Comparison of Pathologist and Artificial Intelligence-based Grading for Prediction of Metastatic Outcomes After Radical Prostatectomy.

Gleason grade group (GG) is the most powerful prognostic variable in localized prostate cancer; however, interobserver variability remains a challenge. Artificial intelligence algorithms applied to histopathologic images standardize grading, but most have been tested only for agreement with pathologist GG, without assessment of performance with respect to oncologic outcomes. We compared deep learning-based and pathologist-based GGs for an association with metastatic outcome in three surgical cohorts comprising 777 unique patients. A digitized whole slide image of the representative hematoxylin and eosin-stained slide of the dominant tumor nodule was assigned a GG by an artificial intelligence-based grading algorithm and was compared with the GG assigned by a contemporary pathologist or the original pathologist-assigned GG for the entire prostatectomy. Harrell's C-indices based on Cox models for time to metastasis were compared. In a combined analysis of all cohorts, the C-index for the artificial intelligence-assigned GG was 0.77 (95% confidence interval [CI]: 0.73-0.81), compared with 0.77 (95% CI: 0.73-0.81) for the pathologist-assigned GG. By comparison, the original pathologist-assigned GG for the entire case had a C-index of 0.78 (95% CI: 0.73-0.82). PATIENT SUMMARY: Artificial intelligence-enabled prostate cancer grading on a single slide was comparable with pathologist grading for predicting metastatic outcome in men treated by radical prostatectomy, enabling equal access to expert grading in lower resource settings.

PTEN Loss Is Associated with Adverse Outcomes in the Setting of Salvage Radiation Therapy.

BACKGROUND: Salvage radiation therapy (SRT) is a mainstay of treatment for biochemical relapse following radical prostatectomy; however, few studies have examined genomic biomarkers in this context. OBJECTIVE: We characterized the prognostic impact of previously identified deleterious molecular phenotypes-loss of PTEN, ERG expression, and TP53 mutation-for patients undergoing SRT. DESIGN, SETTING, AND PARTICIPANTS: We leveraged an institutional database of 320 SRT patients with available tissue and follow-up. Tissue microarrays were used for genetically validated immunohistochemistry assays. INTERVENTION: All men underwent SRT with or without androgen deprivation therapy OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Univariable and multivariable Cox-proportional hazard models assessed the association of molecular phenotypes with biochemical recurrence-free (bRFS) and metastasis-free (MFS) survival after SRT. RESULTS AND LIMITATIONS: Loss of PTEN (n = 123, 43%) and ERG expression (n = 118, 39%) were common in this cohort, while p53 overexpression (signifying TP53 missense mutation) was infrequent (n = 21, 7%). In univariable analyses, any loss of PTEN portended worse bRFS (hazard ratio [HR] 1.86; 95% confidence interval 1.36-2.57) and MFS (HR 1.89; 1.21-2.94), with homogeneous PTEN loss being associated with the highest risk of MFS (HR 2.47; 1.54-3.95). Similarly, p53 overexpression predicted worse bRFS (HR 1.95; 1.14-3.32) and MFS (HR 2.79; 1.50-5.19). ERG expression was associated with worse MFS only (HR 1.6; 1.03-2.48). On the multivariable analysis adjusting for known prognostic features, homogeneous PTEN loss remained predictive of adverse bRFS (HR 1.82; 1.12-2.96) and MFS (HR 2.08; 1.06-4.86). The study is limited by its retrospective and single-institution design. CONCLUSIONS: PTEN loss by immunohistochemistry is an independent adverse prognostic factor for bRFS and MFS in prostate cancer patients treated with SRT. Future trials will determine the optimal approach to treating SRT patients with adverse molecular prognostic features. PATIENT SUMMARY: Loss of the PTEN tumor suppressor protein is associated with worse outcomes after salvage radiotherapy, independent of other clinical or pathologic patient characteristics.

Association of Genomic Prostate Score at positive margin with recurrence after radical prostatectomy.

