대한의용생체공학회:의공학회지 (Journal of Biomedical Engineering Research)

  • 제44권1호
  • /
  • Pages.11-18
  • /
  • 2023
  • /
  • 1229-0807(pISSN)
  • /
  • 2288-9396(eISSN)
대한의용생체공학회 (The Korean Society of Medical and Biological Engineering)
권호 표지
DOI QR코드

DOI QR Code

라디오믹스 기반 직장암 수술 위험도 예측을 위한 MRI 반자동 선택 바이오마커 검증 연구

A Study on MRI Semi-Automatically Selected Biomarkers for Predicting Risk of Rectal Cancer Surgery Based on Radiomics

  • 백영서 (가천대길병원 의료기기 R&D센터) ;
  • 김영재 (가천대길병원 의료기기 R&D센터) ;
  • 전영배 (가천대학교 의과대학 길병원 외과학교실 대장항문외과) ;
  • 황태식 (가천대학교 의과대학 길병원 외과학교실 대장항문외과) ;
  • 백정흠 (가천대학교 의과대학 길병원 외과학교실 대장항문외과) ;
  • 김광기 (가천대길병원 의료기기 R&D센터)
  • Young Seo, Baik (Medical Devices R&D Center, Gil Medical Center) ;
  • Young Jae, Kim (Medical Devices R&D Center, Gil Medical Center) ;
  • Youngbae, Jeon (Division of Colon and Rectal Surgery, Department of Surgery, Gil Medical Center, Gachon University College of Medicine) ;
  • Tae-sik, Hwang (Division of Colon and Rectal Surgery, Department of Surgery, Gil Medical Center, Gachon University College of Medicine) ;
  • Jeong-Heum, Baek (Division of Colon and Rectal Surgery, Department of Surgery, Gil Medical Center, Gachon University College of Medicine) ;
  • Kwang Gi, Kim (Medical Devices R&D Center, Gil Medical Center)
  • 투고 : 2022.11.11
  • 심사 : 2022.12.24
  • 발행 : 2023.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Currently, studies to predict the risk of rectal cancer surgery select MRI image slices based on the clinical experience of surgeons. The purpose of this study is to semi-automatically select and classify 2D MRI image slides to predict the risk of rectal cancer surgery using biomarkers. The data used were retrospectively collected MRI imaging data of 50 patients who underwent laparoscopic surgery for rectal cancer at Gachon University Gil Medical Center. Expert-selected MRI image slices and non-selected slices were screened and radiomics was used to extract a total of 102 features. A total of 16 approaches were used, combining 4 classifiers and 4 feature selection methods. The combination of Random Forest and Ridge performed with a sensitivity of 0.83, a specificity of 0.88, an accuracy of 0.85, and an AUC of 0.89±0.09. Differences between expert-selected MRI image slices and non-selected slices were analyzed by extracting the top five significant features. Selected quantitative features help expedite decision making and improve efficiency in studies to predict risk of rectal cancer surgery.

키워드

과제정보

본 연구는 가천대 길병원(FRD2020-19)과 경기도의 경기도 지역협력연구센터 사업의 지원을 받아 수행한 연구임[GRRC-Gachon2020(B01), AI기반 의료영상분석].

