Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Quality Reporting of Radiomics Analysis in Mild Cognitive Impairment and Alzheimer's Disease: A Roadmap for Moving Forward

  • So Yeon Won (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine) ;
  • Yae Won Park (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine) ;
  • Mina Park (Department of Radiology, Gangnam Severance Hospital, Yonsei University College of Medicine) ;
  • Sung Soo Ahn (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine) ;
  • Jinna Kim (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine) ;
  • Seung-Koo Lee (Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine)
  • Received : 2020.05.28
  • Accepted : 2020.08.15
  • Published : 2020.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: To evaluate radiomics analysis in studies on mild cognitive impairment (MCI) and Alzheimer's disease (AD) using a radiomics quality score (RQS) system to establish a roadmap for further improvement in clinical use. Materials and Methods: PubMed MEDLINE and EMBASE were searched using the terms 'cognitive impairment' or 'Alzheimer' or 'dementia' and 'radiomic' or 'texture' or 'radiogenomic' for articles published until March 2020. From 258 articles, 26 relevant original research articles were selected. Two neuroradiologists assessed the quality of the methodology according to the RQS. Adherence rates for the following six key domains were evaluated: image protocol and reproducibility, feature reduction and validation, biologic/clinical utility, performance index, high level of evidence, and open science. Results: The hippocampus was the most frequently analyzed (46.2%) anatomical structure. Of the 26 studies, 16 (61.5%) used an open source database (14 from Alzheimer's Disease Neuroimaging Initiative and 2 from Open Access Series of Imaging Studies). The mean RQS was 3.6 out of 36 (9.9%), and the basic adherence rate was 27.6%. Only one study (3.8%) performed external validation. The adherence rate was relatively high for reporting the imaging protocol (96.2%), multiple segmentation (76.9%), discrimination statistics (69.2%), and open science and data (65.4%) but low for conducting test-retest analysis (7.7%) and biologic correlation (3.8%). None of the studies stated potential clinical utility, conducted a phantom study, performed cut-off analysis or calibration statistics, was a prospective study, or conducted cost-effectiveness analysis, resulting in a low level of evidence. Conclusion: The quality of radiomics reporting in MCI and AD studies is suboptimal. Validation is necessary using external dataset, and improvements need to be made to feature reproducibility, feature selection, clinical utility, model performance index, and pursuits of a higher level of evidence.

Keywords

Acknowledgement

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2020R1I1A1A01071648).

