A comparative study of classification methods for automatic multimodal brain tumor segmentation

The segmentation of brain tumor plays an important role in diagnosis, treatment planning, and surgical simulation. The precise segmentation of brain tumor can help clinicians obtain its location, size, and shape information. We propose a fully automatic brain tumor segmentation method based on kernel sparse coding. It is validated with 3D multiple-modality magnetic resonance imaging (MRI). In this method, MRI images are pre-processed first to reduce the noise, and then kernel dictionary learning is used to extract the nonlinear features to construct five adaptive dictionaries for healthy tissues, necrosis, edema, non-enhancing tumor, and enhancing tumor tissues. Sparse coding is performed on the feature vectors extracted from the original MRI images, which are a patch of m×m×m around the voxel. A kernel-clustering algorithm based on dictionary learning is developed to code the voxels. In the end, morphological filtering is used to fill in the area among multiple connected components to improve the segmentation quality. To assess the segmentation performance, the segmentation results are uploaded to the online evaluation system where the evaluation metrics dice score, positive predictive value (PPV), sensitivity, and kappa are used. The results demonstrate that the proposed method has good performance on the complete tumor region (dice: 0.83; PPV: 0.84; sensitivity: 0.82), while slightly worse performance on the tumor core (dice: 0.69; PPV: 0.76; sensitivity: 0.80) and enhancing tumor (dice: 0.58; PPV: 0.60; sensitivity: 0.65). It is competitive to the other groups in the brain tumor segmentation challenge. Therefore, it is a potential method in differentiation of healthy and pathological tissues.

Intraoperative ultrasound (iUS) is increasingly used in pediatric brain tumor surgery. However, accurate tumor tissue identification and localization within the patient with iUS remains challenging. Automatic tumor segmentation may overcome these difficulties by providing quicker, more consistent, and reliable image analysis. This study evaluated the feasibility of automatic 3-dimensional segmentation of pediatric brain tumors using navigated iUS. A retrospective analysis was conducted on 109 navigated iUS acquisitions from 60 pediatric patients who underwent neurosurgical tumor resection. 3-dimensional nnU-Net was trained on 79 preresectional iUS acquisitions with corresponding tumor segmentations. Evaluation was performed on 30 iUS acquisitions against segmentations validated by 2 neurosurgeons. Performance benchmarks were set at a minimum Dice Similarity Coefficient (DSC) of 0.85 and a maximum mean surface distance and 95th percentile Hausdorff distance of 5 mm. The trained algorithm predicted tumor segmentations for all acquisitions in the test set, which met the predefined benchmark values with a median DSC of 0.89 (IQR: 0.13), a median mean surface distance of 1.1 mm (IQR: 1.0 mm), and a median 95th percentile Hausdorff distance of 5.6 mm (IQR: 3.5 mm). The lowest quartile of DSC values consisted of 5 patients, including craniopharyngiomas (n = 3) and high-grade gliomas (n = 2). Oversegmentation of the lateral ventricle as tumor was observed in 2 patients. In 1 high-grade glioma case, edema was misclassified as tumor because of unclear tumor boundaries. This study demonstrates that automatic segmentation of pediatric brain tumors using navigated iUS is feasible and achieved high performance in most cases, with few outliers that showed moderate performance in tumor prediction. Future efforts will focus on real-time segmentation of residual tumor tissue during tumor resection. Ultimately, real-time visualization of automatically segmented tumors in 3 dimensions could improve intraoperative navigation and support neurosurgical decision making.

CLCU-Net: Cross-level connected U-shaped network with selective feature aggregation attention module for brain tumor segmentation

Accurate and automated brain tumor segmentation using multi modal MR images is essential for the evaluation of the disease progression in order to improve disease diagnosis and treatment planning. We present a new fully automated method for high graded brain tumor segmentation combining sparse autoencoder and multimodal Fuzzy C-means clustering. The approach utilizes multimodal MRI contrast: T1, T2, FLAIR and T1c (contrast-enhanced) for 15 high graded glioma (HGG) subjects. The objective of the proposed study is to segment tumor tissues from HGG including edema and tumor core within edema. The segmentation was performed on the training data of the multimodal brain tumor image segmentation benchmark 2015. Sparse autoencoder, which is an unsupervised learning algorithm, was used to automatically learn features from unlabeled dataset of tumor in order to segment edema. Followed by edema segmentation, tumor core was segmented from edema using multimodal FCM clustering. Evaluating the performance of the segmentation results with the ground truth yields high dice score (DS) of 0.9866±0.01 and 0.9843±0.01 for edema and tumor core respectively and high Jaccard similarity (JS) of 0.9738±0.02 and 0.9692±0.02 for edema and tumor core respectively; showed high accuracy in segmenting the complex tumor structures from multi-contrast MR scans of HGG patients. We also compared our methodology in terms of segmentation efficiency with some recent techniques reported in proceedings of MICCAI-BRATS challenge 2015.

