skip to main content
research-article

Evaluation of U-Net Based Architectures for Automatic Aortic Dissection Segmentation

Authors Info & Claims
Published:15 October 2021Publication History
Skip Abstract Section

Abstract

Segmentation and reconstruction of arteries is important for a variety of medical and engineering fields, such as surgical planning and physiological modeling. However, manual methods can be laborious and subject to a high degree of human variability. In this work, we developed various convolutional neural network (CNN) architectures to segment Stanford type B aortic dissections (TBADs), characterized by a tear in the descending aortic wall creating a normal channel of blood flow called a true lumen and a pathologic channel within the wall called a false lumen. We introduced several variations to the two-dimensional (2D) and three-dimensional (3D) U-Net, where small stacks of slices were inputted into the networks instead of individual slices or whole geometries. We compared these variations with a variety of CNN segmentation architectures and found that stacking the input data slices in the upward direction with 2D U-Net improved segmentation accuracy, as measured by the Dice similarity coefficient (DC) and point-by-point average distance (AVD), by more than \(15\%\). Our optimal architecture produced DC scores of 0.94, 0.88, and 0.90 and AVD values of 0.074, 0.22, and 0.11 in the whole aorta, true lumen, and false lumen, respectively. Altogether, the predicted reconstructions closely matched manual reconstructions.

