Large language models (LLMs) have been successfully used for data extraction from free-text radiology reports. Most current studies were conducted with LLMs accessed via an application programming interface (API). We evaluated the feasibility of using open-source LLMs, deployed on limited local hardware resources for data extraction from free-text mammography reports, using a common data element (CDE)-based structure. Seventy-nine CDEs were defined by an interdisciplinary expert panel, reflecting real-world reporting practice. Sixty-one reports were classified by two independent researchers to establish ground truth. Five different open-source LLMs deployable on a single GPU were used for data extraction using the general-classifier Python package. Extractions were performed for five different prompt approaches with calculation of overall accuracy, micro-recall and micro-F1. Additional analyses were conducted using thresholds for the relative probability of classifications. High inter-rater agreement was observed between manual classifiers (Cohen's kappa 0.83). Using default prompts, the LLMs achieved accuracies of 59.2-72.9%. Chain-of-thought prompting yielded mixed results, while few-shot prompting led to decreased accuracy. Adaptation of the default prompts to precisely define classification tasks improved performance for all models, with accuracies of 64.7-85.3%. Setting certainty thresholds further improved accuracies to > 90% but reduced the coverage rate to < 50%. Locally deployed open-source LLMs can effectively extract information from mammography reports, maintaining compatibility with limited computational resources. Selection and evaluation of the model and prompting strategy are critical. Clear, task-specific instructions appear crucial for high performance. Using a CDE-based framework provides clear semantics and structure for the data extraction.

Effective preoperative planning requires accurate algorithms for segmenting anatomical structures across diverse datasets, but traditional models struggle with generalization. This study presents a novel machine learning methodology to improve algorithm generalization for 3D anatomical reconstruction beyond breast cancer applications. We processed 120 retrospective breast MRIs (January 2018-June 2023) through three phases: anonymization and manual segmentation of T1-weighted and dynamic contrast-enhanced sequences; co-registration and segmentation of whole breast, fibroglandular tissue, and tumors; and 3D visualization using ITK-SNAP. A human-in-the-loop approach refined segmentations using U-Mamba, designed to generalize across imaging scenarios. Dice similarity coefficient assessed overlap between automated segmentation and ground truth. Clinical relevance was evaluated through clinician and patient interviews. U-Mamba showed strong performance with DSC values of 0.97 ($\pm$0.013) for whole organs, 0.96 ($\pm$0.024) for fibroglandular tissue, and 0.82 ($\pm$0.12) for tumors on T1-weighted images. The model generated accurate 3D reconstructions enabling visualization of complex anatomical features. Clinician interviews indicated improved planning, intraoperative navigation, and decision support. Integration of 3D visualization enhanced patient education, communication, and understanding. This human-in-the-loop machine learning approach successfully generalizes algorithms for 3D reconstruction and anatomical segmentation across patient datasets, offering enhanced visualization for clinicians, improved preoperative planning, and more effective patient education, facilitating shared decision-making and empowering informed patient choices across medical applications.

ObjectiveTo study the implications of implementing artificial intelligence (AI) as a decision support tool in the Norwegian breast cancer screening program concerning cost-effectiveness and time savings for radiologists.MethodsIn a decision tree model using recent data from AI vendors and the Cancer Registry of Norway, and assuming equal effectiveness of radiologists plus AI compared to standard practice, we simulated costs, effects and radiologist person-years over the next 20 years under different scenarios: 1) Assuming a €1 additional running cost of AI instead of the €3 assumed in the base case, 2) varying the AI-score thresholds for single vs. double readings, 3) varying the consensus and recall rates, and 4) reductions in the interval cancer rate compared to standard practice.ResultsAI was unlikely to be cost-effective, even when only one radiologist was used alongside AI for all screening exams. This also applied when assuming a 10% reduction in the consensus and recall rates. However, there was a 30-50% reduction in the radiologists' screen-reading volume. Assuming an additional running cost of €1 for AI, the costs were comparable, with similar probabilities of cost-effectiveness for AI and standard practice. Assuming a 5% reduction in the interval cancer rate, AI proved to be cost-effective across all willingness-to-pay values.ConclusionsAI may be cost-effective if the interval cancer rate is reduced by 5% or more, or if its additional cost is €1 per screening exam. Despite a substantial reduction in screening volume, this remains modest relative to the total radiologist person-years available within breast centers, accounting for only 3-4% of person-years.

