Ultrasound-based radiomics score for pre-biopsy prediction of prostate cancer to reduce unnecessary biopsies

Abstract

Background: Patients undergoing prostate biopsies (PBs) suffer from low positive rates and potential risk for complications. This study aimed to develop and validate an ultrasound (US)-based radiomics score for pre-biopsy prediction of prostate cancer (PCa) and subsequently reduce unnecessary PBs.

Methods: Between December 2015 and March 2018, 196 patients undergoing initial transrectal ultrasound (TRUS)-guided PBs were retrospectively enrolled and randomly assigned to the training or validation cohort at a ratio of 7:3. A total of 1044 radiomics features were extracted from grayscale US images of each prostate nodule. After feature selection through the least absolute shrinkage and selection operator (LASSO) regression model, the radiomics score was developed from the training cohort. The prediction nomograms were developed using multivariate logistic regression analysis based on the radiomics score and clinical risk factors. The performance of the nomograms was assessed and compared in terms of discrimination, calibration, and clinical usefulness.

Results: The radiomics score consisted of five selected features. Multivariate logistic regression analysis demonstrated that the radiomics score, age, total prostate-specific antigen (tPSA), and prostate volume were independent factors for prediction of PCa (all p < 0.05). The integrated nomogram incorporating the radiomics score and three clinical risk factors reached an area under the curve (AUC) of 0.835 (95% confidence interval [CI], 0.729-0.941), thereby outperforming the clinical nomogram which based on only clinical factors and yielded an AUC of 0.752 (95% CI, 0.618-0.886) (p = 0.04). Both nomograms showed good calibration. Decision curve analysis indicated that using the integrated nomogram would add more benefit than using the clinical nomogram.

Conclusion: The radiomics score was an independent factor for pre-biopsy prediction of PCa. Addition of the radiomics score to the clinical nomogram shows incremental prognostic value and may help clinicians make precise decisions to reduce unnecessary PBs.

Keywords: nomogram; prostate cancer; radiomics; ultrasound.

Figure 1

The flowchart of this study.

Figure 2

Example of delineating region of interest (ROI) on gray‐scale ultrasound images. The arrow indicates the solitary prostate nodule of a 65‐year‐old man (A). The nodule outline was delineated as the ROI (B). [Color figure can be viewed at wileyonlinelibrary.com]

Figure 3

Radiomics feature selection using the least absolute shrinkage and selection operator (LASSO) regression model in the training cohort. The selection of the optimal penalization coefficient lambda (λ) in the LASSO model used the fivefold cross‐validation (CV) process via minimum criteria. The area under the curve (AUC) was plotted versus log (λ). Dotted vertical lines were drawn at the optimal values using the minimum criteria and the 1 standard error of the minimum criteria (the 1−SE criteria). A λ value of 0.0853 with log (λ) −2.46 was chosen, where optimal λ resulted in five nonzero coefficients. [Color figure can be viewed at wileyonlinelibrary.com]

Figure 4

Two nomograms derived from the training cohort (A, C) and their calibration curves derived from the validation cohort (B, D). Both nomograms demonstrated good agreement in detecting the presence of PCa between prediction and observation in the validation cohort. (A) Clinical nomogram based on age, tPSA, and prostate volume. (B) Calibration curve of the clinical nomogram. (C) Integrated nomogram based on age, tPSA, prostate volume, and radiomics score. (D) Calibration curve of the integrated nomogram. PCa, prostate cancer; PV, prostate volume; Rad‐score, radiomics score; tPSA, total prostate‐specific antigen.

Figure 5

Receiver operating characteristic (ROC) curves of the integrated nomogram (green line), clinical nomogram (blue line), and radiomics score (red line) developed from the training (A) and validation (B) cohorts. Clin‐nom, clinical nomogram; Int‐nom, integrated nomogram; Rad‐score, radiomics score. [Color figure can be viewed at wileyonlinelibrary.com]

Figure 6

Decision curve analysis (DCA) derived from the validation cohort. The y‐axis measures the net benefit. The net benefit is determined by calculating the difference between the expected benefit and the expected harm associated with each proposed model [net benefit = true positive rate − (false positive rate × weighting factor), weighting factor = threshold probability/(1 − threshold probability)]. The gray line represents the assumption that all nodules were malignant (the treat‐all scheme). The black line represents the assumption that all nodules were benign (the treat‐none scheme). If the threshold probability was >10%, using the integrated nomogram (green line) to predict the presence of PCa added more benefit for patients than using the clinical nomogram (blue line). Int‐nom, integrated nomogram; Clin‐nom, clinical nomogram; Rad‐score, radiomics score. [Color figure can be viewed at wileyonlinelibrary.com]