The detection and segmentation of tumor region in brain image is a critical task due to the similarity between abnormal and normal region. In this article, a computer‐aided automatic detection and segmentation of brain tumor is proposed. The proposed system consists of enhancement, transformation, feature extraction, and classification. The shift‐invariant shearlet transform (SIST) is used to enhance the brain image. Further, nonsubsampled contourlet transform (NSCT) is used as multiresolution transform which transforms the spatial domain enhanced image into multiresolution image. The texture features from grey level co‐occurrence matrix (GLCM), Gabor, and discrete wavelet transform (DWT) are extracted with the approximate subband of the NSCT transformed image. These extracted features are trained and classified into either normal or glioblastoma brain image using feed forward back propagation neural networks. Further, K‐means clustering algorithm is used to segment the tumor region in classified glioblastoma brain image. The proposed method achieves 89.7% of sensitivity, 99.9% of specificity, and 99.8% of accuracy.

Gliomas are the most common and aggressive form of all brain tumors, with medial survival rates of less than two years for the highest grade. While accurate and reproducible segmentation of brain tumors is paramount for an effective treatment plan and diagnosis, automatic brain tumor segmentation is challenging because the lesion can appear anywhere in the brain with varying shapes and sizes from one patient to another. Moreover, segmentation is only done by analyzing pixel intensity values of surrounding tissues, and the diffusing nature of aggressive brain tumors makes it even more challenging to delineate tumor boundaries. Nevertheless, deep learning methods have superior performance in automatic brain tumor segmentation. However, their boost in performance comes at the cost of high computational complexity. This paper proposes efficient network architecture for 3D brain tumor segmentation, partially utilizing depthwise separable convolutions to reduce computational costs. The experimental results on the BraTS 2020 dataset show that our methods could achieve comparable results with the state-of-the-art methods with minimum computational complexity. Furthermore, we provide a critical analysis of the current efficient model designs. The code for this project is available at https://github.com/tmagadza/partialDepthwiseNet.

In this work, we propose a fully automatic brain tumor and edema segmentation technique in brain magnetic resonance (MR) images. Different brain tissues are characterized using the novel texture features such as piece-wise triangular prism surface area (PTPSA), multi-fractional Brownian motion (mBm) and Gabor-like textons, along with regular intensity and intensity difference features. Classical Random Forest (RF) classifier is used to formulate the segmentation task as classification of these features in multi-modal MRIs. The segmentation performance is compared with other state-of-art works using a publicly available dataset known as Brain Tumor Segmentation (BRATS) 2012 [1]. Quantitative evaluation is done using the online evaluation tool from Kitware/MIDAS website [2]. The results show that our segmentation performance is more consistent and, on the average, outperforms other state-of-the art works in both training and challenge cases in the BRATS competition.

A Review on Convolutional Neural Networks for Brain Tumor Segmentation: Methods, Datasets, Libraries, and Future Directions

Brain tumor segmentation and classification is really a difficult process to identify and detect the tumor region. Magnetic resonance image (MRI) gives valuable information to find the affected area in the brain. The MRI brain image is initially considered, which specifies four various modalities of the brain such as T1, T2, T1C, and the Flair. The preprocessing methodologies and the state-of-the-art MRI-related brain tumor segmentation and classification methods are discussed. This study describes the different types of brain tumor segmentation and classification techniques with its most important contributions. The survey of brain tumor segmentation and classification (BTSC) technique including the four main phases—preprocessing, feature extraction, segmentation, and classification—is discussed. The different types of BTSC techniques are listed, along with their great contributions. A review of recent articles on classifiers shows the eccentric features of classifiers for research.

Accurate detection and pixel‐wise classification of brain tumors in Magnetic Resonance Imaging (MRI) scans are vital for their diagnosis, prognosis study and treatment planning. Manual segmentation of tumors from MRI is highly subjective and tedious. With recent advances in deep learning, automatic brain tumor segmentation is an emerging research direction in the medical imaging domain. We present a study to improve the automatic segmentation process by introducing size variability in the Convolutional Neural Network (CNN). For pixel‐wise classification of tumorous slices convolutional neural network‐based encoder‐decoder UNET model is referred. A multi‐inception‐UNET model is proposed to improve scalability of the UNET model. Extensive experiments have been performed using the Brain Tumor Segmentation Challenge (BRATS) datasets to establish the validity of our proposed model. Experimental results show that our proposed method achieved the best results on BraTS 2015, 2017 and 2019 datasets for complete tumor, core tumor and enhancing tumor regions respectively.

