Background Understanding the molecular features that underlie metastatic prostate cancer (PCa) is essential to develop prognostic markers and improve treatment decisions. However, such studies are hampered by substantial intratumor and interpatient heterogeneity. Methods To cope with this heterogeneity, we propose a unique study design that leverages the statistical power of multifocal bulk transcriptome profiling with the resolution of a single-cell analysis to identify processes and cell types associated with regional metastatic lymph node seeding in PCa. Results Elaborate analysis of these data allowed identifying a metric to distinguish, based on the multifocal expression data between lesions with high and low potential for regional metastatic lymph node seeding. Subsequently comparing the expression profiles of these lesions with respectively high and low metastatic potential identified an aggressiveness signature. Overlaying this signature with single cell data identified proliferative luminal cells, an adipose derived cancer-associated fibroblast (CAF) state and a specific subtype of arterial endothelial cells. Assessing the prognostic value of these cell states in an independent dataset (TCGA-PRAD) confirmed their association with regional metastatic lymph node seeding and progression free survival and unveiled a complementary role for the proliferative luminal cells and the adipose derived CAF state in driving regional metastatic lymph node seeding. Conclusions Based on our analysis, we hypothesize that lesions with high potential for regional metastatic lymph node seeding are mostly characterized by the presence of highly proliferative luminal cells and a transitioning towards an aggressive adipose derived CAF state. Markers associated with these cell states largely explain the prognostic signal of currently used commercial signatures in PCa, further supporting the role of the identified cell states in driving regional metastatic lymph node seeding and providing an in depth understanding of the success of the currently used commercial signatures.

INTRODUCTION:This study aimed to evaluate the harms and oncological benefits of pelvic lymph node dissection (PLND) during radical prostatectomy (RP) in prostate cancer patients at risk for regional lymph node invasion. METHODS:Patients with cN0M0 prostate cancer who underwent RP between January 2013 and February 2023 were included. Patients were categorized into two groups: 334 patients who underwent RP with PLND (group A) and 161 without PLND (group B). Perioperative and oncologic outcomes were assessed, and multivariate analysis identified independent prognostic factors. Inverse probability of treatment weighting (IPTW) was applied to account for baseline differences. RESULTS:Group A had more advanced disease, longer operation times, and higher complication rates, with 58.3% of complications related to PLND. After a median follow-up of 56 months, there were no significant differences in 4-year biochemical recurrence-free survival (BRFS) (68.9% vs. 75.4%), metastasis-free survival, or overall survival between the groups. Positive surgical margins and tumor grade were independent risk factors for biochemical recurrence, while PLND was not. Cox regression in the IPTW-adjusted cohort confirmed no significant impact of PLND on BRFS (HR: 0.70, p = 0.09). CONCLUSION:PLND during RP increases postoperative complications without improving short-term oncologic outcomes, serving mainly as a staging procedure to inform management.

Metastasis-directed therapy (MDT) is an emerging treatment option for metachronous oligometastatic castration-sensitive prostate cancer (omCSPC) and can delay time to progression and the need to initiate androgen deprivation therapy (ADT). However, optimal ways to synergize MDT and ADT are not known, and better personalization of MDT is needed. We examined the role of combined ADT and MDT and the ability of genomic alterations to provide prognostic and predictive information regarding response to MDT. We found that high-risk (HiRi) mutations in TP53, BRCA1/2, ATM, and Rb1 are poor prognostic markers in omCSPC. In addition, patients harboring HiRi mutations experienced greater benefit from addition of ADT to MDT, indicating that these alterations are predictive biomarkers for treatment intensification. Our results suggest that genetic biomarkers might aid in treatment personalization for patients with omCSPC.

