Early Prediction and Risk Analysis Using Hybrid Deep Learning Techniques in Multimodal Biomedical Image

Medical imaging plays a pivotal role in diagnosing and treating various health conditions, especially in early-stage cancer detection. Despite advancements in imaging techniques, the complexity and variability of multimodal medical images, such as MRI and CT scans, pose challenges for accurate diagnosis. Traditional methods often struggle with combining these heterogeneous data sources effectively, limiting the ability to provide timely and precise predictions for early cancer detection. This study proposes a hybrid deep learning framework that integrates multimodal image fusion techniques to improve early cancer prediction. The primary objective of this work is to develop an efficient model that can process diverse medical images, extract meaningful features, and provide accurate classifications for identifying cancerous regions. The techniques employed include Gaussian smoothing for image pre-processing, feature extraction using ORB (Oriented FAST and Rotated BRIEF) for handcrafted features, and the InceptionV4 network for deep learning-based feature extraction. The final stage involves classification using Sparse Logistic Regression and the MS-GWNN classifier, designed to predict the malignancy stage of tumors. The experimental results demonstrate that the proposed approach significantly outperforms traditional methods, achieving a classification accuracy of 93.4%, sensitivity of 91.8%, and specificity of 92.5%. These metrics show superior performance in early detection and risk assessment, especially for high-risk cancer cases. The model is validated using TCIA dataset and displays robust fusion capabilities, leading to high-quality and reliable predictions. Future work will explore the integration of additional imaging modalities, real-time applications for clinical settings, and optimization of fusion strategies. Furthermore, incorporating explainable AI (XAI) can improve the interpretability of the model, enhancing its usability in clinical practice.