Search Results (799)

Background/Objectives: Patients with breast cancer who do not achieve a complete response to neoadjuvant chemotherapy (NAC) may benefit from intensified adjuvant systemic therapy. However, such treatment escalation is typically delayed until after tumour resection, which occurs several months into the treatment course. Quantitative ultrasound (QUS) can detect early microstructural changes in tumours and may enable timely identification of non-responders during NAC, allowing for earlier treatment intensification. In our previous prospective observational study, 100 breast cancer patients underwent QUS imaging before and four times during NAC. Machine learning algorithms based on QUS texture features acquired in the first week of treatment were developed and achieved 78% accuracy in predicting treatment response. In the current study, we aimed to validate these algorithms in an independent prospective cohort to assess reproducibility and confirm their clinical utility. Methods: We included breast cancer patients eligible for NAC per standard of care, with tumours larger than 1.5 cm. QUS imaging was acquired at baseline and during the first week of treatment. Tumour response was defined as a ≥30% reduction in target lesion size on the resection specimen compared to baseline imaging. Results: A total of 51 patients treated between 2018 and 2021 were included (median age 49 years; median tumour size 3.6 cm). Most were estrogen receptor–positive (65%) or HER2-positive (33%), and the majority received dose-dense AC-T (n = 34, 67%) or FEC-D (n = 15, 29%) chemotherapy, with or without trastuzumab. The support vector machine algorithm achieved an area under the curve of 0.71, with 86% accuracy, 91% specificity, 50% sensitivity, 93% negative predictive value, and 43% positive predictive value for predicting treatment response. Misclassifications were primarily associated with poorly defined tumours and difficulties in accurately identifying the region of interest. Conclusions: Our findings validate QUS-based machine learning models for early prediction of chemotherapy response and support their potential as non-invasive tools for treatment personalization and clinical trial development focused on early treatment intensification. Full article

Background/Objectives: Gastrin-releasing peptide receptor (GRPR) is overexpressed in breast cancer and might be used as a theranostics target. The expression of GRPR strongly correlates with estrogen receptor (ER) expression. Visualization of GRPR-expressing breast tumors might help to select the optimal treatment. Developing GRPR-specific probes for SPECT would permit imaging-guided therapy in regions with restricted access to PET facilities. In this first-in-human study, we evaluated the safety, biodistribution, and dosimetry of the [^99mTc]Tc-DB8 GRPR-antagonistic peptide. We also addressed the important issue of finding the optimal injected peptide mass. Methods: Fifteen female patients with ER-positive primary breast cancer were enrolled and divided into three cohorts receiving [^99mTc]Tc-DB8 (corresponding to three distinct doses of 40, 80, or 120 µg DB8) comprising five patients each. Additionally, four patients with ER-negative primary tumors were injected with 80 µg [^99mTc]Tc-DB8. The injected activity was 360 ± 70 MBq. Planar scintigraphy was performed after 2, 4, 6, and 24 h, and SPECT/CT scans followed planar imaging 2, 4, and 6 h after injection. Results: No adverse events were associated with [^99mTc]Tc-DB8 injections. The effective dose was 0.009–0.014 mSv/MBq. Primary tumors and all known lymph node metastases were visualized irrespective of injected peptide mass. The highest uptake in the ER-positive tumors was 2 h after injection of [^99mTc]Tc-DB8 at a 80 µg DB8 dose (SUV_max 5.3 ± 1.2). Injection of [^99mTc]Tc-DB8 with 80 µg DB8 provided significantly (p < 0.01) higher uptake in primary ER-positive breast cancer lesions than injection with 40 µg DB8 (SUV_max 2.0 ± 0.3) or 120 µg (SUV_max 3.2 ± 1.4). Tumor-to-contralateral breast ratio after injection of 80 μg was also significantly (p < 0.01, ANOVA test) higher than ratios after injection of other peptide masses. The uptake in ER-negative lesions was significantly lower (SUV_max 2.0 ± 0.3) than in ER-positive tumors. Conclusions: Imaging using [^99mTc]Tc-DB8 is safe, tolerable, and associated with low absorbed doses. The tumor uptake is dependent on the injected peptide mass. The injection of an optimal mass (80 µg) provides the highest uptake in ER-positive tumors. At optimal dosing, the uptake was significantly higher in ER-positive than in ER-negative lesions. Full article

