The Use of Multiparametric Magnetic Resonance Imaging (mpMRI) in the Detection, Evaluation, and Surveillance of Clinically Significant Prostate Cancer (csPCa)

Enhancing bone metastasis prediction in prostate cancer using quantitative mpMRI features, ISUP grade and PSA density: a machine learning approach

PURPOSE

Bone metastasis is a critical complication in prostate cancer, significantly impacting patient prognosis and quality of life. This study aims to enhance bone metastasis prediction using machine learning (ML) techniques by integrating dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) perfusion features, International Society of Urological Pathology (ISUP) grade, and prostate-specific antigen (PSA) density.

MATERIALS AND METHODS

A retrospective analysis was conducted on 122 patients with histopathologically confirmed prostate cancer who underwent multiparametric prostate magnetic resonance imaging (mpMRI). Quantitative mpMRI features, PSA density, and ISUP grades were extracted and normalized. The dataset was balanced using oversampling and divided into training (70%) and test (30%) sets. Various ML models were developed and evaluated using area under the curve (AUC) metrics.

RESULTS

Bone metastases were present in 26 patients (21.3%) at diagnosis. IAUGC and MaxSlope showed a statistically significant association with bone metastasis (p = 0.035, p = 0.050 respectively). The optimal PSA density cut-off value of 0.24 yielded a sensitivity of 0.88, specificity of 0.60, and AUC of 0.77. Machine learning models were developed using the dataset created with IAUGC, MaxSlope, ISUP grade, and PSA density values. Among the ML models, XGBoost demonstrated superior performance with validation and test AUCs of 91.5% and 92.6%, respectively, along with high precision (93.3%) and recall (93.1%).

CONCLUSION

Integrating quantitative mpMRI features, ISUP grade, and PSA density through machine learning algorithms, particularly XGBoost, significantly improves the accuracy of bone metastasis prediction in prostate cancer patients. This approach can potentially reduce the need for additional imaging modalities and associated radiation exposure.

Assessment of a fully-automated diagnostic AI software in prostate MRI: Clinical evaluation and histopathological correlation

OBJECTIVE

This study aims to evaluate the diagnostic performance of a commercial, fully-automated, artificial intelligence (AI) driven software tool in identifying and grading prostate lesions in prostate MRI, using histopathological findings as the reference standard, while contextualizing its performance within the framework of PI-RADS v2.1 criteria.

MATERIAL AND METHODS

This retrospective study analyzed 123 patients who underwent multiparametric prostate MRI followed by systematic and targeted biopsies. MRI protocols adhered to international guidelines and included T2-weighted, diffusion-weighted, T1-weighted, and dynamic contrast-enhanced imaging. The AI software tool mdprostate was integrated into the Picture Archiving and Communication System to automatically segment the prostate, calculate prostate volume, and classify lesions according to PI-RADS scores using biparametric T2-weighted and diffusion-weighted imaging. Histopathological analysis of biopsy cores served as the reference standard. Diagnostic performance metrics including sensitivity, specificity, positive and negative predictive value (PPV, NPV), and area under the ROC curve (AUC) were calculated.

RESULTS

mdprostate demonstrated 100 % sensitivity at a PI-RADS ≥ 2 cutoff, effectively ruling out both clinically significant and non-significant prostate cancers for lesions remaining below this threshold. For detecting clinically significant prostate cancer (csPCa) using a PI-RADS ≥ 4 cutoff, mdprostate achieved a sensitivity of 85.5 % and a specificity of 63.2 %. The AUC for detecting cancers of any grade was 0.803. The performance metrics of mdprostate were comparable to those reported in two meta-analyses of PI-RADS v2.1, with no significant differences in sensitivity and specificity (p > 0.05).

CONCLUSION

The evaluated AI tool demonstrated high diagnostic performance in identifying and grading prostate lesions, with results comparable to those reported in meta-analyses of expert readers using PI-RADS v2.1. Its ability to standardize evaluations and potentially reduce variability underscores its potential as a valuable adjunct in the prostate cancer diagnostic pathway. The high accuracy of mdprostate, particularly in ruling out prostate cancers, highlights its clinical utility by reducing workload and enhancing patient outcomes.

A novel biopsy scheme for prostate cancer: targeted and regional systematic biopsy

PURPOSE

To explore a novel biopsy scheme for prostate cancer (PCa), and test the detection rate and pathological agreement of standard systematic (SB) + targeted (TB) biopsy and novel biopsy scheme.

