Microwave Medical Image Segmentation for Brain Stroke Diagnosis: Imaging-Process-Informed Image Processing

In this paper, we propose a novel imaging-process-informed image segmentation method that accounts for uncertainty during the imaging process. A priori information is incorporated to enhance the contrast between stroke area and healthy tissues. The distorted Born iterative method (DBIM) is utilized to reconstruct the stroke area of the brain. Due to the non-linear relationship between actual and estimated dielectric constants resulting from DBIM, the microwave medical image lacks a clearly defined boundary, posing a challenge to accurately segment it using traditional methods. The proposed method achieves effective image segmentation by improving the traditional threshold method. From the simulation results, the region misclassified by the traditional method accounts for 89%, while the proposed method results in a misclassification rate of only 13%. The results demonstrate a significant improvement of 58.85% in accurately reproducing the dielectric constants.