An Uncertainty-Guided Evidential Deep Learning Framework for Reliability-Aware Multimodal Fusion in Cancer Prognosis

FuseMD-XNet: Uncertainty-aware multi-modality fusion network with multilevel visual explanations for skin cancer diagnosis.

Skin cancer is a prevalent and potentially fatal disease that emphasizes the need for accurate and interpretable diagnostic tools to improve patient outcomes. Although DL has advanced automated skin lesion analysis, most models rely solely on dermoscopic images and neglect the complementary clinical metadata. In this study, we propose FuseMD-XNet, a multimodal transformer-based framework that integrates dermoscopic images with structured patient metadata. The model employs intermediate fusion through feature concatenation and cosine similarity alignment, followed by adaptive certainty-guided fusion to dynamically weigh the modality contributions based on confidence estimates. To ensure transparency, the FuseMD-XNet incorporates multilevel explainability using ShapleyCAM, FinerCAM, and SHAP methods. The efficacy of FuseMD-XNet was validated on the PAD-UFES-20 dataset, where it achieved an overall mean diagnostic accuracy of 94.4±0.8% and a mean AUC of 95.9±0.5% across all lesion classes. The highest class-specific performance was observed for basal cell carcinoma (BCC), with an accuracy of 98.4±0.4% and an AUC of 98.7±0.3%, whereas melanoma achieved an accuracy of 97.9±1.8% and an AUC of 98.2±0.5%. On the ISIC 2019 dataset, FuseMD-XNet demonstrated strong generalization performance with an overall mean accuracy of 93.0±0.8% and a mean AUC of 94.6±0.6%, whereas melanoma achieved a class-specific accuracy of 94.7±1.6% and an AUC of 96.3±1.1%. Additionally, an integrated risk stratification module enabled personalized assessments validated by feature importance analysis. These results demonstrate the potential of FuseMD-XNet to improve the classification accuracy and interpretability of skin cancer.

An explainable ensemble deep learning framework for brain tumor classification using covariance matrix adaptation evolution strategy

Towards Reliable Multimodal Clinical Decision Support: From Quality-Aware Fusion to Patient Digital Twins

Multimodal deep learning for clinical decision support frequently fails in real-world deployments due to severe data missingness and sensor noise. Standard fusion and Mixture-of-Experts (MoE) architectures assume all modalities are uniformly informative, causing routing collapse and miscalibrated confidence when faced with corrupted inputs. My doctoral research addresses this fragility by shifting the paradigm from generative imputation to uncertainty-guided abstention. As a foundational step, I introduce QA-MoE (Quality-Aware MoE), which explicitly decouples reliability estimation from the routing process. By quantifying epistemic uncertainty, the model dynamically filters noisy modalities before fusion, ensuring sparse and stable inference. Building on this static robustness, my ongoing and future research extends to longitudinal and structured clinical data. I am developing PathFlow-EM, which integrates Expectation-Maximization to handle hidden variable distributions in unevenly sampled time-series, and Uncertainty-Guided Dynamic Topological Fusion (U-DTF), which uses topological data analysis to gate features based on evolving patient graphs. Ultimately, this research trajectory aims to deliver robust, calibration-aware architectures that form the computational basis for reliable Patient Digital Twins.

Multi-view explainability and ensemble deep learning for prostate lesion classification: A comprehensive study.

BACKGROUND AND OBJECTIVE Explainable artificial intelligence is essential for clinical adoption of deep learning models in prostate magnetic resonance imaging. Although ensemble learning can improve robustness, its impact on explanation stability, spatial consistency, and clinical interpretability remains insufficiently quantified. This study aims to evaluate post-hoc interpretability methods across both single-model and ensemble configurations, and to examine whether ensemble-based explanations provide more reliable and clinically meaningful insights than single-model explanations. Critically, this work treats interpretability as a measurable property rather than a purely qualitative visualization. METHODS Convolutional neural networks and bagging-based ensemble models (five VGG16-based classifiers trained on bootstrap samples with replacement, aggregated by soft averaging) were trained on the public PROSTATEx dataset using T2-weighted and apparent diffusion coefficient images. Visual explanations were generated using Gradient-weighted Class Activation Mapping (Grad-CAM) and saliency maps. Lesion localization was evaluated using centroid distance and Dice similarity coefficient with expert-annotated lesion masks. An agreement metric was introduced to quantify spatial consistency between attribution methods and its relationship with prediction reliability. RESULTS The baseline classifier achieved an area under the curve of 0.84, with sensitivity of 0.81 and specificity of 0.86. Grad-CAM localized lesion centroids with higher precision on T2-weighted images (mean error 6.93 pixels) than apparent diffusion coefficient images (mean error 16.3 pixels). Combining saliency maps and Grad-CAM improved the mean Dice score from 0.42/0.45 (individual methods) to 0.52. Ensemble-based explanations were significantly smoother and less variable than individual classifier explanations (Mann-Whitney U, Levene test, all p<0.001). The agreement metric strongly separated correctly and incorrectly classified cases (Mann-Whitney U=84.5, p<0.001; point-biserial r=0.749; ROC-AUC =0.960). CONCLUSIONS These findings suggest that interpretability quality can be quantitatively assessed and improved through multi-method and ensemble-based analysis. The proposed agreement-driven framework enhances explanation robustness and supports reliable and transparent clinical decision support for prostate magnetic resonance imaging.

An adaptive hierarchical class-aware deep ensemble strategy for robust brain tumor classification

Automated magnetic resonance imaging (MRI) classification can support differentiation of brain tumor categories, but conventional ensembles often depend on opaque probability fusion. This study proposes a validation-driven adaptive hierarchical class-aware ensemble that treats VGG19 and Darknet53 as complementary experts. A balanced working set of 7,200 images representing glioma, meningioma, no tumor, and pituitary classes was stratified into training (70%), validation (15%), and independent test (15%) partitions. Training-only enhancement and best-validation-checkpoint retention were used. Validation data alone produced a frozen expert map: Darknet53 was assigned to glioma, meningioma, and no-tumor cases, whereas VGG19 was assigned to pituitary cases. At test time, the router accepted model consensus, consulted the expert map during disagreement, and used confidence only for residual conflicts. On 1,080 unseen test images, the proposed strategy correctly classified 1,060 cases (98.15% accuracy; 98.16% macro precision; 98.15% macro recall; 98.14% macro F1-score). Darknet53 and VGG19 achieved 97.87% and 97.69% accuracy, while weighted soft voting, and stacking each achieved 98.06%. The proposed strategy therefore achieved the strongest benchmark while preserving a transparent, auditable, and leakage-free decision pathway.

Selective Cross-modal Feature Enhancement Through Collaborative Learning