Breast cancer continues to be one of the leading causes of women’s deaths around the world, and this has emphasized the necessity to have novel and interpretable diagnostic models. This work offers a clear learning deep learning model that integrates the mobility of MobileNet and two bio-driven optimization operators, the Firefly Algorithm (FLA) and Dingo Optimization Algorithm (DOA), in an effort to boost classification appreciation and the convergence of the model. The suggested model demonstrated excellent findings as the DOA-optimized MobileNet acquired the highest performance of 98.96 percent accuracy on the fusion test, and the FLA-optimized MobileNet scaled up to 98.06 percent and 95.44 percent accuracies on mammographic and ultrasound tests, respectively. Further to good quantitative results, Grad-CAM visualizations indeed showed clinically consistent localization of the lesions, which strengthened the interpretability and model diagnostic reliability of Grad-CAM. These results show that lightweight, compact CNNs can be used to do high-performance, multimodal breast cancer diagnosis. Full article

Purpose: This study aimed to develop a predictive nomogram integrating AI-based BI-RADS lexicons and lesion-to-nipple distance (LND) ultrasound features to differentiate mass-type ductal carcinoma in situ (DCIS) from invasive ductal carcinoma (IDC) visible on ultrasound. Methods: The final study cohort consisted of 170 women with 175 pathologically confirmed malignant breast lesions, including 26 cases of DCIS and 149 cases of IDC. LND and AI-based features from the S-Detect system (BI-RADS lexicons) were analyzed. Rare features were consolidated into broader categories to enhance model stability. Data were split into training (70%) and validation (30%) sets. Logistic regression identified key predictors for an LND nomogram. Model performance was evaluated using receiver operating characteristic (ROC) curves, 1000 bootstrap resamples, and calibration curves to assess discrimination and calibration. Results: Multivariate logistic regression identified smaller lesion size, irregular shape, LND ≤ 3 cm, and non-hypoechoic echogenicity as independent predictors of DCIS. These variables were integrated into the LND nomogram, which demonstrated strong discriminative performance (AUC = 0.851 training; AUC = 0.842 validation). Calibration was excellent, with non-significant Hosmer-Lemeshow tests (p = 0.127 training, p = 0.972 validation) and low mean absolute errors (MAE = 0.016 and 0.034, respectively), supporting the model’s accuracy and reliability. Conclusions: The AI-based comprehensive nomogram demonstrates strong reliability in distinguishing mass-type DCIS from IDC, offering a practical tool to enhance non-invasive breast cancer diagnosis and inform preoperative planning. Full article

Obesity and metabolic dysfunction are established risk factors for luminal breast cancer, yet current preclinical models inadequately recapitulate the complex metabolic and immune interactions driving tumorigenesis. To develop and characterize an immunocompetent rat model of luminal breast cancer induced by chronic exposure to a cafeteria diet mimicking Western obesogenic nutrition, female rats were fed a cafeteria diet or standard chow from weaning. Metabolic parameters, plasma biomarkers (including leptin, insulin, IGF-1, adiponectin, and estrone), mammary gland histology, tumor incidence, and gene expression profiles were longitudinally evaluated. Gene expression was assessed by PCR arrays and qPCR. A subgroup underwent dietary reversal to assess the reversibility of molecular alterations. Cafeteria diet induced significant obesity (mean weight 426.76 g vs. 263.09 g controls, p < 0.001) and increased leptin levels without altering insulin, IGF-1, or inflammatory markers. Histological analysis showed increased ductal ectasia and benign lesions, with earlier fibroadenoma and luminal carcinoma development in diet-fed rats. Tumors exhibited luminal phenotype, low Ki67, and elevated PAI-1 expression. Gene expression alterations were time point specific and revealed early downregulation of ID1 and COX2, followed by upregulation of MMP2, THBS1, TWIST1, and PAI-1. Short-term dietary reversal normalized several gene expression changes. Overall tumor incidence was modest (~12%), reflecting early tumor-promoting microenvironmental changes rather than aggressive carcinogenesis. This immunocompetent cafeteria diet rat model recapitulates key metabolic, histological, and molecular features of obesity-associated luminal breast cancer and offers a valuable platform for studying early tumorigenic mechanisms and prevention strategies without carcinogen-induced confounders. Full article

