Search

Abstract Accurate prediction of recurrence and progression in non-muscle invasive bladder cancer (NMIBC) is essential to inform management and eligibility for clinical trials. Despite substantial interest in developing artificial intelligence (AI) applications in NMIBC, their clinical readiness remains unclear. This systematic review aimed to critically appraise AI studies predicting NMIBC outcomes, and to identify common methodological and reporting pitfalls. MEDLINE, EMBASE, Web of Science, and Scopus were searched from inception to February 5th, 2024 for AI studies predicting NMIBC recurrence or progression. APPRAISE-AI was used to assess methodological and reporting quality of these studies. Performance between AI and non-AI approaches included within these studies were compared. A total of 15 studies (five on recurrence, four on progression, and six on both) were included. All studies were retrospective, with a median follow-up of 71 months (IQR 32−93) and median cohort size of 125 (IQR 93−309). Most studies were low quality, with only one classified as high quality. While AI models generally outperformed non-AI approaches with respect to accuracy, c-index, sensitivity, and specificity, this margin of benefit varied with study quality (median absolute performance difference was 10 for low, 22 for moderate, and 4 for high quality studies). Common pitfalls included dataset limitations, heterogeneous outcome definitions, methodological flaws, suboptimal model evaluation, and reproducibility issues. Recommendations to address these challenges are proposed. These findings emphasise the need for collaborative efforts between urological and AI communities paired with rigorous methodologies to develop higher quality models, enabling AI to reach its potential in enhancing NMIBC care.

Abstract Purpose/Objective Definitive radiotherapy (RT) is an alternative to radical cystectomy for select patients with muscle invasive bladder cancer (MIBC); however, there is limited data on dose-painted RT approaches. We report the clinical and dosimetric outcomes of a cohort of MIBC patients treated with dose-painted RT. Material/Methods This was a single institution retrospective study of cT2-4N0M0 MIBC patients treated with external beam radiotherapy (EBRT) to the bladder, and sequential or concomitant boost to the tumor bed. The target delineation was guided by either intravesical injection of Lipiodol or through fusion of the pre-treatment imaging. The majority were treated with daily image-guidance. Kaplan-Meier was used to characterize overall survival (OS) and progression-free survival (PFS). Cumulative incidence function (CIF) was used to estimate local (intravesical) recurrence (LR), regional recurrence (RR) and distant metastasis (DM). Univariable and multivariable cause-specific hazard model was used to assess factors associated with LR and OS. Results 117 patients were analyzed. The median age was 73 years (range 43, 95). The median EQD2 to the boost volume was 66 Gy (range 52.1, 70). Lipiodol injection was used in 64 patients (55%), all treated with IMRT/VMAT. 95 (81%) received concurrent chemotherapy, of whom, 44 (38%) received neoadjuvant chemotherapy. The median follow-up was 37 months (IQR 16.2, 83.3). At 5-year, OS and PFS were 79% (95% CI 70.5–89.2) and 46% (95% CI 36.5–57.5). Forty-five patients had bladder relapse, of which 30 patients (67%) were at site of the tumor bed. Nine patients underwent salvage-cystectomy. Late high-grade (G3-G4) genitourinary and gastrointestinal toxicity were 3% and 1%. Conclusion Partial boost RT in MIBC is associated with good local disease control and high rates of cystectomy free survival. We observed a pattern of predominantly LR in the tumor bed, supporting the use of a dose-painted approach/de-escalation strategy to the uninvolved bladder. Prospective trials are required to compare oncological and toxicity outcomes between dose-painted and homogeneous bladder RT techniques.

