Attention-Guided Version of 2D UNet for Automatic Brain Tumor Segmentation

Noori, Mehrdad; Bahri, Ali; Mohammadi, Karim

doi:10.1109/iccke48569.2019.8964956

Cited by 75 publications

(35 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the attention mechanism has been well applied in the field of image segmentation [ 19 , 20 , 21 ]. Squeeze and Excitation Block has also been verified to be applicable to medical image segmentation [ 26 ]. Similarly, in our proposed ACAU, in order to improve the quality of the representation generated by the network, we use Squeeze and Excitation Block [ 16 ] in each upsampling block, adaptively weight the channel, use global information, and selectively emphasize Information features, suppress useless features.…”

Section: Methodsmentioning

confidence: 99%

Optic Disc Segmentation Using Attention-Based U-Net and the Improved Cross-Entropy Convolutional Neural Network

Jin

Wang

et al. 2020

Entropy

View full text Add to dashboard Cite

Medical image segmentation is an important part of medical image analysis. With the rapid development of convolutional neural networks in image processing, deep learning methods have achieved great success in the field of medical image processing. Deep learning is also used in the field of auxiliary diagnosis of glaucoma, and the effective segmentation of the optic disc area plays an important assistant role in the diagnosis of doctors in the clinical diagnosis of glaucoma. Previously, many U-Net-based optic disc segmentation methods have been proposed. However, the channel dependence of different levels of features is ignored. The performance of fundus image segmentation in small areas is not satisfactory. In this paper, we propose a new aggregation channel attention network to make full use of the influence of context information on semantic segmentation. Different from the existing attention mechanism, we exploit channel dependencies and integrate information of different scales into the attention mechanism. At the same time, we improved the basic classification framework based on cross entropy, combined the dice coefficient and cross entropy, and balanced the contribution of dice coefficients and cross entropy loss to the segmentation task, which enhanced the performance of the network in small area segmentation. The network retains more image features, restores the significant features more accurately, and further improves the segmentation performance of medical images. We apply it to the fundus optic disc segmentation task. We demonstrate the segmentation performance of the model on the Messidor dataset and the RIM-ONE dataset, and evaluate the proposed architecture. Experimental results show that our network architecture improves the prediction performance of the base architectures under different datasets while maintaining the computational efficiency. The results render that the proposed technologies improve the segmentation with 0.0469 overlapping error on Messidor.

show abstract

Section: Methodsmentioning

confidence: 99%

Optic Disc Segmentation Using Attention-Based U-Net and the Improved Cross-Entropy Convolutional Neural Network

Jin

Wang

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

“…Table V and Fig.8demonstrate the comparison results. With reasonably fewer parameters than Noori et al[49] and Shi et al…”

mentioning

confidence: 89%

OFF-eNET: An Optimally Fused Fully End-to-End Network for Automatic Dense Volumetric 3D Intracranial Blood Vessels Segmentation

Nazir

Cheema

Sheng

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Several researches [ 8 , 9 , 10 , 11 ] have demonstrated that 3D architectures perform better than 2D architectures. However, 3D architectures have limitations as they use more parameters and are computational complex [ 12 ]. Specifically, the dataset utilized for applying the 3D model is often reduced to half the size of the existing training data.…”

Section: Introductionmentioning

confidence: 99%

BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder Network

Rehman

Cho

Kim³

et al. 2021

Diagnostics

View full text Add to dashboard Cite

Efficient segmentation of Magnetic Resonance (MR) brain tumor images is of the utmost value for the diagnosis of tumor region. In recent years, advancement in the field of neural networks has been used to refine the segmentation performance of brain tumor sub-regions. The brain tumor segmentation has proven to be a complicated task even for neural networks, due to the small-scale tumor regions. These small-scale tumor regions are unable to be identified, the reason being their tiny size and the huge difference between area occupancy by different tumor classes. In previous state-of-the-art neural network models, the biggest problem was that the location information along with spatial details gets lost in deeper layers. To address these problems, we have proposed an encoder–decoder based model named BrainSeg-Net. The Feature Enhancer (FE) block is incorporated into the BrainSeg-Net architecture which extracts the middle-level features from low-level features from the shallow layers and shares them with the dense layers. This feature aggregation helps to achieve better performance of tumor identification. To address the problem associated with imbalance class, we have used a custom-designed loss function. For evaluation of BrainSeg-Net architecture, three benchmark datasets are utilized: BraTS2017, BraTS 2018, and BraTS 2019. Segmentation of Enhancing Core (EC), Whole Tumor (WT), and Tumor Core (TC) is carried out. The proposed architecture have exhibited good improvement when compared with existing baseline and state-of-the-art techniques. The MR brain tumor segmentation by BrainSeg-Net uses enhanced location and spatial features, which performs better than the existing plethora of brain MR image segmentation approaches.

show abstract

Attention-Guided Version of 2D UNet for Automatic Brain Tumor Segmentation

Cited by 75 publications

References 33 publications

Optic Disc Segmentation Using Attention-Based U-Net and the Improved Cross-Entropy Convolutional Neural Network

Optic Disc Segmentation Using Attention-Based U-Net and the Improved Cross-Entropy Convolutional Neural Network

OFF-eNET: An Optimally Fused Fully End-to-End Network for Automatic Dense Volumetric 3D Intracranial Blood Vessels Segmentation

BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder Network

Contact Info

Product

Resources

About