Background/Objectives: Erysipelas is an acute bacterial skin infection, particularly affecting the lower limbs, with a tendency to recur. Despite its clinical importance, data on demographic and epidemiological risk factors, as well as factors influencing hospitalization, remain limited. This study aimed to analyze the epidemiological and clinical characteristics of patients hospitalized with primary and recurrent erysipelas, focusing on risk factors contributing to disease onset, recurrence, and prolonged hospitalization. Methods: A retrospective single-center analysis was conducted on 239 patients hospitalized for erysipelas at the Department of Dermatology, Pediatric Dermatology, and Oncology at the Medical University of Lodz. Data collected included demographics, lesion location, laboratory markers, comorbidities, and hospitalization outcomes. Statistical analyses were performed to assess associations between risk factors, disease recurrence, and hospitalization duration. Results: The majority of erysipelas cases (85.4%) involved the lower limbs, with a higher prevalence in men. Upper extremities were mostly affected in women, especially those who had undergone breast cancer surgery. Recurrent erysipelas accounted for 75.7% of cases. Most patients (89.1%) had at least one comorbidity, with hypertension, diabetes type 2 (DM2), and obesity being the most common. Higher white blood cell (WBC) count, obesity, atrial fibrillation (AF), and the need for enoxaparin administration were independently associated with prolonged hospitalization. Dyslipidemia was significantly associated with erysipelas recurrence (p < 0.05). Conclusions: Both primary and recurrent erysipelas are associated with specific risk factors. Recurrent erysipelas may be linked to components of metabolic syndrome, particularly obesity and dyslipidemia, which emerged as a significant risk factor in this study. Hospitalization length may be prolonged by inflammation markers (WBC and CRP) and comorbidities such as AF, obesity, or the need for enoxaparin in patients with elevated thrombosis risk. Further multicenter studies with larger cohorts are needed to assess the impact of demographics, biomarkers, metabolic disorders, and treatment strategies on erysipelas recurrence and outcomes. Awareness of these risk factors is essential for effective prevention, management, and recurrence reduction. Full article

Accurate preoperative distinction between in situ and invasive Breast Cancer (BC) is critical for clinical decision-making and treatment planning. Radiomics and Machine Learning (ML) have shown promise in enhancing diagnostic performance from breast MRI, yet their application to this specific task remains underexplored. The aim of this study was to evaluate the performance of several ML classifiers, trained on radiomic features extracted from DCE–MRI and supported by basic clinical information, for the classification of in situ versus invasive BC lesions. In this study, we retrospectively analysed 71 post-contrast DCE–MRI scans (24 in situ, 47 invasive cases). Radiomic features were extracted from manually segmented tumour regions using the PyRadiomics library, and a limited set of basic clinical variables was also included. Several ML classifiers were evaluated in a Leave-One-Out Cross-Validation (LOOCV) scheme. Feature selection was performed using two different strategies: Minimum Redundancy Maximum Relevance (MRMR), mutual information. Axial 3D rotation was used for data augmentation. Support Vector Machine (SVM), K Nearest Neighbors (KNN), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) were the best-performing models, with an Area Under the Curve (AUC) ranging from 0.77 to 0.81. Notably, KNN achieved the best balance between sensitivity and specificity without the need for data augmentation. Our findings confirm that radiomic features extracted from DCE–MRI, combined with well-validated ML models, can effectively support the differentiation of in situ vs. invasive breast cancer. This approach is quite robust even in small datasets and may aid in improving preoperative planning. Further validation on larger cohorts and integration with additional imaging or clinical data are recommended. Full article

Breast cancer accounts for one in four new malignant tumors in women, and misdiagnosis can lead to severe consequences, including delayed treatment. Among patients classified with a BI-RADS 3 rating, the risk of very early-stage malignancy remains over 2%. However, due to the benign imaging characteristics of these lesions, radiologists often recommend follow-up rather than immediate biopsy, potentially missing critical early interventions. This study aims to develop a deep learning (DL) model to accurately identify very early-stage malignancies in BI-RADS 3 lesions using ultrasound (US) images, thereby improving diagnostic precision and clinical decision-making. A total of 852 lesions (256 malignant and 596 benign) from 685 patients who underwent biopsies or 3-year follow-up were collected by Southwest Hospital (SW) and Tangshan People’s Hospital (TS) to develop and validate a deep learning model based on a novel transfer learning method. To further evaluate the performance of the model, six radiologists independently reviewed the external testing set on a web-based rating platform. The proposed model achieved an area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of 0.880, 0.786, and 0.833 in predicting BI-RADS 3 malignant lesions in the internal testing set. The proposed transfer learning method improves the clinical AUC of predicting BI-RADS 3 malignancy from 0.721 to 0.880. In the external testing set, the model achieved AUC, sensitivity, and specificity of 0.910, 0.875, and 0.786 and outperformed the radiologists with an average AUC of 0.653 (p = 0.021). The DL model could detect very early-stage malignancy of BI-RADS 3 lesions in US images and had higher diagnostic capability compared with experienced radiologists. Full article

