• Dipti Vijayanand Patil
• Kishor Mane

With the recent advancement in the medical field, Magnetic Resonance Imaging (MRI) is evolving as a diagnostic tool for critical assessment of the health. It generates the 3D representations of the human body soft tissues for detection of the various abnormalities related to the brain. Traditionally the radiologists can interpret the MRI based on the quantitative data manually based on their expertise which is more time consuming and leading to erroneous prediction. With recent advancement in the technology, machine learning (ML) and diagnosis mechanism with the help of computer have enables the automated information extraction from the MRI images. It supports the faster diagnosis of the disease. This review paper presents a comprehensive study of the existing ML approaches used for MRI analysis inside medical image analysis. It focuses on the review of various mechanism used for feature extraction, classification, anomaly detection and segmentation of MRI images. It also highlights the various challenges identified through the detail literature including noise reduction, interpretability of ML systems, data imbalance. This review paper identifies the potential scope in MRI based knowledge extraction towards design the system of robust and accurate diagnosis of the diseases.

Magnetic Resonance Imaging (MRI), Knowledge Discovery, Machine Learning, Medical Image Analysis, Image Segmentation, Brain Tumor Detection, Computer-Aided Diagnosis (CAD), Deep Learning, Feature Extraction, Anomaly Detection.

"Machine Learning based Knowledge Extraction from MRI Scans: A Comprehensive Survey", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 10, page no.c712-c715, October-2025, Available :http://www.jetir.org/papers/JETIR2510290.pdf

"Machine Learning based Knowledge Extraction from MRI Scans: A Comprehensive Survey", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 10, page no. ppc712-c715, October-2025, Available at : http://www.jetir.org/papers/JETIR2510290.pdf