A Deep Learning Framework for Segmenting Brain Tumors Using MRI and Synthetically Generated CT Images

Abstract

Multi-modal three-dimensional (3-D) image segmentation is used in many medical applications, such as disease diagnosis, treatment planning, and image-guided surgery. Although multi-modal images provide information that no single image modality alone can provide, integrating such information to be used in segmentation is a challenging task. Numerous methods have been introduced to solve the problem of multi-modal medical image segmentation in recent years. In this paper, we propose a solution for the task of brain tumor segmentation. To this end, we first introduce a method of enhancing an existing magnetic resonance imaging (MRI) dataset by generating synthetic computed tomography (CT) images. Then, we discuss a process of systematic optimization of a convolutional neural network (CNN) architecture that uses this enhanced dataset, in order to customize it for our task. Using publicly available datasets, we show that the proposed method outperforms similar existing methods.

SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans

“…It is noted that the results in Table 6 show comparisons based on the entire algorithms, while the results in Table 2 show the comparisons based on the different deep learning architectures. There are several methods [ 71 , 72 , 73 , 74 , 75 ] using the Clinical and BrainWeb datasets [ 76 ]. These CNN methods [ 71 , 72 , 73 , 74 , 75 ] provide segmentation accuracy from 0.85 to 0.94.…”

“…There are several methods [ 71 , 72 , 73 , 74 , 75 ] using the Clinical and BrainWeb datasets [ 76 ]. These CNN methods [ 71 , 72 , 73 , 74 , 75 ] provide segmentation accuracy from 0.85 to 0.94. Due to the difference in experimental conditions, the segmentation results details are not included in this paper.…”

Salp Swarm Algorithm with Multilevel Thresholding Based Brain Tumor Segmentation Model

“…Next, estimated the mean intensity and the 5 blocks with maximal mean intensity have been chosen out of the 8 blocks. The authors in [15] propose a technique of augmenting a present MRI data set by producing synthetic CT image. Next, deliberate a procedure of systematic optimization of (CNN model which employs the improved data set for customizing the task.…”

(Retracted) Deep belief network-based image processing for local directional segmentation in brain tumor detection

“…To assist physicians, it is necessary to have a computerized system that can recognize and classify various types of brain tumours. 27,29 While modeling multiimages that contain classified information, which has no image representation modalities, and combining this information for identification is a difficult undertaking. 7 To address the problem of multimodeling medical segmentation, strategies have been proposed.…”