본문 바로가기
KERD
논문KCI 등재

Prediction of Microsatellite Instability in Colorectal Cancer Using a Machine Learning Model Based on PET/CT Radiomics

백승혁|김소영|이재훈|박은정|이혜선|이강영|유영훈|강정현|전태주
연세대학교의과대학 (Yonsei University College of Medicine)|2023.05|Yonsei Medical Journal|제64권 제5호|pp. 320-326|DOI 10.3349/ymj.2022.0548

2

조회

0

다운로드

0

인용

0

참고문헌

키워드

machine learningimage analysisColorectal cancerpositron emission tomographymicrosatellite instability
주제분류의학일반

초록

Purpose: We investigated the feasibility of preoperative 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT) radiomics with machine learning to predict microsatellite instability (MSI) status in colorectal can cer (CRC) patients. Materials and Methods: Altogether, 233 patients with CRC who underwent preoperative FDG PET/CT were enrolled and divided into training (n=139) and test (n=94) sets. A PET-based radiomics signature (rad_score) was established to predict the MSI status in patients with CRC. The predictive ability of the rad_score was evaluated using the area under the receiver operating character istic curve (AUROC) in the test set. A logistic regression model was used to determine whether the rad_score was an independent predictor of MSI status in CRC. The predictive performance of rad_score was compared with conventional PET parameters. Results: The incidence of MSI-high was 15 (10.8%) and 10 (10.6%) in the training and test sets, respectively. The rad_score was constructed based on the two radiomic features and showed similar AUROC values for predicting MSI status in the training and test sets (0.815 and 0.867, respectively; p=0.490). Logistic regression analysis revealed that the rad_score was an independent pre dictor of MSI status in the training set. The rad_score performed better than metabolic tumor volume when assessed using the AUROC (0.867 vs. 0.794, p=0.015). Conclusion: Our predictive model incorporating PET radiomic features successfully identified the MSI status of CRC, and it also showed better performance than the conventional PET image parameters.

Abstract

Purpose: We investigated the feasibility of preoperative 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT) radiomics with machine learning to predict microsatellite instability (MSI) status in colorectal can cer (CRC) patients. Materials and Methods: Altogether, 233 patients with CRC who underwent preoperative FDG PET/CT were enrolled and divided into training (n=139) and test (n=94) sets. A PET-based radiomics signature (rad_score) was established to predict the MSI status in patients with CRC. The predictive ability of the rad_score was evaluated using the area under the receiver operating character istic curve (AUROC) in the test set. A logistic regression model was used to determine whether the rad_score was an independent predictor of MSI status in CRC. The predictive performance of rad_score was compared with conventional PET parameters. Results: The incidence of MSI-high was 15 (10.8%) and 10 (10.6%) in the training and test sets, respectively. The rad_score was constructed based on the two radiomic features and showed similar AUROC values for predicting MSI status in the training and test sets (0.815 and 0.867, respectively; p=0.490). Logistic regression analysis revealed that the rad_score was an independent pre dictor of MSI status in the training set. The rad_score performed better than metabolic tumor volume when assessed using the AUROC (0.867 vs. 0.794, p=0.015). Conclusion: Our predictive model incorporating PET radiomic features successfully identified the MSI status of CRC, and it also showed better performance than the conventional PET image parameters.

참고문헌 (41)

