대한영상의학회지 (Journal of the Korean Society of Radiology)

  • 제85권4호
  • /
  • Pages.705-713
  • /
  • 2024
  • /
  • 1738-2637(pISSN)
  • /
  • 2288-2928(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

폐결절 검출 인공지능 소프트웨어의 임상적 활용에 관한 연구와 실제 사용 경험

Studies and Real-World Experience Regarding the Clinical Application of Artificial Intelligence Software for Lung Nodule Detection

  • 김정훈 (분당서울대학교병원 영상의학과)
  • Junghoon Kim (Department of Radiology, Seoul National University Bundang Hospital)
  • 투고 : 2024.03.28
  • 심사 : 2024.07.24
  • 발행 : 2024.07.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 종설에서는 모니터코퍼레이션(주)의 폐결절 검출을 위한 인공지능 기반 컴퓨터 보조 병변 검출(artificial intelligence-based computer-aided detection; 이하 AI-CAD) 소프트웨어 LuCAS-plus의 임상적 활용에 관한 연구와 실제 사용 경험을 기술하였다. AI-CAD의 폐암 검진에 대한 임상시험에서는 민감도와 특이도 측면에서 의료진의 판단과 비슷한 수준의 성능을 보였으며, 악성 종양의 폐전이 진단에 적용한 실증연구에서도 높은 검출 성능을 보여주었다. 또한 폐전이 진단에서 AI-CAD와 결절 매칭 알고리즘을 함께 사용할 경우 위양성 결과를 유의하게 감소시킬 수 있었다. 실제 판독에서도 AI-CAD를 적용함으로써 흉부 CT 판독의 정확성을 향상시키고, 판독에 드는 시간과 노력을 절약할 수 있었다. 종합하면, 폐결절 검출 AI-CAD는 폐암 검진과 악성 종양 경과 관찰 흉부 CT 판독에 유의한 도움을 줄 것으로 기대된다.

This article discusses studies and real-world experiences related to the clinical application of artificial intelligence-based computer-aided detection (AI-CAD) software (LuCAS-plus, Monitor Corporation) in detecting pulmonary nodules. During clinical trials for lung cancer screening, AI-CAD exhibited performance comparable to that of medical professionals in terms of sensitivity and specificity. Studies revealed that applying AI-CAD for diagnosing pulmonary metastases led to high detection rates. The use of a nodule matching algorithm in diagnosing pulmonary metastases significantly reduced false non-metastasis results. In clinical settings, implementing AI-CAD enhanced the efficiency of pulmonary nodule detection, saving time and effort during CT reading. Overall, AI-CAD is expected to offer substantial support for lung cancer screening and the interpretation of chest CT scans for malignant tumor surveillance.

키워드

참고문헌

  1. National Lung Screening Trial Research Team; Aberle DR, Adams AM, Berg CD, Black WC, Clapp JD, Fagerstrom RM, et al. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 2011;365:395-409 https://doi.org/10.1056/NEJMoa1102873
  2. de Koning HJ, van der Aalst CM, de Jong PA, Scholten ET, Nackaerts K, Heuvelmans MA, et al. Reduced lung-cancer mortality with volume CT screening in a randomized trial. N Engl J Med 2020;382:503-513 https://doi.org/10.1056/NEJMoa1911793
  3. Chen H, Huang S, Zeng Q, Zhang M, Ni Z, Li X, et al. A retrospective study analyzing missed diagnosis of lung metastases at their early stages on computed tomography. J Thorac Dis 2019;11:3360-3368 https://doi.org/10.21037/jtd.2019.08.19
  4. Committee for Scientific Affairs, The Japanese Association for Thoracic Surgery, Shimizu H, Endo S, Natsugoe S, Doki Y, et al. Thoracic and cardiovascular surgery in Japan in 2016: annual report by the Japanese Association for Thoracic Surgery. Gen Thorac Cardiovasc Surg 2019;67:377-411 https://doi.org/10.1007/s11748-019-01068-9
  5. Kanzaki R, Fukui E, Kanou T, Ose N, Funaki S, Minami M, et al. Preoperative evaluation and indications for pulmonary metastasectomy. J Thorac Dis 2021;13:2590-2602 https://doi.org/10.21037/jtd-19-3791
  6. Petrella F, Diotti C, Rimessi A, Spaggiari L. Pulmonary metastasectomy: an overview. J Thorac Dis 2017;9(Suppl 12):S1291-S1298 https://doi.org/10.21037/jtd.2017.03.175
  7. da Silva GLF, Valente TLA, Silva AC, de Paiva AC, Gattass M. Convolutional neural network-based PSO for lung nodule false positive reduction on CT images. Comput Methods Programs Biomed 2018;162:109-118 https://doi.org/10.1016/j.cmpb.2018.05.006
  8. Dou Q, Chen H, Yu L, Qin J, Heng PA. Multilevel contextual 3-D CNNs for false positive reduction in pulmonary nodule detection. IEEE Trans Biomed Eng 2017;64:1558-1567 https://doi.org/10.1109/TBME.2016.2613502
  9. Li W, Cao P, Zhao D, Wang J. Pulmonary nodule classification with deep convolutional neural networks on computed tomography images. Comput Math Methods Med 2016;2016:6215085
  10. Murphy A, Skalski M, Gaillard F. The utilisation of convolutional neural networks in detecting pulmonary nodules: a review. Br J Radiol 2018;91:20180028
  11. Li L, Liu Z, Huang H, Lin M, Luo D. Evaluating the performance of a deep learning-based computer-aided diagnosis (DL-CAD) system for detecting and characterizing lung nodules: comparison with the performance of double reading by radiologists. Thorac Cancer 2019;10:183-192 https://doi.org/10.1111/1759-7714.12931
  12. Yoon SH, Oh DY, Kim HJ, Jang S, Kim M, Kim J, et al. Usefulness of longitudinal nodule-matching algorithm in computer-aided diagnosis of new pulmonary metastases on cancer surveillance CT scans. Quant Imaging Med Surg 2024;14:1493-1506 https://doi.org/10.21037/qims-23-1174