Explainable Hybrid Deep Learning Approach for Multi-Modality Uterine Fibroid Detection and Clinical Decision Support

Abstract

Uterine fibroids are one of the most common gynaecological tumours, but they can be hard to diagnose because their appearance varies and the images may have poor contrast. Existing computer-aided detection (CAD) methods often use features that were handcrafted or use only a single modality, which limits their reliability and interpretability. An Explainable Hybrid Deep Learning (E-HDL) framework is introduced in this study. It includes a self-improving preprocessing pipeline, adaptive multi-branch feature fusion, and attention-based interpretability for reliably detecting uterine fibroids on both ultrasound and MRI. To make sure that the input quality is the same, the process uses bias-field correction, anisotropic diffusion filtering, CLAHE contrast normalisation, and adaptive spatial alignment. Spatial deep features from a CNN are combined dynamically with contextual embeddings from Transformers and temporal representations from RNNs using an attention-based feature-scaling layer. Extensive experiments on the Mendeley Uterine Fibroid Dataset and cross-dataset evaluation on the HIFU-MRI and UFID-2023 benchmarks show that E-HDL works better than recent state-of-the-art models like Swin-Transformer, MedT, ConvNeXt, and EfficientNetV2. The suggested model is more accurate than previous combination and transformer-based systems, with a 97.1% F1-score and 0.989 AUC. Grad-CAM, SHAP, and attention heatmaps improve interpretability in clinical settings. The study shows that E-HDL is a high-performance, scalable, and easy-to-understand diagnostic aid for detecting uterine tumours.