Background: This study proposes a deep learning-based decision support system for the non-invasive prediction of axillary lymph node (ALN) metastasis in breast cancer using ultrasound (USG). Both localisation and benign–malignant classification of ALNs were performed using YOLO-v11, a single-stage object detection approach. The dataset created from labelled USG images was split into training/validation/test sets at a ratio of 70%/20%/10%, and the model produced a class label and confidence score for each prediction. Performance was found to be high with amAP@0.5 = 0.904s (benign: 0.866, malignant: 0.942); F1-, precision-, and sensitivity-confidence curves showed that thresholds in the 0.52–0.60 range provided a balance between sensitivity and specificity. Confidence scores for the malignant class were observed to be concentrated in the 0.82–0.87 band. The confusion matrix includes an auxiliary ‘background’ row/column representing unmatched predictions (false positives) and missed ground-truth detections (false negatives); background was not modelled as a semantic class during training. The findings point to a rapid and reproducible artificial intelligence approach that could reduce operator dependency in USG. The proposed model has the potential to provide radiologists and clinicians with non-invasive, real-time decision support in ALN assessment. Objective: Axillary lymph node (ALN) metastasis plays a decisive role in the clinical course and treatment planning of breast cancer following diagnosis. Therefore, the accurate and early detection of metastatic lymph nodes directly impacts treatment success. Ultrasonography (USG) stands out as the most common and effective imaging method for evaluating axillary lymph node metastasis. The main objective of this study is to develop an artificial intelligence-supported USG analysis system to provide a decision support system for radiologists and clinicians in the detection of ALN metastasis. Methods: This study included a total of 471 patients: 248 patients diagnosed with breast cancer between 2024 and 2025 and reported as malignant based on axillary lymph node biopsy results, and 223 control cases with benign lymph nodes detected in breast ultrasound scans. Using a dataset created from the acquired ultrasound images, a single-stage object detection model (YOLO-v11) was employed to detect ALN metastasis. The data were split into a 70% training, 20% validation, and 10% testing ratio. The developed model produces a confidence score and class label for each detection. Results: The developed model has demonstrated high accuracy performance in benign and malignant lymph node samples. The mAP@0.5 value calculated under the Precision–Recall (PR) curve was obtained as 0.904 (benign: 0.866, malignant: 0.942). The precision and sensitivity values were found to be 0.866 in benign samples and 0.942 in malignant samples, respectively. Confidence score values for the malignant class were concentrated in the range of 0.82–0.87. When evaluated from a clinical application perspective, the threshold value in the range of 0.5–0.6 provides a balanced trade-off between sensitivity and specificity. Conclusion: The proposed artificial intelligence model can localise axillary lymph nodes with high accuracy on USG images and distinguish between benign and malignant conditions. In this respect, the model has the potential to guide radiologists and clinicians as a decision support tool in the diagnostic process.

The occurrence of primary breast hydatid cysts is exceedingly rare, even in endemic regions, and reported prevalence rates are infrequent. Although classified as a benign condition, it represents a significant health concern caused by the parasitic tapeworm Echinococcus granulosus. Hydatid cyst disease can manifest in various anatomical locations throughout the body, ranging from the head to the extremities. Diagnosis typically involves imaging studies, such as ultrasound, which can reveal the characteristic features of the cyst. Additionally, serological tests may be conducted to detect specific antibodies against Echinococcus. This report aims to present the imaging findings of an exceptionally rare case of an isolated breast hydatid cyst in a 74-year-old female patient.

Background/Objectives: The breast is a highly radiosensitive organ that is directly exposed to ionizing radiation during chest computed tomography (CT) examinations. Excessive radiation exposure increases the risk of radiation-induced malignancies, highlighting the importance of accurate and patient-specific dose estimation. This study aims to estimate the effective radiation dose absorbed by the breast during chest CT examinations using a machine learning (ML)-based personalized prediction approach. Methods: In this retrospective study, a total of 653 female patients who underwent both mammography and chest CT between 2020 and 2024 were included. A structured database was created incorporating demographic and anatomical parameters, including body weight, height, body mass index (BMI), and breast thickness (mm) obtained from mammography, along with dose length product (DLP) values from chest CT scans. Five regression-based ML algorithms—CatBoost, Gradient Boosting, Extra Trees, AdaBoost, and Random Forest—were implemented to predict breast radiation dose. Model performance was evaluated using Mean Squared Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the Coefficient of Determination (R²). Results: Among the evaluated models, the CatBoost algorithm optimized with Particle Swarm Optimization (CatBoostPSO) achieved the best overall predictive performance, yielding the lowest MSE (0.3795), MAE (0.3846), and MAPE (4.37%), along with the highest R² value (0.9875). CatBoost and Gradient Boosting models demonstrated predictions most closely aligned with ground truth values, indicating that ensemble-based and dynamically optimized models are particularly effective for breast dose estimation. Conclusions: The proposed machine learning framework enables rapid, accurate, and clinically applicable estimation of breast radiation dose during chest CT examinations. This patient-specific approach has strong potential to support personalized radiation dose monitoring and optimization strategies, contributing to improved radiation safety in clinical practice.