REFERENCES

  1. Ashton H. A., Buxton M. J., Day N. E., Kim L. G., Marteau T. M., Scott R. A. P., Thompson S. G., and Walker N. M.. 2002. The multicentre aneurysm screening study (MASS) into the effect of abdominal aortic aneurysm screening on mortality in men: A randomised controlled trial. The Lancet 360, 9345 (2002), 15311539.Google ScholarGoogle Scholar
  2. Cao Long, Shi Ruiqiong, Ge Yangyang, Xing Lei, Zuo Panli, Jia Yan, Liu Jie, He Yuan, Wang Xinhao, Luan Shaoliang, et al. 2019. Fully automatic segmentation of type B aortic dissection from CTA images enabled by deep learning. European Journal of Radiology 121 (2019), 108713.Google ScholarGoogle Scholar
  3. Chen Xuhui, Lu Yi, Bai Junjie, Yin Youbing, Cao Kunlin, Li Yuwei, Chen Hanbo, Song Qi, and Wu Jun. 2018. Train a 3D U-Net to segment cranial vasculature in CTA volume without manual annotation. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI’18). IEEE, 559563.Google ScholarGoogle Scholar
  4. Chen Yo-Chuan, Lin Yi-Chen, Wang Ching-Ping, Lee Chia-Yen, Lee Wen-Jeng, Wang Tzung-Dau, and Chen Chung-Ming. 2019. Coronary artery segmentation in cardiac CT angiography using 3D multi-channel U-Net. https://arxiv.org/abs/1907.12246.Google ScholarGoogle Scholar
  5. Cheng Junlong, Tian Shengwei, Yu Long, Ma Xiang, and Xing Yan. 2020. A deep learning algorithm using contrast-enhanced computed tomography (CT) images for segmentation and rapid automatic detection of aortic dissection. Biomedical Signal Processing and Control 62 (2020), 102145.Google ScholarGoogle ScholarCross RefCross Ref
  6. Çiçek Özgün, Abdulkadir Ahmed, Lienkamp Soeren S., Brox Thomas, and Ronneberger Olaf. 2016. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 424432.Google ScholarGoogle Scholar
  7. Erbel Raimund, Oelert Hellmut, Meyer Jürgen, Puth Maria, Mohr-Katoly Susanne, Hausmann Dirk, Daniel Werner, Maffei Stefano, Caruso Aurelio, and Covino F. E.. 1993. Effect of medical and surgical therapy on aortic dissection evaluated by transesophageal echocardiography. Implications for prognosis and therapy. The European Cooperative Study Group on Echocardiography.Circulation 87, 5 (1993), 16041615.Google ScholarGoogle Scholar
  8. Graffy Peter M., Liu Jiamin, O’Connor Stacy, Summers Ronald M., and Pickhardt Perry J.. 2019. Automated segmentation and quantification of aortic calcification at abdominal CT: Application of a deep learning-based algorithm to a longitudinal screening cohort. Abdominal Radiology (2019), 18.Google ScholarGoogle Scholar
  9. Habijan Marija, Galić Irena, Leventić Hrvoje, Romić Krešimir, and Babin Danilo. 2020. Abdominal aortic aneurysm segmentation from CT images using modified 3D U-Net with deep supervision. In 2020 International Symposium ELMAR. IEEE, 123128.Google ScholarGoogle Scholar
  10. Hahn Lewis D., Mistelbauer Gabriel, Higashigaito Kai, Koci Martin, Willemink Martin J., Sailer Anna M., Fischbein Michael, and Fleischmann Dominik. 2020. CT-based true-and false-lumen segmentation in type B aortic dissection using machine learning. Radiology: Cardiothoracic Imaging 2, 3 (2020), e190179.Google ScholarGoogle ScholarCross RefCross Ref
  11. He Yuting, Yang Guanyu, Chen Yang, Kong Youyong, Wu Jiasong, Tang Lijun, Zhu Xiaomei, Dillenseger Jean-Louis, Shao Pengfei, Zhang Shaobo, et al. 2019. DPA-DenseBiasNet: Semi-supervised 3D fine renal artery segmentation with dense biased network and deep priori anatomy. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 139147.Google ScholarGoogle Scholar
  12. Hossien Abdullrazak, Gelsomino Sandro, Mochtar Baheramsjah, Maessen Jos G., and Nia Peyman Sardari. 2015. Novel multi-dimensional modelling for surgical planning of acute aortic dissection type A based on computed tomography scan. European Journal of Cardio-Thoracic Surgery 48, 5 (2015), e95–e101.Google ScholarGoogle Scholar
  13. Huang Weimin, Huang Lu, Lin Zhiping, Huang Su, Chi Yanling, Zhou Jiayin, Zhang Junmei, Tan Ru-San, and Zhong Liang. 2018. Coronary artery segmentation by deep learning neural networks on computed tomographic coronary angiographic images. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’18). IEEE, 608611.Google ScholarGoogle Scholar
  14. Kovács Tamás, Cattin Philippe, Alkadhi Hatem, Wildermuth Simon, and Székely Gábor. 2006. Automatic segmentation of the aortic dissection membrane from 3D CTA images. In International Workshop on Medical Imaging and Virtual Reality. Springer, 317324. Google ScholarGoogle ScholarDigital LibraryDigital Library
  15. Li Jianning, Cao Long, Cheng W., Bowen M., and Guo Wei. 2018a. Towards automatic measurement of Type B aortic dissection parameters: Methods, applications and perspective. In Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. Springer, 6472.Google ScholarGoogle Scholar
  16. Li Ziyan, Feng Jianjiang, Feng Zishun, An Yunqiang, Gao Yang, Lu Bin, and Zhou Jie. 2018b. Lumen segmentation of aortic dissection with cascaded convolutional network. In International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, 122130.Google ScholarGoogle Scholar
