Search Results (1,872)

The widespread fragmentation of patient information across heterogeneous systems and the lack of standardized integration mechanisms hinder efficient and comprehensive medical diagnostics. To address these limitations, this work presents an architecture framework designed to support physicians in the diagnostic process by integrating clinical and socio-health information (patient medical histories), structured documents extracted from Health Information System (HIS), and data automatically extracted from diagnostic images using Artificial Intelligence (AI) techniques. The proposed architecture is made by several modules, in particular a Decision Support System (DSS) that enables risk assessment related to specific patient’s clinical conditions. In addition, the clinical information retrieved is aggregated, standardized, and transmitted to external systems for follow up. Standardization and data interoperability are ensured through the adoption of the international HL7 Fast Healthcare Interoperability Resources (FHIR) standard, which facilitates seamless connection with HIS. An Android application has been developed to communicate with different HISs in order to: (i) retrieve information, (ii) aggregate clinical data, (iii) calculate patient risk scores using AI algorithms, (iv) display results to healthcare professionals, and (v) generate and share relevant clinical information with external systems in a standardized format. To demonstrate architecture’s applicability, a case study on breast cancer diagnosis is presented. In this context, an AI-based Risk Assessment module was developed using the Breast Ultrasound Images Dataset (BUSI), which includes benign, malignant, and normal cases. Machine Learning algorithms were applied to perform the classification task. Model performance was evaluated using a 4-fold cross-validation strategy to ensure robustness and generalizability. The best results were achieved using the Multilayer Perceptron method, with a competitive F1-score of 0.97. Full article

Background: Meta-analyses on the prevalence and clinical significance of breast incidental uptake (BIU) at PET/CT are available only for [¹⁸F]FDG, showing that BIU is rare but malignant in a substantial proportion of cases. This study aimed to update the pooled prevalence and malignancy risk of BIU using different PET radiotracers, expanding [¹⁸F]FDG-based evidence. Methods: A comprehensive literature search of studies on BIU was carried out in two bibliographic databases, and the literature was screened up to 25 May 2025. Only original articles reporting BIU were selected. A proportion meta-analysis was conducted on a patient-based analysis using a random-effects model to estimate pooled prevalence, malignancy rate, and histological distribution. Results: In total, 29 studies were included in the systematic review and meta-analysis. PET/CT was performed using [¹⁸F]FDG (n = 25), radiolabeled somatostatin analogues (SSAs) (n = 3), or [¹⁸F]fluorocholine (n = 1). The pooled prevalence of BIU was 0.5% for [¹⁸F]FDG PET/CT, 3.4% for SSA PET/CT, and 2.6% for [¹⁸F]fluorocholine. The pooled malignancy rate among BIUs (female patients) was 33.5% for [¹⁸F]FDG, 86.4% for SSA, and 70% for [¹⁸F]fluorocholine PET/CT. Histological data were mainly available for [¹⁸F]FDG PET/CT, showing ductal carcinoma as the most frequent malignant histotype (pooled value 42.2%) and fibroadenoma (pooled value 14.8%) as the most frequent benign histotype. Conclusions: Similar to the case for [¹⁸F]FDG, BIU using other PET radiopharmaceuticals is uncommon but often malignant. Therefore, BIU should prompt dedicated breast imaging and, when indicated, histopathological confirmation. Further well-designed studies are needed to clarify the clinical impact of BIU detection and the prevalence and clinical significance of BIU using tracers other than [¹⁸F]FDG. Full article

