodal whole slide foundation model pretrained using 335,645 WSIs via visual self-supervised learning and vision-language alignment with corresponding pathology reports and 423,122 synthetic captions generated from a multimodal generative AI copilot for pathology. Without any finetuning or requiring clinical labels, TITAN can extract general-purpose slide representations and generate pathology reports that generalize to resource-limited clinical scenarios such as rare disease retrieval and cancer prognosis. We evaluate TITAN on diverse clinical tasks and find that TITAN outperforms both ROI and slide foundation models across machine learning settings such as linear probing, few-shot and zero-shot classification, rare cancer retrieval and cross-modal retrieval, and pathology report generation.

Large Vision Language Models (LVLMs) have recently revolutionized computational pathology. LVLMs transform pathology image embeddings into tokens recognizable by large language models, facilitating zero-shot image classification, description generation, question answering, and interactive diagnostics. In clinical practice, pathological assessments often require the analysis of entire tissue slides, integrating information from multiple sub-regions and magnification levels. However, existing LVLM frameworks have been restricted to the analysis of small, predefined regions of interest, lacking the ability to analyze pyramidal, gigapixel-scale whole-slide images (WSIs). In this work, we introduce ALPaCA (Adapting Llama for Pathology Context Analysis), and train the first general-purpose slide-level LVLM, leveraging 35,913 WSIs with curated descriptions alongside 341,051 question and answer pairs encompassing diverse diagnoses, procedures, and tissue types. By developing LongFormer, a vision-text interactive slide-level adaptor, and integrating it with a Gaussian mixture model-based prototyping adaptor, followed by training with Llama3.1, ALPaCA achieves superior performance in slide-level question answering, achieving over 90\% accuracy in close-ended tests and high accuracy in open-ended questions as evaluated by expert pathologists, highlighting its potential for slide-level computer-aided diagnosis systems. Additionally, we show that ALPaCA can be readily fine-tuned on in-depth, organ-specific, or disease-specific datasets, underscoring its adaptability and utility for specialized pathology tasks. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement We acknowledge funding and support from Cancer Research UK and the Cancer Research UK Cambridge Centre [CTRQQR-2021-100012], The Mark Foundation for Cancer Research [RG95043], GE HealthCare, and the CRUK National Cancer Imaging Translational Accelerator (NCITA) [A27066]. Additional support was also provided by the National Institute of Health Research (NIHR) Cambridge Biomedical Research Centre [NIHR203312] and EPSRC Tier-2 capital grant [EP/P020259/1]. The computations described in this research were performed in part using the Sulis Tier 2 HPC platform, hosted by the Scientific Computing Research Technology Platform at the University of Warwick. Sulis is funded by EPSRC Grant EP/T022108/1 and the HPC Midlands+ consortium. Additional computations were carried out using the Baskerville Tier 2 HPC service (https://www.baskerville.ac.uk/), which is operated by Advanced Research Computing at the University of Birmingham. Baskerville was funded by the EPSRC and UKRI through the World Class Labs scheme (EP/T022221/1) and the Digital Research Infrastructure programme (EP/W032244/1). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. The results shown here are in whole or part based upon data generated by the TCGA Research Network (https://www.cancer.gov/tcga). Part of the data used for the analyses described in this manuscript were obtained from the GTEx Portal (accessed on May 31, 2024). ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Only existing public datasets were used. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present work are contained in the manuscript

The rapidly increasing volume of multimodal biomedical data presents unprecedented opportunities in precision oncology but poses significant challenges for researchers analyzing complex modalities such as gigapixel pathology slides. To address these challenges, we developed Judith, an AI-driven research assistant that leverages foundation models, multimodal generative AI, and other advanced computational tools for streamlining complex workflows in biomedical image analysis, predictive modeling, and biomarker discovery. Judith enables researchers to execute computational tasks through natural language commands, automating tasks such as response prediction, multimodal cancer prognosis, and histopathology image retrieval. We demonstrate Judith’s capabilities in several precision oncology use cases. (1) Predictive modeling and biomarker discovery: Using a retrospective dataset of pretreatment biopsies from invasive breast carcinoma patients treated with Trastuzumab (n=85 patients), Judith trained an AI model that predicts pathologic complete response with an AUROC of 0.855. Judith could also interpret the model, identifying key cellular features linked to tumor proliferation and finding histologic biomarkers that explain cohort-level differences between responders and non-responders. (2) Multimodal data integration: Judith orchestrated the development of a survival prediction model integrating histology, radiology, and multi-omics data for progression-free survival prediction in low-grade glioma patients (n=127), achieving a C-Index of 0.684. Using an integrative analysis, Judith further stratified patients into high- and low-risk groups and identified unfavorable prognostic features for cancer progression such as high tumor cellularity and PSPH overexpression. (3) Histology slide retrieval: Judith automated the development of a histology slide search system (n=138), enabling pathologists to retrieve slides with similar cancer diagnoses and morphologies. Judith was then able to validate the performance of histology slide retrieval, with successful retrieval of rare cancer types such as leiomyosarcoma. Overall, Judith represents a major advancement in biomedical research by automating AI workflows and enhancing data-driven discovery. Its ability to analyze diverse data modalities, identify meaningful biomarkers, and generate interpretable insights empowers researchers to maximize the scientific insights in their data. Future developments will focus on expanding multimodal capabilities, refining interpretability tools, and integrating real-time collaboration features. Ming Y. Lu, Faisal Mahmood, Richard J. Chen. Judith: An agentic AI system for biomedical image analysis and scientific discovery in precision oncology. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 2460.

