基于多实例学习及阈值伪标签提取的CT影像颅内出血分割

doi:10.3969/j.issn.0258-8021.2023.06.005

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (10456 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Intracranial hemorrhage is the bleeding caused by the rupture of intracranial blood vessels, and the volume of the hematoma is clinically important for treatment decision and prognosis analysis. The segmentation of the hematoma based on CT images is the basis of the volume measurement. Fully supervised methods rely on manually outlined labels, which are time-consuming and laborious, while existing weakly supervised segmentation methods have poor robustness and are prone to be affected by artifacts. To this end, this study proposed MIL-ICH, a multi-instance learning based weakly supervised network for intracranial hemorrhage segmentation. The network is composed of a two-branch structure. First, the multi-instance learning decoder generated heatmap to locate the hemorrhage area. Then, based on the heatmap, the pseudo-labels were extracted and optimized by CT value thresholding and pixel-adaptive refinement module to train the segmentation decoder. Finally, the two branches were trained simultaneously to improve training efficiency and leverage the multi-branch collaboration to further improve segmentation performance. The test results on 200 CT scans from the RSNA intracranial hemorrhage dataset showed that the Dice similarity coefficient and volume similarity of MIL-ICH reached 0.822 and 0.896, respectively. The correlation of the hematoma volume measured by this network with the actual hematoma volume is better than the ABC/2 estimation method commonly used in clinical practice. In conclusion, the method proposed in this work can improve the performance of weakly supervised segmentation of intracranial hemorrhage and benefit the volume measurement and prognostic evaluation for clinical purposes.

Key words： intracranial hemorrhage CT weakly supervised segmentation multi-instance learning thresholding

Received: 28 April 2023

PACS:

R318

Corresponding Authors: ^*E-mail: weiwei.zhang@ibms.pumc.edu.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Zhang Tongyu
	Li Enhui
	Li Zhenyu
	Cui Pengcheng
	Zhang Weiwei

Cite this article:

Zhang Tongyu,Li Enhui,Li Zhenyu, et al. Segmentation of Intracranial Hemorrhage in CT Images Based on Multi-Instance Learningand Thresholding Pseudo-Labels Extraction[J]. Chinese Journal of Biomedical Engineering, 2023, 42(6): 677-686.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2023.06.005 OR http://cjbme.csbme.org/EN/Y2023/V42/I6/677

