Search Results (59)

Accurate and early identification of breast cancer from mammography is key to reducing breast cancer mortality, and automated analysis is challenging due to subtle lesion appearances, heterogeneous breast density, and the variance caused by modality. Standard Convolutional Neural Networks (CNNs) are excellent at capturing localized textures, whereas Vision Transformers (ViTs) capture long-range dependencies; however, both often struggle to produce a unified representation that consistently supports diagnostic decision-making. To address these limitations, this study presents a dual-stream framework integrating ConvNeXt for high-fidelity local feature extraction with Swin Transformer V2 for hierarchical global context modeling. A Bi-Directional Cross-Guidance (BDCG) mechanism is added to harmonize interactions between the two feature domains and ensure mutual information learning in the representations. Furthermore, a Prototype-Anchored Similarity Head (PASH) is used to stabilize classification using distance-based reasoning instead of using linear separation. Comprehensive experiments show the effectiveness of the proposed method using two benchmark datasets. On Dataset 1, the model achieves accuracy: 98.8%, precision: 98.7%, recall: 98.6%, and F1 score: 97.2%, outperforming existing models based on CNN, ViTs, and hybrid architectures, and provides a lower inference time (8.3 ms/image). On the more heterogeneous Dataset 2, the model maintains strong performance, with an accuracy of 97.0%, precision of 95.4%, recall of 94.8%, and F1-score of 95.1%, demonstrating its resilience to domain shift and imaging variability. These results underscore the value of structural multi-scale feature interaction and prototype-driven classification for robust mammographic analysis. The consistent performance across internal and external evaluations indicates the potential for the proposed framework to be reliably applied in computer-aided screening systems. Full article

Background/Objectives: The objective of this study was to evaluate the performance of Breast-SlimView^®, a deep convolutional neural network for the automatic classification of BI-RADS and breast density in MLO (mediolateral oblique) and CC (craniocaudal) views. Methods: A total of 9560 mammographic images from 2390 Mexican women (age: 54.14 ± 8.72 years) were labeled according to ACR (American College of Radiology) density (A-D) and BI-RADS 1, 2, and 3 (low risk), and BI-RADS 4 and 5 (high risk). All mammograms in the test dataset were blinded and read by two radiologists, and the consensus was taken as the reference standard. The accuracy, sensitivity, and specificity of the automated AI-based classification system was evaluated against the consensus reached by expert radiologists. Results: The classification of MLO and CC projections had a mean sensitivity of 0.81 (95% CI: 0.797–0.829), a specificity of 0.70 (95% CI: 0.686–0.722), and an accuracy of 0.71 (95% CI: 0.698–0.734) in differentiating between low and high risk. Good agreement was observed with ACR breast density classifications A, B, C, and D. Agreement between AI and human readers was “substantial” (Pearson’s chi-square, p = 0.001). Conclusions: AI enables accurate, standardized, observer independent classification. Full article

Background/Objectives: Breast cancer survivors face elevated risk of treatment-related bone loss, yet routine bone health assessment remains underutilized. Opportunistic bone density extraction from routine CT may address this gap. This study validated AI-derived vertebral bone mineral density (AI-vBMD) from non-contrast thoracoabdominal CT for osteoporosis screening and assessed its diagnostic value beyond clinical variables. Methods: This retrospective study included 332 breast cancer patients; AI-vBMD was successfully extracted in 325 (98%). Quantitative CT (QCT) served as reference standard. Agreement between AI-vBMD and QCT-vBMD was assessed using Pearson correlation, Bland–Altman analysis, and weighted kappa for QCT-defined osteoporosis (<80 mg/cm³). Nested logistic regression models compared a clinical model with and without AI-vBMD. Discrimination [area under the curve (AUC)], calibration, and clinical utility [decision-curve analysis (DCA)] were evaluated. Results: AI-vBMD showed strong correlation with QCT-vBMD (r = 0.98, p < 0.001), minimal bias (mean difference +1.82 mg/cm³), and excellent agreement for osteoporosis classification (weighted κ = 0.90). AI-vBMD alone achieved excellent discrimination for osteoporosis (AUC = 0.986). Integrating AI-vBMD into the clinical model yielded significantly higher diagnostic performance (AUC 0.988 vs. 0.879; p < 0.001) and demonstrated superior net benefit across relevant decision thresholds. Conclusions: AI-derived vertebral BMD from routine CT serves as a reliable QCT-aligned imaging biomarker for opportunistic osteoporosis assessment in breast cancer patients and adds significant incremental diagnostic value beyond clinical information alone. Full article

