面向类别不平衡的胎儿心脏超声图像分割算法

doi:10.3778/j.issn.1002-8331.2401-0410

摘要/Abstract

摘要： 基于深度学习的图像分割技术是处理医学图像的有力工具，胎儿心脏超声图像分割任务更是其中的热点研究内容。由于不同心脏部位像素点数量不平衡以及图像模糊等问题，导致现有算法对少数类像素点的分割准确度较低，分割边界通常也不够精确。为此，提出面向类别不平衡的胎儿心脏超声图像分割算法。该算法通过嵌入代价感知层，为少数类像素点的错误分类分配更高的损失权重，以提升少数类像素点的分类准确性。应用全局直方图均衡化，结合空洞空间金字塔池化，获取清晰的图像轮廓和多尺度上下文信息。在真实胎儿心脏数据集上与7种先进分割算法比较，该算法在多项评价指标上均获得了最优的分割结果。

关键词: 胎儿心脏超声, 图像分割, 类别不平衡, 代价感知, 多尺度

Abstract: Deep learning-based image segmentation is a potent tool for medical image analysis, and the fetal echocardiogram segmentation is the frontier research topic. Due to the imbalance problem in the number of pixels in different heart parts and the blurred image, the existing algorithms have low segmentation accuracy for minority pixels, and the segmentation boundaries are usually inaccurate. To address these issues, this paper proposes a fetal echocardiogram segmentation algorithm that focuses on handling class imbalance problem. By embedding a cost-aware layer, which assigns higher loss weights to misclassifications of minority class pixels, thereby improving the classification accuracy of minority class pixels. Additionally, the global histogram equalization combined with dilated spatial pyramid pooling obtain clear image contours and multi-scale contextual information. In comparison with seven advanced segmentation algorithms on a real fetal heart dataset, the proposed algorithm demonstrates optimal results across multiple evaluation metrics.

Key words: fetal cardiac ultrasound, image segmentation, class imbalance, cost-aware, multi-scale

牛亮, 张孟璐, 陈炳华, 姜舒, 陆璐琦, 徐晓, 牛强. 面向类别不平衡的胎儿心脏超声图像分割算法[J]. 计算机工程与应用, 2024, 60(21): 236-243.

NIU Liang, ZHANG Menglu, CHEN Binghua, JIANG Shu, LU Luqi, XU Xiao, NIU Qiang. Fetal Echocardiogram Segmentation Algorithm for Class Imbalance[J]. Computer Engineering and Applications, 2024, 60(21): 236-243.