Brain tumor segmentation, an essential but challenging task, has long attracted much attention from the medical imaging community. Recently, successful applications of sparse coding and dictionary learning has emerged in various vision problems including image segmentation. In this paper, a superpixel-based framework for automated brain tumor segmentation is introduced. The kernel trick is adopted in dictionary learning to transform superpixel-level features to a high-dimensional feature space where their nonlinear similarities are considered to generate discriminative sparse codes. A graph is constructed from the approximation errors given by dictionaries modeling different brain tumor structures so that superpixels belonging to particular tumor regions can be efficiently identified. The proposed framework is evaluated on brain magnetic resonance images of high-grade glioma (HGG) patients provided by the multi-modal Brain Tumor Segmentation (BRATS) Benchmark. Results show that the proposed framework achieves competitive performance when compared with the state-of-the-art methods.

Grid conditional random fields (CRFs) are widely applied in both natural and medical image segmentation tasks. However, they only consider the label coherence in neighborhood pixels or regions, which limits their ability to model long-range connections within the image and generally results in excessive smoothing of tumor boundaries. In this paper, we present a novel method for brain tumor segmentation in MR images based on fully-connected CRF (FC-CRF) model that establishes pairwise potentials on all pairs of pixels in the images. We employ a hierarchical approach to differentiate different structures of tumor and further formulate a FC-CRF model with learned data-driven prior knowledge of tumor core. The methods were evaluated on the testing and leaderboard set of Brain Tumor Image Segmentation Benchmark (BRATS) 2013 challenge. The precision of segmented tumor boundaries is improved significantly and the results are competitive compared to the start-of-the-arts.

Today also, radiologist analyze the MR images manually based on their experience and knowledge for segmenting the tumor. Use some graphical software to make the report about the presence of the tumor, its size, and other features. Based on this report doctors diagnose the patient, it is the main source for any doctor to start the treatment of the patient. However, as the MRI reports are based on the experience of the radiologist so it is a big challenge to maintain uniformity in the reports generated from the different MR imaging centers. Therefore, automation in this particular field is very much required for better precision and to maintain uniformity in the report. Therefore, doctor can diagnose the patient in much better way. Deep learning playing a vital role in automating the process of brain tumor and other organ segmentation using MR images. Many researchers developed various state-of-art methods to automate the process of brain tumor segmentation in MR images. There are multiple deep learning methods such as stacked auto- encoder, artificial neural network, convolutional neural network, and Unet used for the process of segmenting the medial images, where CNN is the most successful method for segmenting. In this chapter, the importance of automatic brain tumor segmentation approach. CNN and process of convolution, max pooling discussed in detail. Moreover, application of CNN for automatically segmenting brain tumor also discussed with some state-of-art methods.

Although the U-shaped architecture, represented by UNet, has become a major network model for brain tumor segmentation, the repeated convolution and sampling operations can easily lead to the loss of crucial information. Additionally, directly fusing features from different levels without distinction can easily result in feature misalignment, affecting segmentation accuracy. On the other hand, traditional convolutional blocks used for feature extraction cannot capture the abundant multi-scale information present in brain tumor images. This paper proposes a multi-scale feature-aligned segmentation model called GMAlignNet that fully utilizes Ghost convolution to solve these problems. Ghost hierarchical decoupled fusion unit and Ghost hierarchical decoupled unit are used instead of standard convolutions in the encoding and decoding paths. This transformation replaces the holistic learning of volume structures by traditional convolutional blocks with multi-level learning on a specific view, facilitating the acquisition of abundant multi-scale contextual information through low-cost operations. Furthermore, a feature alignment unit is proposed that can utilize semantic information flow to guide the recovery of upsampled features. It performs pixel-level semantic information correction on misaligned features due to feature fusion. The proposed method is also employed to optimize three classic networks, namely DMFNet, HDCNet, and 3D UNet, demonstrating its effectiveness in automatic brain tumor segmentation. The proposed network model was applied to the BraTS 2018 dataset, and the results indicate that the proposed GMAlignNet achieved Dice coefficients of 81.65%, 90.07%, and 85.16% for enhancing tumor, whole tumor, and tumor core segmentation, respectively. Moreover, with only 0.29 M parameters and 26.88G FLOPs, it demonstrates better potential in terms of computational efficiency and possesses the advantages of lightweight. Extensive experiments on the BraTS 2018, BraTS 2019, and BraTS 2020 datasets suggest that the proposed model exhibits better potential in handling edge details and contour recognition.

The brain tumor segmentation is essential for diagnosis and treatment of brain diseases. However, most of current 3D deep learning technologies require large number of magnetic resonance images (MRIs). In order to make full use of small dataset like BraTS 2020, we propose a deep supervision-based 2D residual U-net for efficient and automatic brain tumor segmentation. In our network, residual blocks are used to alleviate the gradient dispersion caused by excessive depth of network, while multiple deep supervision branches are used as the regularization of the network, they can improve the training stability and enable the encoder to extract richer visual features. The CBICA’s IPP’s evaluation of the segmentation results verifies the effectiveness of our method. The average Dice of ET, WT and TC are 0.7593, 0.8726 and 0.7879 respectively.KeywordsBrain tumor segmentationDeep supervisionU-netResidual block