| Question 1: The concept of Precision Medicine involves using the following information in tailoring healthcare delivery: |
| Reference: | Collins FS1, Varmus H. A new initiative on precision medicine. N Engl J Med. 2015 Feb 26;372(9):793-5. doi: 10.1056/NEJMp1500523. Epub 2015 Jan 30. |
| Choice A: | Genomics information |
| Choice B: | Proteomics information |
| Choice C: | Radiomics information |
| Choice D: | Metabolomics information |
| Choice E: | A, B, and C |
| Choice F: | A, B, C, and D |
| Question 2: The disease where the concepts of Precision Medicine are most advanced in current patient management is: |
| Reference: | Giuliano AE, Connolly JL, Edge SB, Mittendorf EA, Rugo HS, Solin LJ, Weaver DL, Winchester DJ, Hortobagyi GN. Breast Cancer-Major changes in the American Joint Committee on Cancer eighth edition cancer staging manual. CA Cancer J Clin. 2017 Jul 8;67(4):290-303. doi: 10.3322/caac.21393. Epub 2017 Mar 14. |
| Choice A: | Arteriosclerotic cardiovascular disease |
| Choice B: | Diabetes |
| Choice C: | Breast Cancer |
| Choice D: | Lung cancer |
| Question 3: Which of the following defines radiomics? |
| Reference: | Li H, Zhu Y, Burnside E, Huang E, Drukker K, Hoadley K, Fan C, Conzen S, Zuley M, Net J, Sutton E, Whitman G, Morris E, Perou C, Ji Y, Giger M. Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set. npj Breast Cancer 2, article 16012, 2016 (doi:10.1038/npjbcancer.2016.12) |
| Choice A: | The study of the associations between imaging features and genomic patterns |
| Choice B: | The high throughput extraction of quantitative features from images |
| Choice C: | The conversion of images to mineable data for the purpose of using the data for decision support |
| Choice D: | A) and C) |
| Choice E: | B) and C) |
| Choice F: | A) and B) |
| Question 4: Radiomics studies in breast cancer are being conducted for: |
| Reference: | Li H, Zhu Y, Burnside E, Huang E, Drukker K, Hoadley K, Fan C, Conzen S, Zuley M, Net J, Sutton E, Whitman G, Morris E, Perou C, Ji Y, Giger M. Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set. npj Breast Cancer 2, article 16012, 2016 (doi:10.1038/npjbcancer.2016.12) |
| Choice A: | Prognosis in terms of invasiveness |
| Choice B: | Diagnostic differentiation of malignant from benign tumors |
| Choice C: | Use in discovery studies involving clinical, pathology, and genomic data |
| Choice D: | All of the above |
| Choice E: | None of the above |
| Question 5: Which of the following is currently a limiting factor in the advancement of machine learning healthcare applications? |
| Reference: | Greenspan H., van Ginneken B. and Summers RM. Guest Editorial: Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique. IEEE Trans on Medical Imaging. 2016; 35(5):1153-1159.
Erickson et al. Machine Learning for Medical Imaging. RadioGraphics. 2017;37(2).
Lakhani P et al. Machine Learning in Radiology: Applications Beyond Image Interpretation. J Am Coll Radiol. 2018;15:350-359.
|
| Choice A: | Algorithmic Capabilities |
| Choice B: | Computational Capabilities |
| Choice C: | Data Annotation |
| Choice D: | Data Omission |
| Question 6: Which of the following is currently the most time-intensive step in the machine learning application development pipeline? |
| Reference: | Erickson et al. Machine Learning for Medical Imaging. RadioGraphics. 2017;37(2).
Lakhani P et al. Machine Learning in Radiology: Applications Beyond Image Interpretation. J Am Coll Radiol. 2018;15:350-359.
|
| Choice A: | Cohort Creation |
| Choice B: | Data Anonymization |
| Choice C: | Data Annotation |
| Choice D: | Model Development |
| Question 7: CT screening for lung cancer can improve lung cancer outcomes: |
| Reference: | National Lung Screening Trial Research T, Aberle DR, Adams AM, Berg CD, Black WC, Clapp JD, Fagerstrom RM, Gareen IF, Gatsonis C, Marcus PM, Sicks JD. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 2011; 365: 395-409. |
| Choice A: | By detecting small, surgically-curable lung cancers |
| Choice B: | By reducing symptoms related to metastatic spread of the cancer |
| Choice C: | When used in combination with liquid biopsy and breath-test |
| Choice D: | Never; lung cancer cannot be cured |
| Question 8: In the setting of AI applications, image collections used for feature discriminations of early lung cancer are best obtained from archived DICOM images acquired from what source: |
| Reference: | Reeves AP, Xie Y, Liu S. Automated image quality assessment for chest CT scans. Med Phys. 2018 Feb; 45(2):561-578. doi: 10.1002/mp.12729. Epub 2018 Jan 8. |
| Choice A: | Intensive care unit (ICU) films done with mobile CXR technology |
| Choice B: | CT images performed to measure clinical response in regulatory-directed Phase II clinical trials |
| Choice C: | CT images acquired or assessed for image quality |
| Choice D: | Images produced only by spectral CT |
| Question 9: Which of the following best characterizes the precision of biomarker results when measurements are obtained by two different operators and at times separated by a month? |
| Reference: | Sullivan DC, Obuchowski NA, Kessler LG, et al. Metrology standards for quantitative imaging biomarkers. Radiology 2015; 277(3):813-25 |
| Choice A: | Reproducibility coefficient |
| Choice B: | Repeatability coefficient |
| Choice C: | Root mean square |
| Choice D: | Linearity |
| Question 10: Which of the following characterizes the technical validation of a biomarker? |
| Reference: | Wagner JA, Williams SA, Webster CJ. Biomarkers and surrogate endpoints for fit-for-purpose development and regulatory evaluations of new drugs. Clinical Pharmacology & Therapeutics 2007; 81(1):104-7. |
| Choice A: | A fit-for-purpose evidentiary process linking a biomarker with biological processes and clinical end points |
| Choice B: | Demonstration that the biomarker can substitute for a clinical endpoint in regulatory approvals |
| Choice C: | The determination of the range of conditions under which the measurement will produce accurate and reproducible results |
| Question 11: The Quantitative Imaging Network supports which imaging modalities? |
| Reference: | An Assessment of Imaging Informatics for Precision Medicine in Cancer, C. Chennubhotla, L.P. Clarke, A. Fedorov, D. Foran G. Harris, E. Helton, R. Nordstrom, F. Prior, D. Rubin, J.H. Saltz, E. Shalley, and A. Sharma, IMIA Yearbook of Medical Informatics 2017Aug;26(1):110-119. doi: 10.15265/IY-2017-041 |
| Choice A: | All in-vivo imaging methods. |
| Choice B: | Only imaging methods routinely used in clinical trials. |
| Choice C: | Only modalities produced and supported by Siemens Corp. |
| Choice D: | Imaging methods that do not use targeted agents. |
| Question 12: To become a member of the Quantitative Imaging Network an investigator must: |
| Reference: | Nordstrom RJ, Tomography. 2016 Dec;2(4):239-241. doi: 10.18383/j.tom.2016.00190.PMID: 28083563 |
| Choice A: | Pay an enrollment fee. |
| Choice B: | Write a letter to the network director asking for membership |
| Choice C: | Pass a NIH peer-reviewed study section review. |
| Choice D: | Contact a current member for sponsorship. |
