A Machine Learning-based Multi-Phase Medical Image Classification for Internet of Medical Things

The Internet of Medical Things (IoMT) has revolutionised healthcare by allowing for remote monitoring and diagnosis of patients through medical devices. Medical image classification is essential for IoMT applications, as it enables early detection of diseases and personalised treatments. However, single-phase classification models face challenges distinguishing between similar conditions and differentiating them from normal cases. To address these challenges, this research proposes a Machine Learning-based Multi-Phase Medical Image Classification (ML-MPMIC) model that combines image segmentation and classification techniques to achieve higher accuracy in disease diagnosis. The proposed model is evaluated through simulation analysis and parameter optimisation. The proposed ML-MPMIC approach has high accuracy, precision, F score, and Low Root Mean Square Error (RMSE) values and its potential to improve healthcare outcomes in IoMT applications