Computer Science ›› 2022, Vol. 49 ›› Issue (4): 203-208.doi: 10.11896/jsjkx.201000153

• Computer Graphics & Multimedia • Previous Articles     Next Articles

Intracerebral Hemorrhage Image Segmentation and Classification Based on Multi-taskLearning of Shared Shallow Parameters

ZHAO Kai, AN Wei-chao, ZHANG Xiao-yu, WANG Bin, ZHANG Shan, XIANG Jie   

  1. College of Information and Computer, Taiyuan University of Technology, Taiyuan 030600, China
  • Received:2020-10-27 Revised:2021-03-16 Published:2022-04-01
  • About author:ZHAO Kai,born in 1994,postgraduate.His main research interests include deep learning and medical imaging ana-lysis.XIANG Jie,born in 1970,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.Her main research interests include medical imaging analysis and neuroimaging.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China(61503272,61873178,61876124) and Natural Science Foundation of Shanxi Province,China(201801D121135).

Abstract: Non-enhanced CT scanning is the first choice for the diagnosis of suspected cerebral hemorrhage in the emergency room.Medical staffs usually use CT images to manually segment the lesions of patients with suspected acute cerebral hemorrhage, and then classify them based on clinical experience.This method of manual diagnosis requires the physician's experience and is highly subjective.Moreover, the segmentation and classification tasks are performed separately, and the characteristic information associated between the two tasks cannot be fully utilized, and the time cost is high, which increases the difficulty of quickly segmenting and classifying cerebral hemorrhage lesions based on CT images.In response to the above problems, the paper proposes a model for segmentation and classification of cerebral hemorrhage images based on multi-task learning.On the one hand, the weight of the loss function is optimized according to the difficulty of learning different tasks.On the other hand, public information sharing is realized in the shallow layer of the multi-task learning network, and private information of different tasks is extracted deeply to obtain more representative features, so as to quickly and accurately segment and classify the CT images of patients with cerebral hemorrhage.The experimental results show that the segmentation annotations generated by the multi-task learning network have good visual consistency with the real annotations.Under the optimal weight, the average Dice coefficient (DSC) of all subjects is 0.828, the sensitivity is 0.842, the specificity is 0.985, and the positive predictive value (PPV) is 0.838.The accuracy, sensitivity, specificity and AUC value of multi-task learning network classification are 95.00%, 90.48%, 100.00% and 0.982, respectively.Compared with single-task deep learning, Y-Net and multi task learning assisted by classification, this method makes more effective use of relevant task information, and at the same time improves the segmentation and classification accuracy of hemorrhage lesions by adjusting the weight of the loss function.

Key words: 3DU-Net, Cerebral hematoma, Convolutional neural network, CT, Multi-task learning

CLC Number: 

