journal article·2020-05-09Open access

Segmentation of Intracranial Hemorrhage Using Semi-Supervised Multi-Task Attention-Based U-Net

Justin L. Wang, Hassan Farooq, Hanqi Zhuang, Ali K. Ibrahim

Applied Sciences· Volume 10· Issue 9

Abstract

Intracranial Hemorrhage (ICH) has high rates of mortality, and risk factors associated with it are sometimes nearly impossible to avoid. Previous techniques to detect ICH using machine learning have shown some promise. However, due to a limited number of labeled medical images available, which often causes poor model accuracy in terms of the Dice coefficient, there is much to be improved. In this paper, we propose a modified u-net and curriculum learning strategy using a multi-task semi-supervised attention-based model, initially introduced by Chen et al., to segment ICH sub-groups from CT images. Using a modified inverse-sigmoid-based curriculum learning training strategy, we were able to stabilize Chen’s algorithm experimentally. This semi-supervised model produced higher Dice coefficient values in comparison to a supervised counterpart, regardless of the amount of labeled data used to train the model. Specifically, when training with 80% of the ground truth data, our semi-supervised model produced a Dice coefficient of 0.67, which was higher than 0.61, obtained by a comparable supervised model. This result also surpassed by a greater margin the one obtained by using the out-of-the-box u-net by Hssayeni et al.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Intracerebral and Subarachnoid Hemorrhage Research · Brain Tumor Detection and Classification · Medical Image Segmentation Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Computer Science, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USA

ECE Department, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USA

CEECS Department, Florida Atlantic University, Boca Raton, FL 33431, USA

References (47)