Purpose: The purpose of this study is to assess whether AI-based models improve reproducibility of breast density (BD) and background parenchymal enhancement (BPE) classification and to explore whether contrast-enhanced mammography (CEM) can serve as a proof-of-concept platform for systemic risk surrogates. Materials and Methods: In this retrospective single-center study, 213 women (mean age 58.3 years; range 28–80) underwent CEM in 2022–2023. Histology was obtained when lesions were present (BI-RADS 4/5). Five radiologists independently graded BD and BPE; consensus served as the ground truth. Linear regression and a deep neural network (DNN) were compared with a simple linear baseline. Inter-reader agreement was measured with Fleiss’ κ. External validation was performed on 500 BI-RADS C/D cases from VinDr-Mammo targeted density endpoints. A secondary exploratory analysis tested a multi-output DNN to predict BD/BPE together with bone mineral density and systolic blood pressure surrogates. Results: Baseline inter-reader agreement was κ = 0.68 (BD) and κ = 0.54 (BPE). With AI support, agreement improved to κ = 0.82. Linear regression reduced the prediction error by 26% versus the baseline (MSE 0.641 vs. 0.864), while DNN achieved similar performance (MSE 0.638). AI assistance decreased false positives in C/D by 22% and shortened the reading time by 35% (6.3→4.1 min). Validation confirmed stability (MSE ~0.65; AUC 0.74–0.75). In exploratory analysis, surrogates correlated with DXA (r = 0.82) and sphygmomanometry (r = 0.76). Conclusions: AI significantly improves reproducibility and efficiency of BD/BPE assessments in CEM and supports feasibility of systemic risk profiling. Full article

Timely and precise identification of breast cancer is crucial for enhancing clinical outcomes; however, current AI systems frequently exhibit deficiencies in transparency, trustworthiness, and the capacity to assimilate varied data modalities. We introduce a reliable, multi-agent, multimodal AI system for individualised early breast cancer diagnosis, created on the CBIS-DDSM dataset. The system consists of four specialised agents that cooperatively analyse diverse data. An Imaging Agent employs convolutional and transformer-based models to analyse mammograms for lesion classification and localisation; a Clinical Agent extracts structured features including breast density (ACR), view type (CC/MLO), laterality, mass shape, margin, calcification type and distribution, BI-RADS score, pathology status, and subtlety rating utilising optimised tabular learning models; a Risk Assessment Agent integrates outputs from the imaging and clinical agents to produce personalised malignancy predictions; and an Explainability Agent provides role-specific interpretations through Grad-CAM for imaging, SHAP for clinical features, and natural language explanations customised for radiologists, general practitioners, and patients. Predictive dependability is assessed by Expected Calibration Error (ECE) and Brier Score. The framework employs a modular design with a Streamlit interface, facilitating both comprehensive deployment and interactive demonstration. This paradigm enhances the creation of reliable AI systems for clinical decision assistance in oncology by the integration of strong interpretability, personalised risk assessment, and smooth multimodal integration. Full article

Background: In healthcare institutions, radiologists play an essential role in patients’ care, enabling them to begin treatment and start their recoveries. However, data on the characteristics and distribution of the radiology workforce in Saudi Arabia are limited. Therefore, this study aimed to conduct a comprehensive analysis of the radiology workforce in SA based on national data and identify key distributional and specialty trends relevant to workforce planning and radiology service delivery. Methods: The following data were obtained from the Saudi Commission for Health Specialties (SCFHS) Registry: total number of registered radiologists, age, subspecialty, professional classification, place of qualification, and geographical location. Descriptive statistics were used for data analysis. Additionally, the findings were compared with those of published international benchmarks. Results: There were 5150 radiologists registered with SCFHS in SA, which corresponded to 147 radiologists per 1,000,000 inhabitants. The mean age was 40.8 years (standard deviation [SD] 9.8), with 60% of them being aged 30–44 years. Most of the radiologists specialised in general diagnostic radiology (83.7%), with few of them specialising in interventional radiology (1.8%), paediatric radiology (1.1%), and breast imaging (0.9%). The workforce mainly comprised consultants (35.0%), followed by registrars (29.7%) and senior registrars (22.7%). Two-thirds (65.0%) of the radiologists had obtained their qualifications abroad. More than half of the radiologists resided in three provinces: Riyadh (29%), Mecca (23%), and the Eastern Region (15%), while several provinces had fewer than 2% of the available workforce. Conclusions: The radiology workforce in SA is relatively young and has a higher density than the average in the European Union. Further, most of the radiologists are professionally classified as consultants or registrars. However, there is a clear imbalance in their geographic distribution, which is consistent with the population sizes of the respective cities. Targeted training expansion and reduced reliance on foreign-trained professionals are warranted to meet future service demands in line with the Vision 2030 objectives. Full article

