Effect of learning parameters on the performance of U-Net Model in segmentation of Brain tumor

Automatic brain tumor segmentation using several image processing techniques supports early diagnosis and provides useful information for treatment planning. However, due to the heterogeneous nature of brain tumor makes the segmentation process very challenging and exhaustive. Glioma is one type of the fast-growing brain tumors. Its shape, size, and location vary across the patients. Manual extraction of exact glioma from brain MRI (Magnetic Resonance Imaging) is very tricky and time-consuming task for the radiologists. U-Net model is one of the most popular deep learning models for biomedical image segmentation utilized by the researchers and scientists around the world. The up-sampling and down-sampling architecture of U-Net model deliver a remarkable result with small amount of data in various medical image analysis applications. This paper presents the effect of different learning parameters on the performance of the deep U-Net model for brain tumor segmentation. Here, we have compared the performance by tuning the different learning parameters such as the activation function, pooling strategies, kernel or filter size, dropout and batch normalization and measured the accuracy in terms of AUC (area under the curve) and F1score. The experiment was performed on two well-known freely data sets available, BraTs 2017 and BraTs 2018. The whole tumor along with its core and enhancing parts were segmented from FLAIR (Fluid Attenuated Inversion Recovery) MR scans and it is observed that the AUC is improved by 2% in whole tumor segmentation from base model with fine-tuned parameters.