e16591 Background: Limited biomarkers are available to predict response and outcome in metastatic urothelial carcinoma (mUC) patients treated with pembrolizumab. The Belgian multicenter CORPORA study evaluates the use of tissue, plasma and urine RNA as companion diagnostic in this setting. Results for plasma and urine will be presented. Methods: Baseline plasma (n = 41) and urine (n = 27) were prospectively collected in mUC patients receiving pembrolizumab (200 mg Q3W). Cell-free RNA (cfRNA) isolation and library prep, using Illumina RNA prep with enrichment, was followed by short read RNA sequencing (15M reads/sample). Data analysis included principal component analysis (PCA), differential gene expression (DGE), and gene set enrichment analysis (GSEA). Association to response (RECIST 1.1), survival, and occurrence of immune-related adverse events (irAEs) was determined. Results: PCA of plasma and urine did not reveal any sample clustering. Further downstream DGE indicated no significant difference in plasma cfRNA single gene abundance for response, outcome, or irAEs. In contrast, DGE in urine identified four significantly downregulated genes ( C12orf75 , RPS28P7 , ENSG00000267469 , RPL36AP37 ) and one significantly upregulated gene ( CIDEC ) that differentiate responders from non-responders. Regarding outcome, 5 genes ( ALKBH8 , FSIP1 , GDE1 , HMGB3 , and RHOU ) were identified as candidates for progression-free survival (PFS) and overall survival (OS, Table). A total of 271 genes, including the five genes identified for outcome, were significantly differentially abundant between patients who developed grade 3+ irAEs compared to those with milder grade 1-2 toxicity. GSEA indicated responders to exhibit cellular reprogramming toward enhanced metabolic fitness and tissue remodeling, whereas non-responders show a more stress-associated transcriptional state with altered immune, cell death, and mitochondrial respiration programs. Development of irAEs on the other hand was associated with broad immune hyperactivation and tissue remodeling programs, accompanied by suppression of mitochondrial oxidative metabolism. Conclusions: Urinary cfRNA contains candidate biomarkers for pembrolizumab response prediction, prolonged survival, and the occurrence of more severe irAEs. Further research is ongoing, including comparison to tissue RNA, and study of circular RNA, fusion genes, and immune cell enumeration via deconvolution. Cox regression univariate analysis for urine mRNA and survival. PFS OS Gene HR (95% CI)* P HR (95% CI)* P ALKBH8 0.46 (0.27-0.78) 0.004 0.58 (0.35-0.95) 0.030 FSIP1 0.55 (0.31-0.96) 0.036 0.37 (0.19-0.71) 0.003 GDE1 0.49 (0.25-0.94) 0.032 0.53 (0.29-0.96) 0.037 HMGB3 0.51 (0.31-0.84) 0.009 0.36 (0.17-0.73) 0.005 RHOU 0.57 (0.34-0.94) 0.028 0.38 (0.19-0.79) 0.009 *HRs representing change in risk per one standard deviation increase in gene expression.

