影像生物标志物标准化倡议：高通量基于影像表型的标准化定量放射组学。
The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.
机构信息
From OncoRay-National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden-Rossendorf, Fetscherstr 74, PF 41, 01307 Dresden, Germany (A.Z., S. Leger, E.G.C.T., C.R., S. Löck); National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany (A.Z.); Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden and Helmholtz Association/Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Dresden, Germany (A.Z., S. Leger, E.G.C.T.); German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany (A.Z., S. Leger, E.G.C.T., C.R., S. Löck); Medical Physics Unit, McGill University, Montréal, Canada (M.V., I.E.N.); Image Response Assessment Team Core Facility, Moffitt Cancer Center, Tampa, Fla (M.A.A.); Dana-Farber Cancer Institute, Brigham and Women's Hospital, and Harvard Medical School, Harvard University, Boston, Mass (H.J.W.L.A.); Institute of Information Systems, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland (V.A., A.D., H.M.); Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY (A.A.); Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, Md (S.A.); Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, Md (S.A., A.R.); Center for Biomedical image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, Pa (S.B., C.D., S.M.H., S.P.); Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pa (S.B., C.D., S.M.H., S.P.); Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pa (S.B.); Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen (UMCG), Groningen, the Netherlands (R.J.B., R.B., E.A.G.P.); Radiology and Nuclear Medicine, VU University Medical Centre (VUMC), Amsterdam, the Netherlands (R.B.); Department of Radiation Oncology, University Hospital Zurich, University of Zurich, Zurich, Switzerland (M.B., M.Guckenberger, S.T.L.); Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Rome, Italy (L.B., N.D., R.G., J.L., V.V.); Laboratoire d'Imagerie Translationnelle en Oncologie, Université Paris Saclay, Inserm, Institut Curie, Orsay, France (I.B., C.N., F.O.); Cancer Imaging Dept, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom (G.J.R.C., V.G., M.M.S.); Department of Nuclear Medicine and Molecular Imaging, Lausanne University Hospital, Lausanne, Switzerland (A.D.); Laboratory of Medical Information Processing (LaTIM)-team ACTION (image-guided therapeutic action in oncology), INSERM, UMR 1101, IBSAM, UBO, UBL, Brest, France (M.C.D., M.H., T.U.); Department of Radiation Oncology, the Netherlands Cancer Institute (NKI), Amsterdam, the Netherlands (C.V.D.); Department of Radiology, Stanford University School of Medicine, Stanford, Calif (S.E., S.N.); Department of Radiation Oncology, Physics Division, University of Michigan, Ann Arbor, Mich (I.E.N., A.U.K.R.); Surgical Planning Laboratory, Brigham and Women's Hospital and Harvard Medical School, Harvard University, Boston, Mass (A.Y.F.); Department of Cancer Imaging and Metabolism, Moffitt Cancer Center, Tampa, Fla (R.J.G.); Department of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany (M. Götz, F.I., K.H.M.H., J.S.); The D-Lab, Department of Precision Medicine, GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, the Netherlands (P.L., R.T.H.L.); Section for Biomedical Physics, Department of Radiation Oncology, University of Tübingen, Germany (F.L., J.S.F., D.T.); Department of Clinical Medicine, University of Bergen, Bergen, Norway (A.L.); Department of Radiation Oncology, University of California, San Francisco, Calif (O.M.); University of Geneva, Geneva, Switzerland (H.M.); Department of Electrical Engineering, Stanford University, Stanford, Calif (S.N.); Department of Medicine (Biomedical Informatics Research), Stanford University School of Medicine, Stanford, Calif (S.N.); Departments of Radiology and Physics, University of British Columbia, Vancouver, Canada (A.R.); Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Mich (A.U.K.R.); Department of Radiation Oncology, University of Groningen, University Medical Center Groningen (UMCG), Groningen, the Netherlands (N.M.S., R.J.H.M.S., L.V.v.D.); School of Engineering, Cardiff University, Cardiff, United Kingdom (E.S., P.W.); Department of Medical Physics, Velindre Cancer Centre, Cardiff, United Kingdom (E.S.); Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany (E.G.C.T., C.R., S. Löck), Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiooncology-OncoRay, Dresden, Germany (E.G.C.T., C.R.); Department of Nuclear Medicine, CHU Milétrie, Poitiers, France (T.U.); Department of Radiology, the Netherlands Cancer Institute (NKI), Amsterdam, the Netherlands (J.v.G.); GROW-School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, the Netherlands (J.v.G.); Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, Mass (J.v.G.); and Department of Radiology, Leiden University Medical Center (LUMC), Leiden, the Netherlands (F.H.P.v.V.).
出版信息
Radiology. 2020 May;295(2):328-338. doi: 10.1148/radiol.2020191145. Epub 2020 Mar 10.
Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 See also the editorial by Kuhl and Truhn in this issue.
背景 放射组学特征可定量评估医学影像中的特征。然而，缺乏标准化的定义和经过验证的参考值限制了其临床应用。目的 标准化一组 174 个放射组学特征。材料与方法 放射组学特征评估分为三个阶段。在第一阶段，从基本的 174 个特征集中衍生出 487 个特征。25 个具有独特放射组学软件实现的研究团队直接从数字体模中计算特征值，无需任何额外的图像处理。在第二阶段，15 个团队使用肺癌患者的 CT 图像和预定义的图像处理配置计算了 1347 个衍生特征的值。在这两个阶段，团队通过模态值的频率来衡量对暂定参考值的有效性达成共识，并分为以下几类：少于三个匹配，弱；三到五个匹配，中等；六到九个匹配，强；十个或更多匹配，很强。在最后阶段（第三阶段），使用来自 51 例软组织肉瘤患者的多模态图像（CT、氟-18 氟代脱氧葡萄糖 PET 和 T1 加权 MRI）的公共数据集，前瞻性评估标准化特征的可重复性。结果 在第一阶段，有 232 个特征（76.8%）和在第二阶段有 703 个特征（65.4%）的参考值最初达成弱共识。在最终迭代中，在第一阶段仅 487 个特征中的 2 个（0.4%）和在第二阶段的 1347 个特征中的 19 个（1.4%）保留弱共识。在第一阶段有 463 个特征（95.1%）和在第二阶段有 1220 个特征（90.6%）达成强或更好的共识。总体而言，在第一和第二阶段有 169 个特征被标准化。在最终验证阶段（第三阶段），大部分 169 个标准化特征都能得到极好的重现（CT 有 166 个；PET 有 164 个；MRI 有 164 个）。结论 一组 169 个放射组学特征已标准化，这使得不同的放射组学软件能够得到验证和校准。 ©2020RSNA 本期杂志中还可见 Kuhl 和 Truhn 的社论。
Zotero 插件