This study addresses the limited mechanistic understanding behind medical imaging for tumor microenvironment (TME) assessment. We developed a novel framework that analyzes tumor imaging heterogeneity index (TIHI)-correlated genes to uncover underlying TME biology and therapeutic vulnerabilities. DCE-MRI and mRNA data from 987 high-risk breast cancer patients in the I-SPY2 trial, together with mRNA data from 508 patients in GSE25066, were analyzed. TIHI-associated genes were identified via Pearson correlation, clustered via weighted gene co-expression network analysis (WGCNA), and subgroups were defined via non-negative matrix factorization (NMF). The clinical relevance of the image-to-gene comprehensive (I2G-C) subtype defined by subgroups was assessed using logistic regression and Cox analysis. I2G-C comprised four clusters with distinct immune and replication/repair functions. It further stratified receptor, PAM50, and RPS5 subtypes. The “immune+/replication+” was more likely to achieve pathological complete response (pCR) (OR = 2.587, p < 0.001), while the “immune−/replication−” was the least likely to achieve pCR (OR = 0.402, p < 0.001). The “immune+/replication+” showed sensitivity to pembrolizumab (OR = 10.192, p < 0.001) and veliparib/carboplatin (OR = 5.184, p = 0.006), while “immune-/replication-” responded poorly to pembrolizumab (OR = 0.086, p < 0.001). Additionally, “immune+/replication-” had the best distant recurrence-free survival (DRFS), whereas “immune-/replication+” had the worst (log-rank p = 6 × 10⁻⁴, HR = 5.45). By linking imaging heterogeneity directly to molecular subtypes and therapeutic response, this framework provides a robust, non-invasive surrogate for genomic profiling and a strategic tool for personalized neoadjuvant therapy selection. Full article

Background/Objectives: Accurate intraoperative margin assessment is essential for ensuring complete tumour excision in breast-conserving surgery, minimising local recurrence, and avoiding reoperations. Ex vivo fusion confocal microscopy (EVFCM) provides real-time, high-resolution imaging of fresh, unfixed tissues that closely resembles conventional histological imaging. This study aimed to validate the diagnostic performance and clinical feasibility of EVFCM for real-time intraoperative margin assessment during breast cancer surgery. Methods: A prospective observational diagnostic validation study was conducted using 144 breast tissue specimens. The samples were stained with acridine orange and fast green and scanned using a VivaScope 2500M-G4 system. Two breast pathologists independently evaluated the EVFCM images, blinded to the conventional histology results, which served as the reference standard. The diagnostic accuracy, sensitivity, specificity, and interobserver agreement were calculated using Cohen’s κ. Results: Interobserver agreement was almost perfect for neoplasia detection (97.3%, κ = 0.942) and tumour type classification (93.8%, κ = 0.883). The EVFCM achieved 93.7% sensitivity and specificity, with 94.0% accuracy for tumour detection (κ = 0.929, p < 0.001); 95.8% accuracy for tumour type classification (κ = 0.925, p < 0.001); and 95.1% accuracy for invasive subtype identification (κ = 0.907, p < 0.001). For margin assessment, EVFCM achieved 80% sensitivity, 100% specificity, and 99.3% accuracy (κ = 0.857, p < 0.001), whereas margin distance evaluation (<2 mm vs. ≥2 mm) yielded 75% sensitivity, 100% specificity, and 98.6% accuracy (κ = 0.854, p < 0.001). Conclusions: EVFCM enables rapid, high-resolution imaging of fresh breast tissue, facilitating real-time intraoperative margin evaluation with excellent diagnostic concordance and workflow efficiency. Its integration into surgical practice could reduce re-excisions, enhance oncological safety, and improve patient outcomes in breast-conserving surgeries. Full article