  1. Nojadeh JN, "Microsatellite instability in colorectal cancer", EXCLI J, 17, pp.159~168 (2018)
  2. Boland CR, "Microsatellite instability in colorectal cancer", Gastroenterology, 138, pp.2073~2087 (2010)
  3. Bray F, "Global cancer statistics 2018 : GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries", CA Cancer J Clin, 68, pp.394~424 (2018)
  4. Jover R, "The efficacy of adjuvant chemotherapy with 5-fluorouracil in colorectal cancer depends on the mismatch repair status", Eur J Cancer, 45, pp.365~373 (2009)
  5. Lemery S, "First FDA approval agnostic of cancer site-when a biomarker defines the indication", N Engl J Med, 377, pp.1409~1412 (2017)
  6. Kawakami H, "Microsatellite instability testing and its role in the management of colorectal cancer", Curr Treat Options Oncol, 16, pp.30~ (2015)
  7. Chen W, "Molecular genetics of microsatellite-unstable colorectal cancer for pathologists", Diagn Pathol, 12, pp.24~ (2017)
  8. Kawada K, "Relationship between 18F-FDG PET", CT scans and KRAS mutations in metastatic colorectal cancer, 2015, pp.56, 1322~1327
  9. FDG PET, "CT for microvascular invasion and prognosis prediction in very-early-and early-stage hepatocellular carcinoma", Eur J Nucl Med Mol Imaging, 48, pp.2599~2614 (2021)
  10. Nagarajah J, "Correlation of BRAFV600E mutation and glucose metabolism in thyroid cancer patients : an 18F-FDG PET study", J Nucl Med, 56, pp.662~667 (2015)
  11. Zhang J, "Value of pre-therapy 18F-FDG PET", CT radiomics in predicting EGFR mutation status in patients with non-small cell lung cancer, 2020, pp.47, 1137~1146
  12. Chung HW, "Gastric cancers with microsatellite instability exhibit high fluorodeoxyglucose uptake on positron emission tomography", Gastric Cancer, 16, pp.185~192 (2013)
  13. Li J, "Quantitative prediction of microsatellite instability in colorectal cancer with preoperative PET", CT-based radiomics, 2021, pp.11, 702055~
  14. Liu H, "Predictive value of metabolic parameters derived from 18F-FDG PET", CT for microsatellite instability in patients with colorectal carcinoma, 2021, pp.12, 724464~
  15. Nioche C, "LIFEx : a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity", Cancer Res, 78, pp.4786~4789 (2018)
  16. van Griethuysen JJM, "Computational radiomics system to decode the radiographic phenotype", Cancer Res, 77, pp.e104~e107 (2017)
  17. Leijenaar RT, "The effect of SUV discretization in quantitative FDG-PET radiomics : the need for standardized methodology in tumor texture analysis", Sci Rep, 5, pp.11075~ (2015)
  18. 강정현, "Clinical Implications of Microsatellite Instability in T1 Colorectal Cancer", Yonsei Medical Journal, 56(1), pp.175~181 (2015), 연세대학교의과대학[DOI]
  19. Chang C, "A machine learning model based on PET", CT radiomics and clinical characteristics predicts ALK rearrangement status in lung adenocarcinoma, 2021, pp.11, 603882~
  20. Ribic CM, "Tumor microsatellite-instability status as a predictor of benefit from fluorouracil-based adjuvant chemotherapy for colon cancer", N Engl J Med, 349, pp.247~257 (2003)
  21. Watanabe T, "Molecular predictors of survival after adjuvant chemotherapy for colon cancer", N Engl J Med, 344, pp.1196~1206 (2001)
  22. Yamashita R, "Deep learning model for the prediction of microsatellite instability in colorectal cancer : a diagnostic study", Lancet Oncol, 22, pp.132~141 (2021)
  23. Lee SH, "Feasibility of deep learning-based fully automated classification of microsatellite instability in tissue slides of colorectal cancer", Int J Cancer, 149, pp.728~740 (2021)
  24. Echle A, "Clinical-grade detection of microsatellite instability in colorectal tumors by deep learning", Gastroenterology, 159, pp.1406~1416 (2020)
  25. Kather JN, "Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer", Nat Med, 25, pp.1054~1056 (2019)
  26. Cook GJR, "A role for FDG PET radiomics in personalized medicine?", Semin Nucl Med, 50, pp.532~540 (2020)
  27. Aerts HJ, "Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach", Nat Commun, 5, pp.4006~ (2014)
  28. Jiang Y, "Radiomic signature of 18F fluorodeoxyglucose PET", CT for prediction of gastric cancer survival and chemotherapeutic benefits, 2018, pp.8, 5915~5928
  29. 이정원, "Radiomics in Oncological PET", CT: Clinical Applications, 2018, pp.52(3), 170~189[DOI]
  30. FDG PET, "CT associated with genetic alterations of colorectal cancer", Mol Imaging Biol, 21, pp.183~190 (2019)
  31. He J, "Preoperative prediction of regional lymph node metastasis of colorectal cancer based on 18F-FDG PET", CT and machine learning, 2021, pp.35, 617~627
  32. Ma J, "The value of 18FFDG PET", CT-based radiomics in predicting perineural invasion and outcome in non-metastatic colorectal cancer, 2022, pp.47, 1244~1254
  33. Kang J, "Radiomics features of 18F-fluorodeoxyglucose positron-emission tomography as a novel prognostic signature in colorectal cancer", Cancers(Basel), 13, pp.392~ (2021)
  34. Fan S, "Computed tomography-based radiomic features could potentially predict microsatellite instability status in stage II colorectal cancer : a preliminary study", Acad Radiol, 26, pp.1633~1640 (2019)
  35. Golia Pernicka JS, "Radiomics-based prediction of microsatellite instability in colorectal cancer at initial computed tomography evaluation", Abdom Radiol(NY), 44, pp.3755~3763 (2019)
  36. Hildebrand LA, "Artificial intelligence for histology-based detection of microsatellite instability and prediction of response to immunotherapy in colorectal cancer", Cancers(Basel), 13, pp.391~ (2021)
  37. "Image biomarker standardisation initiative" (2016)[URL]
  38. Hotta M, "Prognostic value of 18F-FDG PET", CT with texture analysis in patients with rectal cancer treated by surgery, 2021, pp.35, 843~852
  39. Liao H, "Preoperative radiomic approach to evaluate tumor-infiltrating CD8+ T cells in hepatocellular carcinoma patients using contrast-enhanced computed tomography", Ann Surg Oncol, 26, pp.4537~4547 (2019)
  40. 임형준, "Current Methods to Define Metabolic Tumor Volume in Positron Emission Tomography: Which One is Better?", Nuclear Medicine and Molecular Imaging, 52(1), pp.5~15 (2018), 대한핵의학회
  41. Jun S, "Accurate FDG PET tumor segmentation using the peritumoral halo layer method : a study in patients with esophageal squamous cell carcinoma", Cancer Imaging, 18, pp.35~ (2018)

이 간행물의 다른 논문 (8건)

Dr. Donald S. Mattson and His Service in Gangwon Province윤종원, 이상훈, 고상백, 안성구, 이솔암pp. 297-300Health Effects of Microplastic Exposures: Current Issues and Perspectives in South Korea김창수, 이용진, 조재림, 손정우pp. 301-308Review of North Korean Reports on Cardiovascular Disease Research and Management윤호중, 이정훈, 최윤석, 황준형, 이민지pp. 309-312Combined PCL and PLC Reconstruction Improves Residual Laxity in PCL Injury Patients with Posterolateral Knee Laxity Less Than Grade III오현철, 하중원, 최희민, 윤한국, 박상훈pp. 313-319Impact of Awareness Time Interval on the Effect of Bystander Cardiopulmonary Resuscitation on Out-of-Hospital Cardiac Arrest: A Nationwide Study황승식, 박정호, 신상도, 이선영, 송경준pp. 327-335
원문 보기