ROC or FROC? It depends on the research question.
作者信息
Hillis Stephen L, Chakraborty Dev P, Orton Colin G
机构信息
Departments of Radiology and Biostatistics, The University of Iowa, Iowa City, Iowa, 52242-1077, USA.
ExpertCAD Analytics, LLC, 2103 Noble Court, Murrysville, Pennsylvania, 15668, USA.
出版信息
Med Phys. 2017 May;44(5):1603-1606. doi: 10.1002/mp.12151. Epub 2017 Mar 17.
Abstract
摘要
相似文献
1
ROC or FROC? It depends on the research question.
Med Phys. 2017 May;44(5):1603-1606. doi: 10.1002/mp.12151. Epub 2017 Mar 17.
2
Nonparametric signal detectability evaluation using an exponential transformation of the FROC curve.
Med Phys. 2011 Oct;38(10):5690-702. doi: 10.1118/1.3633938.
3
Perceptually based FROC analysis.
Acad Radiol. 2005 Dec;12(12):1567-74. doi: 10.1016/j.acra.2005.06.015.
4
Bayesian bootstrap estimation of ROC curve.
Stat Med. 2008 Nov 20;27(26):5407-20. doi: 10.1002/sim.3366.
5
Ideal AFROC and FROC observers.
IEEE Trans Med Imaging. 2010 Feb;29(2):375-86. doi: 10.1109/TMI.2009.2031840.
6
On the meaning of the weighted alternative free-response operating characteristic figure of merit.
Med Phys. 2016 May;43(5):2548. doi: 10.1118/1.4947125.
7
[Performance assessment of mammographic diagnostic systems: evolution of methods and their application to a digital image study].
Radiol Med. 1999 Mar;97(3):179-87.
8
Maximum likelihood fitting of FROC curves under an initial-detection-and-candidate-analysis model.
Med Phys. 2002 Dec;29(12):2861-70. doi: 10.1118/1.1524631.
9
How to read a receiver operating characteristic curve.
BMJ. 2015 May 8;350:h2464. doi: 10.1136/bmj.h2464.
10
The interpretation of diagnostic tests.
Stat Methods Med Res. 1999 Jun;8(2):113-34. doi: 10.1177/096228029900800203.
引用本文的文献
1
Evaluating a clinically available artificial intelligence model for intracranial aneurysm detection: a multi-reader study and algorithmic audit.
Neuroradiology. 2025 Apr;67(4):855-864. doi: 10.1007/s00234-024-03536-3. Epub 2025 Jan 15.
2
Fully-automated detection of small bowel carcinoid tumors in CT scans using deep learning.
Med Phys. 2023 Dec;50(12):7865-7878. doi: 10.1002/mp.16391. Epub 2023 Apr 5.
本文引用的文献
1
On the meaning of the weighted alternative free-response operating characteristic figure of merit.
Med Phys. 2016 May;43(5):2548. doi: 10.1118/1.4947125.
2
Computer-aided detection (CADe) and diagnosis (CADx) system for lung cancer with likelihood of malignancy.
Biomed Eng Online. 2016 Jan 6;15(1):2. doi: 10.1186/s12938-015-0120-7.
3
Correlation of free-response and receiver-operating-characteristic area-under-the-curve estimates: results from independently conducted FROC∕ROC studies in mammography.
Med Phys. 2012 Oct;39(10):5917-29. doi: 10.1118/1.4747262.
4
Clinical relevance of the ROC and free-response paradigms for comparing imaging system efficacies.
Radiat Prot Dosimetry. 2010 Apr-May;139(1-3):37-41. doi: 10.1093/rpd/ncq017. Epub 2010 Feb 5.
5
Bias, underestimation of risk, and loss of statistical power in patient-level analyses of lesion detection.
Eur Radiol. 2010 Mar;20(3):584-94. doi: 10.1007/s00330-009-1590-4. Epub 2009 Sep 16.
6
Performance assessments of diagnostic systems under the FROC paradigm: experimental, analytical, and results interpretation issues.
Acad Radiol. 2008 Oct;15(10):1312-5. doi: 10.1016/j.acra.2008.05.006.
7
Nonparametric ROC and LROC analysis.
Med Phys. 2007 May;34(5):1556-64. doi: 10.1118/1.2717407.
8
ROC curves predicted by a model of visual search.
Phys Med Biol. 2006 Jul 21;51(14):3463-82. doi: 10.1088/0031-9155/51/14/013. Epub 2006 Jul 6.
9
Observer studies involving detection and localization: modeling, analysis, and validation.
Med Phys. 2004 Aug;31(8):2313-30. doi: 10.1118/1.1769352.
10
The continuing unethical conduct of underpowered clinical trials.
JAMA. 2002 Jul 17;288(3):358-62. doi: 10.1001/jama.288.3.358.
Zotero 插件