The field of computational pathology has been transformed with recent advances in foundation models that encode histopathology region-of-interests (ROIs) into versatile and transferable feature representations via self-supervised learning. However, translating these advancements to address complex clinical challenges at the patient and slide level remains constrained by limited clinical data in disease-specific cohorts, especially for rare clinical conditions. We propose Transformer-based pathology Image and Text Alignment Network (TITAN), a multimodal whole-slide foundation model pretrained using 335,645 whole-slide images via visual self-supervised learning and vision-language alignment with corresponding pathology reports and 423,122 synthetic captions generated from a multimodal generative AI copilot for pathology. Without any fine-tuning or requiring clinical labels, TITAN can extract general-purpose slide representations and generate pathology reports that generalize to resource-limited clinical scenarios such as rare disease retrieval and cancer prognosis. We evaluate TITAN on diverse clinical tasks and find that it outperforms both ROI and slide foundation models across machine learning settings, including linear probing, few-shot and zero-shot classification, rare cancer retrieval, cross-modal retrieval and pathology report generation.

Despite increasing numbers of regulatory approvals, deep learning-based computational pathology systems often overlook the impact of demographic factors on performance, potentially leading to biases. This concern is all the more important as computational pathology has leveraged large public datasets that underrepresent certain demographic groups. Using publicly available data from The Cancer Genome Atlas and the EBRAINS brain tumor atlas, as well as internal patient data, we show that whole-slide image classification models display marked performance disparities across different demographic groups when used to subtype breast and lung carcinomas and to predict IDH1 mutations in gliomas. For example, when using common modeling approaches, we observed performance gaps (in area under the receiver operating characteristic curve) between white and Black patients of 3.0% for breast cancer subtyping, 10.9% for lung cancer subtyping and 16.0% for IDH1 mutation prediction in gliomas. We found that richer feature representations obtained from self-supervised vision foundation models reduce performance variations between groups. These representations provide improvements upon weaker models even when those weaker models are combined with state-of-the-art bias mitigation strategies and modeling choices. Nevertheless, self-supervised vision foundation models do not fully eliminate these discrepancies, highlighting the continuing need for bias mitigation efforts in computational pathology. Finally, we demonstrate that our results extend to other demographic factors beyond patient race. Given these findings, we encourage regulatory and policy agencies to integrate demographic-stratified evaluation into their assessment guidelines. In a series of clinically relevant tasks in computational pathology, AI-driven models display marked performance disparities across demographic groups, which can only partially be mitigated by self-supervision on large training datasets and existing debiasing techniques.

The accelerated adoption of digital pathology and advances in deep learning have enabled the development of powerful models for various pathology tasks across a diverse array of diseases and patient cohorts. However, model training is often difficult due to label scarcity in the medical domain and the model's usage is limited by the specific task and disease for which it is trained. Additionally, most models in histopathology leverage only image data, a stark contrast to how humans teach each other and reason about histopathologic entities. We introduce CONtrastive learning from Captions for Histopathology (CONCH), a visual-language foundation model developed using diverse sources of histopathology images, biomedical text, and notably over 1.17 million image-caption pairs via task-agnostic pretraining. Evaluated on a suite of 13 diverse benchmarks, CONCH can be transferred to a wide range of downstream tasks involving either or both histopathology images and text, achieving state-of-the-art performance on histology image classification, segmentation, captioning, text-to-image and image-to-text retrieval. CONCH represents a substantial leap over concurrent visual-language pretrained systems for histopathology, with the potential to directly facilitate a wide array of machine learning-based workflows requiring minimal or no further supervised fine-tuning.

Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks, requiring the objective characterization of histopathological entities from whole-slide images (WSIs). The high resolution of WSIs and the variability of morphological features present significant challenges, complicating the large-scale annotation of data for high-performance applications. To address this challenge, current efforts have proposed the use of pretrained image encoders through transfer learning from natural image datasets or self-supervised learning on publicly available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using more than 100 million images from over 100,000 diagnostic H&E-stained WSIs (>77 TB of data) across 20 major tissue types. The model was evaluated on 34 representative CPath tasks of varying diagnostic difficulty. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient artificial intelligence models that can generalize and transfer to a wide range of diagnostically challenging tasks and clinical workflows in anatomic pathology.

The use of Artificial Intelligence (AI) within pathology and healthcare has advanced extensively. We have accordingly witnessed increased adoption of various AI tools which are transforming our approach to clinical decision support, personalized medicine, predictive analytics, automation, and discovery. The familiar and more reliable AI tools that have been incorporated within healthcare thus far fall mostly under the non-generative AI domain, which includes supervised and unsupervised machine learning (ML) techniques. This review article explores how such non-generative AI methods, rooted in traditional rules-based systems, enhance diagnostic accuracy, efficiency, and consistency within medicine. Key concepts and the application of supervised learning models (i.e. classification and regression) such as decision trees, support vector machines, linear and logistic regression, K-nearest neighbor, and neural networks are explained along with the newer landscape of neural network-based non-generative foundation models. Unsupervised learning techniques including clustering, dimensionality reduction, and anomaly detection are also discussed for their role in uncovering novel disease subtypes or identifying outliers. Technical details related to the application of non-generative AI algorithms for analyzing whole slide images is also highlighted. The performance, explainability and reliability of non-generative AI models essential for clinical decision-making is also reviewed, as well as challenges related to data quality, model interpretability, and risk of data drift. An understanding of which AI-ML models to employ and which shortcomings need to be addressed is imperative to safely and efficiently leverage, integrate, and monitor these traditional AI tools in clinical practice and research.

Spatial transcriptomics enables interrogating the molecular composition of tissue with ever-increasing resolution and sensitivity. However, costs, rapidly evolving technology, and lack of standards have constrained computational methods in ST to narrow tasks and small cohorts. In addition, the underlying tissue morphology, as reflected by H E-stained whole slide images (WSIs), encodes rich information often overlooked in ST studies. Here, we introduce HEST-1k, a collection of 1,229 spatial transcriptomic profiles, each linked to a WSI and extensive metadata. HEST-1k was assembled from 153 public and internal cohorts encompassing 26 organs, two species (Homo Sapiens and Mus Musculus), and 367 cancer samples from 25 cancer types. HEST-1k processing enabled the identification of 2.1 million expression–morphology pairs and over 76 million nuclei. To support its development, we additionally introduce the HEST-Library, a Python package designed to perform a range of actions with HEST samples. We test HEST-1k and Library on three use cases: (1) benchmarking foundation models for pathology (HEST-Benchmark), (2) biomarker exploration, and (3) multimodal representation learning. HEST-1k, HEST-Library, and HEST-Benchmark can be freely accessed at https://github.com/mahmoodlab/hest.

The field of computational pathology[1,2] has witnessed remarkable progress in the development of both task-specific predictive models and task-agnostic self-supervised vision encoders[3,4]. However, despite the explosive growth of generative artificial intelligence (AI), there has been limited study on building general purpose, multimodal AI assistants and copilots[5] tailored to pathology. Here we present PathChat, a vision-language generalist AI assistant for human pathology. We build PathChat by adapting a foundational vision encoder for pathology, combining it with a pretrained large language model and finetuning the whole system on over 456,000 diverse visual language instructions consisting of 999,202 question-answer turns. We compare PathChat against several multimodal vision language AI assistants and GPT4V, which powers the commercially available multimodal general purpose AI assistant ChatGPT-4[7]. PathChat achieved state-of-the-art performance on multiple-choice diagnostic questions from cases of diverse tissue origins and disease models. Furthermore, using open-ended questions and human expert evaluation, we found that overall PathChat produced more accurate and pathologist-preferable responses to diverse queries related to pathology. As an interactive and general vision-language AI Copilot that can flexibly handle both visual and natural language inputs, PathChat can potentially find impactful applications in pathology education, research, and human-in-the-loop clinical decision making.

