Association between changes in suspicious prostate lesions on serial MRI examinations and follow-up biopsy results

AI-assisted biparametric MRI surveillance of prostate cancer: feasibility study

OBJECTIVES

To evaluate the feasibility of automatic longitudinal analysis of consecutive biparametric MRI (bpMRI) scans to detect clinically significant (cs) prostate cancer (PCa).

METHODS

This retrospective study included a multi-center dataset of 1513 patients who underwent bpMRI (T2 + DWI) between 2014 and 2020, of whom 73 patients underwent at least two consecutive bpMRI scans and repeat biopsies. A deep learning PCa detection model was developed to produce a heatmap of all PIRADS ≥ 2 lesions across prior and current studies. The heatmaps for each patient's prior and current examination were used to extract differential volumetric and likelihood features reflecting explainable changes between examinations. A machine learning classifier was trained to predict from these features csPCa (ISUP > 1) at the current examination according to biopsy. A classifier trained on the current study only was developed for comparison. An extended classifier was developed to incorporate clinical parameters (PSA, PSA density, and age). The cross-validated diagnostic accuracies were compared using ROC analysis. The diagnostic performance of the best model was compared to the radiologist scores.

RESULTS

The model including prior and current study (AUC 0.81, CI: 0.69, 0.91) resulted in a higher (p = 0.04) diagnostic accuracy than the current only model (AUC 0.73, CI: 0.61, 0.84). Adding clinical variables further improved diagnostic performance (AUC 0.86, CI: 0.77, 0.93). The diagnostic performance of the surveillance AI model was significantly better (p = 0.02) than of radiologists (AUC 0.69, CI: 0.54, 0.81).

CONCLUSIONS

Our proposed AI-assisted surveillance of prostate MRI can pick up explainable, diagnostically relevant changes with promising diagnostic accuracy.

KEY POINTS

• Sequential prostate MRI scans can be automatically evaluated using a hybrid deep learning and machine learning approach. • The diagnostic accuracy of our csPCa detection AI model improved by including clinical parameters.

Multiparametric magnetic resonance imaging facilitates reclassification during active surveillance for prostate cancer

OBJECTIVE

To investigate the utility of multiparametric magnetic resonance imaging (mpMRI) in the reassessment and monitoring of patients on active surveillance (AS) for Grade Group (GG) 1 prostate cancer (PCa).

PATIENTS AND METHODS

We identified, from our prospectively maintained institutional review board-approved database, 181 consecutive men enrolled on AS for GG 1 PCa who underwent at least one surveillance mpMRI followed by MRI/prostate biopsy (PBx). A subset analysis was performed among 68 patients who underwent serial (at least two) mpMRI/PBx during AS. Pathological progression (PP) was defined as upgrade to GG ≥2 on follow up biopsy.

RESULTS

Baseline MRI was performed in 34 patients (19%). At a median follow-up of 2.2 years for the overall cohort, the PP was 12% (6/49) for Prostate Imaging Reporting and Data System (PI-RADS) 1-2 lesions and 37% (48/129) for the PI-RADS ≥3 lesions. The 2-year PP-free survival rate was 84%. Surveillance prostate-specific antigen density (P < 0.001) and surveillance PI-RADS ≥3 (P = 0.002) were independent predictors of PP on reassessment MRI/PBx. In the serial MRI cohort, the 2-year PP-free survival was 95% for the No-MRI-progression group vs 85% for the MRI-progression group (P = 0.02). MRI progression was significantly higher in the PP (62%) than in the No-PP (31%) group (P = 0.04). If serial MRI were used for PCa surveillance and biopsy were triggered based only on MRI progression, 63% of PBx might be postponed at the cost of missing 12% of GG ≥2 PCa in those with stable MRI. Conversely, this strategy would miss 38% of those with upgrading to GG ≥2 PCa on biopsy. Stable serial mpMRI correlates with no reclassification to GG ≥3 PCa during AS.

CONCLUSION

On surveillance mpMRI, PI-RADS ≥3 was associated with increased risk of PCa reclassification. Surveillance biopsy based only on MRI progression may avoid a large number of biopsies at the cost of missing many PCa reclassifications.

