• Mr. Revanth Bokka
• Sai Krishna Janigorla
• Doddipatla Rakesh
• Areti Reethika
• Kammula lakshmi Dhiraj

Microwave Medical Imaging (MMI) is an advanced imaging technique capable of detecting minor brain tissue abnormalities, providing enhanced diagnostic accuracy for brain stroke compared to traditional MRI and CT imaging. However, the nonlinear nature of MMI's dielectric constants, lacking well-defined boundaries, limits the effectiveness of conventional segmentation algorithms. This study introduces the Distorted Born Iterative Method (DBIM), a novel image processing technique that reconstructs stroke areas with superior precision. Unlike the OTSU method, which faces challenges in accurately segmenting strokes in MMI, DBIM refines thresholding and segmentation to produce reliable and detailed results. A Python-based web server implementation enables users to upload MMI images and compare segmentation outputs of OTSU and DBIM. Experimental findings demonstrate that DBIM significantly enhances image segmentation accuracy, particularly for tumor and stroke detection, thereby contributing to improved diagnostic capabilities in brain stroke detection through MMI.

Microwave Medical Imaging (MMI), Brain Stroke Diagnosis, Image Segmentation, Distorted Born Iterative Method (DBIM), Thresholding Techniques, Diagnostic Accuracy.

"Microwave Medical Image Segmentation For Brain Stroke Diagnosis: Image Processing-Informed Deep Learning.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.d856-d867, March-2025, Available :http://www.jetir.org/papers/JETIR2503395.pdf

"Microwave Medical Image Segmentation For Brain Stroke Diagnosis: Image Processing-Informed Deep Learning.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppd856-d867, March-2025, Available at : http://www.jetir.org/papers/JETIR2503395.pdf