This paper presents a novel blockchain-embedded cybersecurity framework for industrial solar power systems, integrating immutable machine learning (ML) with distributed ledger technology. Our contribution focused on three factors, Quantum-resistant feature engineering using the UNSW-NB15 dataset adapted for solar infrastructure anomalies. An enhanced Light Gradient Boosting Machine (LightGBM) classifier with blockchain-validated decision thresholds, and A cryptographic proof-of-threat (PoT) consensus mechanism for cyber attack verification. The proposed Immutable LightGBM model with majority voting and cryptographic feature encoding achieves 96.9% detection accuracy with 0.97 weighted average of precision, recall and F1-score, outperforming conventional intrusion detection systems (IDSs) by 12.7% in false positive reduction. The blockchain layer demonstrates a 2.4-s average block confirmation time with 256-bit SHA-3 hashing, enabling real-time threat logging in photovoltaic networks. Experimental results improve in attack traceability compared to centralized security systems, establishing new benchmarks for trustworthy anomaly detection in smart grid infrastructures. This study also compared traditional and hybrid ML based blockchian driven IDSs and attained better classification results. The proposed framework not only delivers a resilient, adaptable threat mitigation system (TMS) for Industry 4.0 solar powered infrastructure but also attains high explainability, scalability with tamper-proof logs, and remarkably exceptional ability of endurance to cyber attacks.

Feature selection (FS) plays a crucial role in medical imaging by reducing dimensionality, improving computational efficiency, and enhancing diagnostic accuracy. Traditional FS techniques, including filter, wrapper, and embedded methods, have been widely used but often struggle with high-dimensional and heterogeneous medical imaging data. Deep learning-based FS methods, particularly Convolutional Neural Networks (CNNs) and autoencoders, have demonstrated superior performance but lack interpretability. Hybrid approaches that combine classical and deep learning techniques have emerged as a promising solution, offering improved accuracy and explainability. Furthermore, integrating multi-modal imaging data (e.g., Magnetic Resonance Imaging (MRI), Computed Tomography (CT), Positron Emission Tomography (PET), and Ultrasound (US)) poses additional challenges in FS, necessitating advanced feature fusion strategies. Multi-modal feature fusion combines information from different imaging modalities to improve diagnostic accuracy. Recently, quantum computing has gained attention as a revolutionary approach for FS, providing the potential to handle high-dimensional medical data more efficiently. This systematic literature review comprehensively examines classical, Deep Learning (DL), hybrid, and quantum-based FS techniques in medical imaging. Key outcomes include a structured taxonomy of FS methods, a critical evaluation of their performance across modalities, and identification of core challenges such as computational burden, interpretability, and ethical considerations. Future research directions—such as explainable AI (XAI), federated learning, and quantum-enhanced FS—are also emphasized to bridge the current gaps. This review provides actionable insights for developing scalable, interpretable, and clinically applicable FS methods in the evolving landscape of medical imaging.