Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

A Three-Dimensional Deep Convolutional Neural Network for Automatic Segmentation and Diameter Measurement of Type B Aortic Dissection

  • Yitong Yu (Department of Radiology, Fuwai Hospital, Peking Union Medical College & Chinese Academy of Medical Sciences: State Key Lab and National Center for Cardiovascular Diseases) ;
  • Yang Gao (Department of Radiology, Fuwai Hospital, Peking Union Medical College & Chinese Academy of Medical Sciences: State Key Lab and National Center for Cardiovascular Diseases) ;
  • Jianyong Wei (ShuKun (BeiJing) Technology Co., Ltd.) ;
  • Fangzhou Liao (Institute of Information Engineering, Chinese Academy of Sciences) ;
  • Qianjiang Xiao (ShuKun (BeiJing) Technology Co., Ltd.) ;
  • Jie Zhang (Department of Radiology, Fuwai Hospital, Peking Union Medical College & Chinese Academy of Medical Sciences: State Key Lab and National Center for Cardiovascular Diseases) ;
  • Weihua Yin (Department of Radiology, Fuwai Hospital, Peking Union Medical College & Chinese Academy of Medical Sciences: State Key Lab and National Center for Cardiovascular Diseases) ;
  • Bin Lu (Department of Radiology, Fuwai Hospital, Peking Union Medical College & Chinese Academy of Medical Sciences: State Key Lab and National Center for Cardiovascular Diseases)
  • Received : 2020.03.19
  • Accepted : 2020.05.24
  • Published : 2021.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: To provide an automatic method for segmentation and diameter measurement of type B aortic dissection (TBAD). Materials and Methods: Aortic computed tomography angiographic images from 139 patients with TBAD were consecutively collected. We implemented a deep learning method based on a three-dimensional (3D) deep convolutional neural (CNN) network, which realizes automatic segmentation and measurement of the entire aorta (EA), true lumen (TL), and false lumen (FL). The accuracy, stability, and measurement time were compared between deep learning and manual methods. The intra- and inter-observer reproducibility of the manual method was also evaluated. Results: The mean dice coefficient scores were 0.958, 0.961, and 0.932 for EA, TL, and FL, respectively. There was a linear relationship between the reference standard and measurement by the manual and deep learning method (r = 0.964 and 0.991, respectively). The average measurement error of the deep learning method was less than that of the manual method (EA, 1.64% vs. 4.13%; TL, 2.46% vs. 11.67%; FL, 2.50% vs. 8.02%). Bland-Altman plots revealed that the deviations of the diameters between the deep learning method and the reference standard were -0.042 mm (-3.412 to 3.330 mm), -0.376 mm (-3.328 to 2.577 mm), and 0.026 mm (-3.040 to 3.092 mm) for EA, TL, and FL, respectively. For the manual method, the corresponding deviations were -0.166 mm (-1.419 to 1.086 mm), -0.050 mm (-0.970 to 1.070 mm), and -0.085 mm (-1.010 to 0.084 mm). Intra- and inter-observer differences were found in measurements with the manual method, but not with the deep learning method. The measurement time with the deep learning method was markedly shorter than with the manual method (21.7 ± 1.1 vs. 82.5 ± 16.1 minutes, p < 0.001). Conclusion: The performance of efficient segmentation and diameter measurement of TBADs based on the 3D deep CNN was both accurate and stable. This method is promising for evaluating aortic morphology automatically and alleviating the workload of radiologists in the near future.

Keywords

Acknowledgement

The authors thank Dr. Iain Charles Bruce for help in editing the manuscript.

