Back to Search
Start Over
Artificial Intelligence Improves the Ability of Physicians to Identify Prostate Cancer Extent.
- Source :
-
The Journal of urology [J Urol] 2024 Jul; Vol. 212 (1), pp. 52-62. Date of Electronic Publication: 2024 Jun 11. - Publication Year :
- 2024
-
Abstract
- Purpose: Defining prostate cancer contours is a complex task, undermining the efficacy of interventions such as focal therapy. A multireader multicase study compared physicians' performance using artificial intelligence (AI) vs standard-of-care methods for tumor delineation.<br />Materials and Methods: Cases were interpreted by 7 urologists and 3 radiologists from 5 institutions with 2 to 23 years of experience. Each reader evaluated 50 prostatectomy cases retrospectively eligible for focal therapy. Each case included a T2-weighted MRI, contours of the prostate and region(s) of interest suspicious for cancer, and a biopsy report. First, readers defined cancer contours cognitively, manually delineating tumor boundaries to encapsulate all clinically significant disease. Then, after ≥ 4 weeks, readers contoured the same cases using AI software. Using tumor boundaries on whole-mount histopathology slides as ground truth, AI-assisted, cognitively-defined, and hemigland cancer contours were evaluated. Primary outcome measures were the accuracy and negative margin rate of cancer contours. All statistical analyses were performed using generalized estimating equations.<br />Results: The balanced accuracy (mean of voxel-wise sensitivity and specificity) of AI-assisted cancer contours (84.7%) was superior to cognitively-defined (67.2%) and hemigland contours (75.9%; P < .0001). Cognitively-defined cancer contours systematically underestimated cancer extent, with a negative margin rate of 1.6% compared to 72.8% for AI-assisted cancer contours ( P < .0001).<br />Conclusions: AI-assisted cancer contours reduce underestimation of prostate cancer extent, significantly improving contouring accuracy and negative margin rate achieved by physicians. This technology can potentially improve outcomes, as accurate contouring informs patient management strategy and underpins the oncologic efficacy of treatment.
- Subjects :
- Humans
Male
Retrospective Studies
Magnetic Resonance Imaging methods
Middle Aged
Prostatectomy methods
Aged
Prostate pathology
Prostate diagnostic imaging
Sensitivity and Specificity
Clinical Competence
Prostatic Neoplasms pathology
Prostatic Neoplasms diagnostic imaging
Prostatic Neoplasms surgery
Artificial Intelligence
Subjects
Details
- Language :
- English
- ISSN :
- 1527-3792
- Volume :
- 212
- Issue :
- 1
- Database :
- MEDLINE
- Journal :
- The Journal of urology
- Publication Type :
- Academic Journal
- Accession number :
- 38860576
- Full Text :
- https://doi.org/10.1097/JU.0000000000003960