Korean Journal of Radiology

  • 제22권6호
  • /
  • Pages.912-921
  • /
  • 2021
  • /
  • 1229-6929(pISSN)
  • /
  • 2005-8330(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

Diagnostic Performance of Deep Learning-Based Lesion Detection Algorithm in CT for Detecting Hepatic Metastasis from Colorectal Cancer

  • Kiwook Kim (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine) ;
  • Sungwon Kim (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine) ;
  • Kyunghwa Han (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine) ;
  • Heejin Bae (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine) ;
  • Jaeseung Shin (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine) ;
  • Joon Seok Lim (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine)
  • 투고 : 2020.04.14
  • 심사 : 2020.12.04
  • 발행 : 2021.06.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objective: To compare the performance of the deep learning-based lesion detection algorithm (DLLD) in detecting liver metastasis with that of radiologists. Materials and Methods: This clinical retrospective study used 4386-slice computed tomography (CT) images and labels from a training cohort (502 patients with colorectal cancer [CRC] from November 2005 to December 2010) to train the DLLD for detecting liver metastasis, and used CT images of a validation cohort (40 patients with 99 liver metastatic lesions and 45 patients without liver metastasis from January 2011 to December 2011) for comparing the performance of the DLLD with that of readers (three abdominal radiologists and three radiology residents). For per-lesion binary classification, the sensitivity and false positives per patient were measured. Results: A total of 85 patients with CRC were included in the validation cohort. In the comparison based on per-lesion binary classification, the sensitivity of DLLD (81.82%, [81/99]) was comparable to that of abdominal radiologists (80.81%, p = 0.80) and radiology residents (79.46%, p = 0.57). However, the false positives per patient with DLLD (1.330) was higher than that of abdominal radiologists (0.357, p < 0.001) and radiology residents (0.667, p < 0.001). Conclusion: DLLD showed a sensitivity comparable to that of radiologists when detecting liver metastasis in patients initially diagnosed with CRC. However, the false positives of DLLD were higher than those of radiologists. Therefore, DLLD could serve as an assistant tool for detecting liver metastasis instead of a standalone diagnostic tool.

키워드

과제정보

This study was supported by a Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2018R1D1A1B07048179).

참고문헌

  1. Qiu M, Hu J, Yang D, Cosgrove DP, Xu R. Pattern of distant metastases in colorectal cancer: a SEER based study. Oncotarget 2015;6:38658-38666
  2. Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2018;68:394-424
  3. Manfredi S, Lepage C, Hatem C, Coatmeur O, Faivre J, Bouvier AM. Epidemiology and management of liver metastases from colorectal cancer. Ann Surg 2006;244:254-259
  4. Hackl C, Neumann P, Gerken M, Loss M, Klinkhammer-Schalke M, Schlitt HJ. Treatment of colorectal liver metastases in Germany: a ten-year population-based analysis of 5772 cases of primary colorectal adenocarcinoma. BMC Cancer 2014;14:810
  5. Engstrand J, Nilsson H, Stromberg C, Jonas E, Freedman J. Colorectal cancer liver metastases - a population-based study on incidence, management and survival. BMC Cancer 2018;18:78
  6. Valls C, Andia E, Sanchez A, Guma A, Figueras J, Torras J, et al. Hepatic metastases from colorectal cancer: preoperative detection and assessment of resectability with helical CT. Radiology 2001;218:55-60
  7. Scheer A, Auer RA. Surveillance after curative resection of colorectal cancer. Clin Colon Rectal Surg 2009;22:242-250
  8. Dhir M, Sasson AR. Surgical management of liver metastases from colorectal cancer. J Oncol Pract 2016;12:33-39
  9. Bilello M, Gokturk SB, Desser T, Napel S, Jeffrey RB Jr, Beaulieu CF. Automatic detection and classification of hypodense hepatic lesions on contrast-enhanced venous-phase CT. Med Phys 2004;31:2584-2593
  10. Schwier M, Moltz JH, Peitgen HO. Object-based analysis of CT images for automatic detection and segmentation of hypodense liver lesions. Int J Comput Assist Radiol Surg 2011;6:737-747
  11. Chi Y, Zhou J, Venkatesh SK, Huang S, Tian Q, Hennedige T, et al. Computer-aided focal liver lesion detection. Int J Comput Assist Radiol Surg 2013;8:511-525
  12. Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016;316:2402-2410
  13. Nam JG, Park S, Hwang EJ, Lee JH, Jin KN, Lim KY, et al. Development and validation of deep learning-based automatic detection algorithm for malignant pulmonary nodules on chest radiographs. Radiology 2019;290:218-228
  14. Wang J, Yang X, Cai H, Tan W, Jin C, Li L. Discrimination of breast cancer with microcalcifications on mammography by deep learning. Sci Rep 2016;6:27327
  15. Yasaka K, Akai H, Abe O, Kiryu S. Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT: a preliminary study. Radiology 2018;286:887-896
  16. Vivanti R, Joskowicz L, Lev-Cohain N, Ephrat A, Sosna J. Patient-specific and global convolutional neural networks for robust automatic liver tumor delineation in follow-up CT studies. Med Biol Eng Comput 2018;56:1699-1713
  17. Yan K, Bagheri M, Summers RM. 3D context enhanced region-based convolutional neural network for end-to-end lesion detection. International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2018:511-519
  18. Horton KM, Abrams RA, Fishman EK. Spiral CT of colon cancer: imaging features and role in management. Radiographics 2000;20:419-430
  19. Seo N, Park MS, Han K, Lee KH, Park SH, Choi GH, et al. Magnetic resonance imaging for colorectal cancer metastasis to the liver: comparative effectiveness research for the choice of contrast agents. Cancer Res Treat 2018;50:60-70
  20. Redmon J, Farhadi A. Yolov3: an incremental improvement. arXiv preprint 2018;arXiv:1804.02767
  21. de Hoop B, De Boo DW, Gietema HA, van Hoorn F, Mearadji B, Schijf L, et al. Computer-aided detection of lung cancer on chest radiographs: effect on observer performance. Radiology 2010;257:532-540
  22. Chakraborty DP, Berbaum KS. Observer studies involving detection and localization: modeling, analysis, and validation. Med Phys 2004;31:2313-2330
  23. Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics 1977;33:159-174
  24. Choi SH, Kim SY, Park SH, Kim KW, Lee JY, Lee SS, et al. Diagnostic performance of CT, gadoxetate disodium-enhanced MRI, and PET/CT for the diagnosis of colorectal liver metastasis: systematic review and meta-analysis. J Magn Reson Imaging 2018;47:1237-1250
  25. Adam R, Delvart V, Pascal G, Valeanu A, Castaing D, Azoulay D, et al. Rescue surgery for unresectable colorectal liver metastases downstaged by chemotherapy: a model to predict long-term survival. Ann Surg 2004;240:644-657; discussion 657-648
  26. Schwartz LH, Gandras EJ, Colangelo SM, Ercolani MC, Panicek DM. Prevalence and importance of small hepatic lesions found at CT in patients with cancer. Radiology 1999;210:71-74
  27. Jones EC, Chezmar JL, Nelson RC, Bernardino ME. The frequency and significance of small (less than or equal to 15 mm) hepatic lesions detected by CT. AJR Am J Roentgenol 1992;158:535-539
  28. Garden OJ, Rees M, Poston GJ, Mirza D, Saunders M, Ledermann J, et al. Guidelines for resection of colorectal cancer liver metastases. Gut 2006;55 Suppl 3:iii1-8