Introduction: Breast density is a well-recognized factor in breast cancer risk assessment, with higher density linked to increased malignancy risk and reduced sensitivity of conventional mammography. Background parenchymal enhancement (BPE), observed in contrast-enhanced imaging, reflects physiological contrast uptake in non-pathologic breast tissue. While extensively characterized in breast MRI, the role of BPE in contrast-enhanced mammography (CEM) remains uncertain due to inconsistent findings regarding its correlation with breast density and cancer risk. Unlike breast density—standardized through the ACR BI-RADS lexicon—BPE lacks a uniform classification system in CEM, leading to variability in clinical interpretation and research outcomes. To address this gap, we introduce the BPE-CEM Standard Scale (BCSS), a structured four-tiered classification system specifically tailored to the two-dimensional characteristics of CEM, aiming to improve consistency and diagnostic alignment in BPE evaluation. Materials and Methods: In this retrospective single-center study, 213 patients who underwent mammography (MG), ultrasound (US), and contrast-enhanced mammography (CEM) between May 2022 and June 2023 at the “A. Perrino” Hospital in Brindisi were included. Breast density was classified according to ACR BI-RADS (categories A–D). BPE was categorized into four levels: Minimal (< 10% enhancement), Light (10–25%), Moderate (25–50%), and Marked (> 50%). Three radiologists independently assessed BPE in a subset of 50 randomly selected cases to evaluate inter-observer agreement using Cohen’s kappa. Correlations between BPE, breast density, and age were examined through regression analysis. Results: BPE was Minimal in 57% of patients, Light in 31%, Moderate in 10%, and Marked in 2%. A significant positive association was found between higher breast density (BI-RADS C–D) and increased BPE (p < 0.05), whereas lower-density breasts (A–B) were predominantly associated with minimal or light BPE. Regression analysis confirmed a modest but statistically significant association between breast density and BPE (R² = 0.144), while age showed no significant effect. Inter-observer agreement for BPE categorization using the BCSS was excellent (κ = 0.85; 95% CI: 0.78–0.92), supporting its reproducibility. Conclusions: Our findings indicate that breast density is a key determinant of BPE in CEM. The proposed BCSS offers a reproducible, four-level framework for standardized BPE assessment tailored to the imaging characteristics of CEM. By reducing variability in interpretation, the BCSS has the potential to improve diagnostic consistency and facilitate integration of BPE into personalized breast cancer risk models. Further prospective multicenter studies are needed to validate this classification and assess its clinical impact. Full article

Breast cancer remains one of the leading causes of mortality among women worldwide, highlighting the critical need for early and accurate detection methods. Traditional mammography, although widely used, has limitations, including radiation exposure and challenges in detecting early-stage lesions. Electrical Impedance Mammography (EIM) has emerged as a non-invasive and radiation-free alternative that assesses the density and electrical conductivity of breast tissue. EIM images consist of seven layers, each representing different tissue depths, offering a detailed representation of the breast structure. However, analyzing these layers individually can be redundant and complex, making it difficult to identify relevant features for lesion classification. To address this issue, advanced computational techniques are employed for image integration, such as the Root Mean Square ($C_{\mathrm{RMS}}$) Contrast and Contrast-Limited Adaptive Histogram Equalization (CLAHE), combined with the Coefficient of Variation (CV), CLAHE-based fusion, weighted average fusion, Gaussian pyramid fusion, and Wavelet–PCA fusion. Each method enhances the representation of tissue features, optimizing the image quality and diagnostic utility. This study evaluated the impact of these integration techniques on EIM image analysis, aiming to improve the accuracy and reliability of computational diagnostic models for breast cancer detection. According to the obtained results, the best performance was achieved using Wavelet–PCA fusion in combination with XGBoost as a classifier, yielding an accuracy rate of 89.5% and an F1-score of 81.5%. These results are highly encouraging for the further investigation of this topic. Full article

