Hybrid Machine Learning Approach: SVM with ANN Kernel for HSI Medical Image Enhancement

In medicine image processing provides a perceptive study on disease diagnosis and identification as well as treatment preparation. Since it can acquire complete spectral information over a wide spectrum of wavelengths, especially hyperspectral imaging (HSI) has shown great potential for the non-invasive characterization of tissue. On the other hand, due to their high-dimensional character as well as the presence of noise HSI medical images present a great challenge for processing and enhancement. Even if traditional methods are effective since they sometimes struggle to manage the complexity of these datasets, more sophisticated approaches are needed and demanded. The proposed a hybrid machine learning model including a support vector machine (SVM) classifier and an artificial neural network (ANN) kernel inside the scope of this work to improve and classify HSI images. The ANN kernel is designed to control the inherently complex and non-linear elements in HSI data. Acting as a mapping tool, the artificial neural network kernel transforms the input space into a feature space easily managed in which the SVM can operate with higher accuracy. Main goals are to lower image noise and increase contrast to improve diagnosis correctness. The method was evaluated with a readily available general public HSI medical image collection. In the experimental results, image quality and classification accuracy show appreciable rise. Comparatively to the traditional SVM methods, the signal-to-noise ratio (SNR) increased by 15%; hence, the general classification accuracy was found to be 94.8%. Moreover, the better images show more clear tissue limits and spectral features, which helps clinical interpretation of the results. The results imply that the SVM with ANN kernel model provides a strong solution for the enhancement and classification of HSI medical images, so opening a new path for the improvement of medical diagnostics.