Objectives: This single-center retrospective study evaluates the clinical efficacy and safety of percutaneous ablation using microwave ablation (MWA) and irreversible electroporation (IRE) in patients with breast cancer liver metastases (BCLM). Methods: Between August 2018 and December 2023, 32 patients underwent 40 image-guided ablations for 57 BCLM. Mean age was 61.3 years (range: 32–85), and mean tumor size was 2.9 cm (range: 0.9–7.0 cm). Fifty lesions were treated with MWA and seven with IRE. Clinical efficacy was assessed by m-RECIST response at first follow-up imaging (after ≥1 month) and by monitoring local tumor progression (LTP), local tumor progression-free survival (LTPFS), and overall survival (OS). Safety was evaluated by adverse events according to CTCAE. Kaplan–Meier statistics were used for LTPFS and OS. Results: Median follow-up was 32.4 months (95% CI 16.6–48.0). Complete response was observed in 34 tumors (59.6%), partial response in 14 (24.6%), and progressive disease in 9 (15.8%). LTP occurred in 37 tumors (64.9%), with a median time to progression of 11.1 months (95% CI 1.4–20.8). One- and two-year LTPFS rates were 43.6% and 34.1%. Sixteen patients died during follow-up, with median OS of 27.8 months (95% CI 19.0–36.6) and 1- and 2-year OS rates of 90.1% and 55.9%. No major complications occurred. Complications included eight Grade 1 and two Grade 2 complications. Conclusions: Percutaneous ablation demonstrates clinical efficacy and a favorable safety profile in selected BCLM patients, achieving OS comparable to the current literature. Further studies should clarify its additive role within multimodality treatment. Full article

The sternalis muscle, a well-documented anatomical variation in the chest muscles, has garnered attention in anatomical research but remains relatively unfamiliar to clinicians and radiologists. This variation exhibits a wide array of descriptions and classifications in the literature, emphasizing its highly variable characteristics. This study presents a new variant of the sternalis muscle with seven muscle bellies in a 79-year-old male donor. Bilateral accessory heads of the sternocleidomastoid muscles gave rise to two superior heads. Furthermore, five additional heads originated from the pectoralis major fascia, with three on the left and two on the right, together having widths of 6.6 cm on the left and 5.3 cm on the right. Innervation of the inferior heads was provided by the intercostal nerves. The configuration of the sternalis muscle with seven heads found in this study is exceptionally distinctive and has never been reported. This unique anatomical variation, coupled with three-dimensional imaging using photogrammetry, offers valuable insights for clinicians, especially in the context of breast surgery. Full article

Background: Preoperative breast MRI is widely used in surgical planning because of its high sensitivity. However, discrepancies with histopathology remain common and can affect tumor size assessment and treatment decisions. In addition, recent comparative studies have highlighted the growing role of contrast-enhanced mammography (CEM) and multiparametric MRI (mpMRI), both of which may improve specificity and accessibility compared to conventional MRI. Methods: A structured literature review was conducted in PubMed (2000–2025) according to PRISMA guidelines. Studies included if they evaluated preoperative breast MRI with histopathological correlation and reported sensitivity, specificity, or concordance outcomes. Data extraction focused on study design, patient and tumor characteristics, imaging methods, and clinical impact. Results: MRI demonstrates high sensitivity, particularly in detecting IDC and ILC. However, overestimation of tumor size remains a concern, particularly in ILC and high-grade DCIS, while underestimation is frequently observed after neoadjuvant therapy, especially in Luminal A tumors. Tumor size and stage significantly affect concordance, with advanced-stage tumors (T2–T3) showing better MRI-histopathology concordance than early-stage lesions (T0–T1). Specificity remains limited, particularly in DCIS and multifocal disease. Emerging evidence suggests that contrast-enhanced mammography (CEM) achieves comparable sensitivity with higher specificity, while multiparametric MRI (mpMRI) incorporating diffusion-weighted imaging (DWI) improves lesion characterization and prediction of treatment response. Conclusions: While MRI remains a valuable diagnostic tool for breast cancer, histopathological validation is essential to guide treatment decisions. Future research should focus on AI-enhanced imaging techniques, CEM and multiparametric MRI to improve concordance rates, reduce overdiagnosis and translate imaging advances into meaningful clinical outcomes. Full article