Background and Objectives: Breast cancer is a leading global health challenge, where early detection is essential for improving survival outcomes. Two-dimensional (2D) mammography is the established standard for breast cancer screening; however, its diagnostic accuracy is limited by factors such as breast density and inter-reader variability. Recent advances in artificial intelligence (AI) have shown promise in enhancing radiological interpretation. This study aimed to assess the utility of AI in improving lesion detection and classification in 2D mammography. Materials and Methods: A retrospective analysis was performed on a dataset of 578 mammographic images obtained from a single radiology center. The dataset consisted of 36% pathologic and 64% normal cases, and was partitioned into training (403 images), validation (87 images), and test (88 images) sets. Image preprocessing involved grayscale conversion, contrast-limited adaptive histogram equalization (CLAHE), noise reduction, and sharpening. A convolutional neural network (CNN) model was developed using transfer learning with ResNet50. Model performance was evaluated using sensitivity, specificity, accuracy, and area under the receiver operating characteristic (AUC-ROC) curve. Results: The AI model achieved an overall classification accuracy of 88.5% and an AUC-ROC of 0.93, demonstrating strong discriminative capability between normal and pathologic cases. Notably, the model exhibited a high specificity of 92.7%, contributing to a reduction in false positives and improved screening efficiency. Conclusions: AI-assisted 2D mammography holds potential to enhance breast cancer detection by improving lesion classification and reducing false-positive findings. Although the model achieved high specificity, further optimization is required to minimize false negatives. Future efforts should aim to improve model sensitivity, incorporate multimodal imaging techniques, and validate results across larger, multicenter prospective cohorts to ensure effective integration into clinical radiology workflows. Full article

Hollow-dependent wildlife has been declining globally due to the removal of hollow-bearing trees, yet these trees are often unaccounted for in habitat mapping. As on-ground field surveys are costly and time-consuming, we aimed to develop a simple, accessible and transferrable geospatial approach using freely accessible LiDAR to refine habitat mapping by identifying high densities of potential hollow-bearing trees. We assessed if LiDAR from 2009 could be accurately used to detect tree heights, which would correlate to tree diameter at breast height (DBH), which in turn would identify trees that are more likely to be hollow-bearing. Here, we use habitat mapping of greater gliders (Petauroides spp.) in the Fraser Coast region of Australia as a case study. Across four sites, field surveys were conducted in 2023 to assess the tree height and density of large trees (>50 cm DBH per 1 km²) at 19 transects (n = 91). This was compared to outputs from individual tree detection derived from unsupervised classification using a local maximal filter and variable window size to identify treetops in freely available LiDAR. Tree height was measured with an accuracy of RMSE 5.75 m, and we were able to identify transects with large trees (>50 cm DBH), which were more likely hollow bearing. However, there was no statistical evidence to suggest that transects with a high density of large trees could be accurately identified based on LiDAR alone (>50 cm DBH p 0.2298). Despite this, we have demonstrated that freely accessible LiDAR and unsupervised machine learning techniques can be utilised to identify large, potentially hollow-bearing trees on a broad scale to refine habitat mapping for hollow-dependent species. It is important to develop geospatial analysis methods that are more accessible to land managers, as deep machine learning methods and current LiDAR can be computationally intensive and expensive. We propose a workflow using free and accessible geospatial analysis methods to identify large, potentially hollow-bearing trees and determine how to address some limitations in this geospatial approach. Full article

Background: To progress research into the biological mechanisms that link mammographic breast density to breast cancer risk, fibroglandular breast density can be used as a surrogate measure. This study aimed to develop a computational tool to classify fibroglandular breast density in hematoxylin and eosin (H&E)-stained breast tissue sections using deep learning approaches that would assist future mammographic density research. Methods: Four different architectural configurations of transferred MobileNet-v2 convolutional neural networks (CNNs) and four different models of vision transformers were developed and trained on a database of H&E-stained normal human breast tissue sections (965 tissue blocks from 93 patients) that had been manually classified into one of five fibroglandular density classes, with class 1 being very low fibroglandular density and class 5 being very high fibroglandular density. Results: The MobileNet-Arc 1 and ViT model 1 achieved the highest overall F1 scores of 0.93 and 0.94, respectively. Both models exhibited the lowest false positive rate and highest true positive rate in class 5, while the most challenging classification was class 3, where images from classes 2 and 4 were mistakenly classified as class 3. The area under the curves (AUCs) for all classes were higher than 0.98. Conclusions: Both the ViT and MobileNet models showed promising performance in the accurate classification of H&E-stained tissue sections across all five fibroglandular density classes, providing a rapid and easy-to-use computational tool for breast density analysis. Full article

