Breast cancer diagnosis from histopathology images is often time consuming and prone to human error, impacting treatment and prognosis. Deep learning diagnostic methods offer the potential for improved accuracy and efficiency in breast cancer detection and classification. However, they struggle with limited data and subtle variations within and between cancer types. Attention mechanisms provide feature refinement capabilities that have shown promise in overcoming such challenges. To this end, this paper proposes the Efficient Channel Spatial Attention Network (ECSAnet), an architecture built on EfficientNetV2 and augmented with a convolutional block attention module (CBAM) and additional fully connected layers. ECSAnet was fine-tuned using the BreakHis dataset, employing Reinhard stain normalization and image augmentation techniques to minimize overfitting and enhance generalizability. In testing, ECSAnet outperformed AlexNet, DenseNet121, EfficientNetV2-S, InceptionNetV3, ResNet50, and VGG16 in most settings, achieving accuracies of 94.2% at 40×, 92.96% at 100×, 88.41% at 200×, and 89.42% at 400× magnifications. The results highlight the effectiveness of CBAM in improving classification accuracy and the importance of stain normalization for generalizability.

Syringomatous tumor of the nipple is a benign, locally infiltrative tumor. There are reports in the literature of tumor recurrence in cases of incomplete excision. Clinical and mammographic findings in syringomatous tumors are like those of breast carcinoma and the pathologist has a fundamental role in final tumor diagnosis. Therefore, the aim of this study was to report a case of syringoma located in the areolar region. A 33-year-old woman reported that she had noticed a nodule in her left areolar region 4 years previously (February 2019). A breast ultrasound was performed, detecting intraparenchymatous breast cysts. Surgical resection of the nodule was indicated although it was not performed. Two years later, in August 2021, the patient underwent a mastopexy with prosthesis inclusion. Histopathology study of the surgical specimen revealed a syringomatous tumor with positive margins. Thirteen (13) months after diagnosis (September 3, 2021 - October 16, 2022), the patient is doing well and receives clinical follow-up.

UNASSIGNED: Phyllodes tumor is a rare fibroepithelial neoplasm of the breast, which is classified histologically as benign, borderline, or malignant. Accurate preoperative diagnosis allows the correct surgical planning and reoperation avoidance.
UNASSIGNED: To describe the clinical presentation and radiologic features of phyllodes tumors and differentiate between benign and non-benign (borderline and malignant) groups.
UNASSIGNED: A retrospective study of 57 patients with a diagnosis of phyllodes tumor who had preoperative imaging (mammography, ultrasound, or CT chest) and histological confirmation. The data was collected from 1 June 2011 to 30 September 2021. The imaging features of the phyllodes tumors were described according to the 5th edition of the ACR BI-RADS lexicon. For comparing between two groups, the student t-test, Wilcoxon rank sum test, Chi-square test, and Fisher\'s exact test were used for statistical analyses. The logistic regression analysis was calculated for non-benign phyllodes tumor prediction.
UNASSIGNED: From 57 patients, the pathologic results were benign for 43 cases and non-benign phyllodes tumors for 14 cases. There was no differentiation of mammographic and CT features between benign and non-benign groups. Non-benign phyllodes tumors had the statistical significance of menopausal status, entire breast involvement, tumor size larger than 10 cm, and heterogeneous echo on univariable analysis. After multivariable analysis, menopausal status (odd ratios=13.79, p=0.04) and presence of vessels in the rim (odd ratios=16.51, p=0.019) or absent vascularity (odd ratios=8.45, p=0.047) on doppler ultrasound were significantly increased possibility of non-benign phyllodes tumor.
UNASSIGNED: Menopausal status and presence of vessels in the rim or absent vascularity on Doppler ultrasound were important predictors for the diagnosis of non-benign phyllodes tumor.

The development of novel topoisomerase I (TOP1) inhibitors is crucial for overcoming the drawbacks and limitations of current TOP1 poisons. Here, we identified two potential TOP1 inhibitors, namely, FTY720 (a sphingosine 1-phosphate antagonist) and COH29 (a ribonucleotide reductase inhibitor), through experimental screening of known active compounds. Biological experiments verified that FTY720 and COH29 were nonintercalative TOP1 catalytic inhibitors that did not induce the formation of DNA-TOP1 covalent complexes. Molecular docking revealed that FTY720 and COH29 interacted favorably with TOP1. Molecular dynamics simulations revealed that FTY720 and COH29 could affect the catalytic domain of TOP1, thus resulting in altered DNA-binding cavity size. The alanine scanning and interaction entropy identified Arg536 as a hotspot residue. In addition, the bioinformatics analysis predicted that FTY720 and COH29 could be effective in treating malignant breast tumors. Biological experiments verified their antitumor activities using MCF-7 breast cancer cells. Their combinatory effects with TOP1 poisons were also investigated. Further, FTY720 and COH29 were found to cause less DNA damage compared with TOP1 poisons. The findings provide reliable lead compounds for the development of novel TOP1 catalytic inhibitors and offer new insights into the potential clinical applications of FTY720 and COH29 in targeting TOP1.