Rare presentations are surprising and may disturb the day-to-day routine of a medical unit; however, they are expected (not as individual entities, but as a group of “uncommon causes”). While reviewing the literature in relation to three clinical cases of upper gastrointestinal bleeding (UGIB) encountered in our institution—gastric metastases of breast cancer (GMB), pyloric gland adenoma, and gastrointestinal stromal tumor (GIST)—we identified seven and 29 case reports for the first two entities, and over 100 publications addressing GIST. This prompted a shift in focus from novel reporting to diagnostic contextualization. We found it difficult to obtain an overview of the spectrum of UGIB etiologies, as most publications refer to a few individual entities or to a subgroup of rare causes. The narrative review we conducted arose from this particular research methodology. Based on a broad literature search, UGIB etiologies were organized in five categories (lesions of the mucosa, neoplasms, vascular causes, bleeding predisposition, and external sources of bleeding). In the management of patients with UGIB, the underlying etiology deviates from the classic peptic ulcer disease/esophageal varices dyad in approximately half of the cases. This underscores the need for heightened clinical vigilance, particularly in complex scenarios, where endoscopic findings, imaging results, and histopathological interpretations may be unexpected or prone to misinterpretation. As an illustration, we conducted two systematic reviews of case reports of bleeding GMB and PGA. Our findings support a proactive diagnostic and research mindset and advocate for improved awareness of uncommon UGIB etiologies. Full article

Breast cancer is one of the most commonly diagnosed malignant tumours in women worldwide. Although modern medicine has led to advanced diagnostic methods and therapies that allow for increasingly effective treatment, the mechanisms underlying breast cancer development and progression remain the subject of intensive research. In the pathogenesis of this cancer, significant importance is attributed to interactions between tumour cells and the tumour microenvironment, in which soluble immune system mediators—cytokines—play a key role, including IL-21 and IL-22. These interleukins, by modulating the immune response, can both promote and inhibit tumour progression, and analysing their concentrations may prove helpful in diagnosis, disease progression prognosis, and the development of new therapies, including immunotherapy. The aim of this study was to determine the concentrations of IL-21 and IL-22 in a group of patients with invasive cancer, depending on the biological type of the tumour and its malignancy grade. The study involved 60 women with breast cancer and 20 women with benign breast lesions, and the analysis of IL-21 and IL-22 protein concentrations was performed using the enzyme-linked immunosorbent assay (ELISA) method. The analysis shows that the concentrations of IL-21 and IL-22 do not differ significantly depending on the malignancy grade of the tumour. However, a statistically significant negative correlation between the concentrations of IL-21 and IL-22 was observed exclusively in the group of patients with benign breast lesions. Due to the high heterogeneity of breast cancers, further research with a larger study group is necessary to better understand these parameters and possibly apply them clinically in patients with breast cancer. Full article