Driver gene mutations that are more prevalent in metastatic, castration-resistant prostate cancer (mCRPC) than localized disease represent candidate prognostic biomarkers. We analyze 1,844 localized (1,289) or mCRPC (555) tumors and quantify the prevalence of 113 somatic driver single nucleotide variants (SNVs), copy number aberrations (CNAs), and structural variants (SVs) in each state. One-third are significantly more prevalent in mCRPC than expected while a quarter are less prevalent. Mutations in AR and its enhancer are more prevalent in mCRPC, as are those in TP53, MYC, ZNRF3 and PRKDC. ZNRF3 loss is associated with decreased ZNRF3 mRNA abundance, WNT, cell cycle & PRC1/2 activity, and genomic instability. ZNRF3 loss, RNA downregulation and hypermethylation are prognostic of metastasis and overall survival, independent of clinical and pathologic indices. These data demonstrate a strategy for identifying biomarkers of localized cancer aggression, with ZNRF3 loss as a predictor of metastasis in prostate cancer.

IntroductionUpper tract urothelial carcinoma (UTUC) accounts for

IntroductionActive surveillance (AS) is standard of care in low-risk prostate cancer (PCa). This study describes a novel total cancer location (TCLo) density metric and aims to determine its performance in predicting clinical progression (CP) and grade progression (GP).MethodsThis was a retrospective study of patients on AS after confirmatory biopsy (CBx). We excluded patients with Gleason ≥7 at CBx and 0.05) was independently associated with time to CP (hazard ratio [HR] 4.70; 95% confidence interval [CI] 2.62-8.42; p

Summary: Background: Accurate prediction of side-specific extraprostatic extension (ssEPE) is essential for performing nerve-sparing surgery to mitigate treatment-related side-effects such as impotence and incontinence in patients with localised prostate cancer. Artificial intelligence (AI) might provide robust and personalised ssEPE predictions to better inform nerve-sparing strategy during radical prostatectomy. We aimed to develop, externally validate, and perform an algorithmic audit of an AI-based Side-specific Extra-Prostatic Extension Risk Assessment tool (SEPERA). Methods: Each prostatic lobe was treated as an individual case such that each patient contributed two cases to the overall cohort. SEPERA was trained on 1022 cases from a community hospital network (Trillium Health Partners; Mississauga, ON, Canada) between 2010 and 2020. Subsequently, SEPERA was externally validated on 3914 cases across three academic centres: Princess Margaret Cancer Centre (Toronto, ON, Canada) from 2008 to 2020; L'Institut Mutualiste Montsouris (Paris, France) from 2010 to 2020; and Jules Bordet Institute (Brussels, Belgium) from 2015 to 2020. Model performance was characterised by area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), calibration, and net benefit. SEPERA was compared against contemporary nomograms (ie, Sayyid nomogram, Soeterik nomogram [non-MRI and MRI]), as well as a separate logistic regression model using the same variables included in SEPERA. An algorithmic audit was performed to assess model bias and identify common patient characteristics among predictive errors. Findings: Overall, 2468 patients comprising 4936 cases (ie, prostatic lobes) were included in this study. SEPERA was well calibrated and had the best performance across all validation cohorts (pooled AUROC of 0·77 [95% CI 0·75–0·78] and pooled AUPRC of 0·61 [0·58–0·63]). In patients with pathological ssEPE despite benign ipsilateral biopsies, SEPERA correctly predicted ssEPE in 72 (68%) of 106 cases compared with the other models (47 [44%] in the logistic regression model, none in the Sayyid model, 13 [12%] in the Soeterik non-MRI model, and five [5%] in the Soeterik MRI model). SEPERA had higher net benefit than the other models to predict ssEPE, enabling more patients to safely undergo nerve-sparing. In the algorithmic audit, no evidence of model bias was observed, with no significant difference in AUROC when stratified by race, biopsy year, age, biopsy type (systematic only vs systematic and MRI-targeted biopsy), biopsy location (academic vs community), and D'Amico risk group. According to the audit, the most common errors were false positives, particularly for older patients with high-risk disease. No aggressive tumours (ie, grade >2 or high-risk disease) were found among false negatives. Interpretation: We demonstrated the accuracy, safety, and generalisability of using SEPERA to personalise nerve-sparing approaches during radical prostatectomy. Funding: None.

