JI-ADF: Joint-Individual Learning with Adaptive Decision Fusion for Multimodal Skin Lesion Classification

TL;DR

This paper introduces JI-ADF, a multimodal deep learning framework that combines images and patient data for improved skin lesion classification, addressing the underutilization of clinical evidence in existing systems.

Contribution

It proposes a novel joint learning and adaptive decision fusion approach with a multimodal attention module, enhancing classification robustness and clinical relevance.

Findings

Improves sensitivity and Dice score on MILK10k benchmark.

Maintains high specificity and calibration across lesion categories.

Demonstrates robustness through ablation and visualization analyses.

Abstract

Skin lesion classification is essential for early dermatological diagnosis, yet many existing computer-aided systems rely primarily on dermoscopic images and underutilize the multimodal evidence routinely available in clinical practice. To address this gap, we propose \textbf{JI-ADF}, a trimodal deep learning framework that integrates dermoscopic images, clinical photographs, and structured patient metadata for clinically grounded skin lesion classification. The proposed architecture combines joint multimodal representation learning with modality-specific auxiliary supervision and an adaptive decision fusion mechanism that dynamically calibrates modality contributions on a per-sample basis. To enhance cross-modal reasoning while preserving modality-specific evidence, we further introduce a multimodal fusion attention (MMFA) module. We evaluate JI-ADF on the large-scale MILK10k benchmark, which reflects real-world clinical acquisition conditions and severe class imbalance. The proposed method demonstrates strong and well-balanced performance across lesion categories, improving sensitivity and Dice score while maintaining high specificity and good calibration. Extensive analyses, including modality ablation, calibration evaluation, and Grad-CAM visualization, further confirm the robustness and clinically meaningful behavior of the model. These results indicate that JI-ADF provides a reliable and practical foundation for multimodal skin lesion classification in real-world clinical settings.