Intra- and interreader reproducibility of PI-RADSv2: A multireader study

BACKGROUND

The Prostate Imaging Reporting and Data System version 2 (PI-RADSv2) has been in use since 2015; while interreader reproducibility has been studied, there has been a paucity of studies investigating the intrareader reproducibility of PI-RADSv2.

PURPOSE

To evaluate both intra- and interreader reproducibility of PI-RADSv2 in the assessment of intraprostatic lesions using multiparametric magnetic resonance imaging (mpMRI).

STUDY TYPE

Retrospective.

POPULATION/SUBJECTS

In all, 102 consecutive biopsy-naïve patients who underwent prostate MRI and subsequent MR/transrectal ultrasonography (MR/TRUS)-guided biopsy.

FIELD STRENGTH/SEQUENCES

Prostate mpMRI at 3T using endorectal with phased array surface coils (TW MRI, DW MRI with ADC maps and b2000 DW MRI, DCE MRI).

ASSESSMENT

Previously detected and biopsied lesions were scored by four readers from four different institutions using PI-RADSv2. Readers scored lesions during two readout rounds with a 4-week washout period.

STATISTICAL TESTS

Kappa (κ) statistics and specific agreement (Po ) were calculated to quantify intra- and interreader reproducibility of PI-RADSv2 scoring. Lesion measurement agreement was calculated using the intraclass correlation coefficient (ICC).

RESULTS

Overall intrareader reproducibility was moderate to substantial (κ = 0.43-0.67, Po  = 0.60-0.77), while overall interreader reproducibility was poor to moderate (κ = 0.24, Po  = 46). Readers with more experience showed greater interreader reproducibility than readers with intermediate experience in the whole prostate (P = 0.026) and peripheral zone (P = 0.002). Sequence-specific interreader agreement for all readers was similar to the overall PI-RADSv2 score, with κ = 0.24, 0.24, and 0.23 and Po  = 0.47, 0.44, and 0.54 in T2 -weighted, diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE), respectively. Overall intrareader and interreader ICC for lesion measurement was 0.82 and 0.71, respectively.

DATA CONCLUSION

PI-RADSv2 provides moderate intrareader reproducibility, poor interreader reproducibility, and moderate interreader lesion measurement reproducibility. These findings suggest a need for more standardized reader training in prostate MRI.

LEVEL OF EVIDENCE

2 Technical Efficacy: Stage 2.

Outcomes of Serial Multiparametric Magnetic Resonance Imaging and Subsequent Biopsy in Men with Low-risk Prostate Cancer Managed with Active Surveillance

BACKGROUND

Outcomes of serial multiparametric magnetic resonance imaging (mpMRI) and subsequent biopsy in monitoring prostate cancer (PCa) in men on active surveillance (AS) have not been defined clearly.

OBJECTIVE

To determine whether changes in serial mpMRI can predict pathological upgrade among men with grade group (GG) 1 PCa managed with AS.

DESIGN, SETTING, AND PARTICIPANTS

Retrospective analysis of men with GG1 on AS with at least two consecutive mpMRI examinations during 2012-2018 who underwent mpMRI/ultrasound fusion or systematic biopsies.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Progression on serial mpMRI was evaluated as a predictor of pathological upgrading to GG≥2 on a follow-up biopsy using clinical, pathological, and imaging factors in binary logistic regression. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were determined.

RESULTS AND LIMITATIONS

Of 122 patients, 29 men (23.8%) experienced pathological upgrade on the follow-up biopsy. Progression on mpMRI was not associated with pathological upgrade. The sensitivity, specificity, PPV, and NPV of mpMRI progression for predicting pathological upgrade were 41.3%, 54.8%, 22.2%, and 75%, respectively. Age (odds ratio [OR] 1.17, p=0.006), Prostate Imaging Reporting and Data System (PI-RADS) score on initial mpMRI (4-5 vs ≤3, OR 7.48, p=0.01), number of positive systematic cores (OR 1.84, p=0.03), number of positive targeted cores (OR 0.44, p=0.04), and maximum percent of targeted core tumor involvement (OR 1.04, p=0.01) were significantly associated with pathological upgrade.

