CompNet: Complementary Segmentation Network for Brain MRI Extraction

Dey, Raunak; Hong, Yi

doi:10.1007/978-3-030-00931-1_72

Cited by 44 publications

(36 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) CompSeg Block: Inspired by [43], we further propose a complementary segmentation (CompSeg) block that performs segmentation via two complementary pathways. As shown in Fig.…”

Section: Cross-task Guided Attentionmentioning

confidence: 99%

One-Pass Multi-Task Networks With Cross-Task Guided Attention for Brain Tumor Segmentation

Zhou

Ding

Wang

et al. 2020

IEEE Trans. on Image Process.

183

View full text Add to dashboard Cite

Class imbalance has been one of the major challenges for medical image segmentation. The model cascade (MC) strategy, as a popular scheme, significantly alleviates class imbalance issue via running a set of individual deep models for coarseto-fine segmentation. In spite of its outstanding performance, this method leads to an undesired system complexity and meanwhile ignores the relevance among the models. To handle these flaws of MC, we propose in this paper a light-weight deep model, i.e., the One-pass Multi-task Network (OM-Net) to solve class imbalance better than MC and require only one-pass computation for brain tumor segmentation. First, OM-Net integrates the separate segmentation tasks into one deep model, which consists of shared parameters to learn joint features and task-specific parameters to learn discriminative features. Second, to optimize OM-Net more effectively, we take advantage of the correlation among tasks to design an online training data transfer strategy and a curriculum learning-based training strategy. Third, we further propose to share prediction results between tasks, which enables us to design a cross-task guided attention (CGA) module. With the guidance of prediction results provided by the previous task, CGA can adaptively recalibrate channel-wise feature responses based on the category-specific statistics. Finally, a simple yet effective post-processing method is introduced to refine the segmentation results of the proposed attention network. Extensive experiments are performed to justify the effectiveness of the proposed techniques. Most impressively, we achieve state-of-theart performance on the BraTS 2015 testing set and BraTS 2017 online validation set. With the proposed approaches, we also won the joint third place in the BraTS 2018 challenge among 64 participating teams. We will make the code publicly available at https://github.com/chenhong-zhou/OM-Net.

show abstract

“…2) CompSeg Block: Inspired by [43], we further propose a complementary segmentation (CompSeg) block that performs segmentation via two complementary pathways. As shown in Fig.…”

Section: Cross-task Guided Attentionmentioning

confidence: 99%

One-Pass Multi-Task Networks With Cross-Task Guided Attention for Brain Tumor Segmentation

Zhou

Ding

Wang

et al. 2020

IEEE Trans. on Image Process.

183

View full text Add to dashboard Cite

show abstract

“…After successful application of CNNs on 2D biomedical images, efforts had been made on 3D biomedical volumetric data, specifically on the brain MRI [10,40]. Auto-Context CNN (Auto-Net) [41], Active Shape Model and CNN (ASM-CNN) [42], and complementary segmentation networks (CompNet) [43] are the most recently published works on brain segmentation. F. Milletari et al [40] presented CNN with Hough voting approach that enables fully automatic localization and segmentation of a region of interest for 3D segmentation of the deep brain region.…”

Section: Introductionmentioning

confidence: 99%

3D U-Net for Skull Stripping in Brain MRI

2019

View full text Add to dashboard Cite

Skull stripping in brain magnetic resonance imaging (MRI) is an essential step to analyze images of the brain. Although manual segmentation has the highest accuracy, it is a time-consuming task. Therefore, various automatic segmentation algorithms of the brain in MRI have been devised and proposed previously. However, there is still no method that solves the entire brain extraction problem satisfactorily for diverse datasets in a generic and robust way. To address these shortcomings of existing methods, we propose the use of a 3D-UNet for skull stripping in brain MRI. The 3D-UNet was recently proposed and has been widely used for volumetric segmentation in medical images due to its outstanding performance. It is an extended version of the previously proposed 2D-UNet, which is based on a deep learning network, specifically, the convolutional neural network. We evaluated 3D-UNet skull-stripping using a publicly available brain MRI dataset and compared the results with three existing methods (BSE, ROBEX, and Kleesiek’s method; BSE and ROBEX are two conventional methods, and Kleesiek’s method is based on deep learning). The 3D-UNet outperforms two typical methods and shows comparable results with the specific deep learning-based algorithm, exhibiting a mean Dice coefficient of 0.9903, a sensitivity of 0.9853, and a specificity of 0.9953.

show abstract

“…The skull and the brain look very similar in MRI images, so it is difficult to differentiate them. To solve this problem, Dey et al [118] created a CompNet network using creative ideas. The network employed encoder-decoder networks.…”

Section: D Skull-stripping Methodsmentioning

confidence: 99%

Conventional and Deep Learning Methods for Skull Stripping in Brain MRI

2020

View full text Add to dashboard Cite

Skull stripping in brain magnetic resonance volume has recently been attracting attention due to an increased demand to develop an efficient, accurate, and general algorithm for diverse datasets of the brain. Accurate skull stripping is a critical step for neuroimaging diagnostic systems because neither the inclusion of non-brain tissues nor removal of brain parts can be corrected in subsequent steps, which results in unfixed error through subsequent analysis. The objective of this review article is to give a comprehensive overview of skull stripping approaches, including recent deep learning-based approaches. In this paper, the current methods of skull stripping have been divided into two distinct groups—conventional or classical approaches, and convolutional neural networks or deep learning approaches. The potentials of several methods are emphasized because they can be applied to standard clinical imaging protocols. Finally, current trends and future developments are addressed giving special attention to recent deep learning algorithms.

show abstract

CompNet: Complementary Segmentation Network for Brain MRI Extraction

Cited by 44 publications

References 13 publications

One-Pass Multi-Task Networks With Cross-Task Guided Attention for Brain Tumor Segmentation

One-Pass Multi-Task Networks With Cross-Task Guided Attention for Brain Tumor Segmentation

3D U-Net for Skull Stripping in Brain MRI

Conventional and Deep Learning Methods for Skull Stripping in Brain MRI

Contact Info

Product

Resources

About