METHODS

Positive needles were collected from 194 patients who underwent SB + TB (STB) followed by radical prostatectomy (RP). Our novel biopsy scheme, targeted and regional systematic biopsy (TrSB) was defined as TB + regional SB (4 SB-needles closest to the TB-needles). The McNemar test was utilized to compare the detection rate performance for clinical significant PCa (csPCa) and clinical insignificant PCa (ciPCa). Moreover, the accuracy, positive predictive value (PPV) and negative predictive value (NPV) were investigated. The agreement between the different biopsy schemes grade group (GG) and RP GG were assessed. The concordance between the biopsy and the RP GG was evaluated using weighted κ coefficient analyses.

RESULTS

In this study, the overall detection rate for csPCa was 83.5% (162 of 194) when SB and TB were combined. TrSB showed better NPV than TB (97.0% vs. 74.4%). Comparing to STB, the TB-detection rate of csPCa had a significant difference (p < 0.01), while TrSB showed no significant difference (p > 0.999). For ciPCa, the overall detection rate was 16.5% (32 of 194). TrSB showed better PPV (96.6% vs. 83.3%) and NPV (97.6% vs. 92.9%) than TB. Comparing to STB, the detection rate of both schemes showed no significant difference (p = 0.077 and p = 0.375). All three schemes GG showed poor agreement with RP GG (TB: 43.3%, TrSB: 46.4%, STB: 45.9%). Using weighted κ, all three schemes showed no difference (TB: 0.48, TrSB: 0.51, STB: 0.51). In our subgroup analysis (PI-RADS = 4/5, n = 154), all three schemes almost showed no difference (Weighted κ: TB-0.50, TrSB-0.51, STB-0.50).

CONCLUSION

Our novel biopsy scheme TrSB (TB + 4 closest SB needles) may reduce 8 cores of biopsy compared with STB (standard SB + TB), which also showed better csPCa detection rate than TB only, but the same as STB. The pathological agreement between three different biopsy schemes (TB/TrSB/STB) GG and RP GG showed no difference.

68Ga-PSMA PET/CT-based multivariate model for highly accurate and noninvasive diagnosis of clinically significant prostate cancer in the PSA gray zone

BACKGROUND

The prostate-specific antigen (PSA) has been widely used in screening and early diagnosis of prostate cancer (PCa). However, in the PSA grey zone of 4-10 ng/ml, the sensitivity and specificity for diagnosing PCa are limited, resulting in considerable number of unnecessary and invasive prostate biopsies, which may lead to potential overdiagnosis and overtreatment. We aimed to predict clinically significant PCa (CSPCa) by combining the maximal standardized uptake value (SUVmax) based on 68Ga‑PSMA PET/CT and clinical indicators in men with gray zone PSA levels.

METHODS

81 patients with suspected PCa based on increased serum total PSA (TPSA) levels of 4 - 10 ng/mL who underwent transrectal ultrasound/magnetic resonance imaging (MRI)/PET fusion-guided biopsy were enrolled. Among them, patients confirmed by histopathology were divided into the CSPCa group and the non-CSPCa group, and data on PSA concentration, prostate volume (PV), PSA density (PSAD), free PSA (FPSA)/TPSA, Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS v2.1) score, 68Ga-PSMA PET/CT imaging evaluation results and SUVmax were compared. Multivariate logistic regression analysis was performed to identify the independent predictors for CSPCa, thereby establishing a predictive model based on SUVmax that was evaluated by analyzing the receiver operating characteristic (ROC) curve and decision curve analysis.

RESULTS

Compared to non-CSPCa, CSPCa patients had smaller PVs (median, 31.40 mL), lower FPSA/TPSA (median, 0.12), larger PSADs (median, 0.21 ng/mL2) and higher PI-RADS scores (P < 0.05). The prediction model comprising 68Ga-PSMA PET/CT maximal standardized uptake value, PV and FPSA/TPSA had the highest AUC of 0.927 compared with that of other predictors alone (AUCs of 0.585 for PSA, 0.652 for mpMRI and 0.850 for 68Ga-PSMA PET/CT). The diagnostic sensitivity and specificity of the prediction model were 86.21% and 86.54%, respectively.

CONCLUSION

Given the low diagnostic accuracy of regular PSA tests, a new prediction model based on the 68Ga-PSMA PET/CT SUVmax, PV and FPSA/TPSA was developed and validated, and this model could provide a more satisfactory predictive accuracy for CSPCa. This study provides a noninvasive prediction model with high accuracy for the diagnosis of CSPCa in the PSA gray zone, thus may be better avoiding unnecessary biopsy procedures.