Mammography is a primary method for early screening, and developing deep learning-based computer-aided systems is of great significance. However, current deep learning models typically treat each image as an independent entity for diagnosis, rather than integrating images from multiple views to diagnose the patient. These methods do not fully consider and address the complex interactions between different views, resulting in poor diagnostic performance and interpretability. To address this issue, this paper proposes a novel end-to-end framework for breast cancer diagnosis: lesion asymmetry screening assisted global awareness multi-view network (LAS-GAM). More than just the most common image-level diagnostic model, LAS-GAM operates at the patient level, simulating the workflow of radiologists analyzing mammographic images. The framework processes the four views of a patient and revolves around two key modules: a global module and a lesion screening module. The global module simulates the comprehensive assessment by radiologists, integrating complementary information from the craniocaudal (CC) and mediolateral oblique (MLO) views of both breasts to generate global features that represent the patient's overall condition. The lesion screening module mimics the process of locating lesions by comparing symmetric regions in contralateral views, identifying potential lesion areas and extracting lesion-specific features using a lightweight model. By combining the global features and lesion-specific features, LAS-GAM simulates the diagnostic process, making patient-level predictions. Moreover, it is trained using only patient-level labels, significantly reducing data annotation costs. Experiments on the Digital Database for Screening Mammography (DDSM) and In-house datasets validate LAS-GAM, achieving AUCs of 0.817 and 0.894, respectively.

The aim of this study is to evaluate the prognostic performance of a nomogram integrating clinical parameters with deep learning radiomics (DLRN) features derived from ultrasound and multi-sequence magnetic resonance imaging (MRI) for predicting survival, recurrence, and metastasis in patients diagnosed with triple-negative breast cancer (TNBC) undergoing neoadjuvant chemotherapy (NAC). This retrospective, multicenter study included 103 patients with histopathologically confirmed TNBC across four institutions. The training group comprised 72 cases from the First People's Hospital of Lianyungang, while the validation group included 31 cases from three external centers. Clinical and follow-up data were collected to assess prognostic outcomes. Radiomics features were extracted from two-dimensional ultrasound and three-dimensional MRI images following image segmentation. A DLRN model was developed, and its prognostic performance was evaluated using the concordance index (C-index) in comparison with alternative modeling approaches. Risk stratification for postoperative recurrence was subsequently performed, and recurrence and metastasis rates were compared between low- and high-risk groups. The DLRN model demonstrated strong predictive capability for DFS (C-index: 0.859-0.887) and moderate performance for overall survival (OS) (C-index: 0.800-0.811). For DFS prediction, the DLRN model outperformed other models, whereas its performance in predicting OS was slightly lower than that of the combined MRI + US radiomics model. The 3-year recurrence and metastasis rates were significantly lower in the low-risk group than in the high-risk group (21.43-35.71% vs 77.27-82.35%). The preoperative DLRN model, integrating ultrasound and multi-sequence MRI, shows promise as a prognostic tool for recurrence, metastasis, and survival outcomes in patients with TNBC undergoing NAC. The derived risk score may facilitate individualized prognostic evaluation and aid in preoperative risk stratification within clinical settings.

Data scarcity hinders deep learning for medical imaging. We propose a framework for breast cancer classification in thermograms that addresses this using a Diffusion Probabilistic Model (DPM) for data augmentation. Our DPM-based augmentation is shown to be superior to both traditional methods and a ProGAN baseline. The framework fuses deep features from a pre-trained ResNet-50 with handcrafted nonlinear features (e.g., Fractal Dimension) derived from U-Net segmented tumors. An XGBoost classifier trained on these fused features achieves 98.0\% accuracy and 98.1\% sensitivity. Ablation studies and statistical tests confirm that both the DPM augmentation and the nonlinear feature fusion are critical, statistically significant components of this success. This work validates the synergy between advanced generative models and interpretable features for creating highly accurate medical diagnostic tools.

Background: Precise breast ultrasound (BUS) segmentation supports reliable measurement, quantitative analysis, and downstream classification, yet remains difficult for small or low-contrast lesions with fuzzy margins and speckle noise. Text prompts can add clinical context, but directly applying weakly localized text-image cues (e.g., CAM/CLIP-derived signals) tends to produce coarse, blob-like responses that smear boundaries unless additional mechanisms recover fine edges. Methods: We propose XBusNet, a novel dual-prompt, dual-branch multimodal model that combines image features with clinically grounded text. A global pathway based on a CLIP Vision Transformer encodes whole-image semantics conditioned on lesion size and location, while a local U-Net pathway emphasizes precise boundaries and is modulated by prompts that describe shape, margin, and Breast Imaging Reporting and Data System (BI-RADS) terms. Prompts are assembled automatically from structured metadata, requiring no manual clicks. We evaluate on the Breast Lesions USG (BLU) dataset using five-fold cross-validation. Primary metrics are Dice and Intersection over Union (IoU); we also conduct size-stratified analyses and ablations to assess the roles of the global and local paths and the text-driven modulation. Results: XBusNet achieves state-of-the-art performance on BLU, with mean Dice of 0.8765 and IoU of 0.8149, outperforming six strong baselines. Small lesions show the largest gains, with fewer missed regions and fewer spurious activations. Ablation studies show complementary contributions of global context, local boundary modeling, and prompt-based modulation. Conclusions: A dual-prompt, dual-branch multimodal design that merges global semantics with local precision yields accurate BUS segmentation masks and improves robustness for small, low-contrast lesions.

