Segmentation of COVID-19 CT Images Based on Dual Attention Mechanism

doi:10.12068/j.issn.1005-3026.2023.09.006

Abstract

Abstract: Rapid and accurate segmentation of COVID-19 lesions from CT images is an important step to realize computer-assisted diagnosis and treatment of COVID-19. Therefore， a CT image segmentation method of COVID-19 lesions based on dual-attention mechanism is proposed. Firstly， the attention gate module is introduced to enhance the focus on the focal region in space and reduce the influence of image brightness imbalance and low contrast on the segmentation accuracy. Secondly， the SE-Res module combined with residual element was introduced to enhance the channel of the lesion region， extract the fine structural features， and improve the segmentation performance of the network for the lesion shape change and ground glass boundary region. Experiments on the public datasets of COVID-19 show that the Dice， PPV and IoU achieved by the proposed method are 0.9088， 0.9152 and 0.8589， respectively， which are 0.75%， 0.11% and 0.65%higher than previous studies， respectively. The proposed method can improve the segmentation accuracy of the lesions with large shape changes and ground glass boundaries， and the overall performance is better than current mainstream models.

Key words: image processing; medical image segmentation; COVID-19; dual attention mechanism; UNet

CLC Number:

TP391.4

JIANG Yang， LIU Cheng， DING Qi-chuan， WANG Li. Segmentation of COVID-19 CT Images Based on Dual Attention Mechanism[J]. Journal of Northeastern University(Natural Science), 2023, 44(9): 1259-1268.

