A Novel Interval Iterative Multi-Thresholding Algorithm Based on Hybrid Spatial Filter and Region Growing for Medical Brain MR Images

Medical image segmentation is widely used in clinical medicine, and the accuracy of algorithm will affect diagnosis results treatment plans. However, manual medical images requires extensive experience knowledge, it both time-consuming labor-intensive. To overcome problems above, we propose a novel interval iterative multi-thresholding based on hybrid spatial filter region growing for brain MR images. First, designed to perform original image, which can make full use information while denoising. Second, Otsu method proposed segment its filtering layer. The initial thresholds be quickly obtained by algorithm, reduce time complexity. optimize thresholds. Finally, weighted strategy refine results. our outperform other comparison algorithms subjective objective evaluations. Subjectively, have clear edges, complete consistent regions. We uniformity measure (U) evaluation, U value significantly higher than algorithms. achieved an average 0.9854 across all test well expand doctor’s ability utilize