Abstract
Despite the great success, deep learning based segmentation methods still face a critical obstacle: the difficulty in acquiring sufficient training data due to high annotation costs. In this paper, we propose a deep active learning framework that combines the attention gated fully convolutional network (ag-FCN) and the distribution discrepancy based active learning algorithm (dd-AL) to significantly reduce the annotation effort by iteratively annotating the most informative samples to train the ag-FCN for the better segmentation performance. Our framework is evaluated on 2015 MICCAI Gland Segmentaion dataset and 2017 MICCAI 6-month infant brain MRI Segmentation dataset. Experiment results show that our framework can achieve state-of-the-art segmentation performance by using only a portion of the training data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this paper, the labeled set and unlabeled set refer to the labeled and unlabeled portions of a training dataset, respectively.
- 2.
The encoding part of each ag-FCN can be utilized as a feature extractor. Given an input image to K ag-FCNs, the average of outputs of Layer 6 in these ag-FCNs can be viewed as a high-dimensional feature representation of the input image.
- 3.
We replace all 2D operations with 3D operations (e.g., 2D conv \(\rightarrow \) 3D conv, etc.).
References
Kamnitsas, K., Ledig, C., et al.: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med. Image Anal. 36, 61–78 (2017)
Liao, F., Liang, M., et al.: Evaluate the malignancy of pulmonary nodules using the 3-D deep leaky noisy-or network. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3484–3495 (2019)
Long, J., Shelhamer, E., et al.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
He, K., Gkioxari, G., et al.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
Papandreou, G., Chen, L.C., et al.: Weakly-and semi-supervised learning of a DCNN for semantic image segmentation. arXiv, arXiv preprint arXiv:1502.02734 (2015)
Xiao, H., Wei, Y., et al.: Transferable semi-supervised semantic segmentation. In: AAAI Conference on Artificial Intelligence (2018)
Hong, S., Noh, H., et al.: Decoupled deep neural network for semi-supervised semantic segmentation. In: Advances in Neural Information Processing Systems, pp. 1495–1503 (2015)
Settles, B.: Active learning literature survey. University of Wisconsin-Madison Department of Computer Sciences (2009)
Dutt Jain, S., Grauman, K.: Active image segmentation propagation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2864–2873 (2016)
Yang, L., Zhang, Y., et al.: Suggestive annotation: a deep active learning framework for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 399–407 (2017)
Wang, X., Girshick, R., et al.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794–7803 (2018)
Sirinukunwattana, K., Pluim, J.P., et al.: Gland segmentation in colon histology images: the glas challenge contest. Med. Image Anal. 35, 489–502 (2017)
Wang, L., Nie, D., et al.: Benchmark on automatic six-month-old infant brain segmentation algorithms: the iSeg-2017 challenge. IEEE Trans. Med. Imaging 38(9), 2219–2230 (2019)
Graham, S., Chen, H., et al.: MILD-Net: minimal information loss dilated network for gland instance segmentation in colon histology images. Med. Image Anal. 52, 199–211 (2019)
Graham, S., Chen, H., et al.: DCAN: deep contour-aware networks for accurate gland segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2487–2496 (2016)
Ding, H., Pan, Z., et al.: Multi-scale fully convolutional network for gland segmentation using three-class classification. Neurocomputing 380, 150–161 (2020)
TESLA V100 Performance Guide. https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/tesla-product-literature/v100-application-performance-guide.pdf
Çiçek, Ö., Abdulkadir, A., et al.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 424–432 (2016)
Chen, H., Dou, Q., et al.: VoxResNet: deep voxelwise residual networks for brain segmentation from 3D MR images. NeuroImage 170, 446–455 (2018)
Bui, T.D., Shin, J., et al.: Skip-connected 3D DenseNet for volumetric infant brain MRI segmentation. Biomed. Signal Process. Control 54, 101613 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, H., Yin, Z. (2020). Attention, Suggestion and Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12261. Springer, Cham. https://doi.org/10.1007/978-3-030-59710-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-59710-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59709-2
Online ISBN: 978-3-030-59710-8
eBook Packages: Computer ScienceComputer Science (R0)