Background/Objectives: Cisplatin-based neoadjuvant chemotherapy (NAC) followed by radical cystectomy has been the standard of care for muscle-invasive bladder cancer (MIBC) for two decades, yet a substantial proportion of patients derive no benefit. As antibody–drug conjugates and immune checkpoint inhibitors reshape perioperative treatment, it is unclear which patients retain meaningful benefit from platinum. We describe long-term outcomes and exploratory paired immune and genomic analyses in a single-centre cohort treated with dose-dense MVAC (dd-MVAC). Methods: We retrospectively identified 54 consecutive patients with MIBC treated with neoadjuvant dd-MVAC between November 2013 and November 2019. Forty-two underwent radical cystectomy and are assessable for pathologic response. Immunohistochemistry for CD3, CD8, FOXP3, PD-1, PD-L1, PD-L2, and NY-ESO-1 was evaluable in 31 baseline specimens and 22 paired specimens; paired genomic profiling was evaluable in 12 cases, with paired tumour mutational burden (TMB) in 10 by whole-exome sequencing and 7 by TSO-500. Paired analyses necessarily exclude patients achieving a pathologic complete response (pCR), who have no residual tumour, and most early progressors. Results: pCR was achieved in 11/42 operated patients (26%, 95% CI 15–41). Median follow-up was 87 months (IQR 24–104). Hydronephrosis was the only baseline factor associated with absence of pCR (p = 0.016). Within the operated cohort, pCR was associated with longer recurrence-free survival (log-rank p = 0.017), but the difference in overall survival did not reach significance (p = 0.121). NAC reduced intratumoral FOXP3 (q = 0.001), NY-ESO-1 (q = 0.013), PD-L2 (q = 0.013), and CD3 (q = 0.043) after correction for multiple comparisons, whereas TMB showed no significant change (TSO-500 p = 0.67; WES p = 0.86). No statistically significant association was detected between any baseline immune marker, including PD-L1, and pCR. The mutational landscape was largely concordant before and after NAC. Conclusions: This study was exploratory and was not powered to validate predictive biomarkers. In this long-term cohort, dd-MVAC was associated with measurable depletion of intratumoral immune populations in chemoresistant tumours, while paired genomic profiles remained broadly concordant. No pre-treatment biomarker identified platinum-refractory patients, but the small evaluable subsets mean these are hypothesis-generating rather than negative findings, and prospective studies with pre-specified biomarker endpoints are required.

OBJECTIVES:PSMA PET/CT (Prostate-Specific Membrane Antigen Positron Emission Tomography/Computed Tomography) offers improved accuracy in detecting lymph node invasion (LNI) in prostate cancer (PC) patients, potentially reducing the need for extended pelvic lymph node dissection (ePLND). This study aims to evaluate a patient-tailored care pathway in which ePLND is performed only in patients with unfavorable intermediate- or high-risk PC who are deemed at risk for LNI based on PSMA PET/CT findings. METHODS:In this interventional cohort study, 81 patients were managed according to the new care pathway. ePLND was omitted in cases of negative PSMA PET/CT findings (N0M0), while those with positive PSMA PET/CT findings (N1M0) underwent ePLND. A comparator group of 81 patients was selected from a prospectively generated database for comparison. RESULTS:The intervention group experienced a 75% reduction in the number of ePLNDs performed compared to the comparator group (p < 0.001). ePLND-related complications were significantly lower in the intervention group (p = 0.008). No significant difference was observed in 3-year biochemical-recurrence free survival (BRFS) between the two groups (p = 0.958). CONCLUSION:Omitting ePLND in patients with negative PSMA PET/CT findings (N0M0) leads to a substantial reduction in the number of ePLNDs performed, resulting in a decrease in morbidity, without compromising early oncological outcomes.

Background/Objectives: Cisplatin-based neoadjuvant chemotherapy (NAC) followed by radical cystectomy has been the standard of care for muscle-invasive bladder cancer (MIBC) for two decades, yet a substantial proportion of patients derive no benefit. With antibody–drug conjugates and immune checkpoint inhibitors now reshaping the treatment landscape, characterising the determinants of platinum resistance and the consequences for treatment sequencing has become clinically pressing. We aimed to describe, in a single-centre cohort with long follow-up, the patient trajectories, survival, immune microenvironment, tumour mutational burden (TMB) and genetic alterations associated with response to NAC. Methods: We retrospectively identified 54 consecutive patients with MIBC treated with neoadjuvant dose-dense MVAC (dd-MVAC) between November 2013 and November 2019. Pathologic response, recurrence, survival and subsequent therapy lines were recorded. Immunohistochemistry for CD3, CD8, FOXP3, PD-1, PD-L1, PD-L2 and NY-ESO-1, and paired genetic profiling (whole-exome sequencing and TSO-500) were performed on transurethral resection (TURBT) and cystectomy specimens. Marker changes after NAC were tested with Wilcoxon signed-rank tests; associations with pathologic complete response (pCR) with Fisher exact and Mann–Whitney tests; survival differences with the log-rank test. Results: pCR was achieved in 11/42 operated patients; 12 patients did not undergo cystectomy. Median follow-up was 87 months (IQR 24–104). Hydronephrosis (p = 0.016) was associated with absence of pCR. Overall and recurrence-free survival differed significantly by pathologic response (log-rank p = 0.040 and p = 0.026). NAC significantly reduced intratumoral FOXP3 (p < 0.001), NY-ESO-1 (p = 0.004), PD-L2 (p = 0.007) and CD3 (p = 0.029), whereas TMB was unchanged (TSO-500 p = 0.67; WES p = 0.86). No baseline immune marker, including PD-L1, predicted pCR. The mutational landscape was largely concordant before and after NAC. Conclusions: NAC remodels the bladder cancer immune microenvironment without altering the tumour genome or TMB. Baseline immune and genomic markers did not identify platinum-refractory patients, underscoring the need for better predictive biomarkers to guide patient selection and treatment sequencing in the antibody–drug conjugate era.