  17. Lindholt Jes S., Juul Svend, Fasting Helge, and Henneberg Eskild W.. 2005. Screening for abdominal aortic aneurysms: Single centre randomised controlled trial. BMJ 330, 7494 (2005), 750.Google ScholarGoogle Scholar
  18. Long Jonathan, Shelhamer Evan, and Darrell Trevor. 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 34313440.Google ScholarGoogle ScholarCross RefCross Ref
  19. López-Linares Karen, Aranjuelo Nerea, Kabongo Luis, Maclair Gregory, Lete Nerea, Ceresa Mario, García-Familiar Ainhoa, Macía Iván, and Ballester Miguel A. González. 2018. Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks. Medical Image Analysis 46 (2018), 202214.Google ScholarGoogle ScholarCross RefCross Ref
  20. López-Linares Karen, Kabongo Luis, Lete Nerea, Maclair Gregory, Ceresa Mario, García-Familiar Ainhoa, Macía Iván, and Ballester Miguel Ángel González. 2017. DCNN-based automatic segmentation and quantification of aortic thrombus volume: Influence of the training approach. In Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. Springer, 2938.Google ScholarGoogle Scholar
  21. Meszaros Istvan, Morocz Jozsef, Szlavi Jozsef, Schmidt Janos, Tornoci Laszlo, Nagy Laszlo, and Szép Laszlo. 2000. Epidemiology and clinicopathology of aortic dissection. Chest 117, 5 (2000), 12711278.Google ScholarGoogle Scholar
  22. Milletari Fausto, Navab Nassir, and Ahmadi Seyed-Ahmad. 2016. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 4th International Conference on 3D Vision (3DV’16). IEEE, 565571.Google ScholarGoogle Scholar
  23. Noothout Julia M. H., Vos Bob D. de, Wolterink Jelmer M., and Išgum Ivana. 2018. Automatic segmentation of thoracic aorta segments in low-dose chest CT. In Medical Imaging 2018: Image Processing, Vol. 10574. International Society for Optics and Photonics, 105741S.Google ScholarGoogle Scholar
  24. Norman Paul E., Jamrozik Konrad, Lawrence-Brown Michael M., Le Max T. Q., Spencer Carole A., Tuohy Raywin J., Parsons Richard W., and Dickinson James A.. 2004. Population based randomised controlled trial on impact of screening on mortality from abdominal aortic aneurysm. BMJ 329, 7477 (2004), 1259.Google ScholarGoogle Scholar
  25. Pepe Antonio, Li Jianning, Rolf-Pissarczyk Malte, Gsaxner Christina, Chen Xiaojun, Holzapfel Gerhard A., and Egger Jan. 2020. Detection, segmentation, simulation and visualization of aortic dissections: A review. Medical Image Analysis 65 (2020), 101773.Google ScholarGoogle Scholar
  26. Pham Dzung L., Xu Chenyang, and Prince Jerry L.. 2000. Current methods in medical image segmentation. Annual Review of Biomedical Engineering 2, 1 (2000), 315337.Google ScholarGoogle ScholarCross RefCross Ref
  27. Ronneberger Olaf, Fischer Philipp, and Brox Thomas. 2015. U-Net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 234241.Google ScholarGoogle Scholar
  28. Taha Abdel Aziz and Hanbury Allan. 2015. Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool. BMC Medical Imaging 15, 1 (2015), 29.Google ScholarGoogle ScholarCross RefCross Ref
  29. Tong Qianqian, Ning Munan, Si Weixin, Liao Xiangyun, and Qin Jing. 2017. 3D deeply-supervised U-Net based whole heart segmentation. In International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, 224232.Google ScholarGoogle Scholar
  30. Updegrove Adam, Wilson Nathan M., Merkow Jameson, Lan Hongzhi, Marsden Alison L., and Shadden Shawn C.. 2017. SimVascular: An open source pipeline for cardiovascular simulation. Annals of Biomedical Engineering 45, 3 (2017), 525541.Google ScholarGoogle Scholar
  31. Wang Yueyue, Zhao Liang, Wang Manning, and Song Zhijian. 2019. Organ at risk segmentation in head and neck CT images using a two-stage segmentation framework based on 3D U-Net. IEEE Access 7 (2019), 144591144602.Google ScholarGoogle Scholar
  32. Xie Saining and Tu Zhuowen. 2015. Holistically-nested edge detection. In Proceedings of the IEEE International Conference on Computer vision. 13951403. Google ScholarGoogle ScholarDigital LibraryDigital Library
  33. Zeng Guodong, Yang Xin, Li Jing, Yu Lequan, Heng Pheng-Ann, and Zheng Guoyan. 2017. 3D U-Net with multi-level deep supervision: Fully automatic segmentation of proximal femur in 3D MR images. In International Workshop on Machine Learning in Medical Imaging. Springer, 274282.Google ScholarGoogle Scholar
  34. Zheng Jian-Qing, Zhou Xiao-Yun, Li Qing-Biao, Riga Celia, and Yang Guang-Zhong. 2018. Abdominal aortic aneurysm segmentation with a small number of training subjects. https://arxiv.org/abs/1804.02943.Google ScholarGoogle Scholar

Index Terms

  1. Evaluation of U-Net Based Architectures for Automatic Aortic Dissection Segmentation

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Full Text

      View this article in Full Text.

      View Full Text

      HTML Format

      View this article in HTML Format .

      View HTML Format
      About Cookies On This Site

      We use cookies to ensure that we give you the best experience on our website.

      Learn more

      Got it!