Background/Objectives: To evaluate the ability of radiomics analysis of QUS spectral parametric imaging to non-invasively differentiate intermediate-to-high-risk from low-risk Oncotype DX^TM Recurrence Score (ODXRS). Methods: This prospective study included 31 participants (21 intermediate-to-high-risk ODXRS (median age, 56 years [IQR: 49–68 years]) and 10 low-risk ODXRS (median age, 52 years [IQR: 48–58 years])) presenting with ER+ HER2− invasive breast masses acquired between September 2015 and August 2024. Quantitative ultrasound (QUS) spectroscopy produced five spectral maps, from which radiomics features (including statistical, texture, and morphological measures) were extracted from the tumor core and a 5 mm margin. The ground truth label was determined from thresholding the ODXRS. A multivariate predictive model was developed to differentiate intermediate-to-high-risk ODXRS from low-risk ODXRS, with performance assessed via nested leave-one-out cross-validation (LOOCV). Results: A nested leave-one-out cross-validation (LOOCV) analysis demonstrated the generalization performance of a four-feature model. The support vector machine (SVM-RBF) classifier achieved 86% recall, 100% specificity, 93% balanced accuracy, and an area under the receiver operating characteristic curve (AUROC) of 0.95 (CI = 0.88–1.00) in identifying intermediate-to-high-risk versus low-risk ODXRS. Conclusions: The preliminary results suggest the potential radiomics-based model of ODXRS in predicting the risks of recurrence. The results warrant further investigation on a larger cohort. This framework can be a useful surrogate for participants for whom ODX testing is neither affordable nor available. Full article

Background: Neoadjuvant systemic therapy (NST), whose primary purposes include response assessment and treatment individualization, is a key strategy in the treatment of HER2-positive breast cancer. This study investigated the predictive value of the magnetic resonance imaging (MRI)-derived tumor volume reduction rate (δV1) for the early identification of pathological complete response (pCR) during NST and established clinically applicable δV1 thresholds for patient stratification. Methods: HER2-positive breast cancer patients who received THP (taxane, trastuzumab, pertuzumab) followed by epirubicin/cyclophosphamide (EC) were enrolled. MRI was performed at baseline, after THP, and after EC. Tumor volumes were manually segmented using 3D Slicer, and δV1/δV2 were calculated via Python (version3.13). Longest diameter reduction rates (δL1/δL2) were recorded. pCR (ypT0/is ypN0) was the primary endpoint. Receiver operating characteristic (ROC) analysis determined predictive accuracy, and logistic regression identified independent predictors. Thresholds for δV1 were explored, and subgroup analyses were conducted by hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) status. Results: Overall, 59.3% of patients achieved pCR. δV1 demonstrated superior predictive accuracy compared with longest diameter reduction (δL1), with an AUC of 0.745 (95% CI: 0.642–0.847) vs. 0.634 (95% CI: 0.512–0.757). A δV1 cutoff of 0.85 discriminated responders (68.4% vs. 41.4%, p = 0.016), while one of 0.91 represented the optimal predictive threshold. In multivariate analysis, δV1 was independently associated with pCR (OR = 1227.1, 95% CI: 6.86–219,562; p = 0.007), along with HER2 3+ expression (OR = 4.24, 95% CI: 1.26–14.31; p = 0.020). Among HR-positive patients, δV1 < 0.93 identified a subgroup with significantly lower pCR rates (19.0% vs. 81.0%, p < 0.001). Conclusions: δV1 is a reliable and early MRI-based imaging biomarker for predicting pCR in HER2-positive breast cancer. Defining thresholds such as 0.85 and 0.91 supports early therapeutic stratification and may help identify patients who could benefit from anthracycline-containing regimens. Full article

Background/Objectives: Developing effective therapies for patients with triple-negative breast cancer (TNBC) remains an urgent clinical priority. Compared with other subtypes, the basal B type of TNBC exhibits a less differentiated and mesenchymal-like phenotype that models highly invasive and metastatic breast malignancies. To target metastatic TNBC, our current study sought to identify effective therapeutic drugs and the underlying mechanisms. Methods: A systematic screening of 140 FDA-approved drugs was conducted for repurposing using live-cell imaging-based wound-healing assays. Candidate efficacy was validated by in vitro transwell invasion assays, in vivo allograft/xenograft models, and ex vivo three-dimensional air–liquid interface (ALI) and patient-derived organoid (PDO) cultures. Results: Dasatinib emerged as a promising anti-cancer agent in aggressive TNBC, particularly in the basal B type, with high ETS proto-oncogene 1 (ETS1) expression. Mechanistically, dasatinib disrupts the actin cytoskeleton, impairing cell motility and migration while concurrently suppressing the expression of ETS1 and matrix metalloproteinase-3 (MMP3) to remodel the extracellular matrix (ECM) and inhibit invasion. Moreover, the combination of dasatinib with an anti-programmed cell death protein-1 (PD-1) antibody represents a potential therapeutic strategy. Conclusions: These findings highlight dasatinib as a potential therapeutic option for metastatic TNBC and suggest that selecting patients with high ETS1 expression may optimize treatment response. Full article