Objective: We evaluate the performance and relevance of MRI to detect csPC in men with normal PSA. Methods: Out of our database of patients referred for prostate MRI, we selected men with PSA < 4 ng/mL for whom histopathology or at least 2 years of clinical follow-up data were available as standard of reference. Subgroup analyses were performed for the patients with PSA < 3 ng/mL, <2 ng/mL, and 2-3.9 ng/mL. The reasons for prostate MRI referral despite their normal PSA level were retrieved by exploring the patients' files. The prostate MRIs were reported according to the Prostate Imaging and Reporting Data System (PI-RADS), and the overall assessment score was registered. For evaluation of the performance, PI-RADS ≥ 3 was set as a threshold for a positive exam. The patients without PC or only International Society of Urological Pathology (ISUP) grade group 1 PC (Gleason 3+3) were considered as one category having no csPC. The performance of prostate MRI was separately evaluated for detection of ISUP ≥ 2 and for ISUP ≥ 3 csPC. Results: A total of 148 men were included, with PSA ranging from 0.42 to 3.99 ng/mL (median 2.95, IQR 1.68-3.50) and age ranging from 36 to 84 years (median 58, IQR 52-66). A total of 74 men (50.0%) had a PSA level < 3 ng/mL, 42 (28.4%) had a PSA level < 2 ng/mL, and 106 (71.6%) had a PSA level of 2-3.9 ng/mL. They were referred for prostate MRI for a wide variety, and usually a combination of, reasons, such as younger age (<60 years in 55.4%, N = 82; <50 years in 17.6%, N = 26), abnormal digital rectal examination in 31.8% of cases (N = 47), suspicious PSA dynamics in 29.7% (N = 44), positive familial history in 27.0% (N = 40), clinical signs of prostatitis in 18.2% (N = 27), suspicious findings on Transrectal Ultrasound (TRUS) in 16.9% (N = 25), hematospermia in 7.4% (N = 11), hematuria in 4.1% (N = 6), incidental hot spot in the prostate on Fluoro-Deoxy-Glucose (FDG) Positron Emission Tomography (PET)-Computed Tomography (CT) in 4.1% (N = 6), lymphadenopathies on CT in 2.7% (N = 4), or severe patient anxiety in 3.4% (N = 5). Overall, ISUP ≥ 2 PC was present in 18.9% (N = 28) of cases, and MRI detected this with a sensitivity of 92.9%, a specificity of 66.7%, and a positive predictive value of 39.4%. ISUP ≥ 3 PC was present in 9.5% (N = 14) of cases, and prostate MRI detected this with a sensitivity of 100%, a specificity of 61.2%, and a positive predictive value of 21.2%. In patients with PSA < 2 ng/mL (N = 42), no csPC was found, but MRI generated false positives in 33.3%. Conclusions: Performing prostate MRI in men with normal PSA (<4 ng/mL) seems useful if there are other reasons that increase the clinical suspicion of csPC. In about one-fifth of these patients, csPC is present and MRI has high sensitivity for its detection. Prostate MRI has, however, low positive predictive value in this patient group, and clinicians should be aware of the risk of false-positive MRI. Below a PSA level of 2 ng/mL, no csPC was found and prostate MRI generated only false positives, suggesting limited value in this subgroup.

