Timely and precise identification of breast cancer is crucial for enhancing clinical outcomes; however, current AI systems frequently exhibit deficiencies in transparency, trustworthiness, and the capacity to assimilate varied data modalities. We introduce a reliable, multi-agent, multimodal AI system for individualised early breast cancer diagnosis, created on the CBIS-DDSM dataset. The system consists of four specialised agents that cooperatively analyse diverse data. An Imaging Agent employs convolutional and transformer-based models to analyse mammograms for lesion classification and localisation; a Clinical Agent extracts structured features including breast density (ACR), view type (CC/MLO), laterality, mass shape, margin, calcification type and distribution, BI-RADS score, pathology status, and subtlety rating utilising optimised tabular learning models; a Risk Assessment Agent integrates outputs from the imaging and clinical agents to produce personalised malignancy predictions; and an Explainability Agent provides role-specific interpretations through Grad-CAM for imaging, SHAP for clinical features, and natural language explanations customised for radiologists, general practitioners, and patients. Predictive dependability is assessed by Expected Calibration Error (ECE) and Brier Score. The framework employs a modular design with a Streamlit interface, facilitating both comprehensive deployment and interactive demonstration. This paradigm enhances the creation of reliable AI systems for clinical decision assistance in oncology by the integration of strong interpretability, personalised risk assessment, and smooth multimodal integration.

Oral cancer represents a life-threatening malignancy with profound implications for patient survival and quality of life. Oral squamous cell carcinoma (OSCC), the predominant histological variant of oral cancer, constitutes a substantial healthcare challenge wherein early detection remains critical for therapeutic efficacy and enhanced survival outcomes. Recent advances in deep learning methodologies have demonstrated superior performance in medical imaging applications. However, existing investigations have predominantly employed unimodal image data for oral lesion classification, thereby neglecting the potential advantages of multimodal data integration. To address this limitation, we propose a comprehensive multimodal pipeline for the classification of OSCC versus leukoplakia through the integration of histopathological imagery with tabular data encompassing anatomical characteristics and behavioral risk factors. Our methodology achieved a precision of 0.97, F1-score of 0.97, recall of 0.98, and accuracy of 0.97. These findings demonstrate the enhanced diagnostic precision and efficacy afforded by multimodal approaches in oral cancer classification, suggesting a promising avenue for improved diagnostic accuracy and treatment planning optimization.

In breast cancer radiotherapy, clinicians must deliver an adequate tumor dose while protecting surrounding healthy organs. This balance remains difficult: planning is often limited by manual contours, the loss of spatial information, and simplified toxicity indices that do not fully exploit spatial dose information. To address these gaps, we introduce a proof-of-concept AI pipeline that links three tasks into a single workflow: segmentation of organs-at-risk (OARs), voxel-based dose estimation, and toxicity prediction, all derived from planning computed tomography (CT) scans through intermediate dose and dose–volume representations. The first module performs multi-organ segmentation of the heart, lungs, and clinical target volume (CTV) using a Hybrid Residual Transformer Network (HRTNet). The second module employs a lightweight three-dimensional U-Net (3D U-Net) to reconstruct patient-specific dose distributions. The third module uses a Gated Recurrent Unit–Transformer (GRU- Transformer) model to estimate organ-specific toxicity based on dose–volume histograms (DVHs). Experiments conducted on a retrospective cohort of 52 breast cancer cases using patient-wise five-fold cross-validation demonstrate that the proposed pipeline achieves consistent OAR and target segmentation performance, produces dose distributions that are spatially consistent with clinical reference plans, and enables exploratory toxicity prediction under limited and imbalanced data conditions. Explainability techniques, including Grad-CAM and SHapley Additive exPlanations (SHAP), provide qualitative insight into model attention patterns and learned dose–toxicity relationships within the dataset. These components, when combined, illustrate the viability of an end-to-end pipeline capable of supporting more consistent and spatially informed radiotherapy planning workflows, subject to external validation.