[1] Caceres JA, Goldstein JN. Intracranial hemorrhage [J]. Emergency Medicine Clinics of North America, 2012, 30(3): 771-794.
[2] Kidwell CS, Wintermark M. Imaging of intracranial haemorrhage [J]. The Lancet Neurology, 2008, 7(3): 256-267.
[3] Zhu Ying, Wang Jialu, He Zhiyi, et al. Association of altered serum microRNAs with perihematomal edema after acute intracerebral hemorrhage [J]. PLoS ONE, 2015, 10(7): e0133783.
[4] Arab A, Chinda B, Medvedev G, et al. A fast and fully-automated deep-learning approach for accurate hemorrhage segmentation and volume quantification in non-contrast whole-head CT [J]. Scientific Reports, 2020, 10(1): 19389.
[5] Kobayashi S, Sato A, Kageyama Y, et al. Treatment of hypertensive cerebellar hemorrhage–surgical or conservative management? [J]. Neurosurgery, 1994, 34(2): 246-251.
[6] Ironside N, Chen CJ, Mutasa S, et al. Fully automated segmentation algorithm for hematoma volumetric analysis in spontaneous intracerebral hemorrhage [J]. Stroke, 2019, 50(12): 3416-3423.
[7] Chan Tao. Computer aided detection of small acute intracranial hemorrhage on computer tomography of brain [J]. Computerized Medical Imaging and Graphics, 2007, 31(4-5): 285-298.
[8] Loncaric S, Dhawan AP, Cosic D, et al. Quantitative intracerebral brain hemorrhage analysis [C]//Medical Imaging 1999: Image Processing. San Diego. SPIE, 1999, 3661: 886-894.
[9] Bardera A, Boada I, Feixas M, et al. Semi-automated method for brain hematoma and edema quantification using computed tomography [J]. Computerized Medical Imaging and Graphics, 2009, 33(4): 304-311.
[10] Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis [J]. Medical Image Analysis, 2017, 42: 60-88.
[11] 孙若凡,张唯唯. 基于3D U-Net实现人体耳软骨MRI图像的解剖结构分割 [J]. 中国生物医学工程学报, 2021, 40(5): 531-539.
[12] Patel A, Schreuder FHBM, Klijn CJM, et al. Intracerebral haemorrhage segmentation in non-contrast CT [J]. Scientific Reports, 2019, 9(1): 17858.
[13] Zhao Xianjing, Chen Kaixing, Wu Ge, et al. Deep learning shows good reliability for automatic segmentation and volume measurement of brain hemorrhage, intraventricular extension, and peripheral edema [J]. European Radiology, 2021, 31: 5012-5020.
[14] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation [C]// Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference. Munich: Springer Cham, 2015: Part III 234-241.
[15] Isensee F, Petersen J, Klein A, et al. nnu-net: Self-adapting framework for u-net-based medical image segmentation [DB/OL]. https://arxiv.org/abs/1809.10486, 2018-09-27/2023-04-28.
[16] Kyung S, Shin K, Jeong H, et al. Improved performance and robustness of multi-task representation learning with consistency loss between pretexts for intracranial hemorrhage identification in head CT [J]. Medical Image Analysis, 2022, 81: 102489.
[17] Liu Yang, Lian Lijin, Zhang Ersi, et al. Mixed-UNet: refined class activation mapping for weakly-supervised semantic segmentation with multi-scale inference [J]. Frontiers in Computer Science, 2022, 4: 1036934.
[18] Kolesnikov A, Lampert CH. Seed, expand and constrain: three principles for weakly-supervised image segmentation [C]// Computer Vision-ECCV 2016: 14th European Conference. Amsterdam: Springer International Publishing, 2016: Part IV 695-711.
[19] Jia Zhipeng, Huang Xingyi, Eric I, et al. Constrained deep weak supervision for histopathology image segmentation [J]. IEEE Transactions on Medical Imaging, 2017, 36(11): 2376-2388.
[20] Qian Ziniu, Li Kailu, Lai Maode, et al. Transformer based multiple instance learning for weakly supervised histopathology image segmentation [C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2022: 25th International Conference. Singapore: Springer Cham, 2022, Part II: 160-170.
[21] Tajbakhsh N, Jeyaseelan L, Li Qian, et al. Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation [J]. Medical Image Analysis, 2020, 63: 101693.
[22] Kuo Weicheng, Häne C, Mukherjee P, et al. Expert-level detection of acute intracranial hemorrhage on head computed tomography using deep learning [J]. Proceedings of the National Academy of Sciences, 2019, 116(45): 22737-22745.
[23] Flanders AE, Prevedello LM, ShihG, et al. Construction of a machine learning dataset through collaboration: the RSNA 2019 brain CT hemorrhage challenge [J]. Radiology: Artificial Intelligence, 2020, 2(3): e190211.
[24] Radenović F, Tolias G, Chum O. Fine-tuning CNN image retrieval with no human annotation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 41(7): 1655-1668.
[25] Ru Lixiang, Zhan Yibing, Yu Baosheng, et al. Learning affinity from attention: end-to-end weakly-supervised semantic segmentation with transformers [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 16846-16855.
[26] Woo S, Park J, Lee JY, et al. CBAM: Convolutional Block Attention Module [C]//Computer Vision-ECCV 2018: 15th European Conference. Munich: Springer International Publishing, 2018, Part VII:3-19.
[27] Zhou Bolei, Khosla A, Lapedriza A, et al. Learning deep features for discriminative localization [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 2921-2929.
[28] Selvaraju RR, Cogswell M, Das A, et al. Grad-CAM: visual Explanations from Deep Networks via Gradient-Based Localization [C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice: IEEE, 2017: 618-626.
[29] Pathak D, Shelhamer E, Long J, et al. Fully convolutional multi-class multiple instance learning [DB/OL]. https://arxiv.org/abs/1412.7144, 2015-04-15/2023-04-28.
[30] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [C]//Advances in Neural Information Processing Systems. Long Beach: NeurIPS, 2017: 30-30.