References

  1. Erbel R, Aboyans V, Boileau C, Bossone E, Bartolomeo RD, Eggebrecht H, et al. 2014 ESC guidelines on the diagnosis and treatment of aortic diseases: document covering acute and chronic aortic diseases of the thoracic and abdominal aorta of the adult. The Task Force for the Diagnosis and Treatment of Aortic Diseases of the European Society of Cardiology (ESC). Eur Heart J 2014;35:2873-2926 
  2. Sommer T, Fehske W, Holzknecht N, Smekal AV, Keller E, Lutterbey G, et al. Aortic dissection: a comparative study of diagnosis with spiral CT, multiplanar transesophageal echocardiography, and MR imaging. Radiology 1996;199:347-352 
  3. Kaji S, Akasaka T, Katayama M, Yamamuro A, Yamabe K, Tamita K, et al. Long-term prognosis of patients with type B aortic intramural hematoma. Circulation 2003;108 Suppl 1:II307-II311 
  4. Novelline RA, Rhea JT, Rao PM, Stuk JL. Helical CT in emergency radiology. Radiology 1999;213:321-339 
  5. Hagan PG, Nienaber CA, Isselbacher EM, Bruckman D, Karavite DJ, Russman PL, et al. The International Registry of Acute Aortic Dissection (IRAD): new insights into an old disease. JAMA 2000;283:897-903 
  6. Rengier F, Worz S, Godinez WJ, Schumacher H, Bockler D, Rohr K, et al. Development of in vivo quantitative geometric mapping of the aortic arch for advanced endovascular aortic repair: feasibility and preliminary results. J Vasc Interv Radiol 2011;22:980-986 
  7. Sternbergh WC 3rd, Money SR, Greenberg RK, Chuter TA, Zenith Investigators. Influence of endograft oversizing on device migration, endoleak, aneurysm shrinkage, and aortic neck dilation: results from the Zenith Multicenter Trial. J Vasc Surg 2004;39:20-26 
  8. Muller-Eschner M, Rengier F, Partovi S, Weber TF, Kopp-Schneider A, Geisbusch P, et al. Accuracy and variability of semiautomatic centerline analysis versus manual aortic measurement techniques for TEVAR. Eur J Vasc Endovasc Surg 2013;45:241-247 
  9. Tajik AJ. Machine learning for echocardiographic imaging: embarking on another incredible journey. J Am Coll Cardiol 2016;68:2296-2298 
  10. Wang G. A perspective on deep imaging. IEEE Access 2016;4:8914-8924 
  11. Wang G, Kalra M, Orton CG. Machine learning will transform radiology significantly within the next 5 years. Med Phys 2017;44:2041-2044 
  12. Tian Y, Chen Q, Wang W, Peng Y, Wang Q, Duan F, et al. A vessel active contour model for vascular segmentation. Biomed Res Int 2014;2014:106490 
  13. Chartrand G, Cheng PM, Vorontsov E, Drozdzal M, Turcotte S, Pal CJ, et al. Deep learning: a primer for radiologists. Radiographics 2017;37:2113-2131 
  14. Lee JG, Jun S, Cho YW, Lee H, Kim GB, Seo JB, et al. Deep learning in medical imaging: general overview. Korean J Radiol 2017;18:570-584 
  15. Drozdzal M, Chartrand G, Vorontsov E, Shakeri M, Di Jorio L, Tang A, et al. Learning normalized inputs for iterative estimation in medical image segmentation. Med Image Anal 2018;44:1-13 
  16. Moeskops P, Viergever MA, Mendrik AM, de Vries LS, Benders MJ, Isgum I. Automatic segmentation of MR brain images with a convolutional neural network. IEEE Trans Med Imaging 2016;35:1252-1261 
  17. Pereira S, Pinto A, Alves V, Silva CA. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging 2016;35:1240-1251 
  18. Cao L, Shi R, Ge Y, Xing L, Zuo P, Jia Y, et al. Fully automatic segmentation of type B aortic dissection from CTA images enabled by deep learning. Eur J Radiol 2019;121:108713 
  19. Rengier F, Weber TF, Partovi S, Muller-Eschner M, Bockler D, Kauczor HU, et al. Reliability of semiautomatic centerline analysis versus manual aortic measurement techniques for TEVAR among non-experts. Eur J Vasc Endovasc Surg 2011;42:324-331 
  20. Sedghi Gamechi Z, Bons LR, Giordano M, Bos D, Budde RPJ, Kofoed KF, et al. Automated 3D segmentation and diameter measurement of the thoracic aorta on non-contrast enhanced CT. Eur Radiol 2019;29:4613-4623 
  21. Behrens T, Rohr K, Stiehl HS. Robust segmentation of tubular structures in 3-D medical images by parametric object detection and tracking. IEEE Trans Syst Man Cybern B Cybern 2003;33:554-561 
  22. Li X, Chen H, Qi X, Dou Q, Fu CW, Heng PA. H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation From CT volumes. IEEE Trans Med Imaging 2018;37:2663-2674 
  23. Herment A, Kachenoura N, Lefort M, Bensalah M, Dogui A, Frouin F, et al. Automated segmentation of the aorta from phase contrast MR images: validation against expert tracing in healthy volunteers and in patients with a dilated aorta. J Magn Reson Imaging 2010;31:881-888 
  24. Ben Ayed I, Wang M, Miles B, Garvin GJ. TRIC: trust region for invariant compactness and its application to abdominal aorta segmentation. Med Image Comput Comput Assist Interv 2014;17(Pt 1):381-388 
  25. Sahiner B, Pezeshk A, Hadjiiski LM, Wang X, Drukker K, Cha KH, et al. Deep learning in medical imaging and radiation therapy. Med Phys 2019;46:e1-e36 
  26. Alom MZ, Yakopcic C, Hasan M, Taha TM, Asari VK. Recurrent residual U-Net for medical image segmentation. J Med Imaging (Bellingham) 2019;6:014006