Abstract:Whole slide imaging is routinely adopted for carcinoma diagnosis and prognosis. Abundant experience is required for pathologists to achieve accurate and reliable diagnostic results of whole slide images (WSI). The huge size and heterogeneous features of WSIs make the workflow of pathological reading extremely time-consuming. In this paper, we propose a novel framework (WSI-VQA) to interpret WSIs by generative visual question answering. WSI-VQA shows universality by reframing various kinds of slide-level tasks in a question-answering pattern, in which pathologists can achieve immunohistochemical grading, survival prediction, and tumor subtyping following human-machine interaction. Furthermore, we establish a WSI-VQA dataset which contains 8672 slide-level question-answering pairs with 977 WSIs. Besides the ability to deal with different slide-level tasks, our generative model which is named Wsi2Text Transformer (W2T) outperforms existing discriminative models in medical correctness, which reveals the potential of our model to be applied in the clinical scenario. Additionally, we also visualize the co-attention mapping between word embeddings and WSIs as an intuitive explanation for diagnostic results. The dataset and related code are available at https://github.com/cpystan/WSI-VQA.
Abstract:Vision Language Models (VLMs) like CLIP have attracted substantial attention in pathology, serving as backbones for applications such as zero-shot image classification and Whole Slide Image (WSI) analysis. Additionally, they can function as vision encoders when combined with large language models (LLMs) to support broader capabilities. Current efforts to train pathology VLMs rely on pathology image-text pairs from platforms like PubMed, YouTube, and Twitter, which provide limited, unscalable data with generally suboptimal image quality. In this work, we leverage large-scale WSI datasets like TCGA to extract numerous high-quality image patches. We then train a large multimodal model to generate captions for these images, creating PathGen-1.6M, a dataset containing 1.6 million high-quality image-caption pairs. Our approach involves multiple agent models collaborating to extract representative WSI patches, generating and refining captions to obtain high-quality image-text pairs. Extensive experiments show that integrating these generated pairs with existing datasets to train a pathology-specific CLIP model, PathGen-CLIP, significantly enhances its ability to analyze pathological images, with substantial improvements across nine pathology-related zero-shot image classification tasks and three whole-slide image tasks. Furthermore, we construct 200K instruction-tuning data based on PathGen-1.6M and integrate PathGen-CLIP with the Vicuna LLM to create more powerful multimodal models through instruction tuning. Overall, we provide a scalable pathway for high-quality data generation in pathology, paving the way for next-generation general pathology models.
Abstract:Microscopic interpretation of histopathology images underlies many important diagnostic and treatment decisions. While advances in vision-language modeling raise new opportunities for analysis of such images, the gigapixel-scale size of whole slide images (WSIs) introduces unique challenges. Additionally, pathology reports simultaneously highlight key findings from small regions while also aggregating interpretation across multiple slides, often making it difficult to create robust image-text pairs. As such, pathology reports remain a largely untapped source of supervision in computational pathology, with most efforts relying on region-of-interest annotations or self-supervision at the patch-level. In this work, we develop a vision-language model based on the BLIP-2 framework using WSIs paired with curated text from pathology reports. This enables applications utilizing a shared image-text embedding space, such as text or image retrieval for finding cases of interest, as well as integration of the WSI encoder with a frozen large language model (LLM) for WSI-based generative text capabilities such as report generation or AI-in-the-loop interactions. We utilize a de-identified dataset of over 350,000 WSIs and diagnostic text pairs, spanning a wide range of diagnoses, procedure types, and tissue types. We present pathologist evaluation of text generation and text retrieval using WSI embeddings, as well as results for WSI classification and workflow prioritization (slide-level triaging). Model-generated text for WSIs was rated by pathologists as accurate, without clinically significant error or omission, for 78% of WSIs on average. This work demonstrates exciting potential capabilities for language-aligned WSI embeddings.
Abstract:Multiple Instance Learning (MIL) has demonstrated effectiveness in analyzing whole slide images (WSIs), yet it often encounters overfitting challenges in real-world applications. This paper reveals the correlation between MIL's performance and the entropy of attention values. Based on this observation, we propose Attention Diversity Regularization (ADR), a simple but effective technique aimed at promoting high entropy in attention values. Specifically, ADR introduces a negative Shannon entropy loss for attention values into the regular MIL framework. Compared to existing methods aimed at alleviating overfitting, which often necessitate additional modules or processing steps, our ADR approach requires no such extras, demonstrating simplicity and efficiency. We evaluate our ADR on three WSI classification tasks. ADR achieves superior performance over the state-of-the-art on most of them. We also show that ADR can enhance heatmaps, aligning them better with pathologists' diagnostic criteria. The source code is available at \url{https://github.com/dazhangyu123/ADR}.
