Purpose: Planning and evaluating the extent of the spread of brain tumors for the treatment is the main challenge. Magnetic resonance imaging (MRI) has been shown as a great diagnostic tool for brain tumors without harmful radiation. We have found in using the traditional U-net, that there are some errors in identifying the tumor, so we wanted to develop this method so that it overcomes some errors in determining the tumor in the traditional method.
Methods: We demonstrate a way to segment the brain tumor using modify U-net networks. Then compared with traditional U-net, modified U-net, k-means, and thresholding segmentation. The experiments were carried out using three multimodal brain tumor image segmentation datasets (FIGSHARE database), which contain 3929 abnormal (with a tumor) and normal brain MRI images, 100 images obtained from “The Cancer Imaging Archive (TCIA)” and BraTS 2019 challenge which include 4600 cases (normal and abnormal) of HGG (high-grade glioma) and LGG(low-grade glioma).
Results: Through this study, the modified U-net achieved higher accuracy than other methods.
Conclusion: Determining the tumor inside the human brain is an important matter to preserve human life. We used old and modern techniques and modified the basic form of the traditional U-net. The above-mentioned techniques were compared and the experiment was done on many data from different sources. It was found that the modified U-net is the best accurate.