References

  1. Hofman A, Rocca WA, Brayne C, Breteler MM, Clarke M, Cooper B, et al. The prevalence of dementia in Europe: a collaborative study of 1980-1990 findings. Eurodem Prevalence Research Group. Int J Epidemiol 1991;20:736-748
  2. Veitch DP, Weiner MW, Aisen PS, Beckett LA, Cairns NJ, Green RC, et al. Understanding disease progression and improving Alzheimer's disease clinical trials: recent highlights from the Alzheimer's disease neuroimaging initiative. Alzheimers Dement 2019;15:106-152
  3. Dubois B, Feldman HH, Jacova C, Dekosky ST, Barberger-Gateau P, Cummings J, et al. Research criteria for the diagnosis of Alzheimer's disease: revising the NINCDS-ADRDA criteria. Lancet Neurol 2007;6:734-746
  4. Dubois B, Feldman HH, Jacova C, Hampel H, Molinuevo JL, Blennow K, et al. Advancing research diagnostic criteria for Alzheimer's disease: the IWG-2 criteria. Lancet Neurol 2014;13:614-629
  5. Jack CR Jr, Bennett DA, Blennow K, Carrillo MC, Dunn B, Haeberlein SB, et al. NIA-AA research framework: toward a biological definition of Alzheimer's disease. Alzheimers Dement 2018;14:535-562
  6. Jack CR Jr, Knopman DS, Jagust WJ, Shaw LM, Aisen PS, Weiner MW, et al. Hypothetical model of dynamic biomarkers of the Alzheimer's pathological cascade. Lancet Neurol 2010;9:119-128
  7. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology 2016;278:563-577
  8. Kang D, Park JE, Kim YH, Kim JH, Oh JY, Kim J, et al. Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation. Neuro Oncol 2018;20:1251-1261
  9. Kickingereder P, Burth S, Wick A, Gotz M, Eidel O, Schlemmer HP, et al. Radiomic profiling of glioblastoma: identifying an imaging predictor of patient survival with improved performance over established clinical and radiologic risk models. Radiology 2016;280:880-889
  10. Park YW, Choi YS, Ahn SS, Chang JH, Kim SH, Lee SK. Radiomics MRI phenotyping with machine learning to predict the grade of lower-grade gliomas: a study focused on nonenhancing tumors. Korean J Radiol 2019;20:1381-1389
  11. Park YW, Han K, Ahn SS, Choi YS, Chang JH, Kim SH, et al. Whole-tumor histogram and texture analyses of DTI for evaluation of IDH1-mutation and 1p/19q-codeletion status in World Health Organization grade II gliomas. AJNR Am J Neuroradiol 2018;39:693-698
  12. Chaddad A, Desrosiers C, Niazi T. Deep radiomic analysis of MRI related to Alzheimer's disease. IEEE Access 2018;6:58213-58221
  13. Maani R, Yang YH, Kalra S. Voxel-based texture analysis of the brain. PLoS One 2015;10:e0117759
  14. Zhang J, Yu C, Jiang G, Liu W, Tong L. 3D texture analysis on MRI images of Alzheimer's disease. Brain Imaging Behav 2012;6:61-69
  15. Rajeesh J, Moni RS, Gopalakrishnan T. Discrimination of Alzheimer's disease using hippocampus texture features from MRI. Asian Biomedicine 2012;6:87-94
  16. Freeborough PA, Fox NC. MR image texture analysis applied to the diagnosis and tracking of Alzheimer's disease. IEEE Trans Med Imaging 1998;17:475-479
  17. Feng Q, Chen Y, Liao Z, Jiang H, Mao D, Wang M, et al. Corpus callosum radiomics-based classification model in Alzheimer's disease: a case-control study. Front Neurol 2018;9:618
  18. Cai JH, He Y, Zhong XL, Lei H, Wang F, Luo GH, et al. Magnetic resonance texture analysis in Alzheimer's disease. Acad Radiol 2020 Feb 10 [Epub]. https://doi.org/10.1016/j.acra.2020.01.006
  19. Zhou H, Jiang J, Lu J, Wang M, Zhang H, Zuo C, et al. Dual-model radiomic biomarkers predict development of mild cognitive impairment progression to Alzheimer's disease. Front Neurosci 2019;12:1045
  20. Li H, Habes M, Wolk DA, Fan Y; Alzheimer's Disease Neuroimaging Initiative and the Australian Imaging Biomarkers and Lifestyle Study of Aging. A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal magnetic resonance imaging data. Alzheimers Dement 2019;15:1059-1070
  21. Lee S, Lee H, Kim KW; Alzheimer's Disease Neuroimaging Initiative. Magnetic resonance imaging texture predicts progression to dementia due to Alzheimer disease earlier than hippocampal volume. J Psychiatry Neurosci 2020;45:7-14
  22. Lambin P, Leijenaar RTH, Deist TM, Peerlings J, De Jong EEC, Van Timmeren J, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 2017;14:749-762
  23. Waterton JC, Pylkkanen L. Qualification of imaging biomarkers for oncology drug development. Eur J Cancer 2012;48:409-415
  24. Sanduleanu S, Woodruff HC, De Jong EEC, Van Timmeren JE, Jochems A, Dubois L, et al. Tracking tumor biology with radiomics: a systematic review utilizing a radiomics quality score. Radiother Oncol 2018;127:349-360
  25. Park JE, Kim D, Kim HS, Park SY, Kim JY, Cho SJ, et al. Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement. Eur Radiol 2020;30:523-536
  26. Park JE, Kim HS, Kim D, Park SY, Kim JY, Cho SJ, et al. A systematic review reporting quality of radiomics research in neuro-oncology: toward clinical utility and quality improvement using high-dimensional imaging features. BMC Cancer 2020;20:29
  27. Oppedal K, Eftestol T, Engan K, Beyer MK, Aarsland D. Classifying dementia using local binary patterns from different regions in magnetic resonance images. Int J Biomed Imaging 2015;2015:572567
