Development of a nomogram combining multiparametric magnetic resonance imaging and PSA-related parameters to enhance the detection of clinically significant cancer across different region

Radiomics from multisite MRI and clinical data to predict clinically significant prostate cancer

BACKGROUND

Magnetic resonance imaging (MRI) is useful in the diagnosis of clinically significant prostate cancer (csPCa). MRI-derived radiomics may support the diagnosis of csPCa.

PURPOSE

To investigate whether adding radiomics from biparametric MRI to predictive models based on clinical and MRI parameters improves the prediction of csPCa in a multisite-multivendor setting.

MATERIAL AND METHODS

Clinical information (PSA, PSA density, prostate volume, and age), MRI reviews (PI-RADS 2.1), and radiomics (histogram and texture features) were retrieved from prospectively included patients examined at different radiology departments and with different MRI systems, followed by MRI-ultrasound fusion guided biopsies of lesions PI-RADS 3-5. Predictive logistic regression models of csPCa (Gleason score ≥7) for the peripheral (PZ) and transition zone (TZ), including clinical data and PI-RADS only, and combined with radiomics, were built and compared using receiver operating characteristic (ROC) curves.

RESULTS

In total, 456 lesions in 350 patients were analyzed. In PZ and TZ, PI-RADS 4-5 and PSA density, and age in PZ, were independent predictors of csPCa in models without radiomics. In models including radiomics, PI-RADS 4-5, PSA density, age, and ADC energy were independent predictors in PZ, and PI-RADS 5, PSA density and ADC mean in TZ. Comparison of areas under the ROC curve (AUC) for the models without radiomics (PZ: AUC = 0.82, TZ: AUC = 0.80) versus with radiomics (PZ: AUC = 0.82, TZ: AUC = 0.82) showed no significant differences (PZ: P = 0.366; TZ: P = 0.171).

CONCLUSION

PSA density and PI-RADS are potent predictors of csPCa. Radiomics do not add significant information to our multisite-multivendor dataset.

A novel clinically significant prostate cancer prediction system with multiparametric MRI and PSA: P.Z.A. score

PURPOSE

This study aims to establish and validate a new diagnosis model called P.Z.A. score for clinically significant prostate cancer (csPCa).

METHODS

The demographic and clinical characteristics of 956 patients were recorded. Age, prostate-specific antigen (PSA), free/total PSA (f/tPSA), PSA density (PSAD), peripheral zone volume ratio (PZ-ratio), and adjusted PSAD of PZ (aPSADPZ) were calculated and subjected to receiver operating characteristic (ROC) curve analysis. The nomogram was established, and discrimination abilities of the new nomogram were verified with a calibration curve and area under the ROC curve (AUC). The clinical benefits of P.Z.A. score were evaluated by decision curve analysis and clinical impact curves. External validation of the model using the validation set was also performed.

RESULTS

The AUCs of aPSADPZ, age, PSA, f/tPSA, PSAD and PZ-ratio were 0.824, 0.672, 0.684, 0.715, 0.792 and 0.717, respectively. The optimal threshold of P.Z.A. score was 0.41. The nomogram displayed excellent net benefit and better overall calibration for predicting the occurrence of csPCa. In addition, the number of patients with csPCa predicted by P.Z.A. score was in good agreement with the actual number of patients with csPCa in the high-risk threshold. The validation set provided better validation of the model.

CONCLUSION

P.Z.A. score (including PIRADS(P), aPSADPZ(Z) and age(A)) can increase the detection rate of csPCa, which may decrease the risk of misdiagnosis and reduce the number of unnecessary biopsies. P.Z.A. score contains data that is easy to obtain and is worthy of clinical replication.