  • TP391
[1] BALAMI J S,BUCHAN A M.Complications of intracerebralhaemorrhage[J].Lancet Neurology,2012,11(1):101-118.
[2] ROH D,SUN C,SCHMIDT J M,et al.Primary intracerebral hemorrhage:a closer look at hypertension and cerebral amyloid angiopathy[J].Neurocritical Care,2018,29(1):77-83.
[3] FUKUDA K,MAJUMDAR M,MASOUD H,et al.Multicenter assessment of morbidity associated with cerebral arteriovenous malformation hemorrhages[J].Journal of NeuroInterventional Surgery,2017,9(7):664-668.
[4] WANG Z F,YIN M L,LIU S,et al.Microsurgical treatment of cerebral arteriovenous malformation in children[J].Journal of Clinical Neurosurgery,2020,17(2):171-175,181.
[5] DING Z J,ZHANG X.The role of CT angiography in preoperative diagnosis and surgical evaluation of cerebral arteriovenous malformations and intracerebral hematoma[J].Chinese Clinical Doctor,2020,48(5):582-585.
[6] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(4):640-651.
[7] RONNEBERGER O,FISCHER P,BROX T,et al.U-Net:con-volutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention.2015:234-241.
[8] DHAR R,FALCONE G J,CHEN Y,et al.Deep learning forautomated measurement of hemorrhage and perihematomal edema in supratentorial intracerebral hemorrhage[J].Stroke,2020,51(2):648-651.
[9] IRONSIDE N,CHEN C,MUTASA S,et al.Fully automatedsegmentation algorithm for perihematomal edema volumetry after spontaneous intracerebral hemorrhage[J].Stroke,2020,51(3):815-823.
[10] YE Z Y,WU M L.Choroidal Neovascularization Segmentation Combining Temporal Supervision and Attention Mechanism[J].Computer Science,2021,48(8):118-124.
[11] WANG T,LEI Y,TIAN S,et al.Learning-based automatic segmentation of arteriovenous malformations on contrast CT images in brain stereotactic radiosurgery[J].Medical Physics,2019,46(7):3133-3141.
[12] CICEK O,ABDULKADIR A,LIENKAMP S S,et al.3DU-Net:learning dense volumetric segmentation from sparse annotation[J].arXiv:Computer Vision and Pattern Recognition,2016.
[13] HAMIDIAN S,SAHINER B,PETRICK N,et al.3D convolu-tional neural network for automatic detection of lung nodules in chest CT[J].Proceedings of SPIE,2017,10134:1013409.
[14] GAO X W,HUI R,TIAN Z,et al.Classification of CT brainimages based on deep learning networks[J].Computer Methods and Programs in Biomedicine,2017,138:49-56.
[15] SILVA G L,VALENTE T L,SILVA A C,et al.Convolutional neural network-based PSO for lung nodule false positive reduction on CT images[J].Computer Methods and Programs in Bio-medicine,2018:109-118.
[16] HE T,HU J,SONG Y,et al.Multi-task learning for the segmentation of organs at risk with label dependence[J].Medical Image Analysis,2020.
[17] MEHTA S,MERCAN E,BARTLETT J,et al.Y-Net:joint seg-mentation and classification for diagnosis of breast biopsy images[J].arXiv:1806.01313.
[18] ZHANG Y,ZHANG B,LIANG F,et al.Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types[J].European Radiology,2018,29(4):2157-2165.
[19] NAJM M,KUANG H,FEDERICO A,et al.Automated brain extraction from head CT and CTA images using convex optimization with shape propagation[J].Computer Methods and Programs in Biomedicine,2019,176:1-8.
[20] QIU W,YUAN J,UKWATTA E,et al.Prostate segmentation:an efficient convex optimization approach with axial symmetry using 3-D TRUS and MR images[J].IEEE Transactions on Medical Imaging,2014,33(4):947-960.
[21] HE K,ZHANG X,REN S,et al.Delving deep into rectifiers:surpassing human-level performance on ImageNet classification[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV).2015:1206-1034.
[22] LIU M,LI F,YAN H,et al.A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer’s disease[J].NeuroImage,2019,208:116459.
[1] LU Chen-yang, DENG Su, MA Wu-bin, WU Ya-hui, ZHOU Hao-hao. Federated Learning Based on Stratified Sampling Optimization for Heterogeneous Clients [J]. Computer Science, 2022, 49(9): 183-193.
[2] HU Yu-jiao, JIA Qing-min, SUN Qing-shuang, XIE Ren-chao, HUANG Tao. Functional Architecture to Intelligent Computing Power Network [J]. Computer Science, 2022, 49(9): 249-259.
[3] LIU Xin, WANG Jun, SONG Qiao-feng, LIU Jia-hao. Collaborative Multicast Proactive Caching Scheme Based on AAE [J]. Computer Science, 2022, 49(9): 260-267.
[4] FU Yan-ming, ZHU Jie-fu, JIANG Kan, HUANG Bao-hua, MENG Qing-wen, ZHOU Xing. Incentive Mechanism Based on Multi-constrained Worker Selection in Mobile Crowdsourcing [J]. Computer Science, 2022, 49(9): 275-282.
[5] LIU Jie-ling, LING Xiao-bo, ZHANG Lei, WANG Bo, WANG Zhi-liang, LI Zi-mu, ZHANG Hui, YANG Jia-hai, WU Cheng-nan. Network Security Risk Assessment Framework Based on Tactical Correlation [J]. Computer Science, 2022, 49(9): 306-311.
[6] WANG Zi-kai, ZHU Jian, ZHANG Bo-jun, HU Kai. Research and Implementation of Parallel Method in Blockchain and Smart Contract [J]. Computer Science, 2022, 49(9): 312-317.
[7] HU An-xiang, YIN Xiao-kang, ZHU Xiao-ya, LIU Sheng-li. Strcmp-like Function Identification Method Based on Data Flow Feature Matching [J]. Computer Science, 2022, 49(9): 326-332.
[8] JIANG Yang-yang, SONG Li-hua, XING Chang-you, ZHANG Guo-min, ZENG Qing-wei. Belief Driven Attack and Defense Policy Optimization Mechanism in Honeypot Game [J]. Computer Science, 2022, 49(9): 333-339.
[9] CHEN Zhi-qiang, HAN Meng, LI Mu-hang, WU Hong-xin, ZHANG Xi-long. Survey of Concept Drift Handling Methods in Data Streams [J]. Computer Science, 2022, 49(9): 14-32.
[10] WANG Ming, WU Wen-fang, WANG Da-ling, FENG Shi, ZHANG Yi-fei. Generative Link Tree:A Counterfactual Explanation Generation Approach with High Data Fidelity [J]. Computer Science, 2022, 49(9): 33-40.
[11] ZHANG Jia, DONG Shou-bin. Cross-domain Recommendation Based on Review Aspect-level User Preference Transfer [J]. Computer Science, 2022, 49(9): 41-47.
[12] WANG Guan-yu, ZHONG Ting, FENG Yu, ZHOU Fan. Collaborative Filtering Recommendation Method Based on Vector Quantization Coding [J]. Computer Science, 2022, 49(9): 48-54.
[13] SONG Jie, LIANG Mei-yu, XUE Zhe, DU Jun-ping, KOU Fei-fei. Scientific Paper Heterogeneous Graph Node Representation Learning Method Based onUnsupervised Clustering Level [J]. Computer Science, 2022, 49(9): 64-69.
[14] CHAI Hui-min, ZHANG Yong, FANG Min. Aerial Target Grouping Method Based on Feature Similarity Clustering [J]. Computer Science, 2022, 49(9): 70-75.
[15] HUANG Li, ZHU Yan, LI Chun-ping. Author’s Academic Behavior Prediction Based on Heterogeneous Network Representation Learning [J]. Computer Science, 2022, 49(9): 76-82.
Full text



No Suggested Reading articles found!