Traditional and novel imaging modalities for advanced prostate cancer: A critical review

Accurate detection of metastatic prostate cancer in the setting of preoperative staging as well as posttreatment recurrence is crucial to provide patients with appropriate and timely treatment of their disease. This has traditionally been accomplished with a combination of computed tomography, magnetic resonance imaging, and bone scan. Recently, more novel imaging techniques have been developed to help improve the detection of advanced and metastatic prostate cancer. This review discusses the efficacy of the traditional imaging modalities as well as the novel imaging techniques in detecting metastatic prostate cancer. Articles discussed were gathered through a formal PubMed search.

Intravoxel incoherent motion predicts positive surgical margins and Gleason score upgrading after radical prostatectomy for prostate cancer

BACKGROUND

Whether Intravoxel incoherent motion (IVIM) can be used as a predictive tool of positive surgical margins (PSMs) and Gleason score (GS) upgrading in prostate cancer (PCa) patients after radical prostatectomy (RP) still remains unclear. The aim of this study is to explore the ability of IVIM and clinical characteristics to predict PSMs and GS upgrading.

METHODS

A total of 106 PCa patients after RP who underwent pelvic mpMRI (multiparametric Magnetic Resonance Imaging) between January 2016 and December 2021 and met the requirements were retrospectively included in our study. IVIM parameters were obtained using GE Functool post-processing software. Logistic regression models were fitted to confirm the predictive risk factor of PSMs and GS upgrading. The area under the curve and fourfold contingency table were used to evaluate the diagnostic efficacy of IVIM and clinical parameters.

RESULTS

Multivariate logistic regression analyses revealed that percent of positive cores, apparent diffusion coefficient and molecular diffusion coefficient (D) were independent predictors of PSMs (Odds Ratio (OR) were 6.07, 3.62 and 3.16, respectively), Biopsy GS and pseudodiffusion coefficient (D*) were independent predictors of GS upgrading (OR were 0.563 and 7.15, respectively). The fourfold contingency table suggested that combined diagnosis increased the ability of predicting PSMs but had no advantage in predicting GS upgrading except the sensitivity from 57.14 to 91.43%.

CONCLUSIONS

IVIM showed good performance in predicting PSMs and GS upgrading. Combining IVIM and clinical factors enhanced the performance of predicting PSMs, which may contribute to clinical diagnosis and treatment.

An independent practice validation of the Prostate Imaging Reporting and Data System version 2 scoring system and the introduction of PDP (prostate-specific antigen density × PI-RADSv2) score to assist with further risk assessment

Objectives

To provide concise information to clinicians on how to better interpret multiparametric magnetic resonance imaging for prostate cancer risk stratification.

Materials and methods

We analyzed 2 separate cohorts. For patients receiving a Prostate Imaging Reporting and Data System version 2 (PI-RADSv2) score of 1 or 2, we reviewed the charts of 226 patients who underwent multiparametric magnetic resonance imaging of the prostate ordered from 2015 to 2017 to determine who developed clinically significant prostate cancer (csPCa) by August 27, 2020. For patients receiving PI-RADSv2 a score of 3, 4, or 5, we reviewed the results of 733 fusion biopsies on solitary lesions. Statistical analysis was used to further determine risk factors for csPCa.

Results

Ten percent of men with PI-RADSv2 a score of 1 eventually developed csPCa. Seven percent with a score of 2 were eventually diagnosed with csPCa. Only 1 of 226 with a score of 1 or 2 developed metastasis. For PI-RADSv2 scores of 3, 4, and 5, csPCa was detected in 16%, 45%, and 67% of fusion biopsies. Peripheral zone (PZ) PI-RADSv2 score of 4 or 5 and prostate-specific antigen density (PSA-D) were significant predictors of csPCa on multivariable analysis. Using a PSA-D × PI-RADSv2 score of ≤0.39, we identified 38% of men with a PI-RADSv2 score of 3 in the PZ or 3, 4, or 5 in the transition zone who could have avoided a benign biopsy.

Conclusions

The vast majority of patients with PI-RADSv2 scores 1 and 2 can be safely monitored with close surveillance. Lesions with PI-RADSv2 scores of 4 and 5 in the PZ should be biopsied. Peripheral zone lesions with a PI-RADSv2 score of 3 and transition zone lesions with 3, 4, or 5 can be risk-stratified using the PSA-D × PI-RADSv2 score to determine who may safely avoid a biopsy and who should proceed to fusion biopsy.

Optimized grade group for reporting prostate cancer grade in systematic and MRI-targeted biopsies

PURPOSE

To explore an optimized grade group (oGG) criterion from systematic biopsies (SB) and targeted biopsies (TB) and offer a better prediction of radical prostatectomy (RP) grade group (GG).

