Korean Journal of Radiology

  • 제23권8호
  • /
  • Pages.811-820
  • /
  • 2022
  • /
  • 1229-6929(pISSN)
  • /
  • 2005-8330(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

Feasibility of a Clinical-Radiomics Model to Predict the Outcomes of Acute Ischemic Stroke

  • Yiran Zhou (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Di Wu (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Su Yan (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Yan Xie (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Shun Zhang (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Wenzhi Lv (Department of Artificial Intelligence, Julei Technology) ;
  • Yuanyuan Qin (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Yufei Liu (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Chengxia Liu (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Jun Lu (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Jia Li (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Hongquan Zhu (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Weiyin Vivian Liu (MR Research, GE Healthcare) ;
  • Huan Liu (Advanced Application Team, GE Healthcare) ;
  • Guiling Zhang (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) ;
  • Wenzhen Zhu (Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology)
  • 투고 : 2022.03.14
  • 심사 : 2022.04.26
  • 발행 : 2022.08.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objective: To develop a model incorporating radiomic features and clinical factors to accurately predict acute ischemic stroke (AIS) outcomes. Materials and Methods: Data from 522 AIS patients (382 male [73.2%]; mean age ± standard deviation, 58.9 ± 11.5 years) were randomly divided into the training (n = 311) and validation cohorts (n = 211). According to the modified Rankin Scale (mRS) at 6 months after hospital discharge, prognosis was dichotomized into good (mRS ≤ 2) and poor (mRS > 2); 1310 radiomics features were extracted from diffusion-weighted imaging and apparent diffusion coefficient maps. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator logistic regression method were implemented to select the features and establish a radiomics model. Univariable and multivariable logistic regression analyses were performed to identify the clinical factors and construct a clinical model. Ultimately, a multivariable logistic regression analysis incorporating independent clinical factors and radiomics score was implemented to establish the final combined prediction model using a backward step-down selection procedure, and a clinical-radiomics nomogram was developed. The models were evaluated using calibration, receiver operating characteristic (ROC), and decision curve analyses. Results: Age, sex, stroke history, diabetes, baseline mRS, baseline National Institutes of Health Stroke Scale score, and radiomics score were independent predictors of AIS outcomes. The area under the ROC curve of the clinical-radiomics model was 0.868 (95% confidence interval, 0.825-0.910) in the training cohort and 0.890 (0.844-0.936) in the validation cohort, which was significantly larger than that of the clinical or radiomics models. The clinical radiomics nomogram was well calibrated (p > 0.05). The decision curve analysis indicated its clinical usefulness. Conclusion: The clinical-radiomics model outperformed individual clinical or radiomics models and achieved satisfactory performance in predicting AIS outcomes.

키워드

과제정보

This research was funded by the National Natural Science Foundation of China (grant no: 81730049, 81801666, and 82102024).

