Liangrui Pan

The integration of Multimodal Large Language Models (MLLMs) into healthcare has the potential to drive a considerable advancement toward many AI use cases in medicine, offering transformative capabilities across hierarchical levels of clinical granularity, ranging from microscopic tissue analysis over organ level imaging and individual patient modeling to population-level health surveillance. However, such integration into clinical practice is constrained by a multifaceted “trustworthiness gap”: the mismatch between the raw capabilities demonstrated by Medical MLLMs in controlled experiments and their reliability, fairness, safety, privacy protection, explainability, and regulatory accountability required for clinical deployment in the real world. This gap requires systematic examination of both model behavior and clinical risk across the full lifecycle of Medical MLLM development and use. In this paper, we survey the existing literature on methods, evaluation, and benchmarks of trustworthiness research in Medical MLLMs. We first establish a multi-scale clinical landscape across tissue, organ, individual, and population levels to categorize current models, providing critical insights into the interplay between data heterogeneity and clinical task requirements. Subsequently, we propose a holistic, six-dimensional taxonomy of trustworthiness, comprising truthfulness, robustness, fairness, safety, privacy, and explainability. Using this taxonomy, we critically analyze existing literature to elicit recurring Medical MLLM trustworthiness failure modes and suggest appropriate remediation strategies. Furthermore, our survey enumerates open challenges in evaluating trustworthiness by means of traditional automated metrics, frontier “LLM-as-a-Judge” methods and expert-centric assessment protocols. As a response to these challenges we identify emerging research directions including dynamic and workflow-oriented evaluations for interactive Medical MLLMs. We aim for this work to serve as a systematic guide for researchers and practitioners aiming to develop the next generation of trustworthy medical AI by achieving clinically acceptable reliability through technological innovations. Project Link: https://github.com/junyuanM/Trustworthy-Medical-MLLMs-Survey.

Accurate intraoperative and postoperative diagnosis of spread through air spaces (STAS) is essential for guiding surgical decisions and postoperative management in lung cancer. However, histopathological assessment is labor-intensive and is prone to missed or incorrect diagnoses. We propose a Diffusion Attention Expert Model (DAEM) to detect STAS in frozen sections (FSs) and paraffin sections (PSs). Its diffusion attention expert module leverages full attention aggregation to learn multi-scale features from histopathological images, while a dual-branch architecture strengthens multi-scale feature representation. On an internal dataset, DAEM achieves AUCs of 0.8946 for FSs and 0.9112 for PSs. Validation on external multi-center datasets from eight institutions demonstrates strong generalizability and interpretability. Using tumor microenvironment (TME) features in PSs, we further enable semi-automatic measurement of STAS location and its distance from the primary tumor. Several quantitative TME metrics are identified as potential biomarkers for STAS, including micropapillary-type STAS. Overall, DAEM offers a clinically actionable framework for STAS assessment by enabling accurate and interpretable detection on FSs and PSs, supporting postoperative risk stratification through quantitative TME-based analysis.

Interpretability analysis of WSI predicted by NAVF-Bio in patients without target gene mutations in high and low TMB states.

Quantitative TME metrics and correlation analysis of the TP53&EGFR, TP53&KRAS, and TP53&ALK groups compared to the TP53 mutation group, with statistical significance determined by T-test.

Performance comparison of NAVF-Bio and 11 SOTA models in the TP53 mutation subtype prediction task based on the SXHCSU dataset.

Statistics of the number of patients with single gene mutation, double gene mutation and multiple gene co-mutation groups.

Performance comparison of NAVF-Bio and 11 SOTA models on the EGFR mutation prediction task based on the SXHCSU dataset.

Performance comparison of NAVF-Bio and 11 SOTA models on the TP53 exon prediction task based on the SXHCSU dataset.

Statistics of the number of gene mutations, mutation subtypes and protein functional domain samples.