OBJECTIVES: To evaluate the utility of the 17-gene Genomic Prostate Score® (GPS; MDxHealth, Irvine, CA, USA) performed on prostate cancer at the positive margin of the radical prostatectomy (RP) for its association with risk of subsequent biochemical recurrence (BCR). PATIENTS AND METHODS: We designed a case-cohort for the outcome of BCR, selecting 223 from a cohort of 813 RP patients treated at Johns Hopkins from 2008 to 2017 with positive margins and available clinical data; of these, 213 had available tissue and clinical data. RNA was isolated from formalin-fixed paraffin-embedded tumour tissue adjacent to the positive surgical margin and the GPS was evaluable in 203 of these patients with a score ranging from 0 to 100, with higher scores indicating higher risk. All patients underwent RP with or without adjuvant radiation therapy (ART). The statistical analysis employed Cox proportional hazards regression models for outcome of BCR weighted for case-cohort design. RESULTS: In univariable analysis, every 20-unit increase in the GPS was associated with a nearly threefold increase in risk of BCR (hazard ratio [HR] per 20 units 2.82, P < 0.001). In a multivariable Cox model adjusted for age, race, Cancer of the Prostate Risk Assessment Postsurgical score, Grade Group at the positive margin, and ART, the GPS was significantly associated with BCR (HR 1.56 per 20 units; 95% confidence interval 1.11-2.19; P = 0.011). The study is limited by its retrospective and single institution design. CONCLUSIONS: The GPS at the positive surgical margin could help stratify prognosis and inform clinical decision-making regarding adjuvant therapy after RP.

FASN Gene Methylation is Associated with Fatty Acid Synthase Expression and Clinical-genomic Features of Prostate Cancer.

Fatty acid synthase (FASN) catalyzes the synthesis of long-chain saturated fatty acids and is overexpressed during prostatic tumorigenesis, where it is the therapeutic target in several ongoing trials. However, the mechanism of FASN upregulation in prostate cancer remains unclear. Here, we examine FASN gene CpG methylation pattern by InfiniumEPIC profiling and whole-genome bisulfite sequencing across multiple racially diverse primary and metastatic prostate cancer cohorts, comparing with FASN protein expression as measured by digitally quantified IHC assay and reverse phase protein array analysis or FASN gene expression. We demonstrate that the FASN gene body is hypomethylated and overexpressed in primary prostate tumors compared with benign tissue, and FASN gene methylation is significantly inversely correlated with FASN protein or gene expression in both primary and metastatic prostate cancer. Primary prostate tumors with ERG gene rearrangement have increased FASN expression and we find evidence of FASN hypomethylation in this context. FASN expression is also significantly increased in prostate tumors from carriers of the germline HOXB13 G84E mutation compared with matched controls, consistent with a report that HOXB13 may contribute to epigenetic regulation of FASN in vitro. However, in contrast to previous studies, we find no significant association of FASN expression or methylation with self-identified race in models that include ERG status across two independent primary tumor cohorts. Taken together, these data support a potential epigenetic mechanism for FASN regulation in the prostate which may be relevant for selecting patients responsive to FASN inhibitors. SIGNIFICANCE: Here, we leverage multiple independent primary and metastatic prostate cancer cohorts to demonstrate that FASN gene body methylation is highly inversely correlated with FASN gene and protein expression. This finding may shed light on epigenetic mechanisms of FASN regulation in prostate cancer and provides a potentially useful biomarker for selecting patients in future trials of FASN inhibitors.

Predicting Prostate Cancer Molecular Subtype With Deep Learning on Histopathologic Images.

Microscopic examination of prostate cancer has failed to reveal a reproducible association between molecular and morphologic features. However, deep-learning algorithms trained on hematoxylin and eosin (H&E)-stained whole slide images (WSI) may outperform the human eye and help to screen for clinically-relevant genomic alterations. We created deep-learning algorithms to identify prostate tumors with underlying ETS-related gene (ERG) fusions or PTEN deletions using the following 4 stages: (1) automated tumor identification, (2) feature representation learning, (3) classification, and (4) explainability map generation. A novel transformer-based hierarchical architecture was trained on a single representative WSI of the dominant tumor nodule from a radical prostatectomy (RP) cohort with known ERG/PTEN status (n = 224 and n = 205, respectively). Two distinct vision transformer-based networks were used for feature extraction, and a distinct transformer-based model was used for classification. The ERG algorithm performance was validated across 3 RP cohorts, including 64 WSI from the pretraining cohort (AUC, 0.91) and 248 and 375 WSI from 2 independent RP cohorts (AUC, 0.86 and 0.89, respectively). In addition, we tested the ERG algorithm performance in 2 needle biopsy cohorts comprised of 179 and 148 WSI (AUC, 0.78 and 0.80, respectively). Focusing on cases with homogeneous (clonal) PTEN status, PTEN algorithm performance was assessed using 50 WSI reserved from the pretraining cohort (AUC, 0.81), 201 and 337 WSI from 2 independent RP cohorts (AUC, 0.72 and 0.80, respectively), and 151 WSI from a needle biopsy cohort (AUC, 0.75). For explainability, the PTEN algorithm was also applied to 19 WSI with heterogeneous (subclonal) PTEN loss, where the percentage tumor area with predicted PTEN loss correlated with that based on immunohistochemistry (r = 0.58, P = .0097). These deep-learning algorithms to predict ERG/PTEN status prove that H&E images can be used to screen for underlying genomic alterations in prostate cancer.

