Korean Journal of Radiology

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

DOI QR Code

Deep Learning-Based Computed Tomography Image Standardization to Improve Generalizability of Deep Learning-Based Hepatic Segmentation

  • Seul Bi Lee (Department of Radiology, Seoul National University Hospital) ;
  • Youngtaek Hong (CONNECT-AI R&D Center, Yonsei University College of Medicine) ;
  • Yeon Jin Cho (Department of Radiology, Seoul National University Hospital) ;
  • Dawun Jeong (CONNECT-AI R&D Center, Yonsei University College of Medicine) ;
  • Jina Lee (CONNECT-AI R&D Center, Yonsei University College of Medicine) ;
  • Soon Ho Yoon (Department of Radiology, Seoul National University Hospital) ;
  • Seunghyun Lee (Department of Radiology, Seoul National University Hospital) ;
  • Young Hun Choi (Department of Radiology, Seoul National University Hospital) ;
  • Jung-Eun Cheon (Department of Radiology, Seoul National University Hospital)
  • Received : 2022.08.17
  • Accepted : 2023.01.24
  • Published : 2023.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. Materials and Methods: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. Results: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). Conclusion: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (the Ministry of Science and ICT) (No. NRF-2020R1F1A1077320).

References

  1. Cheng PM, Montagnon E, Yamashita R, Pan I, Cadrin-Chenevert A, Perdigon Romero F, et al. Deep learning: an update for radiologists. Radiographics 2021;41:1427-1445 
  2. McBee MP, Awan OA, Colucci AT, Ghobadi CW, Kadom N, Kansagra AP, et al. Deep learning in radiology. Acad Radiol 2018;25:1472-1480 
  3. Rajpurkar P, Irvin J, Ball RL, Zhu K, Yang B, Mehta H, et al. Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med 2018;15:e1002686 
  4. Joo B, Ahn SS, Yoon PH, Bae S, Sohn B, Lee YE, et al. A deep learning algorithm may automate intracranial aneurysm detection on MR angiography with high diagnostic performance. Eur Radiol 2020;30:5785-5793 
  5. Kuo W, Hane C, Mukherjee P, Malik J, Yuh EL. Expert-level detection of acute intracranial hemorrhage on head computed tomography using deep learning. Proc Natl Acad Sci USA 2019;116:22737-22745 
  6. Willemink MJ, Koszek WA, Hardell C, Wu J, Fleischmann D, Harvey H, et al. Preparing medical imaging data for machine learning. Radiology 2020;295:4-15 
  7. Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al. A guide to deep learning in healthcare. Nat Med 2019;25:24-29 
  8. Park SH, Han K. Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction. Radiology 2018;286:800-809 
  9. Candemir S, Nguyen XV, Folio LR, Prevedello LM. Training strategies for radiology deep learning models in data-limited scenarios. Radiol Artif Intell 2021;3:e210014 
  10. Rauschecker AM, Gleason TJ, Nedelec P, Duong MT, Weiss DA, Calabrese E, et al. Interinstitutional portability of a deep learning brain MRI lesion segmentation algorithm. Radiol Artif Intell 2021;4:e200152 
  11. Eche T, Schwartz LH, Mokrane FZ, Dercle L. Toward generalizability in the deployment of artificial intelligence in radiology: role of computation stress testing to overcome underspecification. Radiol Artif Intell 2021;3:e210097 
  12. Yu AC, Mohajer B, Eng J. External validation of deep learning algorithms for radiologic diagnosis: a systematic review. Radiol Artif Intell 2022;4:e210064 
  13. Lee SB, Cho YJ, Hong Y, Jeong D, Lee J, Kim SH, et al. Deep learning-based image conversion improves the reproducibility of computed tomography radiomics features: a phantom study. Invest Radiol 2022;57:308-317 
  14. Chen C, Bai W, Davies RH, Bhuva AN, Manisty CH, Augusto JB, et al. Improving the generalizability of convolutional neural network-based segmentation on CMR images. Front Cardiovasc Med 2020;7:105 
  15. Shi WZ, Caballero J, Huszar F, Totz J, Aitken AP, Bishop R, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network.com Web site. https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Shi_Real-Time_Single_Image_CVPR_2016_paper.pdf. Published September 23, 2016. Accessed December 20, 2021 
