Information bottleneck-guided intracranial hemorrhage segmentation method

doi:10.11772/j.issn.1001-9081.2024060855

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (6): 1998-2006.DOI: 10.11772/j.issn.1001-9081.2024060855

• Multimedia computing and computer simulation • Previous Articles

Information bottleneck-guided intracranial hemorrhage segmentation method

Jie JIANG¹, Gongning LUO¹, Suyu DONG², Fanding LI¹, Xiangyu LI¹(), Qince LI¹, Yongfeng YUAN¹, Kuanquan WANG¹

^1.Faculty of Computing，Harbin Institute of Technology，Harbin Heilongjiang 150001，China
^2.College of Computer and Control Engineering，Northeast Forestry University，Harbin Heilongjiang 150040，China

Received:2024-06-24 Revised:2024-09-06 Accepted:2024-09-10 Online:2024-09-18 Published:2025-06-10
Contact: Xiangyu LI
About author:JIANG Jie， born in 2001， M. S. candidate. His research interests include medical image processing， computer vision.
LUO Gongning， born in 1989， Ph. D.， associate professor. His research interests include computational cardiology， medical image analysis.
DONG Suyu， born in 1989， Ph. D.， associate professor. Her research interests include medical image processing， multimodal medical image analysis.
LI Fanding， born in 2002， Ph. D. candidate. His research interests include medical image processing， computer vision.
LI Qince， born in 1985， Ph. D.， associate research fellow. His research interests include medical image processing， biological system modeling.
YUAN Yongfeng， born in 1979， Ph. D.， associate professor. His research interests include medical image processing， computational cardiology.
WANG Kuanquan， born in 1964， Ph. D.， professor. His research interests include medical image processing， computational cardiology.
Supported by:
National Natural Science Foundation of China(62372135);China Postdoctoral Science Foundation(2024M754207);National Postdoctoral Researcher Program(GZC20242214)

信息瓶颈引导的颅内出血分割方法

蒋杰¹, 骆功宁¹, 董素宇², 李凡丁¹, 李向宇¹(), 李钦策¹, 袁永峰¹, 王宽全¹

^1.哈尔滨工业大学计算学部，哈尔滨 150001
^2.东北林业大学计算机与控制工程学院，哈尔滨 150040

通讯作者: 李向宇
作者简介:蒋杰（2001—），男，重庆人，硕士研究生，主要研究方向：医学图像处理、计算机视觉
骆功宁（1989—），男，山东烟台人，副教授，博士，主要研究方向：计算心脏学、医学图像分析
董素宇（1989—），女，内蒙古乌兰察布人，副教授，博士，主要研究方向：医学图像处理、多模态医学图像分析
李凡丁（2002—），男，吉林长春人，博士研究生，主要研究方向：医学图像处理、计算机视觉
李钦策（1985—），男，山东淄博人，副研究员，博士，主要研究方向：医学图像处理、生物系统建模
袁永峰（1979—），男，四川邛崃人，副教授，博士，主要研究方向：医学图像处理、计算心脏学
王宽全（1964—），男，四川达州人，教授，博士，主要研究方向：医学图像处理、计算心脏学。

Abstract

Abstract:

In the field of computer-aided diagnosis， accurate segmentation of IntraCranial Hemorrhages （ICHs） in Computed Tomography （CT） images is crucial for subsequent treatment and prognosis. To address the challenge of segmenting small hemorrhage regions， an information bottleneck-guided ICH segmentation method was proposed. Based on this method，an Information Bottleneck-Guided Segmentation Network （IBGS-Net） was proposed. Firstly， the U-Net architecture was used as a base， and an information bottleneck layer was introduced to enhance the recognition of key features related to ICH segmentation. Then， through the designed Residual SPatially-ADaptivE normalization （ResSPADE） module， the Information Activation Map （IAM） was integrated effectively into the segmentation process， thereby improving the network’s ability to identify and locate hemorrhage regions. Finally， an Interactive Guided Loss （IGL） function was introduced to optimize the model’s processing of difficult-to-segment regions， thereby further enhancing the model’s generalization performance. Evaluation results on the internal dataset indicate that the proposed method achieves 78.1% in Dice Similarity Coefficient （DSC）， 90.1% in Normalization Surface Dice （NSD）， and 11.5% in Relative Volume Difference （RVD）. On the public dataset INSTANCE 2022， the results of comparison with other segmentation methods show that compared to the suboptimal results， the three indicators of the proposed method increased by 1.9， 2.4， and decreased by 3.2 percentage points， respectively. The above validates the effectiveness and superiority of the proposed method in ICH segmentation tasks， so that the method is suitable for assisting clinicians in segmenting ICHs.