METHODS

Positive needles were collected from 146 patients who underwent SB + TB followed by RP. The grade was assigned for two different kinds of biopsies with five GG criteria: (1) global GG (gGG); (2) most common GG (most common GG from SB + TB, mGG); (3) highest GG (highest numerical GG from SB + TB, hGG); (4) largest volume/linear length cancer GG (defined as GG from the SB + TB with the largest length of cancer in a needle, lGG). These biopsy grades were compared (equivalence, upgrade, or downgrade) with the final grade of the RP lesion, using weighted κ coefficients; (5) Then the best agreement of the (2) (3) (4) grading scores from SB or TB was combined to introduce an oGG.

RESULTS

In this study, gGG showed generally poor agreement (47.2%) with RP GG (weighted κ: 0.43). Using the three criteria (mGG, hGG, and lGG) of SB, mGG had the best agreement (55.5%, weighted κ: 0.46), while hGG and lGG had a lower agreement (48.6% and 48.6%, weighted κ: 0.42 and 0.38). Using the three criteria (mGG, hGG and lGG) of TB: lGG had the best agreement (56.8%, weighted κ: 0.43), while mGG and hGG had lower agreement (50.0% and 49.3%, weighted κ: 0.40 and 0.40); Then oGG was generated (higher GG between mGG of SB and lGG of TB) and the agreement of oGG increased to 59.6% and weighted κ was 0.49. Additionally, oGG had a lower upgrade rate than gGG, while the downgrade rate remained unchanged.

CONCLUSIONS

oGG showed better agreement with RP GG than gGG. oGG had a lower upgrade rate than gGG, while downgrade rate remained unchanged.

Multiparametric MRI and Machine Learning Based Radiomic Models for Preoperative Prediction of Multiple Biological Characteristics in Prostate Cancer

Objectives

This study aims to develop and evaluate multiparametric MRI (MP-MRI)-based radiomic models as a noninvasive diagnostic method to predict several biological characteristics of prostate cancer.

Methods

A total of 252 patients were retrospectively included who underwent radical prostatectomy and MP-MRI examinations. The prediction characteristics of this study were as follows: Ki67, S100, extracapsular extension (ECE), perineural invasion (PNI), and surgical margin (SM). Patients were divided into training cohorts and validation cohorts in the ratio of 4:1 for each group. After lesion segmentation manually, radiomic features were extracted from MP-MRI images and some clinical factors were also included. Max relevance min redundancy (mRMR) and recursive feature elimination (RFE) based on random forest (RF) were adopted to select features. Six classifiers were included (SVM, KNN, RF, decision tree, logistic regression, XGBOOST) to find the best diagnostic performance among them. The diagnostic efficiency of the construction models was evaluated by ROC curves and quantified by AUC.

Results

RF performed best among the six classifiers for the four groups according to AUC values (Ki67 = 0.87, S100 = 0.80, ECE = 0.85, PNI = 0.82). The performance of SVM was relatively the best for SM (AUC = 0.77). The number and importance of DCE features ranked first in the models of each group. The combined models of MP-MRI and clinical characteristics showed no significant difference compared with MP-MRI models according to Delong’s tests.

Conclusions

Radiomics models based on MP-MRI have the potential to predict biological characteristics and are expected to be a noninvasive method to evaluate the risk stratification of prostate cancer.

Detection and Segmentation of Pelvic Bones Metastases in MRI Images for Patients With Prostate Cancer Based on Deep Learning

Objective

To establish and evaluate the 3D U-Net model for automated segmentation and detection of pelvic bone metastases in patients with prostate cancer (PCa) using diffusion-weighted imaging (DWI) and T1 weighted imaging (T1WI) images.

Methods

The model consisted of two 3D U-Net algorithms. A total of 859 patients with clinically suspected or confirmed PCa between January 2017 and December 2020 were enrolled for the first 3D U-Net development of pelvic bony structure segmentation. Then, 334 PCa patients were selected for the model development of bone metastases segmentation. Additionally, 63 patients from January to May 2021 were recruited for the external evaluation of the network. The network was developed using DWI and T1WI images as input. Dice similarity coefficient (DSC), volumetric similarity (VS), and Hausdorff distance (HD) were used to evaluate the segmentation performance. Sensitivity, specificity, and area under the curve (AUC) were used to evaluate the detection performance at the patient level; recall, precision, and F1-score were assessed at the lesion level.