Abstract:With the booming of Large Language Models (LLMs), prompt-learning has become a promising method mainly researched in various research areas. Recently, many attempts based on prompt-learning have been made to improve the performance of text classification. However, most of these methods are based on heuristic Chain-of-Thought (CoT), and tend to be more complex but less efficient. In this paper, we rethink the LLM-based text classification methodology, propose a simple and effective transfer learning strategy, namely LLMEmbed, to address this classical but challenging task. To illustrate, we first study how to properly extract and fuse the text embeddings via various lightweight LLMs at different network depths to improve their robustness and discrimination, then adapt such embeddings to train the classifier. We perform extensive experiments on publicly available datasets, and the results show that LLMEmbed achieves strong performance while enjoys low training overhead using lightweight LLM backbones compared to recent methods based on larger LLMs, i.e. GPT-3, and sophisticated prompt-based strategies. Our LLMEmbed achieves adequate accuracy on publicly available benchmarks without any fine-tuning while merely use 4% model parameters, 1.8% electricity consumption and 1.5% runtime compared to its counterparts. Code is available at: https://github.com/ChunLiu-cs/LLMEmbed-ACL2024.
Abstract:Many clinical tasks require an understanding of specialized data, such as medical images and genomics, which is not typically found in general-purpose large multimodal models. Building upon Gemini's multimodal models, we develop several models within the new Med-Gemini family that inherit core capabilities of Gemini and are optimized for medical use via fine-tuning with 2D and 3D radiology, histopathology, ophthalmology, dermatology and genomic data. Med-Gemini-2D sets a new standard for AI-based chest X-ray (CXR) report generation based on expert evaluation, exceeding previous best results across two separate datasets by an absolute margin of 1% and 12%, where 57% and 96% of AI reports on normal cases, and 43% and 65% on abnormal cases, are evaluated as "equivalent or better" than the original radiologists' reports. We demonstrate the first ever large multimodal model-based report generation for 3D computed tomography (CT) volumes using Med-Gemini-3D, with 53% of AI reports considered clinically acceptable, although additional research is needed to meet expert radiologist reporting quality. Beyond report generation, Med-Gemini-2D surpasses the previous best performance in CXR visual question answering (VQA) and performs well in CXR classification and radiology VQA, exceeding SoTA or baselines on 17 of 20 tasks. In histopathology, ophthalmology, and dermatology image classification, Med-Gemini-2D surpasses baselines across 18 out of 20 tasks and approaches task-specific model performance. Beyond imaging, Med-Gemini-Polygenic outperforms the standard linear polygenic risk score-based approach for disease risk prediction and generalizes to genetically correlated diseases for which it has never been trained. Although further development and evaluation are necessary in the safety-critical medical domain, our results highlight the potential of Med-Gemini across a wide range of medical tasks.
Abstract:Existing performance measures for bandit algorithms such as regret, PAC bounds, or uniform-PAC (Dann et al., 2017), typically evaluate the cumulative performance, while allowing the play of an arbitrarily bad arm at any finite time t. Such a behavior can be highly detrimental in high-stakes applications. This paper introduces a stronger performance measure, the uniform last-iterate (ULI) guarantee, capturing both cumulative and instantaneous performance of bandit algorithms. Specifically, ULI characterizes the instantaneous performance since it ensures that the per-round regret of the played arm is bounded by a function, monotonically decreasing w.r.t. (large) round t, preventing revisits to bad arms when sufficient samples are available. We demonstrate that a near-optimal ULI guarantee directly implies near-optimal cumulative performance across aforementioned performance measures. To examine the achievability of ULI in the finite arm setting, we first provide two positive results that some elimination-based algorithms and high-probability adversarial algorithms with stronger analysis or additional designs, can attain near-optimal ULI guarantees. Then, we also provide a negative result, indicating that optimistic algorithms cannot achieve a near-optimal ULI guarantee. Finally, we propose an efficient algorithm for linear bandits with infinitely many arms, which achieves the ULI guarantee, given access to an optimization oracle.
