Search

Aims To evaluate the prognostic value of clinical, histopathological and molecular features and to relate different treatment modalities to clinical outcome in conjunctival melanomas (CM). Methods Retrospective review of clinical, histopathological and BRAF V600E and telomerase reverse transcriptase (TERT) promoter mutation status and treatment modalities, correlated to recurrence and metastasis in 79 patients with CM, diagnosed between 1987 and 2015 in three tertiary referral centres in the Netherlands and Belgium. Results Out of 78 evaluable patients, recurrences occurred in 16 patients and metastasis in 12 patients (median follow-up time 35 months (0-260 months)). Tumour thickness >2 mm, pT status, the presence of epithelioid cells, ulceration and mitoses was significantly correlated with metastasis (p value 0.046, 0.01, 0.02, 0.001 and 0.003, respectively). Furthermore, CM frequently harbour BRAF V600E and TERT promoter mutations (29% and 43%, respectively). TERT promoter mutations were correlated to shorter metastasis-free survival (p value 0.002). No significant correlation was found for clinical parameters and metastatic disease. Palpebral, forniceal and caruncular melanomas were more prone to develop recurrences (p value: 0.03). Most CM were treated with excision with adjuvant therapy. Conclusion In line with the recommendations in the Eighth Edition of the American Joint Committee on Cancer Staging for CM, the pathology report should include information about pT status, tumour thickness, presence of epithelioid cells, ulceration and mitoses. Furthermore, information about the presence of a TERT promoter mutation and BRAF V600E mutation is of interest for therapeutic decision making. The presence of a TERT promoter mutation is correlated to metastatic disease. [ABSTRACT FROM AUTHOR]

The biopsy Gleason score is an important prognostic marker for prostate cancer patients. It is, however, subject to substantial variability among pathologists. Artificial intelligence (AI)-based algorithms employing deep learning have shown their ability to match pathologists' performance in assigning Gleason scores, with the potential to enhance pathologists' grading accuracy. The performance of Gleason AI algorithms in research is mostly reported on common benchmark data sets or within public challenges. In contrast, many commercial algorithms are evaluated in clinical studies, for which data are not publicly released. As commercial AI vendors typically do not publish performance on public benchmarks, comparison between research and commercial AI is difficult. The aims of this study are to evaluate and compare the performance of top-ranked public and commercial algorithms using real-world data. We curated a diverse data set of whole-slide prostate biopsy images through crowdsourcing containing images with a range of Gleason scores and from diverse sources. Predictions were obtained from 5 top-ranked public algorithms from the Prostate cANcer graDe Assessment (PANDA) challenge and 2 commercial Gleason grading algorithms. Additionally, 10 pathologists (A.C., C.R., J.v.I., K.R.M.L., P.R., P.G.S., R.G., S.F.K.J., T.v.d.K., X.F.) evaluated the data set in a reader study. Overall, the pairwise quadratic weighted kappa among pathologists ranged from 0.777 to 0.916. Both public and commercial algorithms showed high agreement with pathologists, with quadratic kappa ranging from 0.617 to 0.900. Commercial algorithms performed on par or outperformed top public algorithms., (Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)

Background: The first sign of metastatic prostate cancer after radical prostatectomy is rising PSA levels in the blood, termed biochemical recurrence. The prediction of recurrence relies mainly on the morphological assessment of prostate cancer using the Gleason grading system. However, in this system, within-grade morphological patterns and subtle histopathological features are currently omitted, leaving a significant amount of prognostic potential unexplored., Methods: To discover additional prognostic information using artificial intelligence, we trained a deep learning system to predict biochemical recurrence from tissue in H&E-stained microarray cores directly. We developed a morphological biomarker using convolutional neural networks leveraging a nested case-control study of 685 patients and validated on an independent cohort of 204 patients. We use concept-based explainability methods to interpret the learned tissue patterns., Results: The biomarker provides a strong correlation with biochemical recurrence in two sets ( n  = 182 and n  = 204) from separate institutions. Concept-based explanations provided tissue patterns interpretable by pathologists., Conclusions: These results show that the model finds predictive power in the tissue beyond the morphological ISUP grading., Competing Interests: Competing interestsB.v.G. receive funding and royalties from MeVis Medical Solutions AG, (Bremen, Germany), and reports grants and stock/royalties from Thirona, and grants and royalties from Delft Imaging Systems, all outside the submitted work. J.v.d.L. is a member of the advisory boards of Philips, the Netherlands, and ContextVision, Sweden; and received research funding from Philips, the Netherlands; ContextVision, Sweden; and Sectra, Sweden, all outside the submitted work. G.L. reports research grants from the Dutch Cancer Society, the Netherlands Organization for Scientific Research (NWO), and HealthHolland during the conduct of the study, and grants from Philips Digital Pathology Solutions, and consultancy fees from Novartis and Vital Imaging, outside the submitted work. J.M. is supported by Department of Defense Prostate Cancer Research Program, DOD Award No W81XWH-18-2-0016, PCRP Prostate Cancer Biorepository Network A.D.M. is a paid consultant to Cepheid LLC, and Merck & Co., A.D.M has also received research support from Myriad Genetics and Janssen R&D for other studies. All other authors have no competing interests., (© The Author(s) 2022.)