Developing a diagnostic model for predicting prostate cancer: a retrospective study based on Chinese multicenter clinical data

ABSTRACT

The overdiagnosis of prostate cancer (PCa) caused by nonspecific elevation serum prostate-specific antigen (PSA) and the overtreatment of indolent PCa have become a global problem that needs to be solved urgently. We aimed to construct a prediction model and provide a risk stratification system to reduce unnecessary biopsies. In this retrospective study, clinical data of 1807 patients from three Chinese hospitals were used. The final model was built using stepwise logistic regression analysis. The apparent performance of the model was assessed by receiver operating characteristic curves, calibration plots, and decision curve analysis. Finally, a risk stratification system of clinically significant prostate cancer (csPCa) was created, and diagnosis-free survival analyses were performed. Following multivariable screening and evaluation of the diagnostic performances, a final diagnostic model comprised of the PSA density and Prostate Imaging-Reporting and Data System (PI-RADS) score was established. Model validation in the development cohort and two external cohorts showed excellent discrimination and calibration. Finally, we created a risk stratification system using risk thresholds of 0.05 and 0.60 as the cut-off values. The follow-up results indicated that the diagnosis-free survival rate for csPCa at 12 months and 24 months postoperatively was 99.7% and 99.4%, respectively, for patients with a risk threshold below 0.05 after the initial negative prostate biopsy, which was significantly better than patients with higher risk. Our diagnostic model and risk stratification system can achieve a personalized risk calculation of csPCa. It provides a standardized tool for Chinese patients and physicians when considering the necessity of prostate biopsy.

Development and validation of a nomogram based on biparametric MRI PI-RADS v2.1 and clinical parameters to avoid unnecessary prostate biopsies

BACKGROUND

Biparametric MRI (bpMRI) is a faster, contrast-free, and less expensive MRI protocol that facilitates the detection of prostate cancer. The aim of this study is to determine whether a biparametric MRI PI-RADS v2.1 score-based model could reduce unnecessary biopsies in patients with suspected prostate cancer (PCa).

METHODS

The patients who underwent MRI-guided biopsies and systematic biopsies between January 2020 and January 2022 were retrospectively analyzed. The development cohort used to derive the prediction model consisted of 275 patients. Two validation cohorts included 201 patients and 181 patients from 2 independent institutions. Predictive models based on the bpMRI PI-RADS v2.1 score (bpMRI score) and clinical parameters were used to detect clinically significant prostate cancer (csPCa) and compared by analyzing the area under the curve (AUC) and decision curves. Spearman correlation analysis was utilized to determine the relationship between International Society of Urological Pathology (ISUP) grade and clinical parameters/bpMRI score.

RESULTS

Logistic regression models were constructed using data from the development cohort to generate nomograms. By applying the models to the all cohorts, the AUC for csPCa was significantly higher for the bpMRI PI-RADS v2.1 score-based model than for the clinical model in both cohorts (p < 0.001). Considering the test trade-offs, urologists would agree to perform 10 fewer bpMRIs to avoid one unnecessary biopsy, with a risk threshold of 10-20% in practice. Correlation analysis showed a strong correlation between the bpMRI score and ISUP grade.

CONCLUSION

A predictive model based on the bpMRI score and clinical parameters significantly improved csPCa risk stratification, and the bpMRI score can be used to determine the aggressiveness of PCa prior to biopsy.

Prevalence and grade of malignancy differences with respect to the area of involvement in multiparametric resonance imaging of the prostate in the diagnosis of prostate cancer using the PI-RADS version 2 classification

PURPOSE

The peripheral zone is histologically different from the transitional zone. The aim of this study is to analyze the differences between the prevalence and grade of malignancy of mpMRI-targeted biopsies that involve the TZ with respect to the PZ.

METHODS

A cross-sectional study of 597 men evaluated for PC screening between February 2016 and October 2022 was conducted. Exclusion criteria were prior BPH surgery, radiotherapy, 5-alpha-reductase inhibitors treatment, UTI, mixed involvement of PZ-TZ or doubts, and central-zone involvement. Hypothesis contrast test was used to study differences proportions of malignancy (ISUP > 0) and significant (ISUP > 1) and high-grade tumor (ISUP > 3) in PI-RADSv2 > 2-targeted biopsies in PZ with respect to TZ, and logistic regression and hypothesis contrast tests were used to study the influence of the area of exposure as an effect-modifying factor in the diagnosis of malignancy with respect to the PI-RADSv2 classification.

RESULTS

473 patients were selected and 573 lesions biopsied (127 PI-RADS3, 346 PI-RADS4 and 100 PI-RADS5). A significant increase was described in the proportion of malignancy and significant and high-grade tumor in PZ compared to TZ (22.6%, 21.3%, and 8.7%, respectively). Significant increase in proportions and malignancy were described in cores targeted to PZ with respect to TZ, highlight the differences between PZ and TZ for ST (37.3%vs23.7% for PI-RADS4, 69.2%vs27.3% for PI-RADS5, respectively). Statistically significant linear trend was described increasing for malignancy, significant and high-grade tumors with respect to the PI-RADSv2 scores (change > 10%).