Results

The pelvic bony structures segmentation on DWI and T1WI images had mean DSC and VS values above 0.85, and the HD values were <15 mm. In the testing set, the AUC of the metastases detection at the patient level were 0.85 and 0.80 on DWI and T1WI images. At the lesion level, the F1-score achieved 87.6% and 87.8% concerning metastases detection on DWI and T1WI images, respectively. In the external dataset, the AUC of the model for M-staging was 0.94 and 0.89 on DWI and T1WI images.

Conclusion

The deep learning-based 3D U-Net network yields accurate detection and segmentation of pelvic bone metastases for PCa patients on DWI and T1WI images, which lays a foundation for the whole-body skeletal metastases assessment.

In prostatic transition zone lesions (PI-RADS v2.1): which subgroup should be biopsied?

Background

The study aimed to compare the diagnostic performance of T2-weighted imaging (T2WI) score 3 transition zone (TZ) lesions between Prostate Imaging and Reporting Data System (PI-RADS) v2.1 and modified PI-RADS v2.1-B.

Results

Among TZ lesions (n = 78), 47 (60.0%) had T2WI score of 3, and 16 of the 47 (34.0%) were malignant. The rate of malignancy was 8.8% in PI-RADS category 3A, 100% in PI-RADS category 3B, and 100% in PI-RADS category 4. The apparent diffusion coefficient value of PI-RADS category 3B (0.934 ± 0.158 × 10−3 mm2/s) showed significant difference with that of PI-RADS category 3A (1.098 ± 0.146 × 10−3 mm2/s) but none with PI-RADS category 4 (0.821 ± 0.091 × 10−3 mm2/s). There was no significant difference in the sensitivity and negative predictive value of PI-RADS v2.1 and PI-RADS v2.1-B. Specificity and positive predictive value of modified PI-RADS v2.1-B were much higher than those of PI-RADS v2.1 for both readers (p < .001). The area under the receiver operating characteristic curve tended to be higher with PI-RADS v2.1-B than with PI-RADS v2.1.

Conclusion

Biopsy for PI-RADS 3B lesion is necessary due to its superior malignancy potential than that of PI-RADS 3A lesion.

The Role of PSA Density among PI-RADS v2.1 Categories to Avoid an Unnecessary Transition Zone Biopsy in Patients with PSA 4-20 ng/mL

Objective

To evaluate the role of prostate-specific antigen density (PSAD) in different Prostate Imaging Reporting and Data System version 2.1 (PI-RADS v2.1) categories to avoid an unnecessary biopsy in transition zone (TZ) patients with PSA ranging from 4 to 20 ng/mL.

Materials and Methods

In this retrospective and single-center study, 333 biopsy-naïve patients with TZ lesions who underwent biparametric magnetic resonance imaging (bp-MRI) were analyzed from January 2016 to March 2020. Multivariate logistic regression analyses were performed to determine independent predictors of clinically significant prostate cancer (cs-PCa). The receiver operating characteristic (ROC) curve was used to compare diagnostic performance.

Results

PI-RADS v2.1 and PSAD were the independent predictors for TZ cs-PCa in patients with PSA 4-20 ng/mL. 0.9% (2/213), 10.0% (7/70), and 48.0% (24/50) of PI-RADS v2.1 score 1-2, 3, and 4-5 had TZ cs-PCa. However, for patients with PI-RADS v2.1 score 1-2, there were no obvious changes in the detection of TZ cs-PCa (0.8% (1/129), 1.3% (1/75), and 0.0% (0/9)) combining with different PSAD stratification (PSAD < 0.15, 0.15-0.29, and ≥0.30 ng/mL/mL). For patients with PI-RADS v2.1 score ≥ 3, the TZ cs-PCa detection rate significantly varied according to different PSAD stratification. A PI-RADS v2.1 score 3 and PSAD < 0.15 and 0.15-0.29 ng/mL/mL had 8.6% (3/35) and 3.7% (1/27) of TZ cs-PCa, while a PI-RADS v2.1 score 3 and PSAD ≥ 0.30 ng/mL/mL had a higher TZ cs-PCa detection rate (37.5% (3/8)). A PI-RADS v2.1 score 4-5 and PSAD <0.15 ng/mL/mL had no cs-PCa (0.0% (0/9)). In contrast, a PI-RADS v2.1 score 4-5 and PSAD 0.15-0.29 and ≥0.30 ng/mL/mL had the highest cs-PCa detection rate (50.0% (10/20), 66.7% (14/21)). It showed the highest AUC in the combination of PI-RADS v2.1 and PSAD (0.910), which was significantly higher than PI-RADS v2.1 (0.889, P = 0.039) or PSAD (0.803, P < 0.001).