This study aimed to evaluate the performance of ChatGPT (GPT-4o) in interpreting free-text breast magnetic resonance imaging (MRI) reports by assigning BI-RADS categories and recommending appropriate clinical management steps in the absence of explicitly stated BI-RADS classifications. In this retrospective, single-center study, a total of 352 documented full-text breast MRI reports of at least one identifiable breast lesion with descriptive imaging findings between January 2024 and June 2025 were included in the study. Incomplete reports due to technical limitations, reports describing only normal findings, and MRI examinations performed at external institutions were excluded from the study. First, it was aimed to assess ChatGPT's ability to infer the correct BI-RADS category (2-3-4a-4b-4c-5 separately) based solely on the narrative imaging findings. Second, it was evaluated the model's ability to distinguish between benign versus suspicious/malignant imaging features in terms of clinical decision-making. Therefore, BI-RADS 2-3 categories were grouped as "benign," and BI-RADS 4-5 as "suspicious/malignant," in alignment with how BI-RADS categories are used to guide patient management, rather than to represent definitive diagnostic outcomes. Reports originally containing the term "BI-RADS" were manually de-identified by removing BI-RADS categories and clinical recommendations. Each narrative report was then processed through ChatGPT using two standardized prompts as follows: (1) What is the most appropriate BI-RADS category based on the findings in the report? (2) What should be the next clinical step (e.g., follow-up, biopsy)? Responses were evaluated in real time by two experienced breast radiologists, and consensus was used as the reference standard. ChatGPT demonstrated moderate agreement with radiologists' consensus for BI-RADS classification (Cohen's Kappa (κ): 0.510, p<0.001). Classification accuracy was highest for BI-RADS 5 reports (77.9%), whereas lower agreement was observed in intermediate categories such as BI-RADS 3 (52.4% correct) and 4B (29.4% correct). In the binary classification of reports as benign or malignant, ChatGPT achieved almost perfect agreement (κ: 0.843), correctly identifying 91.7% of benign and 93.2% of malignant reports. Notably, the model's management recommendations were 100% consistent with its assigned BI-RADS categories, advising biopsy for all BI-RADS 4-5 cases and short-interval follow-up or conditional biopsy for BI-RADS 3 reports. ChatGPT accurately interprets unstructured breast MRI reports, particularly in benign/malignant discrimination and corresponding clinical recommendations. This technology holds potential as a decision support tool to standardize reporting and enhance clinical workflows, especially in settings with variable reporting practices. Prospective, multi-institutional studies are needed for further validation.

Breast cancer is the leading cause of cancer-related deaths among women worldwide. Early detection through mammography significantly improves outcomes, with breast density acting as both a risk factor and a key interpretive feature. Although the Breast Imaging Reporting and Data System (BI-RADS) provides standardized density categories, assessments are often subjective and variable. While automated tools exist, most are proprietary and resource-intensive, limiting their use in underserved settings. There is a critical need for accessible, low-cost AI solutions that provide consistent breast density classification. This study aims to develop and evaluate an open-source, computer vision-based approach using deep learning techniques for objective breast density assessment in mammography images, with a focus on accessibility, consistency, and applicability in resource-limited healthcare environments. Our approach integrates a custom-designed convolutional neural network (CD-CNN) with an extreme learning machine (ELM) layer for image-based breast density classification. The retrospective dataset includes 10,371 full-field digital mammography images, previously categorized by radiologists into one of four BI-RADS breast density categories (A-D). The proposed model achieved a testing accuracy of 95.4%, with a specificity of 98.0% and a sensitivity of 92.5%. Agreement between the automated breast density classification and the specialists' consensus was strong, with a weighted kappa of 0.90 (95% CI: 0.82-0.98). On the external and independent mini-MIAS dataset, the model achieved an accuracy of 73.9%, a precision of 81.1%, a specificity of 87.3%, and a sensitivity of 75.1%, which is comparable to the performance reported in previous studies using this dataset. The proposed approach advances breast density assessment in mammograms, enhancing accuracy and consistency to support early breast cancer detection.

Breast cancer remains a leading cause of cancer-related mortality among women worldwide. Ultrasound imaging, widely used due to its safety and cost-effectiveness, plays a key role in early detection, especially in patients with dense breast tissue. This paper presents a comprehensive study on the application of machine learning and deep learning techniques for breast cancer classification using ultrasound images. Using datasets such as BUSI, BUS-BRA, and BrEaST-Lesions USG, we evaluate classical machine learning models (SVM, KNN) and deep convolutional neural networks (ResNet-18, EfficientNet-B0, GoogLeNet). Experimental results show that ResNet-18 achieves the highest accuracy (99.7%) and perfect sensitivity for malignant lesions. Classical ML models, though outperformed by CNNs, achieve competitive performance when enhanced with deep feature extraction. Grad-CAM visualizations further improve model transparency by highlighting diagnostically relevant image regions. These findings support the integration of AI-based diagnostic tools into clinical workflows and demonstrate the feasibility of deploying high-performing, interpretable systems for ultrasound-based breast cancer detection.