T2-Weighted MRI Radiomic Features Predict Prostate Cancer Presence and Eventual Biochemical Recurrence
by
,
Savannah R. Duenweg
1,
Samuel A. Bobholz
2,
Michael J. Barrett
2,
Allison K. Lowman
2,
Aleksandra Winiarz
1,
Biprojit Nath
1,
Margaret Stebbins
1,
John Bukowy
3,
Kenneth A. Iczkowski
4,
Kenneth M. Jacobsohn
5,
Stephanie Vincent-Sheldon
2 and
Peter S. LaViolette
1,2,6,* 1
Department of Biophysics, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
2
Department of Radiology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
3
Department of Electrical Engineering and Computer Science, Milwaukee School of Engineering, 1025 N Broadway, Milwaukee, WI 53202, USA
4
Department of Pathology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
5
Department of Urology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
6
Department of Biomedical Engineering, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
*
Author to whom correspondence should be addressed.
Cancers 2023, 15(18), 4437; https://doi.org/10.3390/cancers15184437
Submission received: 30 June 2023
/
Revised: 23 August 2023
/
Accepted: 31 August 2023
/
Published: 6 September 2023
(This article belongs to the Special Issue Non-invasive Methods for Screening, Prognosis, and Prediction in Prostate Cancers)
Simple Summary
Prostate cancer (PCa) is the leading non-cutaneous male cancer diagnosis in the United States. This study used radiomic features calculated from T2-weighted magnetic resonance imaging to predict biochemical recurrence (BCR) and PCa presence. A total of 279 patients (n = 46 BCR) undergoing imaging before surgery were analyzed for this study. Radiomic features were calculated for the whole prostate and within pathologist-annotated cancerous lesions. A tree regression model predicted BCR with AUC = 0.97, and a tree classification model classified PCa presence with 89.9% accuracy. This research demonstrates the feasibly of a radiomic features-based tool for screening PCa presence and metastatic risk in a clinical setting.
Abstract
Prostate cancer (PCa) is the most diagnosed non-cutaneous cancer in men. Despite therapies such as radical prostatectomy, which is considered curative, distant metastases may form, resulting in biochemical recurrence (BCR). This study used radiomic features calculated from multi-parametric magnetic resonance imaging (MP-MRI) to evaluate their ability to predict BCR and PCa presence. Data from a total of 279 patients, of which 46 experienced BCR, undergoing MP-MRI prior to surgery were assessed for this study. After surgery, the prostate was sectioned using patient-specific 3D-printed slicing jigs modeled using the T2-weighted imaging (T2WI). Sectioned tissue was stained, digitized, and annotated by a GU-fellowship trained pathologist for cancer presence. Digitized slides and annotations were co-registered to the T2WI and radiomic features were calculated across the whole prostate and cancerous lesions. A tree regression model was fitted to assess the ability of radiomic features to predict BCR, and a tree classification model was fitted with the same radiomic features to classify regions of cancer. We found that 10 radiomic features predicted eventual BCR with an AUC of 0.97 and classified cancer at an accuracy of 89.9%. This study showcases the application of a radiomic feature-based tool to screen for the presence of prostate cancer and assess patient prognosis, as determined by biochemical recurrence.
