Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Radiomics-based Biomarker Validation Study for Region Classification in 2D Prostate Cross-sectional Images

2D 전립선 단면 영상에서 영역 분류를 위한 라디오믹스 기반 바이오마커 검증 연구

  • Jun Young, Park (Medical Devices R&D Center, Gachon University Gil Medical Center) ;
  • Young Jae, Kim (Medical Devices R&D Center, Gachon University Gil Medical Center) ;
  • Jisup, Kim (Department of Pathology, Gachon University College of Medicine) ;
  • Kwang Gi, Kim (Medical Devices R&D Center, Gachon University Gil Medical Center)
  • 박준영 (가천대길병원 의료기기 R&D센터) ;
  • 김영재 (가천대길병원 의료기기 R&D센터) ;
  • 김지섭 (가천대학교 의과대학 병리학교실) ;
  • 김광기 (가천대길병원 의료기기 R&D센터)
  • Received : 2022.10.30
  • Accepted : 2023.01.17
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Recognizing the size and location of prostate cancer is critical for prostate cancer diagnosis, treatment, and predicting prognosis. This paper proposes a model to classify the tumor region and normal tissue with cross-sectional visual images of prostatectomy tissue. We used specimen images of 44 prostate cancer patients who received prostatectomy at Gachon University Gil Hospital. A total of 289 prostate slice images consist of 200 slices including tumor region and 89 slices not including tumor region. Images were divided based on the presence or absence of tumor, and a total of 93 features from each slice image were extracted using Radiomics: 18 first order, 24 GLCM, 16 GLRLM, 16 GLSZM, 5 NGTDM, and 14 GLDM. We compared feature selection techniques such as LASSO, ANOVA, SFS, Ridge and RF, LR, SVM classifiers for the model's high performances. We evaluated the model's performance with AUC of the ROC curve. The results showed that the combination of feature selection techniques LASSO, Ridge, and classifier RF could be best with an AUC of 0.99±0.005.

Keywords

Acknowledgement

본 연구는 경기도의 경기도 지역협력연구센터 사업[GRRC-Gachon2020(B01), AI기반 의료영상분석]과 과학기술정보통신부의 재원으로 한국연구재단의 지원을 받아 수행한 연구임(No. RS-2022-00166555).