BACKGROUND AND OBJECTIVE:Patients with muscle-invasive bladder cancer (MIBC) who develop a recurrence after radical cystectomy (RC) have poor outcomes. This study aims to evaluate the safety and efficacy of adjuvant radiotherapy (ART) in mitigating pelvic recurrences in high-risk MIBC patients. We report on survival outcomes, health-related quality of life (HRQoL), and hematological toxicity for these patients. METHODS:A multicentric phase 2 trial was conducted from August 2014 to October 2020, in which 72 high-risk MIBC patients received ART after RC. High risk was defined by the presence of one or more of the following criteria: pT3 stage and lymphovascular invasion, pT4 stage, fewer than ten lymph nodes removed, positive lymph nodes, and positive surgical margins. Using intensity-modulated radiotherapy, patients with pelvic lymph nodes ± cystectomy bed (in case of a positive surgical margin) received 50 Gy in 25 fractions. Outcomes were local relapse-free rate (LRFR), clinical relapse-free survival (CRFS), overall survival (OS) (Kaplan-Meier statistics), HRQoL (European Organisation for Research and Treatment of Cancer QLQ-C30/QLQ-BLM30 surveys), and hematological toxicity (Common Terminology Criteria for Adverse Events grading). KEY FINDINGS AND LIMITATIONS:The median follow-up of patients without a recurrence was 39 mo. At 2 and 5 yr, LRFRs were 81% (95% confidence interval [CI] 71-91%) and 79% (95% CI 68-89%), CRFS rates were 32% (95% CI 21-42%) and 20% (95% CI 11-30%), and OS rates were 48% (95% CI 36-59%) and 34% (95% CI 22-45%), respectively. At the end of ART, several symptoms worsened, most returning to baseline within the first few months. Diarrhea showed the greatest deterioration, recovering to baseline score only partially. Hematological toxicity of incidence grade ≥2 included lymphopenia (75%), neutropenia (2%), thrombopenia (2%), and anemia (17%). Limitations include the single-arm design and the limited availability of blood samples and surveys. CONCLUSIONS AND CLINICAL IMPLICATIONS:ART after RC is well tolerated and leads to a favorable local control rate, supporting its use in clinical practice.

Contains 1. significantly differentially expressed genes between eTN and eFP ("FP_TN"), 2. significantly differentially expressed genes between eTN and eTP ("TP_TN"), 3. the pathway overrepresentations for 2-3. ("Reactome_table_FP_TN", "Reactome_table_TP_TN", "MSIGDBHALLMARK_TP_TN", "MSIGDBHALLMARK_FP_TN")

Metastasis-directed therapy (MDT) is an emerging treatment option for metachronous oligometastatic castration-sensitive prostate cancer (omCSPC) and can delay time to progression and the need to initiate androgen deprivation therapy (ADT). However, optimal ways to synergize MDT and ADT are not known, and better personalization of MDT is needed. We examined the role of combined ADT and MDT and the ability of genomic alterations to provide prognostic and predictive information regarding response to MDT. We found that high-risk (HiRi) mutations in TP53, BRCA1/2, ATM, and Rb1 are poor prognostic markers in omCSPC. In addition, patients harboring HiRi mutations experienced greater benefit from addition of ADT to MDT, indicating that these alterations are predictive biomarkers for treatment intensification. Our results suggest that genetic biomarkers might aid in treatment personalization for patients with omCSPC.