In healthcare, the development and deployment of insufficiently fair systems of artificial intelligence (AI) can undermine the delivery of equitable care. Assessments of AI models stratified across subpopulations have revealed inequalities in how patients are diagnosed, treated and billed. In this Perspective, we outline fairness in machine learning through the lens of healthcare, and discuss how algorithmic biases (in data acquisition, genetic variation and intra-observer labelling variability, in particular) arise in clinical workflows and the resulting healthcare disparities. We also review emerging technology for mitigating biases via disentanglement, federated learning and model explainability, and their role in the development of AI-based software as a medical device.

Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works typically train on large datasets of image-text pairs and have been designed to perform downstream tasks involving only small to medium sized-images, neither of which are applicable to the emerging field of computational pathology where there are limited publicly available paired image-text datasets and each image can span up to 100,000 x 100,000 pixels. In this paper we present MI-Zero, a simple and intuitive framework for unleashing the zero-shot transfer capabilities of contrastively aligned image and text models on gigapixel histopathology whole slide images, enabling multiple downstream diagnostic tasks to be carried out by pretrained encoders without requiring any additional labels. MI-Zero reformulates zero-shot transfer under the framework of multiple instance learning to overcome the computational challenge of inference on extremely large images. We used over 550k pathology reports and other available in-domain text corpora to pre-train our text encoder. By effectively leveraging strong pre-trained encoders, our best model pretrained on over 33k histopathology image-caption pairs achieves an average median zero-shot accuracy of 70.2% across three different real-world cancer subtyping tasks. Our code is available at: https://github.com/mahmoodlab/MI-Zero.

Deep learning-based computational pathology models can be trained to make accurate diagnostic, prognostic, and therapeutic response predictions. Such models have also recently received regulatory approval in Europe and in the US. However, a majority of these models are trained and independently evaluated on large repositories of data representative of overall patient populations without extensive evaluation on underrepresented minorities or other subgroups. Here we show that such pathology AI models can be biased when independent and external evaluation test sets are stratified by race, demonstrating the need for more extensive evaluation of such models before regulatory approvals Citation Format: Richard J. Chen, Drew F.K. Williamson, Ming Y. Lu, Tiffany Y. Chen, Jana Lipkova, Muhammad Shaban, Faisal Mahmood. Racial disparities bias oncology AI models [abstract]. In: Proceedings of the 15th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2022 Sep 16-19; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2022;31(1 Suppl):Abstract nr A007.

The field of computational pathology has witnessed remarkable progress in the development of both task-specific predictive models and task-agnostic self-supervised vision encoders. However, despite the explosive growth of generative artificial intelligence (AI), there has been limited study on building general purpose, multimodal AI assistants tailored to pathology. Here we present PathChat, a vision-language generalist AI assistant for human pathology using an in-house developed foundational vision encoder pretrained on 100 million histology images from over 100,000 patient cases and 1.18 million pathology image-caption pairs. The vision encoder is then combined with a pretrained large language model and the whole system is finetuned on over 250,000 diverse disease agnostic visual language instructions. We compare PathChat against several multimodal vision language AI assistants as well as GPT4V, which powers the commercially available multimodal general purpose AI assistant ChatGPT-4. When relevant clinical context is provided with the histology image, PathChat achieved a diagnostic accuracy of 87% on multiple-choice questions based on publicly available cases of diverse tissue origins and disease models. Additionally, using open-ended questions and human expert evaluation, we found that overall PathChat produced more accurate and pathologist-preferable responses to diverse queries related to pathology. As an interactive and general vision language AI assistant that can flexibly handle both visual and natural language inputs, PathChat can potentially find impactful applications in pathology education, research, and human-in-the-loop clinical decision making.

Tissue phenotyping is a fundamental computational pathology (CPath) task in learning objective characterizations of histopathologic biomarkers in anatomic pathology. However, whole-slide imaging (WSI) poses a complex computer vision problem in which the large-scale image resolutions of WSIs and the enormous diversity of morphological phenotypes preclude large-scale data annotation. Current efforts have proposed using pretrained image encoders with either transfer learning from natural image datasets or self-supervised pretraining on publicly-available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using over 100 million tissue patches from over 100,000 diagnostic haematoxylin and eosin-stained WSIs across 20 major tissue types, and evaluated on 33 representative CPath clinical tasks in CPath of varying diagnostic difficulties. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree code classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient AI models that can generalize and transfer to a gamut of diagnostically-challenging tasks and clinical workflows in anatomic pathology.