Korean Journal of Radiology

  • 제22권2호
  • /
  • Pages.281-290
  • /
  • 2021
  • /
  • 1229-6929(pISSN)
  • /
  • 2005-8330(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

Content-Based Image Retrieval of Chest CT with Convolutional Neural Network for Diffuse Interstitial Lung Disease: Performance Assessment in Three Major Idiopathic Interstitial Pneumonias

  • Hye Jeon Hwang (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Joon Beom Seo (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Sang Min Lee (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Eun Young Kim (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Beomhee Park (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Hyun-Jin Bae (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Namkug Kim (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine)
  • 투고 : 2020.03.05
  • 심사 : 2020.06.03
  • 발행 : 2021.02.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objective: To assess the performance of content-based image retrieval (CBIR) of chest CT for diffuse interstitial lung disease (DILD). Materials and Methods: The database was comprised by 246 pairs of chest CTs (initial and follow-up CTs within two years) from 246 patients with usual interstitial pneumonia (UIP, n = 100), nonspecific interstitial pneumonia (NSIP, n = 101), and cryptogenic organic pneumonia (COP, n = 45). Sixty cases (30-UIP, 20-NSIP, and 10-COP) were selected as the queries. The CBIR retrieved five similar CTs as a query from the database by comparing six image patterns (honeycombing, reticular opacity, emphysema, ground-glass opacity, consolidation and normal lung) of DILD, which were automatically quantified and classified by a convolutional neural network. We assessed the rates of retrieving the same pairs of query CTs, and the number of CTs with the same disease class as query CTs in top 1-5 retrievals. Chest radiologists evaluated the similarity between retrieved CTs and queries using a 5-scale grading system (5-almost identical; 4-same disease; 3-likelihood of same disease is half; 2-likely different; and 1-different disease). Results: The rate of retrieving the same pairs of query CTs in top 1 retrieval was 61.7% (37/60) and in top 1-5 retrievals was 81.7% (49/60). The CBIR retrieved the same pairs of query CTs more in UIP compared to NSIP and COP (p = 0.008 and 0.002). On average, it retrieved 4.17 of five similar CTs from the same disease class. Radiologists rated 71.3% to 73.0% of the retrieved CTs with a similarity score of 4 or 5. Conclusion: The proposed CBIR system showed good performance for retrieving chest CTs showing similar patterns for DILD.

