A meta-learning based method for segmentation of few-shot magnetic resonance images_Journal of Biomedical Engineering

Authors：

 CHEN Xiaoqing , FU Zhongliang , YAO Yu

Chengdu Institute of Computer Application, University of Chinese Academy of Sciences, Chengdu 610000, P. R. China;

Corresponding author：

CHEN Xiaoqing, Email: chenxiaoqing@casit.com.cn

Keywords：

Few-shot; Magnetic resonance images; Image segmentation; Meta-learning

DOI：

10.7507/1001-5515.202208004

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

When applying deep learning algorithms to magnetic resonance (MR) image segmentation, a large number of annotated images are required as data support. However, the specificity of MR images makes it difficult and costly to acquire large amounts of annotated image data. To reduce the dependence of MR image segmentation on a large amount of annotated data, this paper proposes a meta-learning U-shaped network (Meta-UNet) for few-shot MR image segmentation. Meta-UNet can use a small amount of annotated image data to complete the task of MR image segmentation and obtain good segmentation results. Meta-UNet improves U-Net by introducing dilated convolution, which can increase the receptive field of the model to improve the sensitivity to targets of different scales. We introduce the attention mechanism to improve the adaptability of the model to different scales. We introduce the meta-learning mechanism, and employ a composite loss function for well-supervised and effective bootstrapping of model training. We use the proposed Meta-UNet model to train on different segmentation tasks, and then use the trained model to evaluate on a new segmentation task, where the Meta-UNet model achieves high-precision segmentation of target images. Meta-UNet has a certain improvement in mean Dice similarity coefficient (DSC) compared with voxel morph network (VoxelMorph), data augmentation using learned transformations (DataAug) and label transfer network (LT-Net). Experiments show that the proposed method can effectively perform MR image segmentation using a small number of samples. It provides a reliable aid for clinical diagnosis and treatment.

Citation： CHEN Xiaoqing, FU Zhongliang, YAO Yu. A meta-learning based method for segmentation of few-shot magnetic resonance images. Journal of Biomedical Engineering, 2023, 40(2): 193-201. doi: 10.7507/1001-5515.202208004 Copy

1.	Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation// Medical Image Computing and Computer-Assisted Intervention(MICCAI), Charm: Springer, 2015: 234-241.
2.	Zeng G, Yang X, Li J, et al. 3D U-net with multi-level deep supervision: fully automatic segmentation of proximal femur in 3D MR images// Machine Learning in Medical Imaging, Cham: Springer, 2017: 274-282.
3.	Milletari F, Navab N, Ahmadi S. V-Net: fully convolutional neural networks for volumetric medical image segmentation// International Conference on 3D Vision (3DV), Stanford: IEEE, 2016: 565-571.
4.	Bouget D, Pedersen A, Hosainey S A M, et al. Fast meningioma segmentation in T1-weighted magnetic resonance imaging volumes using a lightweight 3D deep learning architecture. J Med Imaging (Bellingham), 2021, 8(2): 024002.
5.	Ren J, Sun H, Zhao H, et al. Effective extraction of ventricles and myocardium objects from cardiac magnetic resonance images with a multi-task learning U-net. Pattern Recognit Lett, 2022, 155: 165-170.
6.	Abulnaga S M, Rubin J. Ischemic stroke lesion segmentation in CT perfusion scans using pyramid pooling and focal loss// Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Cham: Springer, 2019: 352-363.
7.	Li F F, Fergus R, Perona P. A bayesian approach to unsupervised one-shot learning of object categories// Proceedings Ninth IEEE International Conference on Computer Vision, 2003, 2003(2): 1134-1141.
8.	Hospedales T, Antoniou A, Micaelli P, et al. Meta-learning in neural networks: a survey. IEEE Trans Pattern Anal Mach Intell, 2022, 44(9): 5149-5169.
9.	Zhao A, Balakrishnan G, Durand F, et al. Data augmentation using learned transformations for one-shot medical image segmentation// Computer Vision and Pattern Recognition (CVPR), Long Beach: IEEE, 2019: 8543-8553.
10.	Chartsias A, Papanastasiou G, Wang C, et al. Disentangle, align and fuse for multimodal and semi-supervised image segmentation. IEEE Trans Med Imaging, 2021, 40(3): 781-792.
11.	Guo J, Odu A, Pedrosa I. Deep learning kidney segmentation with very limited training data using a cascaded convolution neural network. PLoS One, 2022, 17(5): e0267753.
12.	Wang S, Cao S, Wei D, et al. Lt-net: label transfer by learning reversible voxel-wise correspondence for one-shot medical image segmentation// Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2020: 9159-9168.
13.	Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks// International Conference on Machine Learning, Sydney: PMLR, 2017: 1126-1135.
14.	Wang P, Chen P, Yuan Y, et al. Understanding convolution for semantic segmentation// IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe: IEEE, 2018: 1451-1460.
15.	Xu K, Ba J, Kiros R, et al. Show, attend and tell: neural image caption generation with visual attention// International Conference on Machine Learning, Lille: PMLR, 2015: 2048-2057.
16.	Kennedy D N, Haselgrove C, Hodge S M, et al. CANDIShare: a resource for pediatric neuroimaging data. Neuroinformatics, 2012, 10(3): 319-322.
17.	Balakrishnan G, Zhao A, Sabuncu M R, et al. Voxelmorph: a learning framework for deformable medical image registration. IEEE Trans Med Imaging, 2019, 38(8): 1788-1800.

1. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation// Medical Image Computing and Computer-Assisted Intervention(MICCAI), Charm: Springer, 2015: 234-241.
2. Zeng G, Yang X, Li J, et al. 3D U-net with multi-level deep supervision: fully automatic segmentation of proximal femur in 3D MR images// Machine Learning in Medical Imaging, Cham: Springer, 2017: 274-282.
3. Milletari F, Navab N, Ahmadi S. V-Net: fully convolutional neural networks for volumetric medical image segmentation// International Conference on 3D Vision (3DV), Stanford: IEEE, 2016: 565-571.
4. Bouget D, Pedersen A, Hosainey S A M, et al. Fast meningioma segmentation in T1-weighted magnetic resonance imaging volumes using a lightweight 3D deep learning architecture. J Med Imaging (Bellingham), 2021, 8(2): 024002.
5. Ren J, Sun H, Zhao H, et al. Effective extraction of ventricles and myocardium objects from cardiac magnetic resonance images with a multi-task learning U-net. Pattern Recognit Lett, 2022, 155: 165-170.
6. Abulnaga S M, Rubin J. Ischemic stroke lesion segmentation in CT perfusion scans using pyramid pooling and focal loss// Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Cham: Springer, 2019: 352-363.
7. Li F F, Fergus R, Perona P. A bayesian approach to unsupervised one-shot learning of object categories// Proceedings Ninth IEEE International Conference on Computer Vision, 2003, 2003(2): 1134-1141.
8. Hospedales T, Antoniou A, Micaelli P, et al. Meta-learning in neural networks: a survey. IEEE Trans Pattern Anal Mach Intell, 2022, 44(9): 5149-5169.
9. Zhao A, Balakrishnan G, Durand F, et al. Data augmentation using learned transformations for one-shot medical image segmentation// Computer Vision and Pattern Recognition (CVPR), Long Beach: IEEE, 2019: 8543-8553.
10. Chartsias A, Papanastasiou G, Wang C, et al. Disentangle, align and fuse for multimodal and semi-supervised image segmentation. IEEE Trans Med Imaging, 2021, 40(3): 781-792.
11. Guo J, Odu A, Pedrosa I. Deep learning kidney segmentation with very limited training data using a cascaded convolution neural network. PLoS One, 2022, 17(5): e0267753.
12. Wang S, Cao S, Wei D, et al. Lt-net: label transfer by learning reversible voxel-wise correspondence for one-shot medical image segmentation// Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2020: 9159-9168.
13. Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks// International Conference on Machine Learning, Sydney: PMLR, 2017: 1126-1135.
14. Wang P, Chen P, Yuan Y, et al. Understanding convolution for semantic segmentation// IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe: IEEE, 2018: 1451-1460.
15. Xu K, Ba J, Kiros R, et al. Show, attend and tell: neural image caption generation with visual attention// International Conference on Machine Learning, Lille: PMLR, 2015: 2048-2057.
16. Kennedy D N, Haselgrove C, Hodge S M, et al. CANDIShare: a resource for pediatric neuroimaging data. Neuroinformatics, 2012, 10(3): 319-322.
17. Balakrishnan G, Zhao A, Sabuncu M R, et al. Voxelmorph: a learning framework for deformable medical image registration. IEEE Trans Med Imaging, 2019, 38(8): 1788-1800.

Next Article
Multiresolution discrete optimization registration method of ultrasound and magnetic resonance images based on key points

Journal of Biomedical Engineering

A meta-learning based method for segmentation of few-shot magnetic resonance images

Abstract Full text Figures/Tables Video References Cited by

Next Article

Format

Content