A Multi-task Contextual Atrous Residual Network for Brain Tumor
Detection & Segmentation
- URL: http://arxiv.org/abs/2012.02073v1
- Date: Thu, 3 Dec 2020 17:04:16 GMT
- Title: A Multi-task Contextual Atrous Residual Network for Brain Tumor
Detection & Segmentation
- Authors: Ngan Le, Kashu Yamazaki, Dat Truong, Kha Gia Quach, Marios Savvides
- Abstract summary: deep neural networks have achieved state-of-the-art performance in a variety of recognition and segmentation tasks.
We investigate that segmenting a brain tumor is facing to the imbalanced data problem where the number of pixels belonging to the background class is much larger than the number of pixels belonging to the foreground class.
We propose a multi-task network which is formed as a cascaded structure.
- Score: 27.217492086838735
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In recent years, deep neural networks have achieved state-of-the-art
performance in a variety of recognition and segmentation tasks in medical
imaging including brain tumor segmentation. We investigate that segmenting a
brain tumor is facing to the imbalanced data problem where the number of pixels
belonging to the background class (non tumor pixel) is much larger than the
number of pixels belonging to the foreground class (tumor pixel). To address
this problem, we propose a multi-task network which is formed as a cascaded
structure. Our model consists of two targets, i.e., (i) effectively
differentiate the brain tumor regions and (ii) estimate the brain tumor mask.
The first objective is performed by our proposed contextual brain tumor
detection network, which plays a role of an attention gate and focuses on the
region around brain tumor only while ignoring the far neighbor background which
is less correlated to the tumor. The second objective is built upon a 3D atrous
residual network and under an encode-decode network in order to effectively
segment both large and small objects (brain tumor). Our 3D atrous residual
network is designed with a skip connection to enables the gradient from the
deep layers to be directly propagated to shallow layers, thus, features of
different depths are preserved and used for refining each other. In order to
incorporate larger contextual information from volume MRI data, our network
utilizes the 3D atrous convolution with various kernel sizes, which enlarges
the receptive field of filters. Our proposed network has been evaluated on
various datasets including BRATS2015, BRATS2017 and BRATS2018 datasets with
both validation set and testing set. Our performance has been benchmarked by
both region-based metrics and surface-based metrics. We also have conducted
comparisons against state-of-the-art approaches.
Related papers
- Multiclass MRI Brain Tumor Segmentation using 3D Attention-based U-Net [0.0]
This paper proposes a 3D attention-based U-Net architecture for multi-region segmentation of brain tumors.
The attention mechanism helps to improve segmentation accuracy by de-emphasizing healthy tissues and accentuating malignant tissues.
arXiv Detail & Related papers (2023-05-10T14:35:07Z) - View-Disentangled Transformer for Brain Lesion Detection [50.4918615815066]
We propose a novel view-disentangled transformer to enhance the extraction of MRI features for more accurate tumour detection.
First, the proposed transformer harvests long-range correlation among different positions in a 3D brain scan.
Second, the transformer models a stack of slice features as multiple 2D views and enhance these features view-by-view.
Third, we deploy the proposed transformer module in a transformer backbone, which can effectively detect the 2D regions surrounding brain lesions.
arXiv Detail & Related papers (2022-09-20T11:58:23Z) - Detection and Classification of Brain tumors Using Deep Convolutional
Neural Networks [0.0]
Tumour in the brain is fatal as it may be cancerous.
There are different sizes and locations of brain tumors which makes it difficult to understand their nature.
This paper is to differentiate between normal and abnormal pixels and also classify them with better accuracy.
arXiv Detail & Related papers (2022-08-28T18:24:22Z) - Two-Stream Graph Convolutional Network for Intra-oral Scanner Image
Segmentation [133.02190910009384]
We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes.
Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
arXiv Detail & Related papers (2022-04-19T10:41:09Z) - Cross-Modality Deep Feature Learning for Brain Tumor Segmentation [158.8192041981564]
This paper proposes a novel cross-modality deep feature learning framework to segment brain tumors from the multi-modality MRI data.
The core idea is to mine rich patterns across the multi-modality data to make up for the insufficient data scale.
Comprehensive experiments are conducted on the BraTS benchmarks, which show that the proposed cross-modality deep feature learning framework can effectively improve the brain tumor segmentation performance.
arXiv Detail & Related papers (2022-01-07T07:46:01Z) - Triplet Contrastive Learning for Brain Tumor Classification [99.07846518148494]
We present a novel approach of directly learning deep embeddings for brain tumor types, which can be used for downstream tasks such as classification.
We evaluate our method on an extensive brain tumor dataset which consists of 27 different tumor classes, out of which 13 are defined as rare.
arXiv Detail & Related papers (2021-08-08T11:26:34Z) - Cross-Modality Brain Tumor Segmentation via Bidirectional
Global-to-Local Unsupervised Domain Adaptation [61.01704175938995]
In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under a UDA scheme.
Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor.
The proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin.
arXiv Detail & Related papers (2021-05-17T10:11:45Z) - HI-Net: Hyperdense Inception 3D UNet for Brain Tumor Segmentation [17.756591105686]
This paper proposes hyperdense inception 3D UNet (HI-Net), which captures multi-scale information by stacking factorization of 3D weighted convolutional layers in the residual inception block.
Preliminary results on the BRATS 2020 testing set show that achieved by our proposed approach, the dice (DSC) scores of ET, WT, and TC are 0.79457, 0.87494, and 0.83712, respectively.
arXiv Detail & Related papers (2020-12-12T09:09:04Z) - Context Aware 3D UNet for Brain Tumor Segmentation [24.27997192961372]
UNet is the primary source in the performance of 3D CNN architectures for medical imaging tasks.
We propose a modified UNet architecture for brain tumor segmentation.
arXiv Detail & Related papers (2020-10-25T10:32:25Z) - Convolutional 3D to 2D Patch Conversion for Pixel-wise Glioma
Segmentation in MRI Scans [22.60715394470069]
We devise a novel pixel-wise segmentation framework through a convolutional 3D to 2D MR patch conversion model.
In our architecture, both local inter-slice and global intra-slice features are jointly exploited to predict class label of the central voxel in a given patch.
arXiv Detail & Related papers (2020-10-20T20:42:52Z) - Interpretation of 3D CNNs for Brain MRI Data Classification [56.895060189929055]
We extend the previous findings in gender differences from diffusion-tensor imaging on T1 brain MRI scans.
We provide the voxel-wise 3D CNN interpretation comparing the results of three interpretation methods.
arXiv Detail & Related papers (2020-06-20T17:56:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.