Background/Objectives: This study explored the associations of normal breast tissue characteristics on multiparametric MRI with clinical assessments of breast cancer risk in women with dense breasts. Methods: Women with dense breasts who underwent multiparametric MRI were included. Breast cancer risk was determined based on Tyrer–Cuzick (TC) lifetime risk scores, categorized as high (TC ≥ 20%) or low risk. Qualitative background parenchymal enhancement (BPE) assessment was obtained from imaging reports. Quantitative imaging markers were calculated, including median BPE, median apparent diffusion coefficient, and volume measures of the whole breast, fibroglandular tissue (FGT), blood vessels, and BPE regions. The associations between imaging markers and TC risk groups were evaluated using age-adjusted logistic regression and summarized by area under the receiver operating characteristic curve (AUC). Results: Seventy-seven women were evaluated; a total of 20 (26%) were low risk, and 57 (74%) were high risk. After adjusting for age and multiple testing, BPE:breast ratio (adj. p = 0.037), FGT:breast ratio (adj. p = 0.046), and BPE:vessel ratio (adj. p = 0.037) were positively associated with risk, while qualitative BPE was not (adj. p = 0.11). Overall, risk categorizations based on imaging markers were concordant with TC score in up to 70% of women. Conclusions: In women with dense breasts, quantitative measures from multiparametric MRI (BPE:breast, FGT:breast, and BPE:vessel ratios) moderately discriminated high- and low-risk groups, warranting further investigation of their value to supplement conventional breast cancer risk assessment tools. Full article

Artificial intelligence is reshaping breast imaging, yet progress is constrained by data scarcity, privacy restrictions, and uneven representation. This narrative review synthesizes evidence (2020–April 2025) on synthetic data and generative AI—principally GANs and diffusion models—in mammography and related modalities. We examine how synthetic images enable data augmentation, class balancing, external validation, and simulation-based training; summarize reported gains in detection performance; and assess their potential to mitigate or, if misapplied, amplify bias across subgroups (age, density, ethnicity). We analyze threats to validity, including enriched cohorts, distribution shift, and unverifiable realism, and address medico-legal exposure, image provenance, and deepfake risks. Finally, we outline task-specific validation and reporting practices, equity auditing across density and demographics, and governance pathways aligned with EU/US regulatory expectations. Synthetic data and generative AI can enhance performance, training, and data sharing; however, responsible clinical adoption requires rigorous validation, transparency on failure modes, tamper-evident provenance, and shared accountability models. Full article

