2 December 2025 in Russian Journal of Archive of Pathology
The implementation of prostate-specific antigen (PSA) screening over the past decade has led to a significant increase in the number of primary prostate biopsies, thereby imposing a growing workload on pathology departments. Globally, considerable efforts are being directed towards developing artificial intelligence (AI) models capable of assisting pathologists in the morphological diagnosis of prostate cancer (PCa). Objective. Develop an AI-based model for detecting PCa in biopsy samples and compare its diagnostic performance with pathologists with varying levels of experience. Material and methods. A training dataset comprising 470 core biopsy specimens of prostate tissue from 86 patients was utilized. The AI model employed a U-Net neural network architecture. For testing, a separate dataset of 282 scanned specimens, not included in model training, was separated in 2 sets — 1 and 2 (with 141 slides in each). This dataset consisted of 81 specimens with non-neoplastic prostate tissue and 201 specimens with adenocarcinoma structures. The study included 20 pathologists with varying levels of experience from 12 medical institutions in the Russian Federation, who evaluated each case on the «PathVision.ai» platform. The diagnostic performance and agreement between the AI model and pathologists were assessed using comparative statistical analysis. Results. The AI-model demonstrated high diagnostic performance, with sensitivity of 0.99 [95% CI: 0.97—1.00], specificity of 0.93 [95% CI: 0.84—0.97], and accuracy of 0.98 [95% CI: 0.95—0.99] for detecting PCa. These metrics surpassed those of junior pathologists (sensitivity: 0.92 [95% CI: 0.91—0.94]; specificity: 0.89 [95% CI: 0.86—0.91]; accuracy: 0.91 [95% CI: 0.90—0.93]) and were comparable to those of experienced pathologists (sensitivity: 0.93 [95% CI: 0.91—0.95]; specificity: 0.94 [95% CI: 0.91—0.96]; accuracy: 0.94 [95% CI: 0.92—0.95]). Conclusion. Developed model «PathVision.ai» in pilot study demonstrated high sensitivity, specificity and accuracy in the diagnosis of PCa in biopsy samples.
24 November 2025 in Oncopathology
Tumor suppression gene VHL plays an important role in regulation of various cell processes including angiogenesis, apoptosis, and cell cycle control. Mutations in this gene are associated with von Hippel–Lindau disease. This disease affects multiple systems and is associated with marked phenotypic variability and development of both benign and malignant tumors of various locations. Morphology of the tumors in von Hippel–Lindau disease has a number of specific features, and differential diagnosis can be complicated.
7 April 2026 in Oncopathology
Adamantinoma comprises about 0.3 % of all primary malignant tumors of the bones. Currently it is considered a biphasic tumor characterized by variety of morphological types. Usually, the tumor is located in the long bones (97 %), in the majority of cases (80–85 %) in the tibia. It has indolent character and long progressive clinical course which lead to late diagnosis. A clinical case of adamantinoma of the tibia in a young female patient with long-term follow-up, development of local recurrences and metastases is presented.
7 April 2026 in Oncopathology
Invasive lobular carcinoma (ILC) comprises up to 15 % of all breast cancers. In contrast to ductal carcinoma, ILC frequently metastasizes into gastrointestinal organs, retroperitoneal space, and urogenital organs, as well as the eye and orbit, and metastases can be diagnosed 10–15 years after treatment of primary breast tumor. Pleomorphic, alveolar, and solid ILC subtypes are the most prone to metastases. Due to similar morphological picture between ILC and primary tumors with low cell adhesion, differential diagnosis without additional examination methods can be difficult. The article presents the key signs of distant ILC metastases into various organs and systems, as well as minimal antibody panels for differential diagnosis with primary tumors.
14 October 2026 in Oncopathology
This review summarizes data from recent decades on morphological changes in prostate tissue following radiation therapy, including external beam radiation and brachytherapy. Structural, cytological and immunohistochemical changes in both normal tissue and adenocarcinoma are discussed, along with diagnostic pitfalls in the assessment of residual tumor and the interpretation of Gleason score after irradiation. Particular attention is given to the prognostic value of post-treatment biopsy, definition of biochemical recurrence, and prostate-specific antigen bounce phenomenon after brachytherapy.
6 November 2026 in Current Medicinal Chemistry
Three-dimensional prostate cancer organoids represent a promising platform for modeling tumor biology and personalizing therapeutic strategies. However, unlike many other solid tumors, reproducing this pathology in vitro is challenging. Despite initial culture establishment rates reaching 70-90% in certain studies, most cultures undergo early growth arrest (typically within passages P1-P3 or the first 1-2 months), accompanied by a high risk of losing the target tumor clone. In the present work, we provide a critical analysis of the current state of 3D prostate cancer culture technologies and attempt to identify the fundamental reasons for the inefficiency of standard multicomponent media and traditional extracellular matrices. Based on the analysis of single-cell transcriptomic profiling data, we characterized the adaptive drift of organoid cellular composition toward basal and transient states. Furthermore, we substantiated the critical need to modernize approaches for confirming model relevance, particularly by analyzing in detail the limitations of traditional markers. As an effective solution, we propose the concept of integrating multiplex expression test systems based on accessible quantitative PCR platforms, utilizing the extensive arsenal of highly informative RNA biomarkers accumulated in clinical urologic oncology. We conclude that the transition from empirical condition selection to directed niche reconstruction based on single-cell analysis data combined with PCR verification will open new opportunities for the widespread implementation of organoid models in basic research and clinical practice.