Conclusions

For TZ patients with PSA 4-20 ng/mL, PI-RADS v2.1 score ≤ 2 can avoid an unnecessary biopsy regardless of PSAD. PI-RADS v2.1 score ≥ 3 may avoid an unnecessary biopsy after combining with PSAD. PI-RADS v2.1 combined with PSAD could significantly improve diagnostic performance.

Challenges in the Use of Artificial Intelligence for Prostate Cancer Diagnosis from Multiparametric Imaging Data

Simple Summary

Prostate Cancer is one of the main threats to men’s health. Its accurate diagnosis is crucial to properly treat patients depending on the cancer’s level of aggressiveness. Tumor risk-stratification is still a challenging task due to the difficulties met during the reading of multi-parametric Magnetic Resonance Images. Artificial Intelligence models may help radiologists in staging the aggressiveness of the equivocal lesions, reducing inter-observer variability and evaluation time. However, these algorithms need many high-quality images to work efficiently, bringing up overfitting and lack of standardization and reproducibility as emerging issues to be addressed. This study attempts to illustrate the state of the art of current research of Artificial Intelligence methods to stratify prostate cancer for its clinical significance suggesting how widespread use of public databases could be a possible solution to these issues.

Abstract

Many efforts have been carried out for the standardization of multiparametric Magnetic Resonance (mp-MR) images evaluation to detect Prostate Cancer (PCa), and specifically to differentiate levels of aggressiveness, a crucial aspect for clinical decision-making. Prostate Imaging—Reporting and Data System (PI-RADS) has contributed noteworthily to this aim. Nevertheless, as pointed out by the European Association of Urology (EAU 2020), the PI-RADS still has limitations mainly due to the moderate inter-reader reproducibility of mp-MRI. In recent years, many aspects in the diagnosis of cancer have taken advantage of the use of Artificial Intelligence (AI) such as detection, segmentation of organs and/or lesions, and characterization. Here a focus on AI as a potentially important tool for the aim of standardization and reproducibility in the characterization of PCa by mp-MRI is reported. AI includes methods such as Machine Learning and Deep learning techniques that have shown to be successful in classifying mp-MR images, with similar performances obtained by radiologists. Nevertheless, they perform differently depending on the acquisition system and protocol used. Besides, these methods need a large number of samples that cover most of the variability of the lesion aspect and zone to avoid overfitting. The use of publicly available datasets could improve AI performance to achieve a higher level of generalizability, exploiting large numbers of cases and a big range of variability in the images. Here we explore the promise and the advantages, as well as emphasizing the pitfall and the warnings, outlined in some recent studies that attempted to classify clinically significant PCa and indolent lesions using AI methods. Specifically, we focus on the overfitting issue due to the scarcity of data and the lack of standardization and reproducibility in every step of the mp-MR image acquisition and the classifier implementation. In the end, we point out that a solution can be found in the use of publicly available datasets, whose usage has already been promoted by some important initiatives. Our future perspective is that AI models may become reliable tools for clinicians in PCa diagnosis, reducing inter-observer variability and evaluation time.

The modified International Society of Urological Pathology system improves concordance between biopsy and prostatectomy tumour grade

OBJECTIVES

To assess the concordance between biopsy and radical prostatectomy (RP) specimens using the 2005 Gleason score (GS) and the International Society of Urological Pathology (ISUP) 2014/World Health Organization 2016 modified system, accounting for the introduction of transperineal biopsy and pre-biopsy multiparametric magnetic resonance imaging (mpMRI).

PATIENTS AND METHODS

Between 2002 and 2019, we identified 2431 patients with paired biopsy and RP histopathology from a prospectively recorded and maintained prostate cancer database. Biopsy specimens were graded according to the 2005 GS or ISUP 2014 modified system, according to the year of diagnosis. Multivariable logistic regression analysis was conducted to retrospectively assess the impact of prostate-specific antigen (PSA), PSA density, age, pre-biopsy mpMRI, and biopsy method, on the rate of upgraded disease. The kappa coefficient was used to establish the degree of change in concordance between groups.

RESULTS

Overall, 24% of patients had upgraded disease and 8% of patients had downgraded disease when using the modified ISUP 2014 criteria. Agreement in the updated ISUP 2014 cohort was 68%, compared with 55% in the 2005 GS group, which was validated by a kappa coefficient that was good (k = 0.5 ± 0.4) and poor (k = 0.3 ± 0.1), respectively. In multivariable models, a change in grading system independently improved overall disease concordance (P = 0.02), and there were no other co-segregated patient or pathological factors such as PSA, total number of cores, maximum cancer length, biopsy route or the use of mpMRI that impacted this finding.

