Background: BI-RADS (Breast Imaging Reporting and Data System) mammogram classification is central to early breast cancer detection. Despite being an ordinal scale that reflects increasing levels of malignancy suspicion, most models treat BI-RADS as a nominal task using cross-entropy loss, thereby disregarding the inherent class order. This mismatch between the clinical severity of misclassification and the model’s optimization objective remains underexplored. Methods: We systematically evaluate whether incorporating ordinal-aware loss functions improves BI-RADS classification performance under controlled, architecture-fixed conditions and dataset imbalance. Using a unified training pipeline across multiple datasets, we compare ordinal losses to standard cross-entropy, analyzing the effect of dataset- and label-level balancing. Area under the receiver operating characteristic curve (AUROC) and macro-F1 scores are reported as averages over five seeds. Results: Balanced sampling across datasets during training led to statistically significant improvements. Ordinal loss functions, such as Earth Mover Distance (EMD), consistently achieved higher performance across multiple metrics compared to conventional cross-entropy approaches commonly reported in the literature. Improvements were particularly evident in reducing severe misclassifications, demonstrating that aligning the learning objective with the ordinal structure of BI-RADS enhances robustness and clinical relevance. Conclusions: Aligning the learning objective with the ordinal BI-RADS structure substantially improves classification accuracy without changing the underlying architecture. These findings emphasize the importance of loss design, regularization, and data-balancing strategies in medical AI, supporting more reliable breast cancer screening.

Background: Significant progress has been made in the field of machine learning, enabling the development of methods for automatic interpretation of medical images that provide high-quality diagnostics. However, most of these methods require access to confidential data, making them difficult to apply under strict privacy requirements. Existing privacy-preserving approaches, such as federated learning and dataset distillation, have limitations related to data access, visual interpretability, etc. Methods: This study explores the use of generative models to create synthetic medical data that preserves the statistical properties of the original data while ensuring privacy. The research is carried out on the VinDr-Mammo dataset of digital mammography images. A conditional generative method using Latent Diffusion Models (LDMs) is proposed with conditioning on diagnostic labels and lesion information. Diagnostic utility and privacy robustness are assessed via cancer classification tasks and re-identification tasks using Siamese neural networks and membership inference. Results: The generated synthetic data achieved a Fréchet Inception Distance (FID) of 5.8, preserving diagnostic features. A model trained solely on synthetic data achieved comparable performance to one trained on real data (ROC-AUC: 0.77 vs. 0.82). Visual assessments showed that synthetic images are indistinguishable from real ones. Privacy evaluations demonstrated a low re-identification risk (e.g., mAP@R = 0.0051 on the test set), confirming the effectiveness of the privacy-preserving approach. Conclusions: The study demonstrates that privacy-preserving generative models can produce synthetic medical images with sufficient quality for diagnostic task while significantly reducing the risk of patient re-identification. This approach enables secure data sharing and model training in privacy-sensitive domains such as medical imaging.

BACKGROUND: Breast cancer is one of the leading causes of cancer-related mortality in women [1]. Regular mass screening with mammography plays a critical role in the early detection of changes in breast tissue. However, the early stages of pathology often go undetected and are difficult to diagnose [2]. Despite the effectiveness of mammography in reducing breast cancer mortality, manual image analysis can be time consuming and labor intensive. Therefore, attempts to automate this process, for example using computer-aided diagnosis systems, are relevant [3]. In recent years, however, solutions based on neural networks have gained increasing interest, especially in biology and medicine [4-6]. Technological advances using artificial intelligence have already demonstrated their effectiveness in pathology detection [7, 8]. AIM: The study aimed to develop an automated solution to detect breast cancer on mammograms. MATERIALS AND METHODS: The solution is implemented as follows: a deep neural network-based tool has been developed to obtain the probability of malignancy from the input image. A combined dataset from public datasets such as MIAS, CBIS-DDSM, INbreast, CMMD, KAU-BCMD, and VinDr-Mammo [9–14] was used to train the model. RESULTS: The classification model, based on the EfficientNet-B3 architecture, achieved an area under the ROC curve of 0.95, a sensitivity of 0.88, and a specificity of 0.9 when tested on a sample from the combined dataset. The model’s high generalization ability, which is another advantage, was demonstrated by its ability to perform well on images from different datasets with varying data quality and acquisition regions. Furthermore, techniques such as image pre-cropping and augmentations during training were used to enhance the model's performance. CONCLUSIONS: The experimental results demonstrated that the model is capable of accurately detecting malignancies with a high degree of confidence. The obtained high-quality metrics offer a significant potential for implementing this method in automated diagnostics, for instance, as an additional opinion for medical specialists.

Russian-language resources for medical natural language processing (NLP) are expanding rapidly; however, their fragmentation, uneven curation, and limited clinical reliability hinder the development of safe machine learning systems for prognosis, prevention, and precision medicine. We provide the first systematic survey of Russian medical NLP datasets and analyze their suitability for clinically meaningful tasks as defined by the MedHELM taxonomy. We additionally perform expert clinical validation of three representative public corpora—RuMedPrimeData (real outpatient notes), MedSyn (synthetic clinical notes), and RuMedNLI (translated natural language inference)—assessing clinical plausibility, diagnosis accuracy, and logical consistency. Experts identified substantial reliability issues: across randomly sampled subsets of each corpus, only approximately 20% of RuMedPrimeData records, fewer than 15% of MedSyn records, and approximately 55% of RuMedNLI pairs met essential quality criteria, which can hinder downstream ML systems built on these data. To support robust applications—ranging from medical chatbots and triage assistants to predictive and preventive models—we outline practical requirements for high-quality datasets: coordinated, expert-validated, machine-readable corpora aligned with clinical guidelines and insurance logic, standardized de-identification, and transparent provenance. Strengthening these data foundations will enable the development of reliable, reproducible, and clinically relevant AI systems suitable for real-world healthcare applications.

The performance of AI solutions in mammography is largely determined by data quality, preprocessing methods, and augmentation strategies. However, systematic evaluation of these factors for models trained on aggregated multicenter datasets remains underexplored. This article presents a comparative assessment of the effects of different stages of the training pipeline on the final diagnostic accuracy. Using a pooled dataset (VinDr-Mammo, INBreast, CMMD, CBIS-DDSM), we evaluated each pipeline step—from filtering to architecture selection (EfficientNet-B3, CLIP). External testing was conducted on the MosMed database. Among the tested preprocessing steps, filtering the darkest 5% of images proved most effective. For EfficientNet-B3, optimal geometric and photometric augmentations increased test AUROC on the prepared MosMed test set from 0.844 to 0.900. Domain-specific pretraining and high resolution yielded the best performance: Mammo-CLIP achieved an AUROC of 0.949 ± 0.012, and EfficientNet-B3 reached 0.934 ± 0.013. Overall, this study developed a standardized pipeline that includes sequential data filtering and harmonization, augmentation optimization, and architecture selection. This approach ensures reliable and reproducible results for automated mammogram classification.