INTRODUCTION:Urinary biomarkers are being developed to detect bladder cancer recurrence/progression in patients with non-muscle-invasive bladder cancer (NMIBC). We conducted a questionnaire-based study to determine what diagnostic accuracy and cost would such test(s) need for both patients and urologic oncologists to comfortably forgo surveillance cystoscopy in favour of these tests. METHODS:Surveys were administered to NMIBC patients at followup cystoscopy visit and to physician members of the Society of Urologic Oncology. Participants were questioned about acceptable false-negative (FN) rates and costs for such alternatives, in addition to demographics that could influence chosen error rates and costs. RESULTS:A total of 137 patient and 51 urologic oncologist responses were obtained. Seventy-seven percent of patients were not comfortable with urinary biomarker(s) alternatives to repeat cystoscopy, with a further 14% willing to accept such alternatives only if the FN rate were 0.5% or lower. Seventy-five percent of urologic oncologists were comfortable with an alternative urinary biomarker test(s), with 37% and 33% willing to accept FN rates of 5% and 1%, respectively. Forty-seven percent of patients were not willing to pay out-of-pocket for such tests, while 61% of urologic oncologists felt that a price range of $100-500 would be reasonable. CONCLUSIONS:This is the first survey evaluating patient and urologic oncologist perspectives on acceptable error rates and costs for urinary biomarker alternatives to surveillance cystoscopy for patients with NMIBC. Despite potential responder bias, this study suggests that urinary biomarker(s) will require sensitivity equivalent to that of cystoscopy in order to completely replace it in surveillance of patients with NMIBC.

Biomarkers of prostate cancer metastasis have been difficult to determine with confidence. Here the authors analyse mutation prevalence in 1844 prostate cancers and show that ZNRF3 loss is enriched in metastatic, castration-resistant prostate cancer and associated with metastasis of localized disease.

Abstract Background In men with metastatic castration‐resistant prostate cancer (mCRPC) with primarily bone metastases, radium‐223 (223Ra) improves overall survival (OS). However, the selection of 223Ra is not guided by specific validated clinicopathologic factors, and thus outcomes are heterogeneous. Patients and methods This retrospective survival analysis was performed in men with mCRPC treated with 223Ra at our cancer center. Demographics and disease characteristics were collected. OS was calculated using the Kaplan–Meier method (log‐rank). The potential prognostic factors were determined using both univariable (UVA) and multivariable analysis (MVA) (Cox‐regression) methods. Results In total, 150 patients with a median age of 74 years (52–93) received 223Ra between May 2015 and July 2018, and 58% had 6–20 bone metastases. Ninety‐four (63%) patients received >4 223Ra doses, and 56 (37%) received ≤4. The following pre‐treatment factors were analyzed (median [range]): eastern cooperative oncology group performance status (ECOG PS), (1 [0–3]); Albumin (ALB), (39 g/L [24–47]); alkaline phosphatase (ALP), (110 U/L [35–1633]); and prostate‐specific antigen (PSA), (49 µg/L [0.83–7238]). The median OS for all patients was 14.5 months (95% CI: 11.2–18). These factors were associated with poor survival outcomes in UVA and MVA: ALB 150 U/L, ECOG PS 2–3, and PSA >80 µg/L. By assigning one point for each of these factors, a prognostic model was developed, wherein three distinct risk groups were identified: good, 0–1 (n = 103); intermediate, 2 (n = 30); and poor risk, 3–4 points (n = 17). The median OS was 19.4, 10.0, and 3.1 months, respectively (p

