Deep Convolutional Neural Networks Using U-Net for Automatic Brain Tumor Segmentation in Multimodal MRI Volumes

Kermi, Adel; Mahmoudi, Issam; Khadir, Mohamed Tarek

doi:10.1007/978-3-030-11726-9_4

Cited by 95 publications

(53 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [53], the authors optimize the network structure by building two almost identical pathways to predict voxels of the final feature map. Compared with Chen et al [52] and Kermi et al [48] methods, our AGResU-Net model acquires a better segmentation performance. For models of Pereira et al and Zhao et al, they apply 2D CNN models with 33 × 33 patches as inputs to predict center voxel [12], [54].…”

Section: ) Experiments On Brats 2017 Training Datasetmentioning

confidence: 80%

“…Generalized Dice Loss (GDL) [47] is a commonly used loss function which helps narrow the gap between training samples and evaluation metric, and it is also immune to the data imbalance problem. Additionally, the weighted cross entropy (WCE) [48] has proved to be effective for multi-task training and class imbalance problem. Therefore, to provide better supervision for the model training, we utilize the combination of generalized dice loss L GDL and weighted cross entropy loss L WCE as a union loss function L as follows:…”

Section: Combined Loss Functionmentioning

confidence: 99%

See 1 more Smart Citation

Attention Gate ResU-Net for Automatic MRI Brain Tumor Segmentation

et al. 2020

View full text Add to dashboard Cite

Brain tumor segmentation technology plays a pivotal role in the process of diagnosis and treatment of MRI brain tumors. It helps doctors to locate and measure tumors, as well as develop treatment and rehabilitation strategies. Recently, MRI brain tumor segmentation methods based on U-Net architecture have become popular as they largely improve the segmentation accuracy by applying skip connection to combine high-level feature information and low-level feature information. Meanwhile, researchers have demonstrated that introducing attention mechanism into U-Net can enhance local feature expression and improve the performance of medical image segmentation. In this work, we aim to explore the effectiveness of a recent attention module called attention gate for brain tumor segmentation task, and a novel Attention Gate Residual U-Net model, i.e., AGResU-Net, is further presented. AGResU-Net integrates residual modules and attention gates with a primeval and single U-Net architecture, in which a series of attention gate units are added into the skip connection for highlighting salient feature information while disambiguating irrelevant and noisy feature responses. AGResU-Net not only extracts abundant semantic information to enhance the ability of feature learning, but also pays attention to the information of small-scale brain tumors. We extensively evaluate attention gate units on three authoritative MRI brain tumor benchmarks, i.e., BraTS 2017, BraTS 2018 and BraTS 2019. Experimental results illuminate that models with attention gate units, i.e., Attention Gate U-Net (AGU-Net) and AGResU-Net, outperform their baselines of U-Net and ResU-Net, respectively. In addition, AGResU-Net achieves competitive performance than the representative brain tumor segmentation methods.

show abstract

Section: ) Experiments On Brats 2017 Training Datasetmentioning

confidence: 80%

Section: Combined Loss Functionmentioning

confidence: 99%

Attention Gate ResU-Net for Automatic MRI Brain Tumor Segmentation

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Authors in [146] proposed multi-scale mask 3D U-nets with atrous spatial pyramid pooling layers, where WT segmentation generated by first networks was passed to the second for TC generation, which in sequence passed to the final network to generate ET output. Other ensemble based CNN approaches were explained in [87], [73], [60], [143], [7], [31], [25], [147].…”

Section: Cnn Methods Classification For Tumor Segmentationmentioning

confidence: 99%

A Survey and Analysis on Automated Glioma Brain Tumor Segmentation and Overall Patient Survival Prediction

Agravat¹,

Raval²

2021

Preprint

View full text Add to dashboard Cite

<div>Glioma is the most deadly brain tumor with high mortality. Treatment planning by human experts depends on the proper diagnosis of physical symptoms along with Magnetic Resonance(MR) image analysis. Highly variability of a brain tumor in terms of size, shape, location, and a high volume of MR images makes the analysis time-consuming. Automatic segmentation methods achieve a reduction in time with excellent reproducible results.</div><div>The article aims to survey the advancement of automated methods for Glioma brain tumor segmentation. It is also essential to make an objective evaluation of various models based on the benchmark. Therefore, the 2012 - 2019 BraTS challenges database evaluates state-of-the-art methods. The complexity of tasks under the challenge has grown from segmentation (Task1) to overall survival prediction (Task 2) to uncertainty prediction for classification (Task 3). The paper covers the complete gamut of brain tumor segmentation using handcrafted features to deep neural network models for Task 1. The aim is to showcase a complete change of trends in automated brain tumor models. The paper also covers end to end joint models involving brain tumor segmentation and overall survival prediction. All the methods are probed, and parameters that affect performance are tabulated and analyzed.</div>

show abstract

“…2D convolutional neural network inspired by U-Net is modified using Generalized Dice Loss (GDL) and Weighted Cross-Entropy (WCE) as a loss function is used to address the class imbalance problems the tumor data. The proposed method was tested on BraTS 2018 dataset and had achieved a good dice score for Whole, Core and Enhancing tumor [114].…”

Section: Approaches Toward Automatic Segmentationmentioning

confidence: 99%

Brain Tumor Analysis Empowered with Deep Learning: A Review, Taxonomy, and Future Challenges

et al. 2020

View full text Add to dashboard Cite

Deep Learning (DL) algorithms enabled computational models consist of multiple processing layers that represent data with multiple levels of abstraction. In recent years, usage of deep learning is rapidly proliferating in almost every domain, especially in medical image processing, medical image analysis, and bioinformatics. Consequently, deep learning has dramatically changed and improved the means of recognition, prediction, and diagnosis effectively in numerous areas of healthcare such as pathology, brain tumor, lung cancer, abdomen, cardiac, and retina. Considering the wide range of applications of deep learning, the objective of this article is to review major deep learning concepts pertinent to brain tumor analysis (e.g., segmentation, classification, prediction, evaluation.). A review conducted by summarizing a large number of scientific contributions to the field (i.e., deep learning in brain tumor analysis) is presented in this study. A coherent taxonomy of research landscape from the literature has also been mapped, and the major aspects of this emerging field have been discussed and analyzed. A critical discussion section to show the limitations of deep learning techniques has been included at the end to elaborate open research challenges and directions for future work in this emergent area.

show abstract

Deep Convolutional Neural Networks Using U-Net for Automatic Brain Tumor Segmentation in Multimodal MRI Volumes

Cited by 95 publications

References 17 publications

Attention Gate ResU-Net for Automatic MRI Brain Tumor Segmentation

Attention Gate ResU-Net for Automatic MRI Brain Tumor Segmentation

A Survey and Analysis on Automated Glioma Brain Tumor Segmentation and Overall Patient Survival Prediction

Brain Tumor Analysis Empowered with Deep Learning: A Review, Taxonomy, and Future Challenges

Contact Info

Product

Resources

About