We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Machine Learning Algorithm Accuracy Using Single- versus Multi-Institutional Image Data in the Classification of Prostate MRI Lesions.
- Authors
Provenzano, Destie; Melnyk, Oleksiy; Imtiaz, Danish; McSweeney, Benjamin; Nemirovsky, Daniel; Wynne, Michael; Whalen, Michael; Rao, Yuan James; Loew, Murray; Haji-Momenian, Shawn
- Abstract
Featured Application: The purpose of this study was to determine the efficacy of highly accurate ML classification algorithms trained on prostate image data from one institution and tested on image data from another institution. (1) Background: Recent studies report high accuracies when using machine learning (ML) algorithms to classify prostate cancer lesions on publicly available datasets. However, it is unknown if these trained models generalize well to data from different institutions. (2) Methods: This was a retrospective study using multi-parametric Magnetic Resonance Imaging (mpMRI) data from our institution (63 mpMRI lesions) and the ProstateX-2 challenge, a publicly available annotated image set (112 mpMRI lesions). Residual Neural Network (ResNet) algorithms were trained to classify lesions as high-risk (hrPCA) or low-risk/benign. Models were trained on (a) ProstateX-2 data, (b) local institutional data, and (c) combined ProstateX-2 and local data. The models were then tested on (a) ProstateX-2, (b) local and (c) combined ProstateX-2 and local data. (3) Results: Models trained on either local or ProstateX-2 image data had high Area Under the ROC Curve (AUC)s (0.82–0.98) in the classification of hrPCA when tested on their own respective populations. AUCs decreased significantly (0.23–0.50, p < 0.01) when models were tested on image data from the other institution. Models trained on image data from both institutions re-achieved high AUCs (0.83–0.99). (4) Conclusions: Accurate prostate cancer classification models trained on single-institutional image data performed poorly when tested on outside-institutional image data. Heterogeneous multi-institutional training image data will likely be required to achieve broadly applicable mpMRI models.
- Subjects
MACHINE learning; MAGNETIC resonance imaging; CLASSIFICATION algorithms; TUMOR classification; RECEIVER operating characteristic curves; PROSTATE
- Publication
Applied Sciences (2076-3417), 2023, Vol 13, Issue 2, p1088
- ISSN
2076-3417
- Publication type
Article
- DOI
10.3390/app13021088