Contains 1. significantly differentially expressed genes between samples with high and low gleason grade ("Gleason_high_low"), 2. the pathway overrepresentations for these genes ("MSigDB_Gleason_HL", "Reactome_Gleason_HL"), 3. the overlapping genes between "Gleason_high_low" and "TP TN" from Suppl. Data 1 ("Gleason_HL_overlap TP_TN"), 4. the pathway overrepresentations for genes from (3) ("reactome_GLHL_TP_TN", "MSigDB_GLHL_TP_TN")

238 Background: Oligometastatic castration-sensitive prostate cancer (omCSPC) represents an early state along the progression of metastatic disease in which patients experience improved outcomes compared to those with higher disease burden. Despite the generally more indolent nature, much heterogeneity still exists with some patients experiencing a more aggressive clinical course unexplained by clinical features alone. Here we correlate tumor genomics with modes of progression (MOP) and patterns of failure (POF) following treatment for omCSPC. Methods: We performed an international multi-institutional retrospective study of men treated for metachronous omCSPC, who underwent tumor next generation sequencing (NGS) with at least 1 year of follow-up. Descriptive POF and MOP were reported with respect to presence of genomic alterations in pathways of interest. Genomic pathways of interest included TP53, SPOP, WNT ( APC, CTNNB1, RNF43), DNA double strand break repair, cell cycle genes ( Rb1, CCND1–3, CDKN1B, and CDKN2A), and PI3K/AKT/mTOR. MOP were defined as oligoprogression (1-3 lesions), polyprogression (≥4 lesions), or long-term control (LTC, no radiographic progression at last follow-up). POF included location of lesions at first failure. Overall survival (OS) was calculated by the Kaplan-Meier method. Genomic associations with patterns/modes of failure were compared with chi-square test. Results: 221 patients were included for analysis with the majority having either 1 (47.5%) or 2 (27.3%) metastatic lesions at oligometastasis. 5-yr OS was associated with MOP 92% vs 89% vs 69% (p<0.01) for LTC, oligo- and polyprogression respectively. TP53 mutations were associated with significantly lower rates of LTC (24.4% vs 46%, p<0.01) and cell cycle mutations associated with high rates of polyprogression (36.7% vs 15.7%, p<0.01). With respect to POF, bone failure was significantly more common within tumors harboring mutations in TP53 (41.2% vs 23.1%, p=0.01) and less common with SPOP mutations (4.2% vs 27.8%, p=0.02). Finally, visceral failures were more common in tumors harboring either WNT pathway (20% vs 5.1%, p<0.01) or SPOP (17.4% vs 5.2%, p=0.04) mutations. Notably, SPOP and WNT pathway mutations cluster together (p<0.01). Conclusions: Tumor genomics provides novel insight into patterns of failure and modes of progression following treatment for metachronous omCSPC. Patients with TP53 and cell cycle mutations have a higher likelihood of progression and TP53, SPOP, and WNT pathway mutations may have a role in metastatic organotropism.

BackgroundMuscle invasive bladder cancer (MIBC) treatment combines systemic therapy and radical cystectomy (RC) or local (chemo-)radiotherapy. Response to systemic therapy is an important outcome predictor but is difficult to assess pre-operatively.MethodsWe analyzed multiparametric MRI (mpMRI) in consecutive MIBC patients receiving cisplatin-based neo-adjuvant chemotherapy at our institution. Two readers, blinded for pathological outcome, independently scored mpMRI before and after 2 and 4 cycles using both a qualitative 3-step method and nacVI-RADS. We analyzed accuracy of mpMRI scores to predict pathologic complete response (pCR) and inter-observer agreement.ResultsWe analyzed 46 patients receiving NAC, 6 patients did not undergo RC after NAC and were excluded. Eleven out of 40 (28%) patients showed a pCR. mpMRI could be assessed in over 90% of patients. Radiologic complete response (rCR) using both methods was significantly associated with pCR, with an overall specificity of 96% and sensitivity of 36% and a high inter-observer agreement. rCR as assessed by the 3-step score was significantly associated with disease free survival (DFS) benefit.ConclusionThe use of nacVI-RADS can predict pCR after NAC with high specificity but low sensitivity and a high inter-observer agreement. A 3-step score adds value in determining local residual disease, rCR assessed by this method could correlate with DFS benefit. mpMRI scores should be prospectively assessed in future trials of multimodal management of MIBC and can be a predictive asset in routine clinical management.

