eng Oriental Scientific Publishing Company Biomedical and Pharmacology Journal 0974-6242 2025-02-20 18 March Spl Edition 73 83 10.13005/bpj/3074 64205 article Karan Kumar 1 Isha Suwalka 2 Harishchander Anandaram 3 Kapil Joshi 4 Electronics and Communication Engineering Department, Maharishi Markandeshwar Engineering College, Maharishi Markandeshwar (Deemed to be University), Mullana, Ambala, India Department of Research and Publication, Indira IVF Hospital Limited, Udaipur, India Department of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, Tamil Nadu, India Department of Computer Science and Engineering, Uttaranchal Institute of Technology (UIT), Uttaranchal University, Dehradun 248007, Uttarakhand, India Brain tumor detection from MRI images is crucial for early diagnosis and treatment. Various clustering algorithms, such as Fuzzy K-means (FKM), Fuzzy C-means (FCM), and Self-Organizing Maps (SOM), have been used for segmentation, but they face challenges like noise and varying image intensities. This study evaluates the performance of the Adaptive Moving Self-Organizing Map (AMSOM) for tumor segmentation in MRI images, comparing it to other clustering methods. We evaluated FCM, FKM, SOM-FKM, and AMSOM on a dataset of 12 MRI images. Performance was measured using Peak Signal-to-Noise Ratio (PSNR), accuracy, Mean Square Error (MSE), and similarity criteria. AMSOM outperformed other methods with an MSE of 0.01, PSNR of 68.16 dB, accuracy of 89.11%, and similarity criteria of 96.8%. In comparison, FCM showed an MSE of 2.880 and PSNR of 43.57 dB, while FKM had an MSE of 1.9 and PSNR of 45.17 dB. AMSOM provides superior segmentation accuracy and computational efficiency, making it a highly effective approach for detecting brain tumors in MRI images. Its robust performance highlights its potential for medical imaging applications. Future research could expand its use to include PET scans and 3D imaging, enabling broader applicability in advanced medical diagnostics and treatment planning. https://biomedpharmajournal.org/vol18marchspledition/an-automatic-simulation-of-mri-using-adaptive-unsupervised-mapping/ AMKFSOM Brain Tumor clustering feature extraction Magnetic Resonance Imaging