Search

Pathology images are crucial for diagnosing and managing various diseases by visualizing cellular and tissue-level abnormalities. Recent advancements in artificial intelligence (AI), particularly multimodal models like ChatGPT, have shown promise in transforming medical image analysis through capabilities such as medical vision-language question answering. However, there remains a significant gap in integrating pathology image data with these AI models for clinical applications. This study benchmarks the performance of GPT on pathology images, assessing their diagnostic accuracy and efficiency in real-word clinical records. We observe significant deficits of GPT in bone diseases and a fair-level performance in diseases from other three systems. Despite offering satisfactory abnormality annotations, GPT exhibits consistent disadvantage in terminology accuracy and multimodal integration. Specifically, we demonstrate GPT's failures in interpreting immunohistochemistry results and diagnosing metastatic cancers. This study highlight the weakness of current generalist GPT model and contribute to the integration of pathology and advanced AI.

The advent of vision-language models fosters the interactive conversations between AI-enabled models and humans. Yet applying these models into clinics must deal with daunting challenges around large-scale training data, financial, and computational resources. Here we propose a cost-effective instruction learning framework for conversational pathology named as CLOVER. CLOVER only trains a lightweight module and uses instruction tuning while freezing the parameters of the large language model. Instead of using costly GPT-4, we propose well-designed prompts on GPT-3.5 for building generation-based instructions, emphasizing the utility of pathological knowledge derived from the Internet source. To augment the use of instructions, we construct a high-quality set of template-based instructions in the context of digital pathology. From two benchmark datasets, our findings reveal the strength of hybrid-form instructions in the visual question-answer in pathology. Extensive results show the cost-effectiveness of CLOVER in answering both open-ended and closed-ended questions, where CLOVER outperforms strong baselines that possess 37 times more training parameters and use instruction data generated from GPT-4. Through the instruction tuning, CLOVER exhibits robustness of few-shot learning in the external clinical dataset. These findings demonstrate that cost-effective modeling of CLOVER could accelerate the adoption of rapid conversational applications in the landscape of digital pathology.

As natural image understanding moves towards the pretrain-finetune era, research in pathology imaging is concurrently evolving. Despite the predominant focus on pretraining pathological foundation models, how to adapt foundation models to downstream tasks is little explored. For downstream adaptation, we propose the existence of two domain gaps, i.e., the Foundation-Task Gap and the Task-Instance Gap. To mitigate these gaps, we introduce PathoTune, a framework designed to efficiently adapt pathological or even visual foundation models to pathology-specific tasks via multi-modal prompt tuning. The proposed framework leverages Task-specific Visual Prompts and Task-specific Textual Prompts to identify task-relevant features, along with Instance-specific Visual Prompts for encoding single pathological image features. Results across multiple datasets at both patch-level and WSI-level demonstrate its superior performance over single-modality prompt tuning approaches. Significantly, PathoTune facilitates the direct adaptation of natural visual foundation models to pathological tasks, drastically outperforming pathological foundation models with simple linear probing. The code is available at https://github.com/openmedlab/PathoDuet., Comment: MICCAI 2024

Assurance cases are used to communicate and assess confidence in critical system properties such as safety and security. Historically, assurance cases have been manually created documents, which are evaluated by system stakeholders through lengthy and complicated processes. In recent years, model-based system assurance approaches have gained popularity to improve the efficiency and quality of system assurance activities. This becomes increasingly important, as systems becomes more complex, it is a challenge to manage their development life-cycles, including coordination of development, verification and validation activities, and change impact analysis in inter-connected system assurance artifacts. Moreover, there is a need for assurance cases that support evolution during the operational life of the system, to enable continuous assurance in the face of an uncertain environment, as Robotics and Autonomous Systems (RAS) are adopted into society. In this paper, we contribute ACCESS - Assurance Case Centric Engineering of Safety-critical Systems, an engineering methodology, together with its tool support, for the development of safety critical systems around evolving model-based assurance cases. We show how model-based system assurance cases can trace to heterogeneous engineering artifacts (e.g. system architectural models, system safety analysis, system behaviour models, etc.), and how formal methods can be integrated during the development process. We demonstrate how assurance cases can be automatically evaluated both at development and runtime. We apply our approach to a case study based on an Autonomous Underwater Vehicle (AUV).