De novo metastatic prostate cancer is highly aggressive, but the paucity of routinely collected tissue has hindered genomic stratification and precision oncology. Here, we leveraged a rare study of surgical intervention in 43 de novo metastatic prostate cancers to assess somatic genotypes across 607 synchronous primary and metastatic tissue regions plus circulating tumor DNA. Intra-prostate heterogeneity was pervasive and impacted clinically relevant genes, resulting in discordant genotypes between select primary restricted regions and synchronous metastases. Additional complexity was driven by polyclonal metastatic seeding from phylogenetically related primary populations. When simulating clinical practice relying on a single tissue region, genomic heterogeneity plus variable tumor fraction across samples caused inaccurate genotyping of dominant disease; however, pooling extracted DNA from multiple biopsy cores before sequencing can rescue misassigned somatic genotypes. Our results define the relationship between synchronous treatment-sensitive primary and metastatic lesions in men with de novo metastatic prostate cancer and provide a framework for implementing genomics-guided patient management.

Medullary sponge kidney (MSK) is an uncommon kidney malformation, characterized by cystic dilatation of the precalyceal papillary collecting ducts. Urography and computed tomography scan represent the gold standard to detect this congenital disorder. A clear diagnosis is not always feasible, especially in the presence of a concomitant renal mass, which in turn can be difficult to detect in MSK patients. When conventional imaging is inconclusive, a renal biopsy can be considered in doubtful cases. Here, we report a unique case of a Bellini duct carcinoma in a patient with MSK and we review the literature on this complex condition.

In prostate cancer, there is an urgent need for objective prognostic biomarkers that identify a tumor’s metastatic potential at an early stage. While recent analyses indicated TP53 mutations as candidate biomarker, molecular profiling in a clinical setting is complicated by tumor heterogeneity. Deep learning models that predict the spatial presence of TP53 mutations in Whole Slide Images (WSIs) offer the potential to mitigate this issue. To assess the potential of WSIs as proxy for spatially resolved profiling or as biomarker for aggressive disease, we developed TiDo, a deep learning model that achieves state-of-the-art performance in predicting TP53 mutations from WSIs of primary prostate tumors. On an independent multi-focal cohort, we could show successful generalization of the model, both at patient and lesion level. Hence, the model offers insight into which lesions on a WSI most likely contain a TP53 mutation. Analysis of model predictions revealed that false positive (FP) predictions could at least partially be explained by TP53 deletions. This suggests that some FP carry another alteration of which the effect converges in the same histological phenotype. Comparative expression analysis and histological cell type analysis identified such common phenotype (related to stromal composition) in both TP and FP predictions. This indicates that WSI-based models might not be able to perfectly predict the spatial presence of individual TP53 mutations. However, we show they have the potential of capturing a tumor’s aggressive potential by observing a downstream phenotype of the tumor cells and TME associated with a biomarker of aggressive disease (TP53). Citation Format: Marija Pizurica, Maarten Larmuseau, Kim Van der Eecken, Louise de Schaetzen van Brienen, Francisco Carrillo-Perez, Simon Isphording, Nicolaas Lumen, Jo Van Dorpe, Piet Ost, Sofie Verbeke, Olivier Gevaert, Kathleen Marchal. WSI based prediction of TP53 mutations identifies aggressive disease phenotype in prostate cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 2 (Clinical Trials and Late-Breaking Research); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(8_Suppl):Abstract nr LB171.