Multiparametric Quantitative Imaging Biomarkers for Phenotype Classification: A Framework for Development and Validation.

Jana G Delfino¹, Gene A Pennello², Huiman X Barnhart³, Andrew J Buckler⁴, Xiaofeng Wang⁵, Erich P Huang⁶, Dave L Raunig⁷, Alexander R Guimaraes⁸, Timothy J Hall⁹, Nandita M deSouza¹⁰, Nancy Obuchowski¹¹

¹Center for Devices and Radiological Health, US Food and Drug Administration, Silver Spring, MD. Electronic address: Jana.Delfino@fda.hhs.gov.

²Center for Devices and Radiological Health, US Food and Drug Administration, Silver Spring, MD.

³Department of Biostatistics and Bioinformatics, Duke University, Durham, NC.

⁴Elucid Bioimaging, Inc, Boston, MA.

⁵Department of Quantitative Health Sciences, Lerner Research Institute, Cleveland Clinic, Cleveland, OH.

⁶Biometric Research Program, Division of Cancer Treatment and Diagnosis - National Cancer Institute, National Institutes of Health, Bethesda, MD.

⁷Data Science Institute, Statistical and Quantitative Sciences, Takeda Pharmaceuticals America Inc, Lexington, MA.

⁸Department of Diagnostic Radiology, Oregon Health & Sciences University, Portland, OR.

⁹Department of Medical Physics, University of Wisconsin, Madison, WI.

¹⁰Division of Radiotherapy and Imaging, the Insitute of Cancer Research and Royal Marsden NHS Foundation Trust, London, United Kingdom; European Imaging Biomarkers Alliance (EIBALL), European Society of Radiology (ESR), Vienna, Austria.

¹¹Department of Quantitative Health Sciences, Lerner Research Institute Cleveland Clinic, Cleveland, OH.

PubMed PMC DOI PDF

Abstract

This manuscript is the third in a five-part series related to statistical assessment methodology for technical performance of multi-parametric quantitative imaging biomarkers (mp-QIBs). We outline approaches and statistical methodologies for developing and evaluating a phenotype classification model from a set of multiparametric QIBs. We then describe validation studies of the classifier for preci…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.