Key words: IntraCranial Hemorrhage (ICH) segmentation, information bottleneck, Interactive Guidance Loss (IGL), Residual SPatially-ADaptivE normalization (ResSPADE), U-Net

摘要：

在计算机辅助诊断领域，精确分割计算机断层扫描（CT）图像中的颅内出血（ICH）对后续的治疗和预后至关重要。针对小出血区域难以分割的问题，提出一种信息瓶颈引导的ICH分割方法并基于该方法构建一个信息瓶颈引导的分割网络（IBGS-Net）。首先，采用U-Net架构作为基础，并引入信息瓶颈层增强与ICH分割相关的关键特征的识别；其次，通过设计的残差空间自适应归一化（ResSPADE）模块，信息激活图（IAM）被有效整合到分割流程中，提升网络对出血区域的识别和定位能力；最后，引入交互引导损失（IGL）函数以优化模型对难分割区域的处理，进一步增强模型的泛化性能。在内部数据集上的评估结果表明，所提方法在Dice相似性系数（DSC）、归一化表面Dice（NSD）和相对体积差（RVD）这3个指标上分别达到了78.1%、90.1%和11.5%；在公开数据集INSTANCE 2022上，与其他的分割方法的比较结果表明，所提方法的3个指标相较于次优结果，分别提升了1.9、2.4和下降了3.2个百分点。以上验证了所提方法在ICH分割任务中的有效性和优越性，可用于协助临床医生进行ICH分割。

关键词: 颅内出血分割, 信息瓶颈, 交互引导损失, 残差空间自适应归一化, U-Net

CLC Number:

TP391.4

Jie JIANG, Gongning LUO, Suyu DONG, Fanding LI, Xiangyu LI, Qince LI, Yongfeng YUAN, Kuanquan WANG. Information bottleneck-guided intracranial hemorrhage segmentation method[J]. Journal of Computer Applications, 2025, 45(6): 1998-2006.

蒋杰, 骆功宁, 董素宇, 李凡丁, 李向宇, 李钦策, 袁永峰, 王宽全. 信息瓶颈引导的颅内出血分割方法[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1998-2006.