Recent advances in semi-supervised learning algorithms (SSL) have made great strides in reducing the training dependency on labeled datasets and requiring that only a subset of the data be labeled. The presented work explores a class of semi-supervised learning algorithms that uses consistency regularization and self-ensembling to leverage the unlabeled portion of the dataset. Labeling medical image datasets are time-consuming and prohibitively expensive, requiring hundreds of hours of effort from expert diagnosticians. This research presents an approach for building and training a deep learning model to grade medical images while requiring only a minimal number of labels. Consistency regularization has been used in SSL to great success in datasets of natural images but not for more complex images such as pathology slides where the dataset consists of cell patterns. This research successfully proposes and applies an SSL algorithm based on the VGG-16 neural network, which combines techniques introduced by the Π model and FixMatch algorithms to a cell pattern-based pathology image dataset. The results presented in this research show that using the proposed approach, it is possible to label only 3% of the samples in a dataset, use the remaining 97% of samples as unlabeled data, and achieve a 19% increase over the baseline accuracy. The second contribution of this research shows a ratio of labeled vs. unlabeled images in a dataset beyond which continuing to label the data increases the cost but offers little performance gains.

Bladder cancer tissue grading, which assigns a numerical grade reflecting how aggressive a tumor looks under a microscope, is essential to determine the proper course of treatment, design a therapeutic plan and determine prognosis. The major problem is that there are considerable and clinically relevant variations in grading by pathologists – as they are humans with different opinions and experience – including in bladder cancer. This work presents a solution, i.e., Artificial Intelligence for Bladder Cancer grading (ABC) system, that is developed based on deep neural network architectures to provide a more reliable and accurate diagnosis for patients affected by this deadly disease and ultimately improve management and clinical outcomes. Whole Slide Images (WSI) are split up into equally-sized square tiles and annotated to build a training dataset. ABC introduces a new grading system concept that can provide a percentage distribution of each different grade in a specific tumor, unlike the current numerical grade value between 1 and 3 based on the general impression of the pathologist. This new approach aims to provide a more granular grading of bladder cancer tissues and better capture tumor grade heterogeneity. This new concept may offer a more precise prognosis and optimize management in the future. The ABC learning model is fully configurable, and any deep architecture model can be trained and used by ABC. Some trained models developed by ABC have shown high accuracy and consistency in grading and intra-observer variability. The combination of a loosely coupled architecture and fully integrated tiles’ utilization makes ABC a universal, scalable, and versatile system that could be configured and deployed worldwide.

Context: Current guidelines suggest several targeted therapies (TTs) and immunotherapies (ITs) in the treatment of advanced or metastatic renal cell carcinoma (mRCC). Ideal sequencing of these treatments is unclear. Objective: The primary objective was to evaluate the overall survival (OS) data of the treatments approved for mRCC. Secondary objectives included evaluating other signs of efficacy and adverse events. Evidence acquisition: We reviewed the current Food and Drug Administration–approved treatments for mRCC. Trials associated with approval were reviewed. We also included pre- and postapproval publications when appropriate. Evidence synthesis: There is minimal evidence supporting OS benefit for the nine approved TTs. They result in adverse events and are a considerable economic burden. For these reasons, their future role in mRCC treatment should be re-evaluated, given the emergence of IT that have demonstrated OS benefits. Accumulating long-term survival data with high-dose interleukin-2 treatment suggests that this older treatment could still be considered for eligible patients. Checkpoint inhibitors have shown promising OS and durable responses; as such, the high cost of treatment might be justified. However, the available evidence does not suggest that adding TT to IT would increase efficacy over IT alone, but would add toxicity. Conclusions: Trial data supporting OS benefit are much stronger for ITs than for TTs. Combining checkpoint inhibitors with TTs has not been shown to produce better OS than checkpoint inhibitors alone, while more adverse events are present. Granting drug approvals based on efficacy without demonstrated OS benefit should be revisited. Patient summary: Approved treatments for metastatic kidney cancer include targeted and immune-based therapies. The former commonly produces temporary tumour shrinkage, but survival benefits are unclear. All approved immunotherapies have increased survival, and a proportion of patients appear cured.