Clinical and Genomic Differences Between Advanced Molecular Imaging-detected and Conventional Imaging-detected Metachronous Oligometastatic Castration-sensitive Prostate Cancer.

In metastatic castration-sensitive prostate cancer (mCSPC), disease volume plays an integral role in guiding treatment recommendations, including selection of docetaxel therapy, metastasis-directed therapy, and radiation to the prostate. Although there are multiple definitions of disease volume, they have commonly been studied in the context of metastases detected via conventional imaging (CIM). One such numeric definition of disease volume, termed oligometastasis, is heavily dependent on the sensitivity of the imaging modality. We performed an international multi-institutional retrospective review of men with metachronous oligometastatic CSPC (omCSPC), detected via either advanced molecular imaging alone (AMIM) or CIM. Patients were compared with respect to clinical and genomic features using the Mann-Whitney U test, Pearson's χ2 test, and Kaplan-Meier overall survival (OS) analyses with a log-rank test. A total of 295 patients were included for analysis. Patients with CIM-omCSPC had significantly higher Gleason grade group (p = 0.032), higher prostate-specific antigen at omCSPC diagnosis (8.0 vs 1.7 ng/ml; p < 0.001), more frequent pathogenic TP53 mutations (28% vs 17%; p = 0.030), and worse 10-yr OS (85% vs 100%; p < 0.001). This is the first report of clinical and biological differences between AMIM-detected and CIM-detected omCSPC. Our findings are particularly important for ongoing and planned clinical trials in omCSPC. PATIENT SUMMARY: Metastatic prostate cancer with just a few metastases only detected via newer scanning methods (called molecular imaging) is associated with fewer high-risk DNA mutations and better survival in comparison to metastatic cancer detected via conventional scan methods.

ERG Status at the Margin Is Associated With Biochemical Recurrence After Radical Prostatectomy With Positive Surgical Margins.

Positive surgical margins at radical prostatectomy are associated with an increased risk of biochemical recurrence (BCR). However, there is considerable variability in outcomes, suggesting that molecular biomarkers-when assessed specifically at the margin tumor tissue-may be useful to stratify prognosis in this group. We used a case-cohort design for the outcome of BCR, selecting 215 patients from a cohort of 813 patients undergoing prostatectomy treated at the Johns Hopkins from 2008 to 2017 with positive margins and available clinical data. Tissue microarrays were created from the tumor adjacent to the positive margin and stained for PTEN, ERG, and Ki-67. Cases were scored dichotomously (PTEN and ERG) or by the Ki-67 staining index using previously validated protocols. The analysis used Cox proportional hazards models weighted for the case-cohort design. Overall, 20% (37/185) of evaluable cases had PTEN loss and 38% (71/185) had ERG expression, and the median Ki-67 expression was 0.42%. In multivariable analysis adjusting for the CAPRA-S score, adjuvant radiation, and grade group at the positive margin, ERG-positive tumors were associated with a higher risk of BCR compared to those that were ERGnegative (hazard ratio [HR], 2.4; 95% CI, 1.2-4.9; P = .012) regardless of PTEN status at the margin, and adding ERG to clinicopathologic variables increased the concordance index from 0.827 to 0.847. PTEN loss was associated with an increased risk of BCR on univariable analysis (HR, 3.19; 95% CI, 1.72-5.92; P = .0002), but this association did not remain after adjusting for clinicopathologic variables (HR, 1.06; 95% CI, 0.49-2.29; P = .890). Thus, in the setting of prostate tumors with positive surgical margins after prostatectomy, ERG-positive tumors with or without PTEN loss at the positive margin are associated with a significantly higher risk of BCR after adjusting for clinicopathologic variables. If validated, ERG status may be helpful in decision-making surrounding adjuvant therapy after prostatectomy.