Figures/Tables 9

References 39

1	VAN ASCH C J J， LUITSE M J A， RINKEL G J E， et al. Incidence， case fatality， and functional outcome of intracerebral haemorrhage over time， according to age， sex， and ethnic origin： a systematic review and meta-analysis［J］. The Lancet Neurology， 2010， 9（2）： 167-176.
2	QURESHI A I， PALESCH Y Y. Antihypertensive Treatment of Acute Cerebral Hemorrhage （ATACH） Ⅱ： design， methods， and rationale ［J］. Neurocritical Care， 2011， 15（3）： 559-576.
3	ABRAMOVA V， CLÈRIGUES A， QUILES A， et al. Hemorrhagic stroke lesion segmentation using a 3D U-Net with squeeze-and-excitation blocks ［J］. Computerized Medical Imaging and Graphics， 2021， 90： No.101908.
4	ISLAM M， SANGHANI P， SEE A A Q， et al. ICHNet： IntraCerebral Hemorrhage （ICH） segmentation using deep learning［C］// Proceedings of the 2018 International MICCAI Brainlesion Workshop， LNCS 11383. Cham： Springer， 2019： 456-463.
5	KOTHARI R U， BROTT T， BRODERICK J P， et al. The ABCs of measuring intracerebral hemorrhage volumes［J］. Stroke， 1996， 27（8）： 1304-1305.
6	WEBB A J S， ULLMAN N L， MORGAN T C， et al. Accuracy of the ABC/2 score for intracerebral hemorrhage： systematic review and analysis of MISTIE， CLEAR-IVH， and CLEAR Ⅲ［J］. Stroke， 2015， 46（9）： 2470-2476.
7	HU Q， QIAN G， AZIZ A， et al. Segmentation of brain from computed tomography head images［C］// Proceedings of the 27th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway： IEEE， 2005： 3375-3378.
8	MAKSIMOVIC R， STANKOVIC S， MILOVANOVIC D. Computed tomography image analyzer： 3D reconstruction and segmentation applying active contour models — ‘snakes’［J］. International Journal of Medical Informatics， 2000， 58/59： 29-37.
9	RAMTEKE R J， KHACHANE M Y. Automatic medical image classification and abnormality detection using K-nearest neighbour［J］. International Journal of Advanced Computer Research， 2012， 2（6）： 190-196.
10	HSSAYENI M D， CROOCK M S， SALMAN A D， et al. Intracranial hemorrhage segmentation using a deep convolutional model ［J］. Data， 2020， 5（1）： No.14.
11	RONNEBERGER O， FISCHER P， BROX T. U-Net： convolutional networks for biomedical image segmentation［C］// Proceedings of the 2015 International Conference on Medical Image Computing and Computer Assisted Intervention， LNCS 9351. Cham： Springer， 2015： 234-241.
12	CHANG P D， KUOY E， GRINBAND J， et al. Hybrid 3D/2D convolutional neural network for hemorrhage evaluation on head CT［J］. American Journal of Neuroradiology， 2018， 39（9）： 1609-1616.
13	KUANG Z， DENG X， YU L， et al. Ψ-Net： focusing on the border areas of intracerebral hemorrhage on CT images［J］. Computer Methods and Programs in Biomedicine， 2020， 194： No.105546.
14	LI X， LUO G， WANG W， et al. Hematoma expansion context guided intracranial hemorrhage segmentation and uncertainty estimation［J］. IEEE Journal of Biomedical and Health Informatics， 2022， 26（3）： 1140-1151.
15	SCHULZ K， SIXT L， TOMBARI F， et al. Restricting the flow： information bottlenecks for attribution［EB/OL］. ［2024-06-18］..
16	PARK T， LIU M Y， WANG T C， et al. Semantic image synthesis with spatially-adaptive normalization ［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 2332-2341.
17	KWON D， AHN J， KIM J， et al. Siamese U-Net with healthy template for accurate segmentation of intracranial hemorrhage［C］// Proceedings of the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention， LNCS 11766. Cham： Springer， 2019： 848-855.
18	TOIKKANEN M， KWON D， LEE M. ReSGAN： intracranial hemorrhage segmentation with residuals of synthetic brain CT scans［C］// Proceedings of the 2021 International Conference on Medical Image Computing and Computer Assisted Intervention， LNCS 12901. Cham： Springer， 2021： 400-409.
19	PIAO Z， GU Y H， JIN H， et al. Intracerebral hemorrhage CT scan image segmentation with HarDNet based transformer［J］. Scientific Reports， 2023， 13： No.7208.
20	NIJIATI M， TUERSUN A， ZHANG Y， et al. A symmetric prior knowledge based deep learning model for intracerebral hemorrhage lesion segmentation［J］. Frontiers in Physiology， 2022， 13： No.977427.
21	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： No.102489.
22	张鹏，徐曾春，胡平. 融合密集连接与注意机制的颅内出血分割方法［J］. 小型微型计算机系统， 2021， 42（7）： 1458-1463.
	ZHANG P， XU Z C， HU P. Segmentation of intracranial hemorrhage fusing dense connection and attention mechanism［J］. Journal of Chinese Computer Systems， 2021， 42（7）： 1458-1463.
23	ZHOU B， KHOSLA A， LAPEDRIZA A， et al. Learning deep features for discriminative localization［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 2921-2929.
24	SELVARAJU R R， COGSWELL M， DAS A， et al. Grad-CAM： visual explanations from deep networks via gradient-based localization［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 618-626.
25	张童禹，李恩慧，李振宇，等. 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［J］. 中国生物医学工程学报， 2023， 42（6）： 677-686.
	ZHANG T Y， LI E H， LI Z Y， et al. Segmentation of intracranial hemorrhage in CT images based on multi-instance learning and thresholding pseudo-labels extraction［J］. Chinese Journal of Biomedical Engineering， 2023， 42（6）：677-686.
26	YUN S， HAN D， CHUN S， et al. CutMix： regularization strategy to train strong classifiers with localizable features ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 6022-6031.
27	BABAR S， DAS S. Where to look？： Mining complementary image regions for weakly supervised object localization［C］// Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision. Piscataway： IEEE， 2021： 1009-1018.
28	KIM J， CHOE J， YUN S， et al. Normalization matters in weakly supervised object localization ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 3407-3416.
29	BANG S， XIE P， LEE H， et al. Explaining a black-box by using a deep variational information bottleneck approach ［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2021： 11396-11404.
30	SMILKOV D， THORAT N， KIM B， et al. SmoothGrad： removing noise by adding noise ［EB/OL］. ［2024-06-18］..
31	KLAMBAUER G， UNTERTHINER T， MAYR A， et al. Self-normalizing neural networks［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 972-981.
32	LI X， WANG K， LIU J， et al. The 2022 intracranial hemorrhage segmentation challenge on Non-Contrast head CT （NCCT）（Mar 2022）. ［EB/OL］. ［2024-05-21］. .
33	LI X， LUO G， WANG K， et al. The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT： the INSTANCE challenge［EB/OL］. ［2024-06-18］..
34	KUO W， HÄNE C， YUH E， et al. Cost-sensitive active learning for intracranial hemorrhage detection［C］// Proceedings of the 2018 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 11072. Cham： Springer， 2018： 715-723.
35	YU N， YU H， LI H， et al. A robust deep learning segmentation method for hematoma volumetric detection in intracerebral hemorrhage［J］. Stroke， 2022， 53（1）： 167-176.
36	ÇIÇEK Ö， ABDULKADIR A， LIENKAMP S S， et al. 3D U-Net： learning dense volumetric segmentation from sparse annotation［C］// Proceedings of the 2016 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 9901. Cham： Springer， 2016： 424-432.
37	HATAMIZADEH A， TANG Y， NATH V， et al. UNETR： transformers for 3D medical image segmentation ［C］// Proceedings of the 2022 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway： IEEE， 2022： 1748-1758.
38	XU B， FAN Y， LIU J， et al. CHSNet： automatic lesion segmentation network guided by CT image features for acute cerebral hemorrhage［J］. Computers in Biology and Medicine， 2023， 164： No.107334.
39	ZHANG Y， HUANG Y， HU K. Multi-scale object equalization learning network for intracerebral hemorrhage region segmentation［J］. Neural Networks， 2024， 179： No.106507.

