3D deeply supervised network for automated segmentation of volumetric medical images

By Qi-Yan Dou, Lequan Yu, Hao Chen, Yueming Jin, Xin Yang, Jing Qin, P. Heng. Medical Image Anal., 2017

567 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b31192d40ef06eafc80fef13698ef765bf8e0e68

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. P. Heng
2. Qi-Yan Dou
3. Lequan Yu
4. Hao Chen
5. Holger R. Roth
6. Sébastien Ourselin
7. Zhuowen Tu
8. Lei Xing

In Computer Vision and Pattern Recognition

1. P. Heng
2. Lequan Yu
3. Qi-Yan Dou
4. Hao Chen
5. Jing Qin
6. Holger R. Roth
7. Guotai Wang
8. Ling Shao

Citations in the corpus

• Weakly-supervised convolutional neural networks for multimodal image registration (2018, background): “The benefits of deeper supervision using denser connections have been shown in computer vision tasks (He et al., 2016; Huang et al., 2016; Lee et al., 2015; Szegedy et al., 2015) and medical image analysis (Dou et al., 2017; Garcia-Peraza-Herrera et al., 2017; Gibson et al., 2017a).”
• UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation (2019, background): “[27] demonstrated that deeply supervised layers can improve the learning ability of the hidden layer, enforcing the intermediate layers to learn discriminative features, enabling fast convergence and regularization of the network [26].”
• Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images (2019, background): “Thus, in current practice, segmentation is predominantly done manually, which is time-consuming and suffers from inter- or intra-operator variations [2].”
• Attentional ShapeContextNet for Point Cloud Recognition (2018, background): “Extending 2D-based convolution to 3D-based convolution for 3D computer vision applications such as 3D medical imaging [23, 10], though still effective, is arguably less explosive than the 2D cases.”
• An application of cascaded 3D fully convolutional networks for medical image segmentation (2018, methodology): “…Roth et al. (2016b); Zhou et al. (2016b); Christ et al. (2016); Zhou et al. (2016a), 2D convolutions on orthogonal (2.5D) cross-sections (Roth et al., 2015; Prasoon et al., 2013), and 3D convolutional layers (Milletari et al., 2016; Chen et al., 2016; Dou et al., 2017; Kamnitsas et al., 2017).”
• Medical Image Segmentation Using Deep Learning: A Survey (2020, background): “[103] proposed a 3D DSN for heart and liver segmentation, which incorporates a 3D deep monitoring mechanism into a 3D full convolutional network for volume-to-volume learning and inference, eliminating redundant computation and reducing the risk of over-fitting in the case of limited training data.”
• Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges (2019, methodology): “The auxiliary losses together with the original loss of the hidden layer are combined to strengthening the gradient [23, 86, 87].”
• Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning (2017, unknown): “For 3D volumes, patch-based CNNs have been proposed for segmentation of the brain tumor [7] and pancreas [14], and more powerful end-to-end 3D CNNs include V-Net [15], HighRes3DNet [8], and 3D deeply supervised network [16].”
• SV-RCNet: Workflow Recognition From Surgical Videos Using Recurrent Convolutional Network (2018, background): “Deep learning techniques, extracting the high-level features, have successfully addressed many tasks [42]–[44].”
• Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “Cardiac MRIs were segmented for heart’s left ventricle using DBN [145], and blood pool and myocardium using CNN [157].”
• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation (2018, methodology): “Furthermore, a 3D deeply supervised approach for automated segmentation of volumetric medical images was presented in [36].”
• Deep Learning and Medical Diagnosis: A Review of Literature (2018, unknown): “[18] CNN MRI Automated segmentation; liver, heart and great vessels segmentation; it was concluded that this approach has great potential for clinical applications.”
• 3D Deep Learning on Medical Images: A Review (2020, methodology): “[64] presented a fully connected 3D CNN for liver segmentation from 3D CT scans.”
• Recurrent residual U-Net for medical image segmentation (2019, unknown): “37.”