  28. Ranjbar S, Velgos SN, Dueck AC, Geda YE, Mitchell JR; Alzheimer's Disease Neuroimaging Initiative. Brain MR radiomics to differentiate cognitive disorders. J Neuropsychiatry Clin Neurosci 2019;31:210-219
  29. Sorensen L, Igel C, Liv Hansen N, Osler M, Lauritzen M, Rostrup E, et al. Early detection of Alzheimer's disease using MRI hippocampal texture. Hum Brain Mapp 2016;37:1148-1161
  30. Ben Bouallegue F, Vauchot F, Mariano-Goulart D, Payoux P. Diagnostic and prognostic value of amyloid PET textural and shape features: comparison with classical semi-quantitative rating in 760 patients from the ADNI-2 database. Brain Imaging Behav 2019;13:111-125
  31. Hett K, Ta VT, Manjon JV, Coupe P; Alzheimer's Disease Neuroimaging Initiative. Adaptive fusion of texture-based grading for Alzheimer's disease classification. Comput Med Imaging Graph 2018;70:8-16
  32. Rohini P, Sundar S, Ramakrishnan S. Characterization of Alzheimer conditions in MR images using volumetric and sagittal brainstem texture features. Comput Methods Programs Biomed 2019;173:147-155
  33. Tozer DJ, Zeestraten E, Lawrence AJ, Barrick TR, Markus HS. Texture analysis of T1-weighted and fluid-attenuated inversion recovery images detects abnormalities that correlate with cognitive decline in small vessel disease. Stroke 2018;49:1656-1661
  34. De Oliveira MS, Balthazar ML, D'abreu A, Yasuda C, Damasceno B, Cendes F, et al. MR imaging texture analysis of the corpus callosum and thalamus in amnestic mild cognitive impairment and mild Alzheimer disease. AJNR Am J Neuroradiol 2011;32:60-66
  35. Lopez-Gomez C, Ortiz-Ramon R, Molla-Olmos E, Moratal D; Alzheimer's Disease Neuroimaging Initiative, Initiative AsDN. ALTEA: a software tool for the evaluation of new biomarkers for Alzheimer's disease by means of textures analysis on magnetic resonance images. Diagnostics (Basel) 2018;8:47
  36. Hwang EJ, Kim HG, Kim D, Rhee HY, Ryu CW, Liu T, et al. Texture analyses of quantitative susceptibility maps to differentiate Alzheimer's disease from cognitive normal and mild cognitive impairment. Med Phys 2016;43:4718
  37. Feng F, Wang P, Zhao K, Zhou B, Yao H, Meng Q, et al. Radiomic features of hippocampal subregions in Alzheimer's disease and amnestic mild cognitive impairment. Front Aging Neurosci 2018;10:290
  38. Gao N, Tao LX, Huang J, Zhang F, Li X, O'Sullivan F, et al. Contourlet-based hippocampal magnetic resonance imaging texture features for multivariant classification and prediction of Alzheimer's disease. Metab Brain Dis 2018;33:1899-1909
  39. Martinez-Torteya A, Rodriguez-Rojas J, Celaya-Padilla JM, Galvan-Tejada JI, Trevino V, Tamez-Pena J. Magnetization-prepared rapid acquisition with gradient echo magnetic resonance imaging signal and texture features for the prediction of mild cognitive impairment to Alzheimer's disease progression. J Med Imaging (Bellingham) 2014;1:031005
  40. Feng Q, Song Q, Wang M, Pang P, Liao Z, Jiang H, et al. Hippocampus radiomic biomarkers for the diagnosis of amnestic mild cognitive impairment: a machine learning method. Front Aging Neurosci 2019;11:323
  41. Vaithinathan K, Parthiban L; Alzheimer's Disease Neuroimaging Initiative. A novel texture extraction technique with T1 weighted MRI for the classification of Alzheimer's disease. J Neurosci Methods 2019;318:84-99
  42. Li Y, Jiang J, Lu J, Jiang J, Zhang H, Zuo C. Radiomics: a novel feature extraction method for brain neuron degeneration disease using 18F-FDG PET imaging and its implementation for Alzheimer's disease and mild cognitive impairment. Ther Adv Neurol Disord 2019;12:1756286419838682
  43. Achterberg HC, Sorensen L, Wolters FJ, Niessen WJ, Vernooij MW, Ikram MA, et al. The value of hippocampal volume, shape, and texture for 11-year prediction of dementia: a population-based study. Neurobiol Aging 2019;81:58-66
  44. Jack CR Jr, Bernstein MA, Fox NC, Thompson P, Alexander G, Harvey D, et al. The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods. J Magn Reson Imaging 2008;27:685-691
  45. Saykin AJ, Shen L, Yao X, Kim S, Nho K, Risacher SL, et al. Genetic studies of quantitative MCI and AD phenotypes in ADNI: progress, opportunities, and plans. Alzheimers Dement 2015;11:792-814
  46. Den Heijer T, Oudkerk M, Launer LJ, Van Duijn CM, Hofman A, Breteler MM. Hippocampal, amygdalar, and global brain atrophy in different apolipoprotein E genotypes. Neurology 2002;59:746-748
  47. Moffat SD, Szekely CA, Zonderman AB, Kabani NJ, Resnick SM. Longitudinal change in hippocampal volume as a function of apolipoprotein E genotype. Neurology 2000;55:134-136
  48. Park JE, Park SY, Kim HJ, Kim HS. Reproducibility and generalizability in radiomics modeling: possible strategies in radiologic and statistical perspectives. Korean J Radiol 2019;20:1124-1137
  49. Boccardi M, Gallo V, Yasui Y, Vineis P, Padovani A, Mosimann U, et al. The biomarker-based diagnosis of Alzheimer's disease. 2-lessons from oncology. Neurobiol Aging 2017;52:141-152