Evaluation of a Cascaded Deep Learning–based Algorithm for Prostate Lesion Detection at Biparametric MRI

A deep learning–based algorithm automatically detected cancerous lesions on prostate biparametric MRI scans with reasonable performance and reliably predicted clinically significant prostate cancer at biopsy.

Saved in:
Bibliographic Details
Published inRadiology Vol. 311; no. 2; p. e230750
Main Authors Lin, Yue, Yilmaz, Enis C., Belue, Mason J., Harmon, Stephanie A., Tetreault, Jesse, Phelps, Tim E., Merriman, Katie M., Hazen, Lindsey, Garcia, Charisse, Yang, Dong, Xu, Ziyue, Lay, Nathan S., Toubaji, Antoun, Merino, Maria J., Xu, Daguang, Law, Yan Mee, Gurram, Sandeep, Wood, Bradford J., Choyke, Peter L., Pinto, Peter A., Turkbey, Baris
Format Journal Article
LanguageEnglish
Published United States Radiological Society of North America 01.05.2024
Subjects
Aged
Algorithms
Deep Learning
Humans
Image Interpretation, Computer-Assisted - methods
Image-Guided Biopsy - methods
Magnetic Resonance Imaging - methods
Male
Middle Aged
Multiparametric Magnetic Resonance Imaging - methods
Original Research
Prospective Studies
Prostate - diagnostic imaging
Prostate - pathology
Prostatic Neoplasms - diagnostic imaging
Prostatic Neoplasms - pathology
Online AccessGet full text
ISSN0033-8419
1527-1315
1527-1315
DOI10.1148/radiol.230750

Cover

More Information
Summary:A deep learning–based algorithm automatically detected cancerous lesions on prostate biparametric MRI scans with reasonable performance and reliably predicted clinically significant prostate cancer at biopsy.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Disclosures of conflicts of interest: Y.L. No relevant relationships. E.C.Y. Associate editor on the Radiology In Training Editorial Board. M.J.B. No relevant relationships. S.A.H. Institution (National Cancer Institute) has a cooperative research and development agreement with NVIDIA. J.T. This work was completed under a cooperative research and development agreement between the National Institutes of Health (NIH) and NVIDIA. T.E.P. No relevant relationships. K.M.M. No relevant relationships. L.H. No relevant relationships. C.G. No relevant relationships. D.Y. No relevant relationships. Z.X. No relevant relationships. N.S.L. This research supported by NIH Intramural Research Program; receives shared royalties from NIH for an unrelated prostate cancer detection system patent (US patent no. US11200667B2). A.T. No relevant relationships. M.J.M. No relevant relationships. D.X. No relevant relationships. Y.M.L. No relevant relationships. S.G. No relevant relationships. B.J.W. Institution (NIH) and NVIDIA have a cooperative research and development agreement; NIH and Philips have a cooperative research and development agreement that includes work in the space of prostate cancer and also artificial intelligence; principal investigator on cooperative research and development agreements between NIH and Philips, Celsion, Biocompatibles, Boston Scientific, Siemens, NVIDIA, XACT Robotics, and Promaxo; support for research from 3T Technologies (devices), Exact Imaging (data), AngioDynamics (equipment), AstraZeneca (pharmaceuticals, National Cancer Institute cooperative research and development agreement), ArciTrax (devices and equipment), Johnson & Johnson (equipment), Medtronic (equipment), Theromics (supplies), Profound Medical (equipment and supplies), QT Imaging (equipment and supplies), Boston Scientific (equipment), Varian (materials), Combat Medical (equipment), Clinical LaserThermia Systems (equipment), MediView (equipment), CIVCO Medical Solutions (equipment), Galvanize (equipment); royalties from a patent licensing agreement between Philips and NIH; licensing agreements between NIH and NVIDIA and Canon; NIH and CIVCO are coinventors of intellectual property; NIH and ArciTrax are coinventors of intellectual property; NIH and Philips are coinventors of intellectual property; NIH and Boston Scientific are coinventors of intellectual property; NIH and NVIDIA are coinventors of intellectual property; NIH may own intellectual property in the field; another nonlicensed family of patents available upon request (includes 50 patents); editor of Springer book, Interventional Urology, 2nd Edition, which may contain indirect mention of the topic of this work; NIH liaison to Academy for Radiology & Biomedical Imaging Research; and NIH liaison to Society of Interventional Oncology. P.L.C. Patents planned, issued, or pending with Philips Medical Systems and NVIDIA (author does not receive royalty payments). P.A.P. Royalties from a licensing agreement between Philips and institution (NIH); cooperative research and development agreement between NIH and Philips; NIH has intellectual property in the field including, among other patents and patent applications, System and Method for Prostate Cancer Detection and Distribution Mapping (US patent no. 8,447,384) and System and Method for Computer Aided Cancer Detection Using T2-weighted and High-Value Diffusion-weighted Magnetic Resonance Imaging (US patent no. 10,215,830); and licensing agreement with NIH and Philips (Invivo). B.T. Cooperative research and development agreement with NVIDIA and Philips and receives royalties from NIH.
Author contributions: Guarantors of integrity of entire study, Y.L., M.J.B., L.H., P.A.P., B.T.; study concepts/study design or data acquisition or data analysis/interpretation, all authors; manuscript drafting or manuscript revision for important intellectual content, all authors; approval of final version of submitted manuscript, all authors; agree to ensure any questions related to the work are appropriately resolved, all authors; literature research, Y.L., E.C.Y., M.J.B., D.Y., Z.X., B.J.W., B.T.; clinical studies, Y.L., E.C.Y., M.J.B., L.H., C.G., D.Y., A.T., M.J.M., Y.M.L., S.G., B.J.W., P.L.C., P.A.P., B.T.; experimental studies, Y.L., E.C.Y., M.J.B., S.A.H., J.T., D.Y., Z.X., Y.M.L., B.J.W., B.T.; statistical analysis, Y.L., M.J.B., S.A.H., J.T., D.Y., Z.X., Y.M.L., P.A.P., B.T.; and manuscript editing, Y.L., E.C.Y., M.J.B., S.A.H., T.E.P., K.M.M., L.H., Z.X., N.S.L., M.J.M., D.X., Y.M.L., S.G., B.J.W., P.L.C., P.A.P., B.T.
ISSN:0033-8419
1527-1315
1527-1315
DOI:10.1148/radiol.230750