Association of self-identified race and genetic ancestry with the immunogenomic landscape of primary prostate cancer.

The genomic and immune landscapes of prostate cancer differ by self-identified race. However, few studies have examined the genome-wide copy number landscape and immune content of matched cohorts with genetic ancestry data and clinical outcomes. Here, we assessed prostate cancer somatic copy number alterations (sCNA) and tumor immune content of a grade-matched, surgically treated cohort of 145 self-identified Black (BL) and 145 self-identified White (WH) patients with genetic ancestry estimation. A generalized linear model adjusted with age, preoperative prostate-specific antigen (PSA), and Gleason Grade Group and filtered for germline copy number variations (gCNV) identified 143 loci where copy number varied significantly by percent African ancestry, clustering on chromosomes 6p, 10q, 11p, 12p, and 17p. Multivariable Cox regression models adjusted for age, preoperative PSA levels, and Gleason Grade Group revealed that chromosome 8q gains (including MYC) were significantly associated with biochemical recurrence and metastasis, independent of genetic ancestry. Finally, Treg density in BL and WH patients was significantly correlated with percent genome altered, and these findings were validated in the TCGA cohort. Taken together, our findings identify specific sCNA linked to genetic ancestry and outcome in primary prostate cancer and demonstrate that Treg infiltration varies by global sCNA burden in primary disease.

An mTORC1-mediated negative feedback loop constrains amino acid-induced FLCN-Rag activation in renal cells with TSC2 loss.

The mechanistic target of rapamycin complex 1 (mTORC1) integrates inputs from growth factors and nutrients, but how mTORC1 autoregulates its activity remains unclear. The MiT/TFE transcription factors are phosphorylated and inactivated by mTORC1 following lysosomal recruitment by RagC/D GTPases in response to amino acid stimulation. We find that starvation-induced lysosomal localization of the RagC/D GAP complex, FLCN:FNIP2, is markedly impaired in a mTORC1-sensitive manner in renal cells with TSC2 loss, resulting in unexpected TFEB hypophosphorylation and activation upon feeding. TFEB phosphorylation in TSC2-null renal cells is partially restored by destabilization of the lysosomal folliculin complex (LFC) induced by FLCN mutants and is fully rescued by forced lysosomal localization of the FLCN:FNIP2 dimer. Our data indicate that a negative feedback loop constrains amino acid-induced, FLCN:FNIP2-mediated RagC activity in renal cells with constitutive mTORC1 signaling, and the resulting MiT/TFE hyperactivation may drive oncogenesis with loss of the TSC2 tumor suppressor.

Long-Term Outcomes and Genetic Predictors of Response to Metastasis-Directed Therapy Versus Observation in Oligometastatic Prostate Cancer: Analysis of STOMP and ORIOLE Trials.

Clinical trials frequently include multiple end points that mature at different times. The initial report, typically based on the primary end point, may be published when key planned co-primary or secondary analyses are not yet available. Clinical Trial Updates provide an opportunity to disseminate additional results from studies, published in JCO or elsewhere, for which the primary end point has already been reported.The initial STOMP and ORIOLE trial reports suggested that metastasis-directed therapy (MDT) in oligometastatic castration-sensitive prostate cancer (omCSPC) was associated with improved treatment outcomes. Here, we present long-term outcomes of MDT in omCSPC by pooling STOMP and ORIOLE and assess the ability of a high-risk mutational signature to risk stratify outcomes after MDT. The primary end point was progression-free survival (PFS) calculated using the Kaplan-Meier method. High-risk mutations were defined as pathogenic somatic mutations within ATM, BRCA1/2, Rb1, or TP53. The median follow-up for the whole group was 52.5 months. Median PFS was prolonged with MDT compared with observation (pooled hazard ratio [HR], 0.44; 95% CI, 0.29 to 0.66; P value < .001), with the largest benefit of MDT in patients with a high-risk mutation (HR high-risk, 0.05; HR no high-risk, 0.42; P value for interaction: .12). Within the MDT cohort, the PFS was 13.4 months in those without a high-risk mutation, compared with 7.5 months in those with a high-risk mutation (HR, 0.53; 95% CI, 0.25 to 1.11; P = .09). Long-term outcomes from the only two randomized trials in omCSPC suggest a sustained clinical benefit to MDT over observation. A high-risk mutational signature may help risk stratify treatment outcomes after MDT.