Background: Nasopharyngeal carcinoma (NPC) treatment is mainly based on clinical staging. We hypothesize that better understanding of the molecular heterogeneity of NPC can aid in better treatment decisions. Therefore, the purpose of this study was to present our exploration of cancer gene copy-number alterations (CNAs) of Epstein-Barr virus (EBV)-positive and EBV-negative NPC., Methods: Multiplex ligation-dependent probe amplification was applied to detect CNAs of 36 cancer genes (n = 103). Correlation between CNAs, clinicopathological features, and survival were examined., Results: The CNAs occurred significantly more in EBV-negative NPC, with PIK3CA and MCCC1 (P < .001) gain/amplification occurring more frequently. Gain/amplification of cyclin-L1 (CCNL1) and PTK2 (P < .001) predict worse disease-free survival (DFS) in EBV-positive NPC., Conclusion: The EBV-positive and EBV-negative NPC show some similarities in cancer gene CNAs suggesting a common pathogenic route but also important differences possibly indicating divergence in oncogenesis. Copy number gain/amplification of CCNL1 and PTK2 are possibly good predictors of survival in EBV-positive NPC., (© 2018 Wiley Periodicals, Inc.)

Aims: To assess differences in methylation profiles, and thus pathogenesis, between Epstein-Barr virus (EBV)-positive and negative nasopharyngeal carcinomas (NPCs). Also, promoter hypermethylation is a common phenomenon in early carcinogenesis to inactivate tumour suppressor genes. Since epigenetic changes are reversible, the therapeutic application of methylation inhibitors could provide treatment options., Methods: We evaluated promoter hypermethylation profiles of 22 common tumour suppressor genes in 108 NPCs using methylation-specific multiplex ligation-dependent probe amplification. Correlation between methylation, clinicopathological features (including EBV) and survival was examined. Cluster analysis was also performed., Results: Hypermethylation of RASSF1A and ESR1 was significantly more frequent in EBV-positive NPC, while hypermethylation of DAPK1 was more frequent in EBV-negative NPC. In logistic regression, age, with EBV-positive NPC occurring at earlier age, and RASSF1, with RASSF1 hypermethylation being more frequent in EBV-positive NPC, remained significant. In EBV-positive NPC, hypermethylation of RASSF1A predicted worse overall survival (OS) (HR 3.058,95% CI 1.027 to 9.107). In EBV-negative NPC, hypermethylated adenomatous polyposis coli (APC) was a predictor of poor disease-free survival (DFS) (HR 6.868, 95% CI 2.142 to 22.022)., Conclusion: There are important epigenetic differences between EBV-negative and EBV-positive NPCs, with EBV-negative NPC having a more similar hypermethylation profile to other head and neck squamous cell carcinomas than EBV-positive NPC. Hypermethylation of RASSF1A might contribute to worse OS in EBV-positive NPC, and may be an important event in the pathogenesis of EBV-infected NPC. Hypermethylation of APC might contribute to worse DFS in EBV-negative NPC., Competing Interests: Competing interests: None declared., (© Article author(s) (or their employer(s) unless otherwise stated in the text of the article) 2018. All rights reserved. No commercial use is permitted unless otherwise expressly granted.)