Purpose: Axillary lymph node metastasis (ALNM) is a significant prognostic factor in breast cancer and has an impact on staging, treatment and survival. The objective of this study is to create a machine learning model that will be able to predict axillary lymph node metastasis (ALNM) in a preoperative setting using breast MRI-derived and clinicopathological variables, while also achieving probability calibration and uncertainty-aware prediction for more reliable risk estimates. Patients and Methods: For this retrospective single-centre study, 204 patients who underwent contrast-enhanced breast MRI from 2021 to 2024 were selected. The dataset comprised of 23 independent variables, respectively, representing demographic, clinical, radiological, histopathological, molecular characteristics along with a binary target variable indicating ALNM status. The data was split into 60% called training set, 20% calibration set, and 20% test set. Candidate models were evaluated based on ROC-AUC on the training subset that was used for screening. Subsequently, calibration was performed in a held-out calibration set, following which class-conditional conformal prediction was applied to quantify predictive uncertainty. Results: Out of all the models we evaluated, the Conformal-Calibrated Interpretable Risk Model (CCIRM) was found to be the best model, achieving a test accuracy of 0.9268, a weighted F1 score of 0.9270 and AUC of 0.937. With a precision of 0.9545 and a recall of 0.9130 in the ALNM-positive class, the model was potent. In addition to discrimination strength, the framework produces calibrated risk estimates and uncertainty-aware prediction sets that enable transparent interpretation of model outputs in clinically borderline cases. Conclusion: The proposed approach includes the model selection based on the machine learning and probability calibration, as well as conformal prediction to achieve reliability, beyond label prediction, and uncertainty-aware risk estimation for preoperative ALNM assessment. The results from this analysis suggest that CCIRM is a potential methodological framework for trustworthy clinical decision support, although the prospective and multicentre external validation should be done before it becomes applicable to the clinical setting.

Objectives: This study aims to predict patient-specific Average Glandular Dose (AGD) in mammography using machine learning-based models to support personalised radiation dose optimisation and reduce unnecessary exposure during breast cancer screening. Methods: A retrospective dataset of 671 female patients who underwent full-field digital mammography between 2020 and 2024 was analysed. Right craniocaudal (CC) images were used to construct a structured dataset including mAs, kVp, compressed breast thickness, air kerma (k_air), half-value layer (HVL), and breast pattern. Five regression-based machine learning models (CatBoost, Gradient Boosting, Random Forest, Extra Trees, and AdaBoost) and their Particle Swarm Optimisation (PSO)-enhanced versions were evaluated. Model performance was assessed using MSE, RMSE, MAE, MAPE, and R². SHAP analysis was applied to interpret model predictions and determine variable importance. Results: PSO integration significantly reduced prediction errors, particularly in boosting-based models. The CatBoost + PSO model achieved the best performance (RMSE = 0.0100, MAPE ≈ 1.74%, R² = 0.9846), followed by the Gradient Boosting + PSO model (R² = 0.9787). PSO reduced RMSE and MAPE by approximately 55% and 52%, respectively. SHAP analysis identified k_air, breast thickness, and breast pattern as the most influential factors affecting AGD. Conclusions: Machine learning models enhanced with PSO, especially CatBoost + PSO, provide accurate and reliable patient-specific AGD predictions. The proposed approach enables rapid and clinically applicable dose estimation and highlights breast pattern as a critical parameter influencing glandular dose, supporting personalised radiation dose optimisation in mammography.

Background/Objectives: Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide. Early and accurate characterization of suspicious mammographic microcalcifications is essential for improving diagnostic decision-making and reducing unnecessary invasive procedures. Microcalcifications classified as BI-RADS 4 and BI-RADS 5 are clinically important radiological findings; however, differentiating benign from malignant lesions remains challenging because of overlapping morphological and distribution patterns. This study aimed to develop a structured feature-based machine learning model for predicting the pathological diagnosis of breast microcalcifications by integrating mammographic descriptors, patient age, and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) contrast enhancement findings. Methods: The dataset included 53 biopsy-confirmed cases and consisted of clinical and radiological variables, including patient age, calcification morphology, calcification size, distribution pattern, DCE-MRI contrast enhancement status, and histopathological outcome. Several conventional machine learning algorithms were evaluated, including Logistic Regression, Support Vector Machine with radial basis function kernel, K-Nearest Neighbors, Decision Tree, Random Forest, Extra Trees, Gradient Boosting, AdaBoost, and CatBoost. Hyperparameter optimization was performed using grid search with five-fold cross-validation. Model performance was assessed using accuracy, precision, recall, F1-score, ROC-AUC, and log loss. Results: Logistic Regression achieved the highest overall performance, with an accuracy of 0.909 and an F1-score of 0.889, while AdaBoost achieved a recall of 1.000 in the internal evaluation. However, given the limited sample size and lack of external validation, these findings should be interpreted as preliminary. Conclusions: The results suggest that structured radiological descriptors combined with DCE-MRI enhancement information may support malignancy risk stratification of BI-RADS 4–5 microcalcifications, although larger multicenter studies are required before clinical implementation.