Probabilistic model checking is a widely used formal verification technique to automatically verify qualitative and quantitative properties for probabilistic models. However, capturing such systems, writing corresponding properties, and verifying them require domain knowledge. This makes it not accessible for researchers and engineers who may not have the required knowledge. Previous studies have extended UML activity diagrams (ADs), developed transformations, and implemented accompanying tools for automation. The research, however, is incomprehensive and not fully open, which makes it hard to be evaluated, extended, adapted, and accessed. In this paper, we propose a comprehensive verification framework for ADs, including a new profile for probability, time, and quality annotations, a semantics interpretation of ADs in three Markov models, and a set of transformation rules from activity diagrams to the PRISM language, supported by PRISM and Storm. Most importantly, we developed algorithms for transformation and implemented them in a tool, called QASCAD, using model-based techniques, for fully automated verification. We evaluated one case study where multiple robots are used for delivery in a hospital and further evaluated six other examples from the literature. With all these together, this work makes noteworthy contributions to the verification of ADs by improving evaluation, extensibility, adaptability, and accessibility., Comment: 43 pages, 29 figures, 5 tables, submitted to Journal of Systems and Software (JSS)

Large amounts of digitized histopathological data display a promising future for developing pathological foundation models via self-supervised learning methods. Foundation models pretrained with these methods serve as a good basis for downstream tasks. However, the gap between natural and histopathological images hinders the direct application of existing methods. In this work, we present PathoDuet, a series of pretrained models on histopathological images, and a new self-supervised learning framework in histopathology. The framework is featured by a newly-introduced pretext token and later task raisers to explicitly utilize certain relations between images, like multiple magnifications and multiple stains. Based on this, two pretext tasks, cross-scale positioning and cross-stain transferring, are designed to pretrain the model on Hematoxylin and Eosin (H&E) images and transfer the model to immunohistochemistry (IHC) images, respectively. To validate the efficacy of our models, we evaluate the performance over a wide variety of downstream tasks, including patch-level colorectal cancer subtyping and whole slide image (WSI)-level classification in H&E field, together with expression level prediction of IHC marker, tumor identification and slide-level qualitative analysis in IHC field. The experimental results show the superiority of our models over most tasks and the efficacy of proposed pretext tasks. The codes and models are available at https://github.com/openmedlab/PathoDuet., Comment: Accepted for Medical Image Analysis

In the paper, by virtue of the famous formula of Fa\`a di Bruno, with the aid of several identities of partial Bell polynomials, by means of a formula for derivatives of the ratio of two differentiable functions, and with availability of other techniques, the authors establish closed-form formulas in terms of the Bernoulli numbers and the second kind Stirling numbers, present determinantal expressions, derive recursive relations, obtain power series, and compute special values of the function $\frac{v^j}{1-\operatorname{e}^{-v}}$, its derivatives, and related ones used in Clark--Ismail's two conjectures. By these results, the authors also discover a formula for the determinant of a Hessenberg matrix and derive logarithmic convexity of a sequence related to the function and its derivatives., Comment: 23 pages

The governance of common-pool resources has vital importance for sustainability. However, in the realistic management systems of common-pool resources, the institutions do not necessarily execute the management policies completely, which will induce that the real implementation intensity is uncertain. In this paper, we consider a feedback-evolving game model with the inspection for investigating the management of renewable resource and assume that there exists the implementation uncertainty of inspection. Furthermore, we use the nonlinear model reference adaptive control approach to handle this uncertainty. We accordingly design a protocol, which is an update law of adjusting the institutional inspection intensity. We obtain a sufficient condition under which the update law can drive the actual system to reach the expected outcome. In addition, we provide several numerical examples, which can confirm our theoretical results. Our work presents a novel approach to address the implementation uncertainty in the feedback-evolving games and thus our results can be helpful for effectively managing the common-pool resources in the human social systems., Comment: 27 pages with 4 figures