A hybrid DenseNet121-UNet model for brain tumor segmentation from MR Images. (July 2022)

• Record Type: Journal Article
• Authors: Cinar, Necip; Ozcan, Alper; Kaya, Mehmet
• Is Part Of: Biomedical signal processing and control. Volume 76(2022)
• Publication Date: 2022-07
• Subjects: Deep learning -- Image processing -- Brain tumor segmentation -- Artificial neural network models -- Image segmentation -- UNet -- DenseNet121; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.103647
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Since we train the images by dividing them into small-sized pieces, the training time is relatively short. We propose a hybrid model by preprocessing the dataset, critical in im-balanced label distributions. A hybrid algorithm for brain tumor segmentation is proposed by using DenseNet121-UNet architecture. We achieve better results than other studies in detecting whole tumor, core tumor, and enhancing tumor by improving low DSC accuracy rate. We ensure unnecessary areas for feature extraction and remove them by cropping images, which improves the accuracy of the segmentation process and shortens the training time of the model. Abstract: Several techniques are used to detect brain tumors in the medical research field; however, Magnetic Resonance Imaging (MRI) is still the most effective technique used by experts. Recently, researchers have proposed different MRI techniques to detect brain tumors with the possibility of uploading and visualizing the image. In the current decade, deep learning techniques have shown promising results in every research area, especially in bioinformatics and medical image analysis. This paper aims to segment brain tumors using deep learning methods of MR images. The UNet architecture, one of the deep learning networks, is used as a hybrid model with pre-trained DenseNet121 architecture for the segmentation process. During training and testing of the model, we focus on smaller sub-regions of tumors that comprise the complex structure. The proposed model is validated on BRATS 2019 publicly available brain tumor dataset that contains high-grade and low-grade glioma tumors. The experimental results indicate that our model performs better than other state-of-the-art methods presented in this particular area. Specifically, the best Dice Similarity Coefficient (DSC) are obtained by using the proposed approach to segment whole tumor (WT), core tumor (CT), and enhancing tumor (ET).