Show source-provided references
1. Caceres, A.J., and Goldstein, J.N. (2012). Intracranial Hemorrhage. Emerg. Med. Clin. N. Am.10.1016/j.emc.2012.06.003 ↗
2. Hssayeni, M.D., Croock, M.S., Al-Ani, A., Al-khafaji, H.F., Yahya, Z.A., and Ghoraani, B. (2019). Intracranial Hemorrhage Segmentation Using Deep Convolutional Model. arXiv.10.3390/data5010014 ↗
3. A Survey on Deep Learning in Medical Image Analysis10.1016/j.media.2017.07.005 ↗
4. Chilamkurthy, S., Ghosh, R., Tanamala, S., Biviji, M., Campeau, N.G., Venugopal, V.K., Mahajan, V., Rao, P., and Warier, P. (2018). Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans. arXiv.10.1016/S0140-6736(18)31645-3 ↗
5. Kervadec, H., Dolz, J., Granger, E., and Ayed, I.B. (2019). Curriculum semi-supervised segmentation. arXiv.10.1007/978-3-030-32245-8_63 ↗
6. Constrained-CNN losses forweakly supervised segmentation10.1016/j.media.2019.02.009 ↗
7. Gao, X., Hui, R., and Tian, Z. (2016). Classification of CT brain images based on deep learning networks. Comput. Methods Programs Biomed., 138.10.1016/j.cmpb.2016.10.007 ↗
8. Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network10.1109/TMI.2016.2535865 ↗
9. Hybrid 3D/2D Convolutional Neural Network for Hemorrhage Evaluation on Head CT10.3174/ajnr.A5742 ↗
10. Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network10.1007/s00330-019-06163-2 ↗
11. Bar, A., Mauda, M., Turner, Y., Safadi, M., and Elnekave, E. (2019). Improved ICH classification using task-dependent learning. arXiv.10.1109/ISBI.2019.8759176 ↗
12. Automatic Detection of the Existence of Subarachnoid Hemorrhage from Clinical CT Images10.1007/s10916-010-9587-8 ↗
13. An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets10.1038/s41551-018-0324-9 ↗
14. Segmenting Hemorrhagic and Ischemic Infarct Simultaneously From Follow-Up Non-Contrast CT Images in Patients with Acute Ischemic Stroke10.1109/ACCESS.2019.2906605 ↗
15. Segmentation and quantification of intra-ventricular/cerebral hemorrhage in CT scans by modified distance regularized level set evolution technique10.1007/s11548-012-0670-0 ↗
16. Kuo, W., Häne, C., Yuh, E.L., Mukherjee, P., and Malik, J. (2018). Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection. arXiv.10.1007/978-3-030-00931-1_82 ↗
17. Computer-Aided Assessment of Head Computed Tomography (CT) Studies in Patients with Suspected Traumatic Brain Injury10.1089/neu.2008.0590 ↗
18. Shahangian, B., and Pourghassem, H. (2015). Automatic brain hemorrhage segmentation and classification algorithm based on weighted grayscale histogram feature in a hierarchical classification structure. Biocybern. Biomed. Eng., 36.10.1016/j.bbe.2015.12.001 ↗
19. Expert-level detection of acute intracranial hemorrhage on head computed tomography using deep learning10.1073/pnas.1908021116 ↗
20. Kuo, W., Häne, C., Yuh, E.L., Mukherjee, P., and Malik, J. (2018). PatchFCN for Intracranial Hemorrhage Detection. arXiv.
21. Cho, J., Choi, I., Kim, J., Jeong, S., Lee, Y.S., Park, J., Kim, J., and Lee, M. (2019, January 12–15). Affinity Graph Based End-to-End Deep Convolutional Networks for CT Hemorrhage Segmentation. Proceedings of the 2019 International Conference on Neural Information Processing, Sydney, Australia.10.1007/978-3-030-36708-4_45 ↗
22. Sivanesan, U., Braga, L.H., Sonnadara, R.R., and Dhindsa, K. (2019). Unsupervised Medical Image Segmentation with Adversarial Networks: From Edge Diagrams to Segmentation Maps. arXiv.
23. Moriya, T., Roth, H.R., Nakamura, S., Oda, H., Nagara, K., Oda, M., and Mori, K. (2018). Unsupervised segmentation of 3D medical images based on clustering and deep representation learning. arXiv.10.1117/12.2293414 ↗
24. Auto-Association by Multilayer Perceptrons and Singular Value Decomposition10.1007/BF00332918 ↗
25. Montúfar, G. (2018). Restricted Boltzmann Machines: Introduction and Review. arXiv.10.1007/978-3-319-97798-0_4 ↗
26. Koo, J., and Klabjan, D. (2018). Improved Classification Based on Deep Belief Networks. arXiv.
27. Deep Boltzmann Machines
28. Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., and Weinberger, K.Q. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems 27, Curran Associates, Inc.
29. Raza, K., and Singh, N.K. (2018). A Tour of Unsupervised Deep Learning for Medical Image Analysis. arXiv.
30. Luc, P., Couprie, C., Chintala, S., and Verbeek, J. (2016). Semantic Segmentation using Adversarial Networks. arXiv.
31. Cheplygina, V., de Bruijne, M., and Pluim, J.P.W. (2018). Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis. arXiv.10.1016/j.media.2019.03.009 ↗
32. Feng, Z., Zhou, Q., Cheng, G., Tan, X., Shi, J., and Ma, L. (2020). Semi-Supervised Semantic Segmentation via Dynamic Self-Training and Class-Balanced Curriculum. arXiv.
33. Bortsova, G., Dubost, F., Hogeweg, L., Katramados, I., and de Bruijne, M. (2019). Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations. arXiv.10.1007/978-3-030-32226-7_90 ↗
34. Chen, S., Bortsova, G., Juarez, A.G., van Tulder, G., and de Bruijne, M. (2019). Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation. arXiv.10.1007/978-3-030-32248-9_51 ↗
35. (2019, December 06). RSNA Intracranial Hemorrhage Detection. Available online: https://www.kaggle.com/c/rsna-intracranial-hemorrhage-detection.
36. Liu, X., Zachariah, D., Wågberg, J., and Schön, T.B. (2018). Reliable Semi-Supervised Learning when Labels are Missing at Random. arXiv.
37. Tajbakhsh, N., Jeyaseelan, L., Li, Q., Chiang, J., Wu, Z., and Ding, X. (2019). Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation. arXiv.10.1016/j.media.2020.101693 ↗
38. Pereira, F., Burges, C.J.C., Bottou, L., and Weinberger, K.Q. (2012). Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images. Advances in Neural Information Processing Systems 25, Curran Associates, Inc.
39. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv.10.1007/978-3-319-24574-4_28 ↗
40. Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., and Ronneberger, O. (2016). 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. arXiv.10.1007/978-3-319-46723-8_49 ↗
41. Long, J., Shelhamer, E., and Darrell, T. (2014). Fully Convolutional Networks for Semantic Segmentation. arXiv.10.1109/CVPR.2015.7298965 ↗
42. Park, D.H., Hendricks, L.A., Akata, Z., Schiele, B., Darrell, T., and Rohrbach, M. (2016). Attentive Explanations: Justifying Decisions and Pointing to the Evidence. arXiv.
43. Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A.C., Salakhutdinov, R., Zemel, R.S., and Bengio, Y. (2015). Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. arXiv.
44. Luong, M., Pham, H., and Manning, C.D. (2015). Effective Approaches to Attention-based Neural Machine Translation. arXiv.10.18653/v1/D15-1166 ↗
45. Tran, P.V. (2019). Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning. arXiv.
46. Bengio, S., Vinyals, O., Jaitly, N., and Shazeer, N. (2015). Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks. arXiv.
47. Salehi, S.S.M., Erdogmus, D., and Gholipour, A. (2017). Tversky loss function for image segmentation using 3D fully convolutional deep networks. arXiv.10.1007/978-3-319-67389-9_44 ↗