数据集	方法	Dice	NSD	RVD
内部数据集	Patch-FCN^［34］	75.5	84.9	17.2
	DR-UNet^［35］	76.3	85.4	14.3
	U-Net^［11］	75.8	83.9	21.2
	3D U-Net^［36］	76.4	87.0	16.2
	SLEX-Net^［14］	76.1	86.8	15.7
	IBGS-Net	78.1	90.1	11.5
公共数据集	UNETR^［37］	60.7	45.4	47.8
	U-Net^［11］	57.5	41.5	54.3
	3D U-Net^［36］	59.3	46.3	36.3
	CHSNet^［38］	61.3	45.2	35.2
	MOEL-Net^［39］	58.9	43.4	40.3
	IBGS-Net	63.2	48.7	32.0

数据集	方法	Dice	NSD	RVD
内部数据集	Patch-FCN^［34］	75.5	84.9	17.2
	DR-UNet^［35］	76.3	85.4	14.3
	U-Net^［11］	75.8	83.9	21.2
	3D U-Net^［36］	76.4	87.0	16.2
	SLEX-Net^［14］	76.1	86.8	15.7
	IBGS-Net	78.1	90.1	11.5
公共数据集	UNETR^［37］	60.7	45.4	47.8
	U-Net^［11］	57.5	41.5	54.3
	3D U-Net^［36］	59.3	46.3	36.3
	CHSNet^［38］	61.3	45.2	35.2
	MOEL-Net^［39］	58.9	43.4	40.3
	IBGS-Net	63.2	48.7	32.0

实验	IAM	ResSPADE	IGL	Dice	NSD	RVD
A				75.7	84.1	19.2
B	√			76.1	84.7	15.5
C	√	√		76.9	87.3	13.2
D			√	77.2	86.9	14.1
E	√	√	√	78.1	90.1	11.5

