본문 바로가기
KERD
논문KCI 등재

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

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

김지섭|김광기|김영재|박준영
대한의용생체공학회 (The Korea Society Of Medical & Biological Engineering)|2023.02|의공학회지 (Journal of biomedical Engineering Research)|제44권 제1호|pp. 25-32

2

조회

0

다운로드

0

인용

0

참고문헌

키워드

Machine learningFeature selectionProstate cancerRadiomics

초록

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.

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.

참고문헌 (27)

  1. Zhu Y, "Prostate cancer in East Asia : evolving trend over the last decade", Asian journal of andrology, 17(1), pp.48~ (2015)
  3. Chung BI, "Comparison of prostate cancer tumor volume and percent cancer in prediction of biochemical recurrence and cancer specific survival", Urologic Oncology : Seminars and Original Investigations, 29(3), pp.314~318 (2011)
  4. Akatsuka J, "Tumor locations in the prostate gland affect the incidence", clinicopathological features and prognosis of prostate cancer, 18(1), pp.219~220 (2019)
  5. Gatti M, "Prostate cancer detection with biparametric magnetic resonance imaging(bpMRI)by readers with different experience : performance and comparison with multiparametric(mpMRI)", Abdominal Radiology, 44(5), pp.1883~1893 (2019)
  6. Gertych A, "Machine learning approaches to analyze histological images of tissues from radical prostatectomies", Computerized Medical Imaging and Graphics, 46, pp.197~208 (2016)
  7. Rosai J, "Why microscopy will remain a cornerstone of surgical pathology", Lab Invest, 87(5), pp.403~408 (2007)
  8. Mehralivand S, "A cascaded deep learning--based artificial intelligence algorithm for automated lesion detection and classification on biparametric prostate magnetic resonance imaging", Academic Radiology, 29(8), pp.1159~1168 (2022)
  9. Tsuneki M, "A deep learning model for prostate adenocarcinoma classification in needle biopsy wholeslide images using transfer learning", Diagnostics, 12(3), pp.768~ (2022)
  10. Han W, "Histologic tissue components provide major cues for machine learning-based prostate cancer detection and grading on prostatectomy specimens", Scientific reports, 10(1), pp.1~12 (2020)
  11. Renshaw AA, "Correlation of gross morphologic features with histologic features in radical prostatectomy specimens", American journal of clinical pathology, 110(1), pp.38~42 (1998)
  12. Barut C, "Guidelines for standard photography in gross and clinical anatomy", Anat Sci Educ, 4(6), pp.348~356 (2011)
  13. García-Alvarez C, "Black and white box : Take good gross pathology photographs", J Surg Oncol, 119(8), pp.1179~1180 (2019)
  14. Van Griethuysen JJM, "Computational Radiomics System to Decode the Radiographic Phenotype", Cancer research, 77(21), pp.104~107 (2017)
  15. Otsu N, "A threshold selection method from gray-level histograms", IEEE transactions on systems, man, and cybernetics, 9(1), pp.62~66 (1979)
  16. Raid AN, "Image restoration based on morphological operations, International Journal of Computer Science", Engineering and Information Technology(IJCSEIT), 4(3), pp.9~21 (2014)
  17. Yang Y, "Optimizing texture retrieving model for multimodal MR image-based support vector machine for classifying glioma", Journal of Magnetic Resonance Imaging, 49(5), pp.1263~1274 (2019)
  18. Liu QL, "Prediction of aneurysm stability using a machine learning model based on PyRadiomics-derived morphological features", Stroke, 50(9), pp.2314~2321 (2019)
  19. Kumar V, "Radiomics : the process and the challenges", Magnetic resonance imaging, 30(9), pp.1234~1248 (2012)
  20. Shi Z, "Ontologyguided radiomics analysis workflow(O-RAW)", Medical physics, 46(12), pp.5677~5684 (2019)
  21. Tang J, "Feature selection for classification:A review", Data classification: Algorithms and applications, 37 (2014)
  22. Bommert A, "Benchmark for filter methods for feature selection in high-dimensional classification data", Computational Statistics & Data Analysis, 143, pp.106839~ (2020)
  23. Aboudi N El, "Review on wrapper feature selection approaches", 016 International Conference on Engineering & MIS (ICEMIS), pp.1~5 (2016)
  24. Muthukrishnan R, "LASSO: A feature selection technique in predictive modeling for machine learning", 2016IEEE international conference on advances in computer applications (ICACA) (2016)
  25. Wang H, "An efficient linear regression classifier", 2012IEEE International Conference on Signal Processing, Computing and Control, pp.1~6 (2012)
  26. Azar AT, "A random forest classifier for lymph diseases", Computer methods and programs in biomedicine, 113(2), pp.465~473 (2014)
  27. Suthaharan S, "Support vector machine", pp.207~235 (2016), Springer

관련 논문AI추천

라디오믹스 기반 직장암 수술 위험도 예측을 위한 MRI 반자동 선택 바이오마커 검증 연구김광기, 김영재, 백영서, 백정흠, 전영배, 황태식대한의용생체공학회 · 의공학회지2023 · 제44권 제1호Radiomics Reproducibility in Prostate Cancer Diagnosis Based on PROSTATExJae-Seoung Kim, Sumin Jung대한배뇨장애요실금학회 · International Neurourology Journal2025 · 제29권 제4호다중 파라미터 MR 영상 융합과 자기지도학습 모델의 추가 학습을 통한 전립선암 악성도 예측 성능 개선신예진, 이민진, 홍헬렌, 황성일(사)한국컴퓨터그래픽스학회 · 한국컴퓨터그래픽스학회논문지2024 · 제30권 제5호컴퓨터 단층 촬영 영상에서의 전이성 척추 종양의 정량적 분류를 위한 라디오믹스 기반의 머신러닝 기법강혜원, 김광기, 김영재, 이은우, 임상헌, 전지수, 전지영대한의용생체공학회 · 의공학회지2021 · 제42권 제3호후두내시경 영상에서의 라디오믹스에 의한 병변 분류 연구김광기, 김영재, 박준하, 우주현대한의용생체공학회 · 의공학회지2022 · 제43권 제5호초음파 전립선 영상에서 전립선 경계 방향 특징을 이용한 전립선 경계 추출박재흥, 서영건한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2016 · 제21권 제11호

이 간행물의 다른 논문 (11건)

일회용 의료기기에 적용을 위한 ISO 14971:2019 분석과 Periodic Safety Update Report 작성 방법 – Medical Device Regulation 2017/745 요구사항 중심으로유규하, 박상민pp. 1-10라디오믹스 기반 직장암 수술 위험도 예측을 위한 MRI 반자동 선택 바이오마커 검증 연구김영재, 백정흠, 백영서, 황태식, 전영배, 김광기pp. 11-18ISO14971 기반 FMEA를 이용한 중환자실내 인공호흡기 신뢰성 관리김태종, 김원규, 서지영, 김현준pp. 19-24경피적 귀 미주신경 자극이 자율신경계의 활동 및 식후 혈당 변화에 미치는 영향김도용, 이민주, 김현, 조승관, 이한아, 김한성pp. 33-40주요국의 의료기기 품목 분류체계 조사분석을 통한 국내 의료기기 품목 신설 및 세분화 연구김유림, 권경민, 이희성, 장원석, 손지민, 유강현pp. 41-52
원문 보기