DSpace Arşivi :: by Yazar "Izaddin, Barish Mohammed Izaddin" değerine göre listeleniyor

Listeleniyor 1 - 1 / 1

Combination of fuzzy C-means and thresholding for segmentation using medical images
(Altınbaş Üniversitesi, 2021) Izaddin, Barish Mohammed Izaddin; Türkben, Ayça Kurnaz
Breast tumor segmentation is a crucial stage in breast cancer therapy and follow-up. Radiologists can minimize the high workload of breast cancer analysis by automating this difficult process. After pre-processing source pictures, this article established a system for accurately segmenting breast tumors and non-infected areas (breast) on medical imaging using combination of Fuzzy c-Means and Thresholding (FCMT). This is a computer-aided diagnostic method that works on each individual breast slice without any training for segmentation. On a database of 79 images of Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). To increase the image quality, we used pre-processing techniques such as contrast augmentation before applying the FCMT for segmentation. To assess the effectiveness of the devised approach, the Mean Square Error, dice coefficient, Structured Similarity Index, Peak Signal-to-Noise Ratio, accuracy, and sensitivity were computed. On the same dataset, we compared our technique to different segmentation methods. With a dice coefficient of 0.9568 and an accuracy of 0.9731, our approach surpassed the other substantially. The suggested approach is more resilient and accurate in segmenting tumor progression on medical pictures, according to the findings of the experiments.