CONCLUSION

The 2014 ISUP modifed system improves overall concordance between biopsy and surgical specimens, and thus allows more accurate prognostication and management in high-grade disease, independent of more extensive prostate sampling and the use of mpMRI.

MRI-based radiomics models to assess prostate cancer, extracapsular extension and positive surgical margins

Purpose

To investigate the performance of magnetic resonance imaging (MRI)-based radiomics models for benign and malignant prostate lesion discrimination and extracapsular extension (ECE) and positive surgical margins (PSM) prediction.

Methods and materials

In total, 459 patients who underwent multiparametric MRI (mpMRI) before prostate biopsy were included. Radiomic features were extracted from both T2-weighted imaging (T2WI) and the apparent diffusion coefficient (ADC). Patients were divided into different training sets and testing sets for different targets according to a ratio of 7:3. Radiomics signatures were built using radiomic features on the training set, and integrated models were built by adding clinical characteristics. The areas under the receiver operating characteristic curves (AUCs) were calculated to assess the classification performance on the testing sets.

Results

The radiomics signatures for benign and malignant lesion discrimination achieved AUCs of 0.775 (T2WI), 0.863 (ADC) and 0.855 (ADC + T2WI). The corresponding integrated models improved the AUC to 0.851/0.912/0.905, respectively. The radiomics signatures for ECE achieved the highest AUC of 0.625 (ADC), and the corresponding integrated model achieved the highest AUC (0.728). The radiomics signatures for PSM prediction achieved AUCs of 0.614 (T2WI) and 0.733 (ADC). The corresponding integrated models reached AUCs of 0.680 and 0.766, respectively.

Conclusions

The MRI-based radiomics models, which took advantage of radiomic features on ADC and T2WI scans, showed good performance in discriminating benign and malignant prostate lesions and predicting ECE and PSM. Combining radiomics signatures and clinical factors enhanced the performance of the models, which may contribute to clinical diagnosis and treatment.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-021-00414-6.

One-year experience of government-funded magnetic resonance imaging prior to prostate biopsy: A case for omitting biopsy in men with a negative magnetic resonance imaging

Objectives:

This study aimed to characterise the accuracy of multiparametric magnetic resonance imaging (mpMRI) as an adjunct to prostate biopsy, and to assess the effect of the new Australian Medicare rebate on practice at a metropolitan public hospital.

Patients and methods:

We identified patients who underwent transrectal ultrasound (TRUS)-guided prostate biopsy at a single institution over a two-year period. Patients were placed into two groups, depending upon whether their consent was obtained before or after the introduction of the Australian Medicare rebate for mpMRI. We extracted data on mpMRI results and TRUS-guided biopsy histopathology. Descriptive statistics were used to demonstrate baseline patient characteristics as well as MRI and histopathology results.

Results:

A total of 252 patients were included for analysis, of whom 128 underwent biopsy following the introduction of the Medicare rebate for mpMRI. There was a significant association between Prostate Imaging Reporting and Data System v2 (PI-RADS) classification and the diagnosis of clinically significant prostate cancer ( p<0.01). Only one man with PI-RADS ⩽2 was found to have clinically significant prostate cancer. Four men with a PI-RADS 3 lesion were found to have clinically significant cancer. A PI-RADS 4 or 5 lesion was significantly associated with the diagnosis of clinically significant cancer on multivariable analysis.

Conclusion:

mpMRI is an important adjunct to biopsy in the diagnosis of clinically significant prostate cancer. Our findings support the safety of omitting/delaying prostate biopsy in men with negative mpMRI.

Level of evidence:

Level 3 retrospective case-control study.

Cutoff Values of Prostate Imaging Reporting and Data System Version 2.1 Score in Men With Prostate-specific Antigen Level 4 to 10 ng/mL: Importance of Lesion Location

INTRODUCTION

Multiparametric magnetic resonance imaging (mpMRI) has been shown to have a good performance in predicting cancer among patients with a prostate-specific antigen (PSA) level of 4 to 10 ng/mL. However, lesion location on mpMRI has never been separately considered.

PATIENTS AND METHODS

Patients with PSA level of 4 to 10 ng/mL were prospectively enrolled and underwent transrectal ultrasound-guided prostate biopsy. Patient information was collected, and logistic regression analysis was performed to determine the predictive factors of clinically significant prostate cancer (csPCa). Patients were grouped by lesion location to determine the Prostate Imaging Reporting and Data System (PI-RADS) v2.1 cutoff value in predicting csPCa.

