Institution profile

Dana-Farber Cancer Institute

Academic institutionnorthamerica · us
Official website
Research library12linked papers
Opportunities0open roles
Selected work

Representative Papers

Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies

Oct 02, 2026

This study addresses the scarcity of annotated oncological data that constrains deep learning-based biomarker development by proposing a two-stage multimodal AI framework. The approach first infers transcriptomic features from histopathology images and subsequently integrates clinical variables to predict pathological complete response to neoadjuvant therapy in breast cancer. Its core innovation lies in introducing a biologically informed compression strategy that overcomes the target selection constraints of conventional genomic assays, enabling robust generalization under data-sparse conditions while ensuring reliability through spatial consistency validation. Experimental results demonstrate that the model achieves a mixed AUROC of 0.79, outperforming traditional pathology-based biomarkers. Furthermore, it exhibits strong discriminative capacity across molecular subtypes and exceptional sampling robustness, highlighting its potential for precision oncology applications where labeled training data remain limited.

0 citationsRead paper

OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation

Oct 01, 2026

This study addresses the problem of clinical recommendation misclassification caused by excessive refusal in large language models deployed within molecular tumor boards. To this end, we construct an open-source benchmark and a multimodal safety labeling system. Methodologically, we propose an auditing agent architecture that decouples verification from classification to mitigate label collapse, alongside a seven-module deterministic reasoning framework designed to precisely distinguish between evidence-supported recommendations and clinical warnings. Experimental results demonstrate that the proposed approach reduces the over-refusal rate to 6.7% while achieving a classification accuracy of 91.2%. This work provides an effective paradigm for enhancing the reliability and clinical utility of medical AI systems.

0 citationsRead paper

Deep Learning for Longitudinal Medical Imaging: A Scoping Review

Sep 29, 2026

Longitudinal medical image analysis lacks a systematic review, leaving its technical challenges and scientific landscape unclear. This study addresses this gap by conducting a scoping review of 102 deep learning-related studies published between 2018 and 2025, systematically synthesizing their methodological architectures, clinical applications, and validation strategies. The findings reveal that CNN-LSTM serves as the predominant architecture, MRI as the primary modality, and classification tasks within neurology and ophthalmology as the dominant applications. This work provides the first comprehensive delineation of the technical landscape in this field while identifying the critical bottleneck of severely insufficient external validation. Ultimately, it offers clear directions for advancing the clinical translation of artificial intelligence models applied to longitudinal medical imaging.

0 citationsRead paper
Recent publications

Latest Papers

Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies

Oct 02, 2026

This study addresses the scarcity of annotated oncological data that constrains deep learning-based biomarker development by proposing a two-stage multimodal AI framework. The approach first infers transcriptomic features from histopathology images and subsequently integrates clinical variables to predict pathological complete response to neoadjuvant therapy in breast cancer. Its core innovation lies in introducing a biologically informed compression strategy that overcomes the target selection constraints of conventional genomic assays, enabling robust generalization under data-sparse conditions while ensuring reliability through spatial consistency validation. Experimental results demonstrate that the model achieves a mixed AUROC of 0.79, outperforming traditional pathology-based biomarkers. Furthermore, it exhibits strong discriminative capacity across molecular subtypes and exceptional sampling robustness, highlighting its potential for precision oncology applications where labeled training data remain limited.

0 citationsRead paper

OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation

Oct 01, 2026

This study addresses the problem of clinical recommendation misclassification caused by excessive refusal in large language models deployed within molecular tumor boards. To this end, we construct an open-source benchmark and a multimodal safety labeling system. Methodologically, we propose an auditing agent architecture that decouples verification from classification to mitigate label collapse, alongside a seven-module deterministic reasoning framework designed to precisely distinguish between evidence-supported recommendations and clinical warnings. Experimental results demonstrate that the proposed approach reduces the over-refusal rate to 6.7% while achieving a classification accuracy of 91.2%. This work provides an effective paradigm for enhancing the reliability and clinical utility of medical AI systems.

0 citationsRead paper

Deep Learning for Longitudinal Medical Imaging: A Scoping Review

Sep 29, 2026

Longitudinal medical image analysis lacks a systematic review, leaving its technical challenges and scientific landscape unclear. This study addresses this gap by conducting a scoping review of 102 deep learning-related studies published between 2018 and 2025, systematically synthesizing their methodological architectures, clinical applications, and validation strategies. The findings reveal that CNN-LSTM serves as the predominant architecture, MRI as the primary modality, and classification tasks within neurology and ophthalmology as the dominant applications. This work provides the first comprehensive delineation of the technical landscape in this field while identifying the critical bottleneck of severely insufficient external validation. Ultimately, it offers clear directions for advancing the clinical translation of artificial intelligence models applied to longitudinal medical imaging.

0 citationsRead paper