키워드

참고문헌

  1. Walsh SL, Calandriello L, Sverzellati N, Wells AU, Hansell DM, Consort UIPO. Interobserver agreement for the ATS/ERS/JRS/ALAT criteria for a UIP pattern on CT. Thorax 2016;71:45-51
  2. Watadani T, Sakai F, Johkoh T, Noma S, Akira M, Fujimoto K, et al. Interobserver variability in the CT assessment of honeycombing in the lungs. Radiology 2013;266:936-944
  3. Jacob J, Bartholmai BJ, Rajagopalan S, Kokosi M, Nair A, Karwoski R, et al. Mortality prediction in idiopathic pulmonary fibrosis: evaluation of computer-based CT analysis with conventional severity measures. Eur Respir J 2017;49:1601011
  4. Lee SM, Seo JB, Oh SY, Kim TH, Song JW, Lee SM, et al. Prediction of survival by texture-based automated quantitative assessment of regional disease patterns on CT in idiopathic pulmonary fibrosis. Eur Radiol 2018;28:1293-1300
  5. Salisbury ML, Lynch DA, van Beek EJ, Kazerooni EA, Guo J, Xia M, et al. Idiopathic pulmonary fibrosis: the association between the adaptive multiple features method and fibrosis outcomes. Am J Respir Crit Care Med 2017;195:921-929
  6. Yoon RG, Seo JB, Kim N, Lee HJ, Lee SM, Lee YK, et al. Quantitative assessment of change in regional disease patterns on serial HRCT of fibrotic interstitial pneumonia with texture-based automated quantification system. Eur Radiol 2013;23:692-701
  7. Kim GB, Jung KH, Lee Y, Kim HJ, Kim N, Jun S, et al. Comparison of shallow and deep learning methods on classifying the regional pattern of diffuse lung disease. J Digit Imaging 2018;31:415-424
  8. Depeursinge A, Vargas A, Gaillard F, Platon A, Geissbuhler A, Poletti PA, et al. Case-based lung image categorization and retrieval for interstitial lung diseases: clinical workflows. Int J Comput Assist Radiol Surg 2012;7:97-110
  9. Dhara AK, Mukhopadhyay S, Dutta A, Garg M, Khandelwal N. Content-based image retrieval system for pulmonary nodules: assisting radiologists in self-learning and diagnosis of lung cancer. J Digit Imaging 2017;30:63-77
  10. Oosawa A, Kurosaki A, Kanada S, Takahashi Y, Ogawa K, Hanada S, et al. Development of a CT image case database and content-based image retrieval system for non-cancerous respiratory diseases: method and preliminary assessment. Respir Investig 2019;57:490-498
  11. Park B, Park H, Lee SM, Seo JB, Kim N. Lung segmentation on HRCT and volumetric CT for diffuse interstitial lung disease using deep convolutional neural networks. J Digit Imaging 2019;32:1019-1026
  12. Kundel HL, Polansky M. Measurement of observer agreement. Radiology 2003;228:303-308
  13. Aisen AM, Broderick LS, Winer-Muram H, Brodley CE, Kak AC, Pavlopoulou C, et al. Automated storage and retrieval of thin-section CT images to assist diagnosis: system description and preliminary assessment. Radiology 2003;228:265-270
  14. Muller H, Michoux N, Bandon D, Geissbuhler A. A review of content-based image retrieval systems in medical applications-clinical benefits and future directions. Int J Med Inform 2004;73:1-23
  15. Muller H, Rosset A, Garcia A, Vallee JP, Geissbuhler A. Informatics in radiology (infoRAD): benefits of content-based visual data access in radiology. Radiographics 2005;25:849-858
  16. Sasso G, Marsiglia HR, Pigatto F, Basilicata A, Gargiulo M, Abate AF, et al. A visual query-by-example image database for chest CT images: potential role as a decision and educational support tool for radiologists. J Digit Imaging 2005;18:78-84
  17. Shyu CR, Brodley CE, Kak AC, Kosaka A, Aisen AM, Broderick LS. ASSERT: a physician-in-the-loop content-based retrieval system for HRCT image databases. Comput Vis Image Underst 1999;75:111-132
  18. Brodley C, Kak A, Shyu C, Dy J, Broderick L, Aisen AM. Content-based retrieval from medical image databases: a synergy of human interaction, machine learning and computer vision. Menlo Park: AAAI Press, 1999:760-767
  19. Neveol A, Deserno TM, Darmoni SJ, Guld MO, Aronson AR. Natural language processing versus content-based image analysis for medical document retrieval. J Am Soc Inf Sci Technol 2008;60:123-134
  20. Freer TW, Ulissey MJ. Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. Radiology 2001;220:781-786
  21. Lo SB, Freedman MT, Gillis LB, White CS, Mun SK. JOURNAL CLUB: computer-aided detection of lung nodules on CT with a computerized pulmonary vessel suppressed function. AJR Am J Roentgenol 2018;210:480-488
  22. Roos JE, Paik D, Olsen D, Liu EG, Chow LC, Leung AN, et al. Computer-aided detection (CAD) of lung nodules in CT scans: radiologist performance and reading time with incremental CAD assistance. Eur Radiol 2010;20:549-557
  23. Warren Burhenne LJ, Wood SA, D'Orsi CJ, Feig SA, Kopans DB, O'Shaughnessy KF, et al. Potential contribution of computer-aided detection to the sensitivity of screening mammography. Radiology 2000;215:554-562