참고문헌

  1. Campbell BCV, Khatri P. Stroke. Lancet 2020;396:129-142
  2. Liu Z, Xin H, Chopp M. Axonal remodeling of the corticospinal tract during neurological recovery after stroke. Neural Regen Res 2021;16:939-943
  3. Powers WJ, Rabinstein AA, Ackerson T, Adeoye OM, Bambakidis NC, Becker K, et al. 2018 guidelines for the early management of patients with acute ischemic stroke: a guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke 2018;49:e46-e110
  4. Campbell BCV, De Silva DA, Macleod MR, Coutts SB, Schwamm LH, Davis SM, et al. Ischaemic stroke. Nat Rev Dis Primers 2019;5:70
  5. Barber PA, Powers W. MR DWI does not substitute for stroke severity scores in predicting stroke outcome. Neurology 2006;66:1138-1139
  6. Kim TJ, Lee JS, Oh MS, Kim JW, Yoon JS, Lim JS, et al. Predicting functional outcome based on linked data after acute ischemic stroke: S-SMART score. Transl Stroke Res 2020;11:1296-1305
  7. Barrett KM, Ding YH, Wagner DP, Kallmes DF, Johnston KC; ASAP Investigators. Change in diffusion-weighted imaging infarct volume predicts neurologic outcome at 90 days. Stroke 2009;40:2422-2427
  8. Lestro Henriques I, Gutierrez-Fernandez M, Rodriguez-Frutos B, Ramos-Cejudo J, Otero-Ortega L, Navarro Hernanz T, et al. Intralesional patterns of MRI ADC maps predict outcome in experimental stroke. Cerebrovasc Dis 2015;39:293-301
  9. Rosso C, Colliot O, Pires C, Delmaire C, Valabregue R, Crozier S, et al. Early ADC changes in motor structures predict outcome of acute stroke better than lesion volume. J Neuroradiol 2011;38:105-112
  10. Chen Q, Xia T, Zhang M, Xia N, Liu J, Yang Y. Radiomics in stroke neuroimaging: techniques, applications, and challenges. Aging Dis 2021;12:143-154
  11. Limkin EJ, Sun R, Dercle L, Zacharaki EI, Robert C, Reuze S, et al. Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology. Ann Oncol 2017;28:1191-1206
  12. Kocak B, Durmaz ES, Ates E, Sel I, Turgut Gunes S, Kaya OK, et al. Radiogenomics of lower-grade gliomas: machine learning-based MRI texture analysis for predicting 1p/19q codeletion status. Eur Radiol 2020;30:877-886
  13. Park CJ, Han K, Kim H, Ahn SS, Choi YS, Park YW, et al. Radiomics risk score may be a potential imaging biomarker for predicting survival in isocitrate dehydrogenase wild-type lower-grade gliomas. Eur Radiol 2020;30:6464-6474
  14. Kassner A, Liu F, Thornhill RE, Tomlinson G, Mikulis DJ. Prediction of hemorrhagic transformation in acute ischemic stroke using texture analysis of postcontrast T1-weighted MR images. J Magn Reson Imaging 2009;30:933-941
  15. Betrouni N, Yasmina M, Bombois S, Petrault M, Dondaine T, Lachaud C, et al. Texture features of magnetic resonance images: an early marker of post-stroke cognitive impairment. Transl Stroke Res 2020;11:643-652
  16. Koo TK, Li MY. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med 2016;15:155-163
  17. Zwanenburg A, Vallieres M, Abdalah MA, Aerts HJWL, Andrearczyk V, Apte A, et al. The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 2020;295:328-338
  18. Jiang M, Li C, Tang S, Lv W, Yi A, Wang B, et al. Nomogram based on Shear-Wave elastography radiomics can improve preoperative cervical lymph node staging for papillary thyroid carcinoma. Thyroid 2020;30:885-897
  19. Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 2005;27:1226-1238
  20. Tibshirani R. Regression shrinkage and selection via the lasso: a retrospective. J R Stat Soc 2011;73:273-282
  21. Kramer AA, Zimmerman JE. Assessing the calibration of mortality benchmarks in critical care: the Hosmer-Lemeshow test revisited. Crit Care Med 2007;35:2052-2056
  22. Fitzgerald M, Saville BR, Lewis RJ. Decision curve analysis. JAMA 2015;313:409-410
  23. van Vliet P, Carey L, Nilsson M. Targeting stroke treatment to the individual. Int J Stroke 2012;7:480-481
  24. Qiu W, Kuang H, Nair J, Assis Z, Najm M, McDougall C, et al. Radiomics-based intracranial thrombus features on CT and CTA predict recanalization with intravenous alteplase in patients with acute ischemic stroke. AJNR Am J Neuroradiol 2019;40:39-44
  25. Cui H, Wang X, Bian Y, Song S, Feng DD. Ischemic stroke clinical outcome prediction based on image signature selection from multimodality data. Annu Int Conf IEEE Eng Med Biol Soc 2018;2018:722-725
  26. Tang TY, Jiao Y, Cui Y, Zhao DL, Zhang Y, Wang Z, et al. Penumbra-based radiomics signature as prognostic biomarkers for thrombolysis of acute ischemic stroke patients: a multicenter cohort study. J Neurol 2020;267:1454-1463
  27. Wang H, Sun Y, Ge Y, Wu PY, Lin J, Zhao J, et al. A clinical-radiomics nomogram for functional outcome predictions in ischemic stroke. Neurol Ther 2021;10:819-832
  28. Ali SF, Siddiqui K, Ay H, Silverman S, Singhal A, Viswanathan A, et al. Baseline predictors of poor outcome in patients too good to treat with intravenous thrombolysis. Stroke 2016;47:2986-2992
  29. Rost NS, Bottle A, Lee JM, Randall M, Middleton S, Shaw L, et al. Stroke severity is a crucial predictor of outcome: an international prospective validation study. J Am Heart Assoc 2016;5:e002433
  30. Echouffo-Tcheugui JB, Xu H, Matsouaka RA, Xian Y, Schwamm LH, Smith EE, et al. Diabetes and long-term outcomes of ischaemic stroke: findings from Get With The Guidelines-Stroke. Eur Heart J 2018;39:2376-2386
  31. Andrew N, Kilkenny M, Harris D, Price C, Cadilhac DA. Outcomes for people with atrial fibrillation in an Australian national audit of stroke care. Int J Stroke 2014;9:270-277
  32. Krause DN, Duckles SP, Pelligrino DA. Influence of sex steroid hormones on cerebrovascular function. J Appl Physiol (1985) 2006;101:1252-1261
  33. Lisabeth LD, Reeves MJ, Baek J, Skolarus LE, Brown DL, Zahuranec DB, et al. Factors influencing sex differences in poststroke functional outcome. Stroke 2015;46:860-863
  34. Reeves MJ, Bushnell CD, Howard G, Gargano JW, Duncan PW, Lynch G, et al. Sex differences in stroke: epidemiology, clinical presentation, medical care, and outcomes. Lancet Neurol 2008;7:915-926
  35. Gill D, James NE, Monori G, Lorentzen E, Fernandez-Cadenas I, Lemmens R, et al. Genetically determined risk of depression and functional outcome after ischemic stroke. Stroke 2019;50:2219-2222