  16. Wang X, Xie L, Dong C, Shan Y. Real-ESRGAN: training realworld blind super-resolution with pure synthetic data.com Web site. https://openaccess.thecvf.com/content/ICCV2021W/AIM/papers/Wang_Real-ESRGAN_Training_Real-World_Blind_Super-Resolution_With_Pure_Synthetic_Data_ICCVW_2021_paper.pdf. Published August 17, 2021. Accessed December 20, 2021 
  17. Johnson J, Alahi A, Fei-Fei L. Perceptual losses for real-time style transfer and super-resolution.com Web site. https://doi.org/10.1007/978-3-319-46475-6_43. Published March 27, 2016. Accessed December 20, 2021 
  18. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets.com Web site. https://papers.nips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf. Published June 10, 2014. Accessed December 20, 2021 
  19. Ledig C, Theis L, Huszar F, Caballero J, Cunningham A, Acosta A, et al. Photo-realistic single image super-resolution using a generative adversarial network.com Web site. https://openaccess.thecvf.com/content_cvpr_2017/papers/Ledig_Photo-Realistic_Single_Image_CVPR_2017_paper.pdf. Published May 25, 2017. Accessed December 20, 2021 
  20. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [Preprint]. [posted September 4, 2014; revised April 10, 2015; cited December 22, 2021] https://arxiv.org/abs/1409.1556 
  21. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv:1412.6980 [Preprint]. [posted December 22, 2014; revised January 30, 2017; cited December 22, 2021] https://doi.org/10.48550/arXiv.1412.6980 
  22. Lin LI. A concordance correlation coefficient to evaluate reproducibility. Biometrics 1989;45:255-268 
  23. Bluemke DA, Moy L, Bredella MA, Ertl-Wagner BB, Fowler KJ, Goh VJ, et al. Assessing radiology research on artificial intelligence: a brief guide for authors, reviewers, and readers-from the radiology editorial board. Radiology 2020;294:487-489 
  24. van Winkel SL, Rodriguez-Ruiz A, Appelman L, Gubern-Merida A, Karssemeijer N, Teuwen J, et al. Impact of artificial intelligence support on accuracy and reading time in breast tomosynthesis image interpretation: a multi-reader multi-case study. Eur Radiol 2021;31:8682-8691 
  25. Quon JL, Han M, Kim LH, Koran ME, Chen LC, Lee EH, et al. Artificial intelligence for automatic cerebral ventricle segmentation and volume calculation: a clinical tool for the evaluation of pediatric hydrocephalus. J Neurosurg Pediatr 2020;27:131-138 
  26. Winkel DJ, Wetterauer C, Matthias MO, Lou B, Shi B, Kamen A, et al. Autonomous detection and classification of PI-RADS lesions in an MRI screening population incorporating multicenter-labeled deep learning and biparametric imaging: proof of concept. Diagnostics (Basel) 2020;10:951 
  27. Kawaguchi K, Kaelbling LP, Bengio Y. Generalization in deep learning. arXiv:1710.05468 [Preprint]. [posted October 16, 2017; revised December 11, 2017; cited December 22, 2021] https://doi.org/10.48550/arXiv.1710.05468 
  28. Futoma J, Simons M, Panch T, Doshi-Velez F, Celi LA. The myth of generalisability in clinical research and machine learning in health care. Lancet Digit Health 2020;2:e489-e492 
  29. Bhuva AN, Bai W, Lau C, Davies RH, Ye Y, Bulluck H, et al. A multicenter, scan-rescan, human and machine learning CMR study to test generalizability and precision in imaging biomarker analysis. Circ Cardiovasc Imaging 2019;12:e009214 
  30. Onofrey JA, Casetti-Dinescu DI, Lauritzen AD, Sarkar S, Venkataraman R, Fan RE, et al. Generalizable multi-site training and testing of deep neural networks using image normalization. Proc IEEE Int Symp Biomed Imaging 2019;2019:348-351 
  31. Sanford TH, Zhang L, Harmon SA, Sackett J, Yang D, Roth H, et al. Data augmentation and transfer learning to improve generalizability of an automated prostate segmentation model. AJR Am J Roentgenol 2020;215:1403-1410 
  32. Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data 2019;6:1-48