[New ultrasound technologies for the diagnostics of prostate cancer]

Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancer

Objective

To investigate the effect of transrectal multimodal ultrasound combined with serum prostate-specific antigen (PSA)-related indicators and machine learning for the diagnosis of clinically significant prostate cancer.

Methods

Based on Gleason score of postoperative pathological results, the subjects were divided into clinically significant prostate cancer groups(GS>6)and non-clinically significant prostate cancer groups(GS ≤ 6). The independent risk factors were obtained by univariate logistic analysis. Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and K-nearest neighbor (KNN) machine learning models were combined with clinically significant prostate cancer risk factors to establish the machine learning model, calculate the model evaluation indicators, construct the receiver operating characteristic curve (ROC), and calculate the area under the curve (AUC).

Results

Independent risk factor items (P< 0.05) were entered into the machine learning model. A comparison of the evaluation indicators of the model and the area under the ROC curve showed the ANN model to be best at predicting clinically significant prostate cancer, with a sensitivity of 80%, specificity of 88.6%, F1 score of 0.897, and the AUC was 0.855.

Conclusion

Establishing a machine learning model by rectal multimodal ultrasound and combining it with PSA-related indicators has definite application value in predicting clinically significant prostate cancer.

Contrast-enhanced transrectal ultrasound can reduce collection of unnecessary biopsies when diagnosing prostate cancer and is predictive of biochemical recurrence following a radical prostatectomy in patients with localized prostate cancer

Background

To investigate the value of using contrast-enhanced transrectal ultrasound (CETRUS) to reduce unnecessary collection of biopsies during prostate cancer diagnosis and its utility in predicting biochemical recurrence in patients with localized prostate cancer.

Methods

This was a prospective study of suspected prostate cancer patients who were evaluated with CETRUS followed by a prostate biopsy. Prostate blood flow via CETRUS was graded using a 5-point scale. The relationship between CETRUS score and biopsy outcome was then analyzed for all patients; univariate and multi-variate analyses were used to determine the probable prognostic factors for biochemical recurrence in patients with localized prostate cancer that underwent a radical prostatectomy.

Results

A total of 347 patients were enrolled in the study. Prostate cancer was found in 164 patients. A significant positive correlation (r = 0.69, p < 0.001) was found between CETRUS scores and prostate cancer incidence. Using CETRUS scores ≥2 as the threshold for when to biopsy could have safely reduced the number of biopsies taken overall by 12.1% (42/347) and spared 23.0% (42/183) of patients from undergoing an unnecessary biopsy. 77 patients with localized prostate cancer underwent a radical prostatectomy. The median follow-up time was 30 months (range: 8–56 months) and 17 of these 77 patients exhibited biochemical recurrence during the follow-up period. 3-year biochemical recurrence-free survival rates were 86% for patients with low CETRUS scores (≤ 3) and 59% for patients with high scores (> 3; p = 0.015). Multivariate Cox regression analysis indicated that CETRUS score was an independent predictor of biochemical recurrence (HR: 7.02; 95% CI: 2.00–24.69; p = 0.002).

Conclusions

CETRUS scores may be a useful tool for reducing the collection unnecessary biopsy samples during prostate cancer diagnosis and are predictive of biochemical recurrence in patients with localized prostate cancer following a radical prostatectomy.