참고문헌

  1. Valentini V, Beets-Tan R, Borras JM, Krivokapic Z, Leer JW, Pahlman L, Rodel C, Schmoll HJ, Scott N, Velde CVD, Verfaillie C. Evidence and research in rectal cancer. Radiotherapy and Oncology. 2008;87(3):449-474. https://doi.org/10.1016/j.radonc.2008.05.022
  2. Enker WE. Total mesorectal excision-the new golden standard of surgery for rectal cancer. Annals of medicine. 1997;29(2):127-133. https://doi.org/10.3109/07853899709113698
  3. Shihab OC, Moran BJ, Heald RJ, Quirke P and Brown G. MRI staging of low rectal cancer. European radiology. 2009;19(3):643-650. https://doi.org/10.1007/s00330-008-1184-6
  4. Brown G, Daniels IR, Richardson C, Revell P, Peppercorn D, Bourne M. Techniques and trouble-shooting in high spatial resolution thin slice MRI for rectal cancer. The British journal of radiology. 2005;78(927):245-251. https://doi.org/10.1259/bjr/33540239
  5. Akiyoshi T, Kuroyanagi H, Oya M, Konishi T, Fukuda M, Fujimoto Y, Ueno M, Miyata S, Yamaguchi T. Factors affecting the difficulty of laparoscopic total mesorectal excision with double stapling technique anastomosis for low rectal cancer. Surgery. 2009;146(3):483-489. https://doi.org/10.1016/j.surg.2009.03.030
  6. Chen J, Sun Y, Chi P and Sun BMRI pelvimetry-based evaluation of surgical difficulty in laparoscopic total mesorectal excision after neoadjuvant chemoradiation for male rectal cancer. Surgery today. 2021;51(7):1144-1151 https://doi.org/10.1007/s00595-020-02211-3
  7. Escal L, Nougaret S, Guiu B, Bertrand MM, de Forges H, Tetreau R, Thezenas S, Rouanet P. MRI-based score to predict surgical difficulty in patients with rectal cancer. Journal of British Surgery. 2018;105(1):140-146. https://doi.org/10.1002/bjs.10642
  8. Yamamoto T, Kawada K, Kiyasu Y, Itatani Y, Mizuno R, Hida K, Sakai Y. Prediction of surgical difficulty in minimally invasive surgery for rectal cancer by use of MRI pelvimetry. BJS Open. 2020;4(4):666-677. https://doi.org/10.1002/bjs5.50292
  9. Lee JM, Han YD, Cho MS, Hur H, Min BS, Lee KY, Kim NK. Prediction of transabdominal total mesorectal excision difficulty according to the angle of pelvic floor muscle. Surgical Endoscopy. 2020;34(7):3043-3050. https://doi.org/10.1007/s00464-019-07102-4
  10. Trebeschi S, van Griethuysen JJM, Lambregts DMJ, Lahaye MJ, Parmar C, Bakers FCH, Peters NHGM, Beets-Tan RGH and Aerts HJWL. Deep learning for fully-automated localization and segmentation of rectal cancer on multiparametric MR. Scientific reports. 2017;7(1):1-9. https://doi.org/10.1038/s41598-016-0028-x
  11. Doi K. Current status and future potential of computer-aided diagnosis in medical imaging. The British journal of radiology. 2005;78(suppl_1):s3-s19 https://doi.org/10.1259/bjr/82933343
  12. Kumar V, Gu Y, Basu S, Berglund A, Eschrich SA, Schabath MB, Foster K, Aerts HJWL, Dekker A, Fenstermacher D, Goldgof DB, Hall LO, Lambin P, Balagurunathan Y, Gatenby RA, Gillies RJ. Radiomics: the process and the challenges. Magnetic Resonance Imaging. 2012;30(9):1234-1248. https://doi.org/10.1016/j.mri.2012.06.010
  13. Van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, Beets-Tan RGH, Fillion-Robin JC, Pieper S, Aerts HJWL. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer research. 2017;77(21):e104-e107. https://doi.org/10.1158/0008-5472.CAN-17-0339
  14. Machicado JD, Koay EJ, Krishna SG. Radiomics for the Diagnosis and Differentiation of Pancreatic Cystic Lesions. Diagnostics. 2020;10(7):505.
  15. Zhang S, Yu M, Chen D, Li P, Tang B, Li J. Role of MRI-based radiomics in locally advanced rectal cancer. Oncology Reports. 2022;47(2):1-10. https://doi.org/10.3892/or.2021.8245
  16. Yip SSF, Aerts HJWL. Applications and limitations of radiomics. Physics in Medicine & Biology. 2016;61(13):R150.
  17. Kniep HC, Madesta F, Schneider T, Hanning U, Schonfeld MH, Schon G, Fiehler J, Gauer T, Werner R, Gellissen S. Radiomics of brain MRI: utility in prediction of metastatic tumor type. Radiology. 2019;290(2):479-487. https://doi.org/10.1148/radiol.2018180946
  18. Kandemirli SG, Chopra S, Pyiya S, Ward C, Locke T, Soni N, Srivastava S, Jones K, Bathla G. Presurgical detection of brain invasion status in meningiomas based on first-order histogram-based texture analysis of contrast enhanced imaging. Clinical neurology and neurosurgery. 2020;198:106205.
  19. Mohanaiah P, Sathyanarayana P, GuruKumar I. Image texture feature extraction using GLCM approach. International journal of scientific and research publications. 2013;3(5):1-5.
  20. Ahmadi N, Akbarizadeh G. Iris tissue recognition based on GLDM feature extraction and hybrid MLPNN-ICA classifier. Neural Computing and Applications. 2020;32(7):2267-2281. https://doi.org/10.1007/s00521-018-3754-0
  21. Sohail ASM, Bhattacharya P, Mudur SP, Krishnamurthy S. Local relative GLRLM-based texture feature extraction for classifying ultrasound medical images. 2011 24th Canadian Conference on Electrical and Computer Engineering (CCECE). 2011;:001092-001095.
  22. Thibault G, Angulo J, Meyer F. Advanced statistical matrices for texture characterization: Application to DNA chromatin and microtubule network classification. 2011 18th IEEE International Conference on Image Processing. 2011;53-56.
  23. Amadasun M, King R. Textural features corresponding to textural properties. in IEEE Transactions on Systems, Man, and Cybernetics. 1989;19(5):1264-1274. https://doi.org/10.1109/21.44046
  24. Chandrashekar G, Sahin F. A survey on feature selection methods. Computers & Electrical Engineering. 40.1. 2014;40(1):16-28. https://doi.org/10.1016/j.compeleceng.2013.11.024
  25. Lu M. Embedded feature selection accounting for unknown data heterogeneity. Expert Systems with Applications. 2019;119:350-361 https://doi.org/10.1016/j.eswa.2018.11.006
  26. Yan K, Zhang D. Feature selection and analysis on correlated gas sensor data with recursive feature elimination. Sensors and Actuators B: Chemical. 2015;212:353-363. https://doi.org/10.1016/j.snb.2015.02.025
  27. Biau G, Scornet E. A random forest guided tour. TEST. 2016;25(2):197-227. https://doi.org/10.1007/s11749-016-0481-7
  28. Verma C, Illes Z, Sttofova V. Real-time classification of national and international students for ICT and mobile technology: an experimental study on Indian and Hungarian University. Journal of Physics: Conference Series. 2020;1432(1):012091.