Prostate Surface Distension and Tumor Texture Descriptors From Pre-Treatment MRI Are Associated With Biochemical Recurrence Following Radical Prostatectomy: Preliminary Findings

Rakesh Shiradkar; Soumya Ghose; Amr Mahran; Lin Li; Isaac Hubbard; Pingfu Fu; Sree Harsha Tirumani; Lee Ponsky; Andrei Purysko; Anant Madabhushi

doi:10.3389/fonc.2022.841801

Prostate Surface Distension and Tumor Texture Descriptors From Pre-Treatment MRI Are Associated With Biochemical Recurrence Following Radical Prostatectomy: Preliminary Findings

Front Oncol. 2022 May 20:12:841801. doi: 10.3389/fonc.2022.841801. eCollection 2022.

Authors

Affiliations

¹ Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States.
² GE Global Research, Niskayuna, NY, United States.
³ Department of Urology, University Hospitals Cleveland Medical Center, Cleveland, OH, United States.
⁴ Department of Population and Quantitative Health Sciences, Case Western Reserve University, Cleveland, OH, United States.
⁵ Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, OH, United States.
⁶ Department of Abdominal Imaging and Nuclear Radiology, Imaging Institute, Cleveland Clinic, Cleveland, OH, United States.

Abstract

Objective: To derive and evaluate the association of prostate shape distension descriptors from T2-weighted MRI (T2WI) with prostate cancer (PCa) biochemical recurrence (BCR) post-radical prostatectomy (RP) independently and in conjunction with texture radiomics of PCa.

Methods: This retrospective study comprised 133 PCa patients from two institutions who underwent 3T-MRI prior to RP and were followed up with PSA measurements for ≥3 years. A 3D shape atlas-based approach was adopted to derive prostate shape distension descriptors from T2WI, and these descriptors were used to train a random forest classifier (C_S ) to predict BCR. Texture radiomics was derived within PCa regions of interest from T2WI and ADC maps, and another machine learning classifier (C_R ) was trained for BCR. An integrated classifier C_S ₊ _R was then trained using predictions from C_S and C_R . These models were trained on D₁ (N = 71, 27 BCR+) and evaluated on independent hold-out set D₂ (N = 62, 12 BCR+). C_S ₊ _R was compared against pre-RP, post-RP clinical variables, and extant nomograms for BCR-free survival (bFS) at 3 years.

Results: C_S ₊ _R resulted in a higher AUC (0.75) compared to C_R (0.70, p = 0.04) and C_S (0.69, p = 0.01) on D₂ in predicting BCR. On univariable analysis, C_S ₊ _R achieved a higher hazard ratio (2.89, 95% CI 0.35-12.81, p < 0.01) compared to other pre-RP clinical variables for bFS. C_S ₊ _R , pathologic Gleason grade, extraprostatic extension, and positive surgical margins were associated with bFS (p < 0.05). C_S ₊ _R resulted in a higher C-index (0.76 ± 0.06) compared to CAPRA (0.69 ± 0.09, p < 0.01) and Decipher risk (0.59 ± 0.06, p < 0.01); however, it was comparable to post-RP CAPRA-S (0.75 ± 0.02, p = 0.07).

Conclusions: Radiomic shape descriptors quantifying prostate surface distension complement texture radiomics of prostate cancer on MRI and result in an improved association with biochemical recurrence post-radical prostatectomy.

Keywords: artificial intelligence; machine learning; magnetic resonance imaging; prostate cancer; prostatectomy; retrospective studies.