Brain Tumour Image Segmentation Using Deep Networks

Abstract

Automated segmentation of brain tumour from multimodal MR images is pivotal for the analysis and monitoring of disease progression. As gliomas are malignant and heterogeneous, efficient and accurate segmentation techniques are used for the successful delineation of tumours into intra-tumoural classes. Deep learning algorithms outperform on tasks of semantic segmentation as opposed to the more conventional, context-based computer vision approaches. Extensively used for biomedical image segmentation, Convolutional Neural Networks have significantly improved the state-of-the-art accuracy on the task of brain tumour segmentation. In this paper, we propose an ensemble of two segmentation networks: a 3D CNN and a U-Net, in a significant yet straightforward combinative technique that results in better and accurate predictions. Both models were trained separately on the BraTS-19 challenge dataset and evaluated to yield segmentation maps which considerably differed from each other in terms of segmented tumour sub-regions and were ensembled variably to achieve the final prediction. The suggested ensemble achieved dice scores of 0.750, 0.906 and 0.846 for enhancing tumour, whole tumour, and tumour core, respectively, on the validation set, performing favourably in comparison to the state-of-the-art architectures currently available.

Metaheuristic Optimization-Driven Novel Deep Learning Approach for Brain Tumor Segmentation

“…To resolve disparities, the data is removed from the skull, aligned to suit an anatomical template, and resampled at 1 mm 3 resolution. A volume (dimension) of 240 * 240 * 155 is assigned to each sequence [16]. All photos have anisotropic resolutions that are resampled to become isotropic.…”

Evaluation of a hybrid pipeline for automated segmentation of solid lesions based on mathematical algorithms and deep learning

“…Zhao et al 41 made use of a pipeline involving a CNN and a number of expedients including different methods of sampling, patch-based training and teacher-student models, resulting in a reported mean DICE score of 0.883. Ali et al 42 exploited multiple CNNs trained separately, with final predictions based on ensembling the probability maps from each CNN, with a mean DICE of 0.906 for the whole tumour. These works developed specific pipelines with a particular focus on brain tumour segmentation, making use of all available sequences.…”

“…The BraTS dataset is a widely used imaging dataset in the literature 40 – 42 . All scans include several MR sequences, including T1, post-contrast T1-weighted, T2-weighted and T2-FLAIR.…”

Unsupervised Multimodal Supervoxel Merging Towards Brain Tumor Segmentation

“…Brain tumor and lesion segmentation is often formulated as a pixel-wise semantic segmentation problem addressed with supervised learning approaches [4]. Among them, Convolutional Neural Networks (CNNs) have emerged as the current best-performing methods [15] taking different forms: 2D CCNs [18,2], 3D CNNs [3], or extended to Fully convolutional [12] or multimodal approaches [23]. Despite their good performance, pixel-wise methods suffer from high computational complexity due to the significant number of redundant pixels, particularly when dealing with multimodal images.…”