References

[1]钱宝鑫，肖志勇，宋威.改进的卷积神经网络在肺部图像上的分割应用［J］.计算机科学与探索，2020，14(8):1358-1367.(Qian Bao-xin，Xiao Zhi-yong，Song Wei.An improved convolutional neural network for segmentation of lung images［J］.Computer Science and Exploration，2020，14(8):1358-1367.)
[2]Mansoor A，Bagci U，Foster B，et al.Segmentation and image analysis of abnormal lungs at CT:current approaces，challenges，and future trends［J］.Radiographics，2015，35(4):1056-1076.
[3]周娇，徐向民，吕华琳.基于医学图像分割的半自动ROI提取［J］.电视技术，2007(2):78-80.(Zhou Jiao，Xu Xiang-min，Lyu Hua-lin.Semi-automatic ROI extraction based on medical image segmentation［J］.Television Technology，2007(2):78-80.)
[4]Hu S，Hoffman E A，Reinhardt J M.Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images［J］.IEEE Transactions on Medical Imaging，2001，20(6):490-498.
[5]Adams R，Bischof L.Seeded region growing［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，1994，16(6):641-647.
[6]Xiao G，Yun X，Wu J M.A multi-cue mean-shift target tracking approach based on fuzzified region dynamic imagefusion［J］.Science China (Information Sciences)，2012，55(3):577-589.
[7]Shelhamer E，Long J，Darrell T.Fully convolutional networks for semantic segmentation［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39(4):640-651.
[8]Ronneberger O，Fischer P，Brox T.U-Net:convolutional networks for biomedical image segmentation［C］//18th International Conference on Medical Image Computing and Computer-Assisted Intervention.Munich，2015:234-241.
[9]Zhou Z W，Siddiquee M M R，Tajbakhsh N，et al.UNet++:a nested U-net architecture for medical image segmentation［C］// 4th International Workshop on Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Granada，2018:3-11.
[10]Oktay O，Schlemper J，Folgoc L L，et al.Attention U-Net:learning where to look for the pancreas［EB/OL］.［2018-05-20］.https://arxiv.org/abs/1804.03999.pdf
[11]Alom M Z，Hasan M，Yakopcic C，et al.Recurrent residual convolutional neural network based on U-Net (R2U-Net) for medical image segmentation［EB/OL］.［2018-05-29］.https://arxiv.org/vc/arxiv/papers/1802/1802.06955v4.pdf.
[12]钟思华，郭兴明，郑伊能.改进U-Net 网络的肺结节分割方法［J］.计算机工程与应用，2020，56(17):203-209.(Zhong Si-hua，Guo Xing-ming，Zheng Yi-neng.Improved segmentation method of pulmonary nodules in U-Net network［J］.Computer Engineering and Applications，2020，56 (17):203-209.)
[13]Zhao C，Xu Y，He Z，et al.Lung segmentation and automatic detection of COVID-19 using radiomic features from chest CT images［J］.Pattern Recognition，2021，119:108071.
[14]Mu N，Wang H Y，Zhang Y，et al.Progressive global perception and local polishing network for lung infection segmentation of COVID-19 CT images［J］.Pattern Recognition，2021，120:108168.
[15]Fan D P，Zhou T，Ji G P，et al.INF-Net:automatic COVID-19 lung infection segmentation from CT images［J］.IEEE Transactions on Medical Imaging，2020，39(8):2626-2637.
[16]Singh V K，Abdel-Nasser M，Pandey N，et al.LungINFseg:segmenting COVID-19 infected regions in lung CT images based on a receptive-field-aware deep learning framework［J］.Diagnostics，2021，11(2):158-158.
[17]Maninis K K，Caelles S，Pont-Tuset J，et al.Deep extreme cut:from extreme points to object segmentation［C］// IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City，2018:616-625.
[18]Kitrungrotsakul T，Chen Q Q，Wu H T，et al.Attention-RefNet:interactive attention refinement network for infected area segmentation of COVID-19［J］.IEEE Journal of Biomedical and Health Informatics，2021，25(7):2363-2373.
[19]宋瑶，刘俊.改进U-Net的新冠肺炎图像分割方法［J］.计算机工程与应用，2021，57(19):243-251.(Song Yao，Liu Jun.Improved COVID-19 image segmentation method based on U-Net［J］.Computer Engineering and Applications，2021，57(19):243-251.)
[20]施俊，汪琳琳，王珊珊，等.深度学习在医学影像中的应用综述［J］.中国图象图形学报，2020，25(10):1953-1981.(Shi Jun，Wang Lin-lin，Wang Shan-shan，et al.A review of deep learning applications in medical imaging［J］.Journal of Image and Graphics，2020，25(10):1953-1981.)
[21]付顺兵，王朝斌，罗建，等.基于改进U-Net模型的脑肿瘤MR图像分割［J］.西华师范大学学报(自然科学版)，2021，42(2):202-208.(Fu Shun-bing，Wang Chao-bin，Luo Jian，et al.Brain tumor MR image segmentation based on improved U-NET model［J］.Journal of China West Normal University，201，42(2):202-208.)
[22]Hu J，Shen L，Albanie S，et al.Squeeze-and-excitation networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42(8):2011-2023.
[23]Szegedy C，Ioffe S，Vanhoucke V，et al.Inception-v4，inception-ResNet and the impact of connections on learning［C］// 31st AAAI Conference on Artificial Intelligence.San Francisco，2017:4278-4284.
[24]张文秀，朱振才，张永合，等.基于残差块和注意力机制的细胞图像分割方法［J］.光学学报，2020，40(17):76-83.(Zhang Wen-xiu，Zhu Zhen-cai，Zhang Yong-he，et al.Cell image segmentation method based on residual block and attention mechanism［J］.Acta Optica Sinica，2020，40(17):76-83.)
[25]易三莉，陈建亭，贺建峰.ASR-UNet:一种基于注意力机制改进的视网膜血管分割算法［J］.山东大学学报(理学版)，2021，56(9):13-20.(Yi San-li，Chen Jian-ting，He Jian-feng.ASR-UNet:an improved retinal vascular segmentation algorithm based on attention mechanism ［J］.Journal of Shandong University，2021，56(9):13-20.)
[26]Chen L C，Papandreou G，Schroff F，et al.Rethinking atrous convolution for semantic image segmentation［EB/OL］.［2017-12-05］.https://arxiv.org/pdf/1706.05587.pdf.
[27]Liang J Y，Sun G L，Zhang K，et al.Mutual affine network for spatially variant kernel estimation in blind image super-resolution［C］// IEEE/CVF International Conference on Computer Vision.Montreal，2021:4076-4085.
[28]Lin T Y，Dollar P，Girshick R，et al.Feature pyramid networks for object detection［EB/OL］.［2017-04-19］.https://arxiv.org/pdf/1612.03144.pdf.
[29]Zhao H S，Shi J P，Qi X J，et al.Pyramid scene parsing network［C］// IEEE Conference on Computer Vision and Pattern Recognition.Honolulu，2017:6230-6239.
[30]Liu S，Qi L，Qin H F，et al.Path aggregation network for instance segmentation［C］// IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City，2018:8759-8768.［31］Wang G T，Zuluaga M A，Li W Q，et al.DeepIGeoS:a deep interactive geodesic framework for medical image segmentation［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2019，41(7):1559-1572.［32］Kitrungrotsakul T，Yutaro I，Lin L，et al.Interactive deep refinement network for medical image segmentation［EB/OL］.［2020-06-27］.https://arxiv.org/pdf/2006.15320v1.pdf.