Background and Objectives: The accuracy of breast cancer diagnosis depends on the concordance between imaging features and pathological findings. While BI-RADS (Breast Imaging Reporting and Data System) provides standardized risk stratification, its correlation with histologic grade and immunohistochemical markers remains underexplored. This study assessed the diagnostic performance of BI-RADS 3, 4, and 5 classifications and their association with tumor grade and markers such as ER, PR, HER2, and Ki-67. Materials and Methods: In this prospective study, 67 women aged 33–82 years (mean 56.4) underwent both mammography and ultrasound. All lesions were biopsied using ultrasound-guided 14G core needles. Imaging characteristics (e.g., margins, echogenicity, calcifications), histopathological subtype, and immunohistochemical data were collected. Statistical methods included logistic regression, Chi-square tests, and Spearman’s correlation to assess associations between BI-RADS, histology, and immunohistochemical markers. Results: BI-RADS 5 lesions showed a 91% malignancy rate. Evaluated features included spiculated margins, pleomorphic microcalcifications, and hypoechoic masses with posterior shadowing, and were correlated with histological and immunohistochemical results. Invasive tumors typically appeared as irregular, hypoechoic masses with posterior shadowing, while mucinous carcinomas mimicked benign features. Higher BI-RADS scores correlated significantly with increased Ki-67 index (ρ = 0.76, p < 0.001). Logistic regression yielded an AUC of 0.877, with 93.8% sensitivity and 80.0% specificity. Conclusions: BI-RADS scoring effectively predicts malignancy and correlates with tumor proliferative markers. Integrating imaging, histopathology, and molecular profiling enhances diagnostic precision and supports risk-adapted clinical management in breast oncology. 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: A breast hamartoma or fibroadenolipoma is a rare, benign mass consisting of disorganized mature breast tissue elements. Surgical excision is recommended if the lesion exhibits rapid progressive growth. However, incomplete excision may result in recurrence. The objective of this study is to provide comprehensive insights into the characteristics of breast hamartomas and to conduct a thorough investigation into their clinical presentation, diagnostic procedures, and management strategies. Methods: We report on 13 cases of breast hamartomas treated surgically between January 2018 and June 2023 at the Obstetrics and Gynecology Hospital “Cuza Vodă” in Iași. We analyzed their histological images and immunohistochemical evaluations. Results: The mean age of the patients was 33.35 years, ranging from 22 to 57 years. Clinically, all patients presented with a painless mass. The diagnosis was confirmed through ultrasound examination, which revealed that hamartomas appeared as well-circumscribed, oval, and heterogeneous in echotexture. The tumor sizes ranged from 1 to 17 cm, with an average size of 6.75 cm. Surgical treatment involved lumpectomy with the excision of a small portion of normal tissue surrounding the tumor. The histological variability of these tumors poses diagnostic challenges for pathologists, potentially leading to underdiagnosis. Conclusions: Most hamartomas exhibit characteristic features on ultrasound attributable to their fibrous, glandular, and adipose tissue composition. Accurate identification of hamartomas is crucial due to the potential for recurrence. Notably, none of the women in our study experienced recurrence during the follow-up period. Full article

This meta-analysis evaluated the diagnostic accuracy of sonoelastography for distinguishing benign and malignant breast lesions, comparing strain elastography and shear wave elastography (SWE). We systematically reviewed 825 publications, selecting 30 studies (6200 lesions: 45% benign, 55% malignant). The pooled sensitivity and specificity for overall sonoelastography were 88% (95% CI: 85–91%) and 84% (95% CI: 81–87%), respectively. Strain elastography showed sensitivity and specificity of 85% and 80%, respectively, while SWE demonstrated superior performance with 90% sensitivity, 86% specificity, and an AUC of 0.92. Moderate heterogeneity (I² = 55%) was attributed to study variation. SWE showed the potential to reduce unnecessary biopsies by 30–40% by increasing specificity. AI-assisted image analysis and standardized protocols may enhance accuracy and reduce variability. These findings support the integration of SWE into breast imaging protocols. Full article

Background/Objectives: Assessment of a novel deep-learning (DL)-based T1w volumetric interpolated breath-hold (VIBE_DL) sequence in breast MRI in comparison with standard VIBE (VIBE_Std) for image quality evaluation. Methods: Prospective study of 52 breast cancer patients examined at 1.5T breast MRI with T1w VIBE_Std and T1 VIBE_DL sequence. T1w VIBE_DL was integrated as an additional early non-contrast and a delayed post-contrast scan. Two radiologists independently scored T1w VIBE _Std/DL sequences both pre- and post-contrast and their calculated subtractions (SUBs) for image quality, sharpness, (motion)–artifacts, perceived signal-to-noise and diagnostic confidence with a Likert-scale from 1: Non-diagnostic to 5: Excellent. Lesion diameter was evaluated on the SUB for T1w VIBE_Std/_DL. All lesions were visually evaluated in T1w VIBE_Std/_DL pre- and post-contrast and their subtractions. Statistics included correlation analyses and paired t-tests. Results: Significantly higher Likert scale values were detected in the pre-contrast T1w VIBE_DL compared to the T1w VIBE_Std for image quality (each p < 0.001), image sharpness (p < 0.001), SNR (p < 0.001), and diagnostic confidence (p < 0.010). Significantly higher values for image quality (p < 0.001 in each case), image sharpness (p < 0.001), SNR (p < 0.001), and artifacts (p < 0.001) were detected in the post-contrast T1w VIBE_DL and in the SUB. SUB_DL provided superior diagnostic certainty compared to SUB_Std in one reader (p = 0.083 or p = 0.004). Conclusions: Deep learning-enhanced T1w VIBE_DL at 1.5T breast MRI offers superior image quality compared to T1w VIBE_Std. Full article