Multi-modal image analysis using deep learning (DL) lays the foundation for neoadjuvant treatment (NAT) response monitoring. However, existing methods prioritize extracting multi-modal features to enhance predictive performance, with limited consideration on real-world clinical applicability, particularly in longitudinal NAT scenarios with multi-modal data. Here, we propose the Multi-modal Response Prediction (MRP) system, designed to mimic real-world physician assessments of NAT responses in breast cancer. To enhance feasibility, MRP integrates cross-modal knowledge mining and temporal information embedding strategy to handle missing modalities and remain less affected by different NAT settings. We validated MRP through multi-center studies and multinational reader studies. MRP exhibited comparable robustness to breast radiologists, outperforming humans in predicting pathological complete response in the Pre-NAT phase (ΔAUROC 14% and 10% on in-house and external datasets, respectively). Furthermore, we assessed MRP’s clinical utility impact on treatment decision-making. MRP may have profound implications for enrolment into NAT trials and determining surgery extensiveness.

Based on breast imaging reports written in three languages, GPT-3.5, GPT-4, and Google Bard achieved moderate agreement with human reader–assigned Breast Imaging Reporting and Data System categories but also yielded a high percentage of discordant category assignments that would negatively impact clinical management.

Accurately determining the molecular subtypes of breast cancer is important for the prognosis of breast cancer patients and can guide treatment selection. In this study, we develop a deep learning-based model for predicting the molecular subtypes of breast cancer directly from the diagnostic mammography and ultrasound images. Multi-modal deep learning with intra- and inter-modality attention modules (MDL-IIA) is proposed to extract important relations between mammography and ultrasound for this task. MDL-IIA leads to the best diagnostic performance compared to other cohort models in predicting 4-category molecular subtypes with Matthews correlation coefficient (MCC) of 0.837 (95% confidence interval [CI]: 0.803, 0.870). The MDL-IIA model can also discriminate between Luminal and Non-Luminal disease with an area under the receiver operating characteristic curve of 0.929 (95% CI: 0.903, 0.951). These results significantly outperform clinicians’ predictions based on radiographic imaging. Beyond molecular-level test, based on gene-level ground truth, our method can bypass the inherent uncertainty from immunohistochemistry test. This work thus provides a noninvasive method to predict the molecular subtypes of breast cancer, potentially guiding treatment selection for breast cancer patients and providing decision support for clinicians.

Digital health data used in diagnostics, patient care, and oncology research continue to accumulate exponentially. Most medical information, and particularly radiology results, are stored in free-text format, and the potential of these data remains untapped. In this study, a radiological repomics-driven model incorporating medical token cognition (RadioLOGIC) is proposed to extract repomics (report omics) features from unstructured electronic health records and to assess human health and predict pathological outcome via transfer learning. The average accuracy and F1-weighted score for the extraction of repomics features using RadioLOGIC are 0.934 and 0.934, respectively, and 0.906 and 0.903 for the prediction of breast imaging-reporting and data system scores. The areas under the receiver operating characteristic curve for the prediction of pathological outcome without and with transfer learning are 0.912 and 0.945, respectively. RadioLOGIC outperforms cohort models in the capability to extract features and also reveals promise for checking clinical diagnoses directly from electronic health records.