IMPROVING MEDICAL IMAGE PIXEL QUALITY USING MICQ UNSUPERVISED MACHINE LEARNING TECHNIQUE

Biomedical image processing and decision making is a growing research demand under global pandemic situation. The quality of medical images plays a vital role in streamlining remote diagnosis and processing via telemedicine platform, in providing unambiguous results and decision supports. This paper presents an improved Medical Image Content Quality (MICQ) technique and it aims to enrich the Magnetic Resonance (MR) image content or pixels based on semi supervised clustering technique for the process of deeper analysis and investigation to identify the normal and abnormal portions. The proposed (IMICQ) system is containing three stages namely pre-processing, clustering and validation respectively. In the pre-processing stage, the MICQ divides the MR image into finite number of non-overlapping blocks or vectors with size (2*2). Next stage, the proposed MICQ system iteratively partitions the MR image dataset or vector set into optimum number of highly relative dissimilar clusters based on K-Means clustering technique. In the last stage, the proposed system measures the quality of clustering result which obtained in the previous stage based on Effective Cluster Validation Measure (ECVM). Experimental results show that the MICQ is better suitable to improve MR image content quality for telemedicine platform and to predict the normal and abnormal portions over the image with higher accuracy ratio.