CONCLUSIONS

We did not observe an association between mpMRI progression and pathological upgrade; however, a PI-RADS score of 4-5 on initial mpMRI was predictive of subsequent pathological progression. The continued use of systematic and fusion biopsies appears necessary due to risks of reclassification over time.

PATIENT SUMMARY

Progression on serial multiparametric magnetic resonance imaging during active surveillance (AS) is not associated with progression on the follow-up biopsy. Both systematic and fusion biopsies are necessary to sufficiently capture progression during AS.

Is magnetic resonance imaging-targeted biopsy a useful addition to systematic confirmatory biopsy in men on active surveillance for low-risk prostate cancer? A systematic review and meta-analysis

OBJECTIVE

To systematically review and meta-analyse evidence regarding the additional value of magnetic resonance imaging (MRI) and MRI-targeted biopsies to confirmatory systematic biopsies in identifying high-grade prostate cancer in men with low-risk disease on transrectal ultrasonography (TRUS) biopsy, as active surveillance (AS) of prostate cancer is recommended for men with Gleason 3 + 3 on standard TRUS-guided biopsy. Confirmatory assessment can include repeat standard TRUS-guided biopsy, and/or MRI with targeted biopsy when indicated.

METHODS

A systematic review of the Embase, Medline, Web-of-science, Google scholar, and Cochrane library was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Identified reports were critically appraised according to the Quality Assessment of Diagnostic Accuracy Studies (QUADAS)-2 criteria. Studies reporting men with Gleason 3 + 3 prostate cancer who had chosen AS based on transrectal systematic biopsy findings and had undergone MRI with systematic ± targeted biopsy at confirmatory assessment were included. The primary outcome was detection of any Gleason pattern ≥4.

RESULTS

Included reports (six) of men on AS (n = 1 159) showed cancer upgrading (Gleason ≥3 + 4) in 27% (95% confidence interval [CI] 22-34%) using a combined approach of MRI-targeted biopsies and confirmatory systematic biopsies. MRI-targeted biopsies alone would have missed cancer upgrading in 10% (95% CI 8-14%) and standard biopsies alone would have missed cancer upgrading in 7% (95% CI 5-10%). No pathway was more favourable than the other (relative risk [RR] 0.92, 95% CI 0.79-1.06). In all, 35% (95% CI 27-43%) of men with a positive MRI were upgraded, compared to 12% (95% CI 8-18%) of men with a negative MRI being upgraded (RR 2.77, 95% CI 1.76-4.38).

CONCLUSIONS

A pre-biopsy MRI should be performed before confirmatory systematic TRUS-guided biopsies in men on AS, together with MRI-targeted biopsies when indicated. A combined approach maximises cancer detection, although other factors within multivariate risk prediction can be used to aid the decision to biopsy in these men.

[Active surveillance in prostate cancer: Assessment of MRI in the selection and follow-up of patients]

AIM

To evaluate the contribution of multiparametric MRI (MRI) and targeted biopsies (TB) in the selection and follow-up of patients under active surveillance (AS).

METHODS

A single-center, retrospective cohort study on 131 patients in AS, with following criteria:≤cT2 stage, PSA≤15ng/mL, Gleason score≤6,≤3 positive biopsies and maximum tumor length≤5mm. Patients' selection and follow-up was performed by the combination of systemic biopsies (SB) and mpMRI±TB. Reclassification was defined by a Gleason score>6 and/or a maximum tumor length>5mm.

RESULTS

Overall, 29 patients (22.1 %) were reclassified. Reclassification free survival rate was 93 % and 70 % at 1 year and 4 years respectively. Reclassification independent risk factors were: PSA density>0.15ng/mL/cm³ (RR=2.75), PSA doubling time<3 years (RR=9.28), suspicious lesion on MRI diagnosis (RR=2.79) and occurrence of MRI progression during follow-up (RR=2). Sensitivity, specificity, PPV and NPV of MRI to assess progression for reclassification were 61 %, 69 %, 45 % and 81 %, respectively.

CONCLUSION

For patients under AS, mpMRI decreases reclassification rates over time through better initial detection of significant cancers. Its high NPV makes it an efficient monitoring tool to distinguish patients with low risk of reclassification.

