A deep conventional neural network model for glioma tumor segmentation

Abstract

Glioma represents one of the most aggressive cancers, which can develop in the brain. The automatic tumor segmentation and its sub‐regions represent a challenging task owing to their considerable structural variation. It can appear in different ways and with several shapes, which makes tissue identification a crucial task. Reliable and accurate segmentation presents an important component in tumor treatment and diagnosis planning. To overcome these drawbacks, various Deep Learning (DL) schemes are proposed to aid doctors. In this paper, a novel Convolutional Neural Network (CNN) scheme for glioma segmentation was proposed. Our suggested technique consists of three phases. First, we use intensity normalization to ameliorate the image quality as a preprocessing step. Second, an automatic segmentation technique based on CNN has been proposed. The new model has several layers. Finally, and with the goal of refining the segmentation results, we employ a post‐processing approach. We use the public benchmark BraTS datasets from 2018 and 2020 with low‐grade and high‐grade glioma tumors to test the suggested framework. These datasets contain about 285 and 369 patients, respectively. The four modalities are exploited. Each patient has about 155 2D images from every modality. All the images have the same size (240 × 240 pixels). Our technique performs well compared to new methods, with Dice scores of 0.88 for the Whole Tumor, 0.84 for Tumor Core, and 0.71 for Enhancing Tumor based on the first dataset. According to the second dataset, the three regions had an average of 0.88, 0.9, and 0.75, respectively. The Jaccard indexes for the first data set are 0.8, 0.73, and 0.56 for the three regions, respectively. The second data set attains 0.8, 0.82, and 0.6 for the three regions. The results show that the suggested framework is an excellent way to segment data, especially compared to other methods.

Brain tumor segmentation and survival time prediction using graph momentum fully convolutional network with modified Elman spike neural network

“…The conventional RBAF 35 method accomplishes higher DSC score of 83% for WT, maximum Sy value of 93% for WT, enhanced Sp score of 99% for all the segments, and minimum Hausdorff 95 of 13.6 for ET. The existing Deep CNN 54 attains improved DSC score of 88% for ET, increased Sy score of 90% for WT, higher Sp value of 99% for all the tumors, and minimum Hausdorff 95 performance of 5.34 for TC. The achieved DSC value for ET is 96%, WT is 94%, TC is 98%, Sy score for ET is 98%, WT is 99%, TC is 98%, Sp score for ET is 100%, WT is 100%, TC is 100%, and Hausdorff 95 for ET is 5.3, WT is 4.2, TC is 4.05 which clearly illustrates that the introduced system attains better performance than the other conventional approaches.…”

“…This section discusses, the analysis of outcomes accomplished from various simulation experiment for BT segmentation and OSP. The existing methods such as ResUNet+, 53 radiomics based automatic framework (RBAF), 35 DCNN, 54 encoder–decoder method with depthwise atrous spatial pyramid pooling Network (EDD‐Net), 55 Weight loss function and Dropout U‐Net with convNeXt block (WD‐UNeXt), 56 focal cross transformer, 57 Attention‐based Multimodal Glioma Segmentation (AMMGS), 58 Segmentation based on Transformer and U2‐Net (STrans‐U2Net), 59 deep Residual U‐Net (dRes U‐Net), 60 and DenseTransformer (DenseTrans) 61 are compared with the introduced approach based on DSC, Sy, Sp and Hausdorff 95 in Table 6.…”

“…method accomplishes higher DSC score of 83% for WT, maximum Sy value of 93% for WT, enhanced Sp score of 99% for all the segments, and minimum Hausdorff 95 of 13.6 for ET. The existing Deep CNN54 attains improved DSC score of 88% for ET,…”