参考文献

[1] STIRNEMANN J J, BESSON R, SPAGGIARI E, et al. Development and clinical validation of real-time artificial intelligence diagnostic companion for fetal ultrasound examination[J]. Ultrasound in Obstetrics & Gynecology, 2023, 62(3): 353-360.
[2] 徐光柱, 钱奕凡, 王阳, 等. 基于两级分割的胎儿四腔心超声切面质量评测[J]. 中国图象图形学报, 2023, 28(8): 2476-2490.
XU G Z， QIAN Y F， WANG Y，et al. Quality assessment for fetal four-chamber ultrasound views based on two-stage segmentation[J]. Journal of Image and Graphics, 2023, 28(8): 2476-2490.
[3] SHEN Y T, CHEN L, YUE W W, et al. Artificial intelligence in ultrasound[J]. European Journal of Radiology, 2021, 139: 109717.
[4] FIORENTINO M C, VILLANI F P, DI COSMO M, et al. A review on deep-learning algorithms for fetal ultrasound-image analysis[J]. Medical Image Analysis, 2023, 83: 102629.
[5] 王波, 袁凤强, 陈宗仁, 等. 多阶U-Net甲状腺超声图像自动分割方法[J]. 计算机工程与应用, 2023, 59(5): 205-212.
WANG B, YUAN F Q, CHEN Z R, et al. Multi-stage U-Net automatic segmentation of thyroid ultrasound images[J]. Computer Engineering and Applications, 2023, 59(5): 205-212.
[6] DINDOYAL I, LAMBROU T, DENG J, et al. Level set snake algorithms on the fetal heart[C]//Proceedings of the IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2007: 864-867.
[7] SIQUEIRA M L, GASPERIN C V, SCHARCANSKI J, et al. Echocardiographic image sequence segmentation using self-organizing maps[C]//Proceedings of the 2000 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing X, 2000: 594-603.
[8] DINDOYAL I, LAMBROU T, DENG J, et al. Level set segmentation of the fetal heart[C]//Proceedings of the International Workshop on Functional Imaging and Modeling of the Heart, 2005: 123-132.
[9] SIQUEIRA M L, NAVAUX P O A. Automatic heart localization in ultrasound fetal images[C]//Proceedings of the 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), 2007: 107-112.
[10] 王燕, 南佩奇. MFFNet: 多级特征融合图像语义分割网络[J]. 计算机科学与探索, 2024, 18(3): 707-717.
WANG Y, NAN P Q. MFFNet: image semantic segmentation network of multi-level feature fusion[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(3): 707-717.
[11] 龚勋, 杨菲, 杜章锦, 等. 甲状腺、乳腺超声影像自动分析技术综述[J]. 软件学报, 2020, 31(7): 2245-2282.
GONG X, YANG F, DU Z J, et al. Survey of automatic ultrasonographic analysis for thyroid and breast[J]. Journal of Software, 2020, 31(7): 2245-2282.
[12] 陈曦, 刘奇, 邓小波, 等. 改进U-Net的超声乳腺肿瘤分割网络[J]. 计算机工程与应用, 2022, 58(22): 219-228.
CHEN X, LIU Q, DENG X B, et al. Enhanced network for ultrasound breast tumor segmentation based on U-Net[J]. Computer Engineering and Applications, 2022, 58(22): 219-228.
[13] RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]//Proceedings of International on Medical Image Computing and Computer-Assisted Intervention, 2015: 234-241.
[14] 徐光宪, 冯春, 马飞. 基于UNet的医学图像分割综述[J]. 计算机科学与探索, 2023, 17(8): 1776-1792.
XU G X, FENG C, MA F. Review of medical image segmentation based on UNet[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(8): 1776-1792.
[15] WANG R, LEI T, CUI R, et al. Medical image segmentation using deep learning: a survey[J]. IET Image Processing, 2022, 16(5): 1243-1267.
[16] RACHMATULLAH M N, NURMAINI S, SAPITRI A I, et al. Convolutional neural network for semantic segmentation of fetal echocardiography based on four-chamber view[J]. Bulletin of Electrical Engineering and Informatics, 2021, 10(4): 1987-1996.
[17] XU L, LIU M, SHEN Z, et al. DW-Net: a cascaded convolutional neural network for apical four-chamber view segmentation in fetal echocardiography[J]. Computerized Medical Imaging and Graphics, 2020, 80: 101690.
[18] SENGAN S, MEHBODNIYA A, BHATIA S, et al. Echocardiographic image segmentation for diagnosing fetal cardiac rhabdomyoma during pregnancy using deep learning[J]. IEEE Access, 2022, 10: 114077-114091.
[19] ZENG Y, TSUI P H, PANG K, et al. MAEF-Net: multi-attention efficient feature fusion network for left ventricular segmentation and quantitative analysis in two-dimensional echocardiography[J]. Ultrasonics, 2023, 127: 106855.
[20] SFAKIANAKIS C, SIMANTIRIS G, TZIRITAS G. GUDU: geometrically-constrained ultrasound data augmentation in U-Net for echocardiography semantic segmentation[J]. Biomedical Signal Processing and Control, 2023, 82: 104557.
[21] ALAM M G R, KHAN A M, SHEJUTY M F, et al. Ejection fraction estimation using deep semantic segmentation neural network[J]. The Journal of Supercomputing, 2023, 79(1): 27-50.
[22] SANDLER M, HOWARD A, ZHU M, et al. MobileNetv2: inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4510-4520.
[23] CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision, 2018: 801-818.
[24] DOUGHERTY E R. Digital image processing methods[M]. [S.l.]: CRC Press, 2020.
[25] PIZER S M, AMBURN E P, AUSTIN J D, et al. Adaptive histogram equalization and its variations[J]. Computer Vision, Graphics, and Image Processing, 1987, 39(3): 355-368.
[26] REZA A M. Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement[J]. Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 2004, 38: 35-44.
[27] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3431-3440.
[28] WANG P, CHEN P, YUAN Y, et al. Understanding convolution for semantic segmentation[C]//Proceedings of the Winter Conference on Applications of Computer Vision, 2018: 1451-1460.
[29] HOSSAIN M S, BETTS J M, PAPLINSKI A P. Dual focal loss to address class imbalance in semantic segmentation[J]. Neurocomputing, 2021, 462: 69-87.
[30] KHAN S H, HAYAT M, BENNAMOUN M, et al. Cost-sensitive learning of deep feature representations from imbalanced data[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 29(8): 3573-3587.
[31] EMARA T, ABD EL MUNIM H E, ABBAS H M. LiteSeg: a novel lightweight convnet for semantic segmentation[J]. arXiv:1912.06683, 2019.
[32] ZHOU Z, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. UNet++: a nested U-Net architecture for medical image segmentation[C]//Proceedings of the International Workshop on Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 2018: 3-11.
[33] SHARIFZADEH M, BENALI H, RIVAZ H. Investigating shift variance of convolutional neural networks in ultrasound image segmentation[J]. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2022, 69(5): 1703-1713.
[34] BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
[35] LOU A, LOEW M. CFPNet: channel-wise feature pyramid for real-time semantic segmentation[C]//Proceedings of the IEEE Conference International Conference on Image Processing, 2021: 1894-1898.