LEVEL OF EVIDENCE

4.

Reproducibility of Multiparametric Magnetic Resonance Imaging and Fusion Guided Prostate Biopsy: Multi-Institutional External Validation by a Propensity Score Matched Cohort

PURPOSE

As the adoption of magnetic resonance imaging/ultrasound fusion guided biopsy expands, the reproducibility of outcomes at expert centers becomes essential. We sought to validate the comprehensive NCI (National Cancer Institute) experience with multiparametric magnetic resonance imaging and fusion guided biopsy in an external, independent, matched cohort of patients.

MATERIALS AND METHODS

We compared 620 patients enrolled in a prospective trial comparing systematic biopsy to fusion guided biopsy at NCI to 310 who underwent a similar procedure at Long Island Jewish Medical Center. The propensity score, defined as the probability of being treated outside NCI, was calculated using the estimated logistic regression model. Patients from the hospital were matched 1:1 for age, prostate specific antigen, magnetic resonance imaging suspicion score and prior negative biopsies. Clinically significant disease was defined as Gleason 3 + 4 or greater.

RESULTS

Before matching we found differences between the cohorts in age, magnetic resonance imaging suspicion score (each p <0.001), the number of patients with prior negative biopsies (p = 0.01), and the overall cancer detection rate and the cancer detection rate by fusion guided biopsy (each p <0.001). No difference was found in the rates of upgrading by fusion guided biopsy (p = 0.28) or upgrading to clinically significant disease (p = 0.95). A statistically significant difference remained in the overall cancer detection rate and the rate by fusion guided biopsy after matching. On subgroup analysis we found a difference in the overall cancer detection rate and the rate by fusion guided biopsy (p <0.001 and 0.003) in patients with prior negative systematic biopsy but no difference in the 2 rates (p = 0.39 and 0.51, respectively) in biopsy naïve patients.

CONCLUSIONS

Improved detection of clinically significant cancer by magnetic resonance imaging and fusion guided biopsy is reproducible by an experienced multidisciplinary team consisting of dedicated radiologists and urologists.

Serial Magnetic Resonance Imaging in Active Surveillance of Prostate Cancer: Incremental Value

PURPOSE

We assessed whether changes in serial multiparametric magnetic resonance imaging can help predict the pathological progression of prostate cancer in men on active surveillance.

MATERIALS AND METHODS

A retrospective cohort study was conducted of 49 consecutive men with Gleason 6 prostate cancer who underwent multiparametric magnetic resonance imaging at baseline and again more than 6 months later, each followed by a targeted prostate biopsy, between January 2011 and May 2015. We evaluated whether progression on multiparametric magnetic resonance imaging (an increase in index lesion suspicion score, increase in index lesion volume or decrease in index lesion apparent diffusion coefficient) could predict pathological progression (Gleason 3 + 4 or greater on subsequent biopsy, in systematic or targeted cores). Diagnostic performance of multiparametric magnetic resonance imaging was determined with and without clinical data using a binary logistic regression model.

RESULTS

The mean interval between baseline and followup multiparametric magnetic resonance imaging was 28.3 months (range 11 to 43). Pathological progression occurred in 19 patients (39%). The sensitivity, specificity, positive predictive value and negative predictive value of multiparametric magnetic resonance imaging was 37%, 90%, 69% and 70%, respectively. Area under the receiver operating characteristic curve was 0.63. A logistic regression model using clinical information (maximum cancer core length greater than 3 mm on baseline biopsy or a prostate specific antigen density greater than 0.15 ng/ml(2) at followup biopsy) had an AUC of 0.87 for predicting pathological progression. The addition of serial multiparametric magnetic resonance imaging data significantly improved the AUC to 0.91 (p=0.044).

CONCLUSIONS

Serial multiparametric magnetic resonance imaging adds incremental value to prostate specific antigen density and baseline cancer core length for predicting Gleason 6 upgrading in men on active surveillance.

Likert score 3 prostate lesions: Association between whole-lesion ADC metrics and pathologic findings at MRI/ultrasound fusion targeted biopsy

BACKGROUND

To assess associations between whole-lesion apparent diffusion coefficient (ADC) metrics and pathologic findings of Likert score 3 prostate lesions at MRI/ultrasound fusion targeted biopsy.