RESULTS

Among 222 patients, 121 were diagnosed with PCa and 92 had csPCa. Age, prostate volume, PSA density, location (peripheral zone, csPCa only), and PI-RADS v2.1 score were correlated with PCa and csPCa, and PI-RADS v2.1 score was the best predictor. A PI-RADS v2.1 score of 4 was the best cutoff value for predicting csPCa in patients with lesions only in the transitional zone with respect to the Youden index (0.5896) and negative predictive value (93.10%) with acceptable sensitivity (81.82%) and specificity (77.14%). An adjustment of the cutoff value to 3 for lesions in the peripheral zone would increase the negative predictive value (92.00%) and decrease the false negative rate (2.90%) with an acceptable sensitivity (97.10%) and specificity (30.67%).

CONCLUSION

PI-RADS v2.1 score is an effective predictor of csPCa in patients with PSA levels of 4 to 10 ng/mL. Patients with transitional zone or peripheral zone lesions should undergo biopsy if the PI-RADS v2.1 score is ≥ 4 or ≥ 3, respectively.

Accuracy of ADC ratio in discriminating true and false positives in multiparametric prostatic MRI

PURPOSE

Our goal was to evaluate the usefulness of apparent diffusion coefficient (ADC) ratios in discriminating true from false positives in multiparametric (mp) prostate MRI in clinical practice.

METHODS

We retrospectively evaluated 98 prostate lesions in a series of 73 patients who had undergone prostate mpMRI and standard 12-core prostatic biopsy in our institution from 2016 to 2018. Two experienced radiologists performed double blind ADC value quantifications of both MRI-identified lesions and apparently benign contralateral prostatic parenchyma in a circular region of interest (ROI) of ∼10 mm². The ratios between the mean values of both measurements (i.e., ADC ratio mean) and between the minimum value of the lesion and the maximum value of the benign parenchyma (i.e., ADC ratio min-max) were automatically calculated. The malignancy of all lesions was determined through biopsy according to Gleason score (GS ≥ 6) and localization.

RESULTS

For Reader 1, the area under the ROC curve (AUC) of ADC ratio mean and ADC ratio min-max were 0.72 and 0.67, respectively, whereas for Reader 2 these values were 0.74 and 0.71, respectively. The best cut-off values for ADC ratio means were ≥ 0.5 (Reader 1) and ≥ 0.6 (Reader 2), with a sensitivity of 76.3 % and 84.2 % and a specificity of 51.7 % and 50 %, respectively. Moreover, based on a threshold of 0.6, no clinically significant prostate cancer (csPCa) was missed by Reader 1, while only one went unnoticed by Reader 2.

CONCLUSION

The ADC ratio is a useful and moderately accurate complementary tool to diagnose prostate cancer in the mp-MRI.

Application of texture analysis based on T2-weighted magnetic resonance images in discriminating Gleason scores of prostate cancer

OBJECTIVE

To investigate the value of texture analysis in magnetic resonance images for the evaluation of Gleason scores (GS) of prostate cancer.

METHODS

Sixty-six prostate cancer patients are retrospective enrolled, which are divided into five groups namely, GS = 6, 3 + 4, 4 + 3, 8 and 9-10 according to postoperative pathological results. Extraction and analysis of texture features in T2-weighted MR imaging defined tumor region based on pathological specimen after operation are performed by texture software OmniKinetics. The values of texture are analyzed by single factor analysis of variance (ANOVA), and Spearman correlation analysis is used to study the correlation between the value of texture and Gleason classification. Receiver operating characteristic (ROC) curve is then used to assess the ability of applying texture parameters to predict Gleason score of prostate cancer.

RESULTS

Entropy value increases and energy value decreases as the elevation of Gleason score, both with statistical difference among five groups (F = 10.826, F = 2.796, P < 0.05). Energy value of group GS = 6 is significantly higher than that of groups GS = 8 and 9-10 (P < 0.005), which is similar between three groups (GS = 3 + 4, 8 and 9-10). The entropy and energy values correlate with GS (r = 0.767, r = -0.692, P < 0.05). Areas under ROC curves (AUC) of combination of entropy and energy are greater than that of using energy alone between groups GS = 6 and ≥7. Analogously, AUC of combination of entropy and energy are significantly higher than that of using entropy alone between groups GS≤3 + 4 and ≥4 + 3, as well as between groups GS≤4 + 3 and ≥8.

CONCLUSION

Texture analysis on T2-weighted images of prostate cancer can evaluate Gleason score, especially using the combination of entropy and energy rendering better diagnostic efficiency.