Abstract:The emergence of large multimodal models has unlocked remarkable potential in AI, particularly in pathology. However, the lack of specialized, high-quality benchmark impeded their development and precise evaluation. To address this, we introduce PathMMU, the largest and highest-quality expert-validated pathology benchmark for LMMs. It comprises 33,573 multimodal multi-choice questions and 21,599 images from various sources, and an explanation for the correct answer accompanies each question. The construction of PathMMU capitalizes on the robust capabilities of GPT-4V, utilizing approximately 30,000 gathered image-caption pairs to generate Q\&As. Significantly, to maximize PathMMU's authority, we invite six pathologists to scrutinize each question under strict standards in PathMMU's validation and test sets, while simultaneously setting an expert-level performance benchmark for PathMMU. We conduct extensive evaluations, including zero-shot assessments of 14 open-sourced and three closed-sourced LMMs and their robustness to image corruption. We also fine-tune representative LMMs to assess their adaptability to PathMMU. The empirical findings indicate that advanced LMMs struggle with the challenging PathMMU benchmark, with the top-performing LMM, GPT-4V, achieving only a 51.7\% zero-shot performance, significantly lower than the 71.4\% demonstrated by human pathologists. After fine-tuning, even open-sourced LMMs can surpass GPT-4V with a performance of over 60\%, but still fall short of the expertise shown by pathologists. We hope that the PathMMU will offer valuable insights and foster the development of more specialized, next-generation LLMs for pathology.
Abstract:Accurate image classification and retrieval are of importance for clinical diagnosis and treatment decision-making. The recent contrastive language-image pretraining (CLIP) model has shown remarkable proficiency in understanding natural images. Drawing inspiration from CLIP, PathCLIP is specifically designed for pathology image analysis, utilizing over 200,000 image and text pairs in training. While the performance the PathCLIP is impressive, its robustness under a wide range of image corruptions remains unknown. Therefore, we conduct an extensive evaluation to analyze the performance of PathCLIP on various corrupted images from the datasets of Osteosarcoma and WSSS4LUAD. In our experiments, we introduce seven corruption types including brightness, contrast, Gaussian blur, resolution, saturation, hue, and markup at four severity levels. Through experiments, we find that PathCLIP is relatively robustness to image corruptions and surpasses OpenAI-CLIP and PLIP in zero-shot classification. Among the seven corruptions, blur and resolution can cause server performance degradation of the PathCLIP. This indicates that ensuring the quality of images is crucial before conducting a clinical test. Additionally, we assess the robustness of PathCLIP in the task of image-image retrieval, revealing that PathCLIP performs less effectively than PLIP on Osteosarcoma but performs better on WSSS4LUAD under diverse corruptions. Overall, PathCLIP presents impressive zero-shot classification and retrieval performance for pathology images, but appropriate care needs to be taken when using it. We hope this study provides a qualitative impression of PathCLIP and helps understand its differences from other CLIP models.
Abstract:Multi-modal Learning has attracted widespread attention in medical image analysis. Using multi-modal data, whole slide images (WSIs) and clinical information, can improve the performance of deep learning models in the diagnosis of axillary lymph node metastasis. However, clinical information is not easy to collect in clinical practice due to privacy concerns, limited resources, lack of interoperability, etc. Although patient selection can ensure the training set to have multi-modal data for model development, missing modality of clinical information can appear during test. This normally leads to performance degradation, which limits the use of multi-modal models in the clinic. To alleviate this problem, we propose a bidirectional distillation framework consisting of a multi-modal branch and a single-modal branch. The single-modal branch acquires the complete multi-modal knowledge from the multi-modal branch, while the multi-modal learns the robust features of WSI from the single-modal. We conduct experiments on a public dataset of Lymph Node Metastasis in Early Breast Cancer to validate the method. Our approach not only achieves state-of-the-art performance with an AUC of 0.861 on the test set without missing data, but also yields an AUC of 0.842 when the rate of missing modality is 80\%. This shows the effectiveness of the approach in dealing with multi-modal data and missing modality. Such a model has the potential to improve treatment decision-making for early breast cancer patients who have axillary lymph node metastatic status.