METHODS

This retrospective Institutional Review Board-approved study received a waiver of consent. We identified patients receiving a highest lesion score of 3 on 3 Tesla multiparametric MRI reviewed by a single experienced radiologist using a 5-point Likert scale and who underwent fusion biopsy. A total of 188 score 3 lesions in 158 patients were included. Three-dimensional volumes-of-interest encompassing each lesion were traced on ADC maps. Logistic regression was used to predict biopsy results based on whole-lesion ADC metrics and patient biopsy history. Biopsy yield was compared between metrics.

RESULTS

By lesion, targeted biopsy identified tumor in 22.3% and Gleason score (GS) > 6 tumor in 8.5%, although results varied by biopsy history: biopsy-naïve (n = 80), 20.0%/8.8%; prior negative biopsy (n = 53), 9.4%/1.9%; prior positive biopsy (n = 55): 40.0%/14.5%. Biopsy history, whole-lesion mean ADC, whole-lesion ADC10-25 , and whole-lesion ADC25-50 were each significantly associated with tumor or GS > 6 tumor at fusion biopsy (P ≤ 0.047). In men without prior negative prostate biopsy, whole-lesion ADC25-50  ≤ 1.04*10(-3) mm2 /s achieved 90.0% sensitivity and 50.0% specificity for GS > 6 tumor, which was significantly higher (P < 0.001) than specificity of PSA (17.5%) at identical sensitivity.

CONCLUSION

For score 3 lesions in patients without prior negative biopsy, whole-lesion ADC metrics help detect GS > 6 cancer while avoiding negative biopsies. However, deferral of fusion biopsy may be considered for score 3 lesions in patients with prior negative biopsy (without applying whole-lesion ADC metrics) given exceedingly low (∼ 2%) frequency of GS > 6 tumor in this group.

Natural History of Pathologically Benign Cancer Suspicious Regions on Multiparametric Magnetic Resonance Imaging Following Targeted Biopsy

PURPOSE

We determined the natural history of pathologically benign cancer suspicious regions on multiparametric magnetic resonance imaging following targeted biopsy.

MATERIALS AND METHODS

Between January 2012 and September 2014, 330 men underwent prostate multiparametric magnetic resonance imaging. A total of 533 cancer suspicious regions were identified and scored on a Likert scale of 1 to 5 based on suspicion for malignancy with 5 indicating the highest suspicion level. Following multiparametric magnetic resonance imaging all men underwent magnetic resonance imaging-ultrasound fusion targeted prostate biopsy using ProFuse software and the ei-Nav|Artemis system (innoMedicus, Cham, Switzerland), and a computer generated 12-core random biopsy. We analyzed a cohort of 34 men with a total of 51 cancer suspicious regions who had benign prostate biopsies and underwent repeat multiparametric magnetic resonance imaging and prostate specific antigen testing at 1 year. Changes in the greatest linear measurement, the suspicion score and serum prostate specific antigen were ascertained.

RESULTS

During 1 year the suspicion score distribution and the mean greatest linear measurement of the cancer suspicious regions decreased significantly (p <0.0001) while mean prostate specific antigen did not significantly change (p = 0.632). Two (3.9%), 15 (29.4%) and 34 cancer suspicious regions (66.7%) showed an increase, no change and decrease in suspicion score, respectively. No (0%), 21 (42.0%) and 29 cancer suspicious regions (58.0%) showed an increase of 20% or greater, no change and a decrease of 20% or greater in greatest linear measurement, respectively. Of the 2 cancer suspicious regions exhibiting an increased suspicion score neither showed a prostate specific antigen increase of 0.5 ng/ml or greater.

CONCLUSIONS

Our study provides compelling evidence that few benign cancer suspicious regions increase in suspicion score and/or the greatest linear measurement within 1 year independent of the baseline suspicion score. Therefore, routinely repeating multiparametric magnetic resonance imaging at 1 year in men with pathologically benign cancer suspicious regions should be discouraged since it is unlikely to influence management decisions.