CONCLUSION

Although the prevalence and grade of malignancy in the TZ is lower than in the PZ, PI-RADS4 and 5-targeted biopsies should not be omitted in this location, but PI-RADS3 could be.

Research progress on deep learning in magnetic resonance imaging-based diagnosis and treatment of prostate cancer: a review on the current status and perspectives

Multiparametric magnetic resonance imaging (mpMRI) has emerged as a first-line screening and diagnostic tool for prostate cancer, aiding in treatment selection and noninvasive radiotherapy guidance. However, the manual interpretation of MRI data is challenging and time-consuming, which may impact sensitivity and specificity. With recent technological advances, artificial intelligence (AI) in the form of computer-aided diagnosis (CAD) based on MRI data has been applied to prostate cancer diagnosis and treatment. Among AI techniques, deep learning involving convolutional neural networks contributes to detection, segmentation, scoring, grading, and prognostic evaluation of prostate cancer. CAD systems have automatic operation, rapid processing, and accuracy, incorporating multiple sequences of multiparametric MRI data of the prostate gland into the deep learning model. Thus, they have become a research direction of great interest, especially in smart healthcare. This review highlights the current progress of deep learning technology in MRI-based diagnosis and treatment of prostate cancer. The key elements of deep learning-based MRI image processing in CAD systems and radiotherapy of prostate cancer are briefly described, making it understandable not only for radiologists but also for general physicians without specialized imaging interpretation training. Deep learning technology enables lesion identification, detection, and segmentation, grading and scoring of prostate cancer, and prediction of postoperative recurrence and prognostic outcomes. The diagnostic accuracy of deep learning can be improved by optimizing models and algorithms, expanding medical database resources, and combining multi-omics data and comprehensive analysis of various morphological data. Deep learning has the potential to become the key diagnostic method in prostate cancer diagnosis and treatment in the future.

Pilot study for generating and assessing nomograms and decision curves analysis to predict clinically significant prostate cancer using only spatially registered multi-parametric MRI

Background

Current prostate cancer evaluation can be inaccurate and burdensome. To help non-invasive prostate tumor assessment, recent algorithms applied to spatially registered multi-parametric (SRMP) MRI extracted novel clinically relevant metrics, namely the tumor's eccentricity (shape), signal-to-clutter ratio (SCR), and volume.

Purpose

Conduct a pilot study to predict the risk of developing clinically significant prostate cancer using nomograms and employing Decision Curves Analysis (DCA) from the SRMP MRI-based features to help clinicians non-invasively manage prostate cancer.

Methods

This study retrospectively analyzed 25 prostate cancer patients. MP-MRI (T1, T2, diffusion, dynamic contrast-enhanced) were resized, translated, and stitched to form SRMP MRI. Target detection algorithm [adaptive cosine estimator (ACE)] applied to SRMP MRI determines tumor's eccentricity, noise reduced SCR (by regularizing or eliminating principal components (PC) from the covariance matrix), and volume. Pathology assessed wholemount prostatectomy for Gleason score (GS). Tumors with GS >=4+3 (<=3+4) were judged as "Clinically Significant" ("Insignificant"). Logistic regression combined eccentricity, SCR, volume to generate probability distribution. Nomograms, DCA used all patients plus training (13 patients) and test (12 patients) sets. Area Under the Curves for (AUC) for Receiver Operator Curves (ROC) and p-values evaluated the performance.

Results

Combining eccentricity (0.45 ACE threshold), SCR (3, 4 PCs), SCR (regularized, modified regularization) with tumor volume (0.65 ACE threshold) improved AUC (>0.70) for ROC curves and p-values (<0.05) for logistic fit. DCA showed greater net benefit from model fit than univariate analysis, treating "all," or "none." Training/test sets achieved comparable AUC but with higher p-values.

Conclusions

Performance of nomograms and DCA based on metrics derived from SRMP-MRI in this pilot study were comparable to those using prostate serum antigen, age, and PI-RADS.