Breast cancer, as of 2022, is the most prevalent type of cancer in women. Breast density—a measure of the non-fatty tissue in the breast—is a strong risk factor for breast cancer that can be estimated from mammograms. The importance of studying breast density is twofold. First, high breast density can be a factor in lowering mammogram sensitivity, as dense tissue can mask tumors. Second, higher breast density is associated with an increased risk of breast cancer, making accurate assessments vital. This paper presents a comprehensive review of the mammographic density estimation literature, with an emphasis on machine-learning-based approaches. The approaches reviewed can be classified as visual, software-, machine learning-, and segmentation-based. Machine learning methods can be further broken down into two categories: traditional machine learning and deep learning approaches. The most commonly utilized models are support vector machines (SVMs) and convolutional neural networks (CNNs), with classification accuracies ranging from 76.70% to 98.75%. Major limitations of the current works include subjectivity and cost-inefficiency. Future work can focus on addressing these limitations, potentially through the use of unsupervised segmentation and state-of-the-art deep learning models such as transformers. By addressing the current limitations, future research can pave the way for more reliable breast density estimation methods, ultimately improving early detection and diagnosis. Full article

Technological developments have allowed helicopter airborne laser scanning (HALS) to produce high-density point clouds below the forest canopy. We present a tree stem classification method that combines linear shape detection and model-based clustering, using four discrete methods to estimate stem diameter. Stem horizontal size was estimated every 25 cm below the living crown, and a cubic spline was used to estimate where there were gaps. Individual stem diameter at breast height (DBH) was estimated for 77% of field-measured trees. The root mean square error (RMSE) of DBH estimates was 7–12 cm using stem circle fitting. Adapting the approach to use an existing stem taper model reduced the RMSE of estimates (<1 cm). In contrast, estimates that were produced from a previously existing DBH estimation method (PREV) could be achieved for 100% of stems (DBH RMSE 6 cm), but only after location-specific error was corrected. The stem classification method required comparatively little development of statistical models to provide estimates, which ultimately had a similar level of accuracy (RMSE < 1 cm) to PREV. HALS datasets can measure broad-scale forest plantations and reduce field efforts and should be considered an important tool for aiding in inventory creation and decision-making within forest management. Full article

Identifying breast masses is relevant in early cancer detection. Automatic identification using computational methods helps assist medical experts with this task. Although high values have been reported in breast mass classification from digital mammograms, most results have focused on a general benign/malignant classification. According to the BI-RADS standard, masses are associated with cancer risk by grade depending on their specific shape, margin, and density characteristics. This work presents a methodology of testing several descriptors on the INbreast dataset, finding those better related to clinical assessment. The analysis provides a description based on BI-RADS for mass classification by combining neural networks and image processing. The results show that masses associated with grades BI-RADS-2 to BI-RADS-5 can be identified, reaching a general accuracy and sensitivity of $0.88\pm 0.07$. While this initial study is limited to a single dataset, it demonstrates the possibility of generating a description for automatic classification that is directly linked to the information analyzed by medical experts in clinical practice. Full article

Breast cancer is among the most prevalent cancers in the female population globally. Therefore, screening campaigns as well as approaches to identify patients at risk are particularly important for the early detection of suspect lesions. This study aims to propose a workflow for the automatic classification of patients based on one of the most relevant risk factors in breast cancer, which is represented by breast density. The proposed classification methodology takes advantage of the features automatically extracted from mammographic images, as digital mammography represents the major screening tool in women. Textural features were extracted from the breast parenchyma through a radiomics approach, and they were used to train different machine learning algorithms and neural network models to classify the breast density according to the standard Breast Imaging Reporting and Data System (BI-RADS) guidelines. Both binary and multiclass tasks have been carried out and compared in terms of performance metrics. Preliminary results show interesting classification accuracy (93.55% for the binary task and 82.14% for the multiclass task), which are promising compared to the current literature. As the proposed workflow relies on straightforward and computationally efficient algorithms, it could serve as a basis for a fast-track protocol for the screening of mammograms to reduce the radiologists’ workload. Full article