Open AccessBRAIN TUMOR SEGMENTATION BASED ON U-NET WITH IMAGE DRIVEN LEVEL SET LOSS
Author(s) -
Truong Van Pham,
Thao Tran
Publication year - 2021
Publication title -
vietnam journal of science and technology/science and technology
Language(s) - English
Resource type - Journals
eISSN - 2815-5874
pISSN - 2525-2518
DOI - 10.15625/2525-2518/59/5/15772
Subject(s) - dice , sørensen–dice coefficient , segmentation , artificial intelligence , computer science , cross entropy , pattern recognition (psychology) , similarity (geometry) , intersection (aeronautics) , set (abstract data type) , artificial neural network , function (biology) , entropy (arrow of time) , image (mathematics) , information loss , image segmentation , mathematics , statistics , engineering , physics , quantum mechanics , evolutionary biology , biology , programming language , aerospace engineering
This paper presents an approach for brain tumor segmentation based on deep neural networks. The paper proposes to utilize U-Net as an architecture of the approach to capture the fine and soars information from input images. Especially, to train the network, instead of using commonly used cross-entropy loss, dice loss or both, in this study, we propose to employ a new loss function including Level set loss and Dice loss function. The level set loss is inspired from Mumford-Shah functional for unsupervised task. Meanwhile, the Dice loss function measures the similarity between the predicted mask and desired mask. The proposed approach is then applied to segment brain tumor from MRI images as well as evaluated and compared with other approaches on a dataset of nearly 4000 brain MRI scans. Experiment results show that the proposed approach achieves high performance in terms of Dice coefficient and Intersection over Union (IoU) scores.