Background: Three-dimensional (3D) culture systems offer a physiologically relevant alternative to monolayers for studying tumor organization, signaling, and drug response. HER2-positive breast cancers (BCa) account for 15–30% of BCa cases and benefit from HER2-targeted therapies, yet predictive in vitro models remain limited. Objective: To generate and compare 3D spheroids from two HER2+ BCa cell lines, SKBR3 and BT474, and investigate how 3D architecture influences HER2 distribution, intracellular signaling, and cellular organization. Methods: Spheroids were reproducibly generated from SKBR3 and BT474 cells and analyzed after 4 days of culture. Cell viability was evaluated using live/dead staining, HER2 distribution was assessed by confocal microscopy and quantified on cryosections, and protein expression/phosphorylation was measured by Western blotting. Epithelial and EMT markers were visualized by immunofluorescence, and ultrastructural features were examined by transmission electron microscopy (TEM). Results: Both cell lines formed viable spheroids with distinct architectures: SKBR3 spheroids were loose and heterogeneous, whereas BT474 spheroids were compact and highly spherical. Confocal and cryosection imaging showed consistent membrane HER2 localization with a progressive signal decrease toward the core of the spheroids, more pronounced in BT474. Western blotting revealed divergent HER2 expression and AKT phosphorylation: SKBR3 spheroids displayed increased HER2 but reduced pAKT, while BT474 spheroids showed reduced HER2 and pAKT levels. EpCAM and E-cadherin staining revealed cell line-specific epithelial organization, and TEM demonstrated differences in intercellular spacing and mitochondrial morphology, reflecting spheroid compactness. Conclusions: 3D architecture profoundly influences HER2 distribution, signaling, and structural organization in HER2+ BCa spheroids. This model provides a robust platform for investigating architecture-dependent molecular processes, with potential applications in drug response, receptor trafficking, and targeted therapy evaluation. Full article

Objectives: To propose a multimodal deep learning method for the classification of benign and malignant breast non-mass lesions (NMLs) using grayscale and color Doppler ultrasound and to compare the performance of multi-modality and single-modality breast ultrasound (BUS) models. Methods: This retrospective study collected 248 pathologically confirmed NMLs from 241 female patients comprising grayscale and color Doppler BUS images from March 2018 to November 2024. Three types of convolutional neural networks (CNNs), including ResNet50, ResNet18, and VGG16, were evaluated as single-modality (grayscale or color Doppler) models via five-fold cross-validations. The optimal model for each single-modality approach was chosen as the backbone network for multimodal deep learning. Features extracted from grayscale and color Doppler BUS images were then concatenated to predict the probabilities of benignity and malignancy. The diagnostic efficacy of the multi-modality BUS models was comparatively evaluated against single-modality counterparts. Results: The single-modality VGG16 models outperformed the other two CNN types for both grayscale and color Doppler BUS using five-fold cross-validations. Additionally, single-modality grayscale models outperformed single-modality color Doppler models. With a mean accuracy of 91.54%, sensitivity of 94.15%, specificity of 87.30%, F1 score of 0.93, and area under the receiver operating characteristic curve (AUC) of 0.96, the multimodal VGG16 models performed better than single-modality counterparts. Conclusions: VGG 16-based multimodal ultrasound deep learning showed excellent diagnostic efficacy in distinguishing between benign and malignant NMLs, indicating therapeutic potential to help radiologists assess NMLs. Full article

The rapid development of nanomedicine is driving extensive research and the synthesis of new nanomaterials. Biocompatible nanoparticles have the potential to serve as both imaging agents for medical diagnostics and carriers for targeted therapy. Among the various nanocomplexes investigated for cancer theranostics, gold nanoparticles stabilized by polyamidoamine (PAMAM) dendrimers have proven to be a promising platform. The unique physicochemical properties of gold nanoparticles, when combined with the branched architecture of PAMAM dendrimers, enhance stability, biocompatibility, and functionalization capability, enabling precise tumour targeting, improved imaging contrast, and controlled drug release. In this paper, we demonstrate the synthesis of gold nanoparticles stabilized by 2nd generation PAMAM dendrimers using three different methods: sonication, microwave, and unassisted techniques. The described synthesis approaches provide a rapid and straightforward method to achieve monodisperse particle size distribution and high colloidal stability up to 3 months. Physicochemical characterization of the nanocomplexes was carried out using ultraviolet-visible light spectroscopy, dynamic light scattering with zeta potential analysis, infrared spectroscopy, and atomic force microscopy. Furthermore, the effects of selected concentrations of PAMAM:HAuCl₄ nanoparticles for all types of synthesis on human breast adenocarcinoma and human osteosarcoma cell lines were investigated using cytotoxicity assays. The results of the conducted tests show cytotoxicity values at a similar level. However, the sample synthesized using the sonication technique exhibited the lowest toxicity. Full article