References

  1. Zhu Y, Wang H-K, Qu Y-Y, Ye D-W. Prostate cancer in East Asia: evolving trend over the last decade, Asian journal of andrology. 2015;17(1):48.
  2. https://ncc.re.kr/cancerStatsView.ncc?bbsnum=598&searchKey=total&searchValue=&pageNum=1, accessed on Oct, 27, 2022.
  3. Chung BI, Tarin TV, Ferrari JD, James DB. Comparison of prostate cancer tumor volume and percent cancer in prediction of biochemical recurrence and cancer specific survival, Urologic Oncology: Seminars and Original Investigations. 2011;29(3):314-318. https://doi.org/10.1016/j.urolonc.2009.06.017
  4. Akatsuka J, Kimura G, Obayashi K, Mikami H, Sano M, Yanagi M, Yakeda H, Matsuzawa I, Suzuki Y, Hamasaki T. Tumor locations in the prostate gland affect the incidence, clinicopathological features and prognosis of prostate cancer. 2019;18(1):219-220.
  5. Gatti M, Flaletti R, Calleris G, Giglio J, Berzovini C, Gentile F, Marra G, Misischi F, Molinaro L, Bergamasco, Gontero P, Papotti M, Fonio P. Prostate cancer detection with biparametric magnetic resonance imaging (bpMRI) by readers with different experience: performance and comparison with multiparametric (mpMRI), Abdominal Radiology. 2019;44(5):1883-1893. https://doi.org/10.1007/s00261-019-01934-3
  6. Gertych A, Ing N, Ma Z, Fuchs TJ, Salman S, Mohanty S, Bhele S, Velasquez-Vacca A, B.Amin M, S.Kundsen B. Machine learning approaches to analyze histological images of tissues from radical prostatectomies, Computerized Medical Imaging and Graphics. 2016;46:197-208. https://doi.org/10.1016/j.compmedimag.2015.08.002
  7. Rosai J. Why microscopy will remain a cornerstone of surgical pathology. Lab Invest. 2007;87(5):403-8. https://doi.org/10.1038/labinvest.3700551
  8. Mehralivand S, Yang D, Harmon SA, Xu D, Xu Z, Roth H, Masoudi S, Sanford TH, Kesani D, Lay NS, Merino MJ, Wood BJ, Pinto PA, Choyke PL, Turkbey B. A cascaded deep learning--based artificial intelligence algorithm for automated lesion detection and classification on biparametric prostate magnetic resonance imaging, Academic Radiology. 2022;29(8):1159-1168. https://doi.org/10.1016/j.acra.2021.08.019
  9. Tsuneki M, Abe M, Kanavati F. A deep learning model for prostate adenocarcinoma classification in needle biopsy wholeslide images using transfer learning, Diagnostics. 2022;12(3):768.
  10. Han W, Johnson C, Gaed M, Gomez JA, Moussa M, Chin JL, Paulter S, Bauman GS, Ward AD. Histologic tissue components provide major cues for machine learning-based prostate cancer detection and grading on prostatectomy specimens, Scientific reports. 2020;10(1):1-12. https://doi.org/10.1038/s41598-019-56847-4
  11. Renshaw AA. Correlation of gross morphologic features with histologic features in radical prostatectomy specimens, American journal of clinical pathology. 1998;110(1):38-42. https://doi.org/10.1093/ajcp/110.1.38
  12. Barut C, Ertilav H. Guidelines for standard photography in gross and clinical anatomy. Anat Sci Educ. 2011;4(6):348-56. https://doi.org/10.1002/ase.247
  13. Garcia-Alvarez C, Sanchez-Tabernero S, Garcia-Lagarto E, Saornil MA. Black and white box: Take good gross pathology photographs. J Surg Oncol. 2019;119(8):1179-1180. https://doi.org/10.1002/jso.25455
  14. Van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, Beets-Tan RGH, Filion-Robin JC, Pieper S, Aerts HJWL. Computational Radiomics System to Decode the Radiographic Phenotype, Cancer research. 2017;77(21):104-107. https://doi.org/10.1158/1538-7445.AM2017-104
  15. Otsu N. A threshold selection method from gray-level histograms, IEEE transactions on systems, man, and cybernetics. 1979;9(1):62-66. https://doi.org/10.1109/TSMC.1979.4310076
  16. Raid AN, Khedr WM, El-Dosuky MA, Aoud M. Image restoration based on morphological operations, International Journal of Computer Science, Engineering and Information Technology (IJCSEIT). 2014;4(3):9-21. https://doi.org/10.5121/ijcseit.2014.4302
  17. Yang Y, Yan LF, Zhang X, Nan HY, Hu YC, Han Y, Zhang J, Liu ZC, Sun YZ, Tian Q, Yu Y, Sun Q, Wang SY, Zhang X, Wang W, Cui GB. Optimizing texture retrieving model for multimodal MR image-based support vector machine for classifying glioma, Journal of Magnetic Resonance Imaging. 2019;49(5):1263-1274. https://doi.org/10.1002/jmri.26524
  18. Liu QL, Jiang P, Jiang YH, Ge HJ, Li SL, Jin HW, Li YX. Prediction of aneurysm stability using a machine learning model based on PyRadiomics-derived morphological features, Stroke. 2019;50(9):2314-2321. https://doi.org/10.1161/STROKEAHA.119.025777
  19. Kumar V, Gu Y, Basu S, Berglund A, Eschrich SA, Schabath MB, Forster 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
  20. Shi Z, Traverso A, Van Soset J, Dekker A, Wee L. Ontologyguided radiomics analysis workflow (O-RAW), Medical physics. 2019;46(12):5677-5684. https://doi.org/10.1002/mp.13844
  21. Tang J, Aleyani S, Liu H. Feature selection for classification: A review, Data classification: Algorithms and applications. 2014:37.
  22. Bommert A, Sun X, Bischl B, Rahnenfuhrer J, Lang M. Benchmark for filter methods for feature selection in high-dimensional classification data, Computational Statistics & Data Analysis. 2020;143:106839.
  23. Aboudi N El, Benhlima L. Review on wrapper feature selection approaches, 2016 International Conference on Engineering & MIS (ICEMIS). 2016;1-5.
  24. Muthukrishnan R, Rohini R. LASSO: A feature selection technique in predictive modeling for machine learning, 2016 IEEE international conference on advances in computer applications (ICACA). 2016;18-20.
  25. Wang H, Hao F. An efficient linear regression classifier, 2012 IEEE International Conference on Signal Processing, Computing and Control. 2012;1-6.
  26. Azar AT, Elshazly HI, Hassanien AE, Elkorany AM. A random forest classifier for lymph diseases, Computer methods and programs in biomedicine. 2014;113(2):465-473. https://doi.org/10.1016/j.cmpb.2013.11.004
  27. Suthaharan S. Support vector machine, Springer. 2016;207-235.