实验	IAM	ResSPADE	IGL	Dice	NSD	RVD
A				75.7	84.1	19.2
B	√			76.1	84.7	15.5
C	√	√		76.9	87.3	13.2
D			√	77.2	86.9	14.1
E	√	√	√	78.1	90.1	11.5

[1]	Minghao SUN, Han YU, Yuqing CHEN, Kai LU. First-arrival picking and inversion of seismic waveforms based on U-shaped multilayer perceptron network [J]. Journal of Computer Applications, 2024, 44(7): 2301-2309.
[2]	Lijun XU, Hui LI, Zuyang LIU, Kansong CHEN, Weixuan MA. 3D-GA-Unet： MRI image segmentation algorithm for glioma based on 3D-Ghost CNN [J]. Journal of Computer Applications, 2024, 44(4): 1294-1302.
[3]	Yusheng LIU, Xuezhong XIAO. High-fidelity image editing based on fine-tuning of diffusion model [J]. Journal of Computer Applications, 2024, 44(11): 3574-3580.
[4]	Di ZHOU, Zili ZHANG, Jia CHEN, Xinrong HU, Ruhan HE, Jun ZHANG. Stomach cancer image segmentation method based on EfficientNetV2 and object-contextual representation [J]. Journal of Computer Applications, 2023, 43(9): 2955-2962.
[5]	Liyao FU, Mengxiao YIN, Feng YANG. Transformer based U-shaped medical image segmentation network： a survey [J]. Journal of Computer Applications, 2023, 43(5): 1584-1595.
[6]	You YANG, Ruhui ZHANG, Pengcheng XU, Kang KANG, Hao ZHAI. Improved U-Net for seal segmentation of Republican archives [J]. Journal of Computer Applications, 2023, 43(3): 943-948.
[7]	Li’an ZHU, Hong ZHANG. Nonhomogeneous image dehazing based on dual-branch conditional generative adversarial network [J]. Journal of Computer Applications, 2023, 43(2): 567-574.
[8]	Zhiang ZHANG, Guangzhong LIAO. Multi-scale feature enhanced retinal vessel segmentation algorithm based on U-Net [J]. Journal of Computer Applications, 2023, 43(10): 3275-3281.
[9]	LIN Jianzhuang, YANG Wenzhong, TAN Sixiang, ZHOU Lexin, CHEN Danni. Fusing filter enhancement and reverse attention network for polyp segmentation [J]. Journal of Computer Applications, 2023, 43(1): 265-272.
[10]	Huazhong JIN, Xiuyang ZHANG, Zhiwei YE, Wenqi ZHANG, Xiaoyu XIA. Image denoising model based on approximate U-shaped network structure [J]. Journal of Computer Applications, 2022, 42(8): 2571-2577.
[11]	Guangzhu XU, Wenjie LIN, Sha CHEN, Wan KUANG, Bangjun LEI, Jun ZHOU. Fundus vessel segmentation method based on U-Net and pulse coupled neural network with adaptive threshold [J]. Journal of Computer Applications, 2022, 42(3): 825-832.
[12]	Qiwen WU, Jianhua WANG, Xiang ZHENG, Ju FENG, Hongyan JIANG, Yubo WANG. Waterweed image segmentation method based on improved U-Net [J]. Journal of Computer Applications, 2022, 42(10): 3177-3183.
[13]	HUANG Li, LU Long. Segmentation of ischemic stroke lesion based on long-distance dependency encoding and deep residual U-Net [J]. Journal of Computer Applications, 2021, 41(6): 1820-1827.
[14]	GAO Haijun, ZENG Xiangyin, PAN Dazhi, ZHENG Bochuan. Rectal tumor segmentation method based on improved U-Net model [J]. Journal of Computer Applications, 2020, 40(8): 2392-2397.
[15]	MA Jinlin, WEI Meng, MA Ziping. Pulmonary nodule segmentation method based on deep transfer learning [J]. Journal of Computer Applications, 2020, 40(7): 2117-2125.

Information bottleneck-guided intracranial hemorrhage segmentation method

信息瓶颈引导的颅内出血分割方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 39

Related Articles 15

Recommended Articles

Metrics