OBJECTIVE: In this study, we aimed to assess the new trends in characteristics, molecular subtypes, and imaging findings of breast cancer in very young women.
METHODS: We retrospectively reviewed the database of a primary breast cancer referral center in southern Iran in 342 cases of 30-year-old or younger women from 2001 to 2020. Pathologic data, including nuclear subtype and grade, tumor stage, presence of in situ cancer, imaging data including lesion type in mammogram and ultrasound, and treatment data were recorded. Descriptive statistics were applied. Differences between categorical values between groups were compared using Pearson\'s Chi-square test.
RESULTS: The mean age was 27.89 years. The tumor type was invasive ductal carcinoma in 82 % of cases. Fourteen patients (4.4 %) had only in situ cancer, and 170 patients had in situ components (49.7 %). Molecular subtypes were available in 278 patients, including 117 (42.1 %) Luminal A, 64 (23.0 %) Luminal B, 58 (20.9 %) triple negative, and 39 (14 %) HER2 Enriched. In those with mammograms available, 63 (30.1 %) had no findings, 53 (25.3 %) had mass, 27 (12.9 %) had asymmetry, whether focal or global, 21 (10 %) had microcalcifications solely, and 45 (21.5 %) had more than one finding. Microcalcifications were significantly more common in Luminal cancers than HER2 and triple-negative cancers (p = 0.041).
CONCLUSIONS: Our study shows the most common subtype to be Luminal A cancer, with 74 % of the tumors being larger than 2 cm at the time of diagnosis. Irregular masses with non-circumscribed margins were the most common imaging findings.

The lack of in vivo studies on the delivery of doxorubicin within human skin, especially the absence of data on the doxorubicin diffusion coefficient, has made understanding its transdermal delivery kinetics challenging. In this study, as a first step, governing equations and finite element methods were employed to reproduce Franz diffusion cell experiment in human cadaver skin. The application of this experiment representative model with a fitting method resulted in approximate values for the diffusivity of doxorubicin across various skin layers. The estimated values were used later to conduct a comprehensive examination of doxorubicin administration for breast tumor treatments. In a 2D axisymmetric model using Fick\'s Law and then a microneedles array 3D model, crucial parameters effects on delivery efficiency were examined, such as the microneedle tip diameter, tip-to-tip distance, and tumor depth. As highlighted by the findings of this study, these parameters have an impact on the effectiveness of doxorubicin delivery for treating breast tumors. The focus of this research is on the potential of numerical methods in biomedical engineering, which addresses the urgent need for data on doxorubicin diffusion in human skin and offers valuable insights into optimizing drug delivery strategies for enhanced therapeutic outcomes.

UNASSIGNED: The objective of this study was to develop a fully automatic mass segmentation method called AMS-U-Net for digital breast tomosynthesis (DBT), a popular breast cancer screening imaging modality. The aim was to address the challenges posed by the increasing number of slices in DBT, which leads to higher mass contouring workload and decreased treatment efficiency.
UNASSIGNED: The study used 50 slices from different DBT volumes for evaluation. The AMS-U-Net approach consisted of four stages: image pre-processing, AMS-U-Net training, image segmentation, and post-processing. The model performance was evaluated by calculating the true positive ratio (TPR), false positive ratio (FPR), F-score, intersection over union (IoU), and 95% Hausdorff distance (pixels) as they are appropriate for datasets with class imbalance.
UNASSIGNED: The model achieved 0.911, 0.003, 0.911, 0.900, 5.82 for TPR, FPR, F-score, IoU, and 95% Hausdorff distance, respectively.
UNASSIGNED: The AMS-U-Net model demonstrated impressive visual and quantitative results, achieving high accuracy in mass segmentation without the need for human interaction. This capability has the potential to significantly increase clinical efficiency and workflow in DBT for breast cancer screening.

OBJECTIVE: This systematic review aimed to summarize evidence for the feasibility and acceptability of psychosocial interventions for body image among women diagnosed with breast cancer and the study methods used to evaluate the interventions in question.
METHODS: Articles were identified via MEDLINE, CINAHL, CENTRAL, PsychINFO, and EMBASE. Inclusion criteria were: (1) peer-reviewed publication in English from 2000 onward with accessible full-text, (2) reported data on the feasibility and/or acceptability of psychosocial interventions and/or study methods, (3) included at least one measure of body image or reported a body-related theme, and (4) sample comprised women diagnosed with breast cancer. All study designs were eligible. Two reviewers independently performed study selection, data extraction, and quality assessment.
RESULTS: Sixty-two articles were included. Participants and comparator groups varied as did interventions. Feasibility and acceptability of the interventions and study methods were inconsistently operationalized and reported across studies. Evidence of feasibility and acceptability was heterogeneous within and across studies, though mostly positive.
CONCLUSIONS: Published psychosocial interventions for body image and study methods are generally feasible and acceptable. Findings should be used to advance the development, implementation, and evaluation of interventions designed to improve outcomes (body image or otherwise) for women diagnosed with breast cancer.
BACKGROUND: This review was registered with the International Prospective Register of Systematic Reviews (PROSPERO; ID: CRD42021269062, 11 September 2021).

BACKGROUND: Breast ultrasound (US) is useful for dense breasts, and the introduction of artificial intelligence (AI)-assisted diagnoses of breast US images should be considered. However, the implementation of AI-based technologies in clinical practice is problematic because of the costs of introducing such approaches to hospital information systems (HISs) and the security risk of connecting HIS to the Internet to access AI services. To solve these problems, we developed a system that applies AI to the analysis of breast US images captured using a smartphone.
METHODS: Training data were prepared using 115 images of benign lesions and 201 images of malignant lesions acquired at the Division of Breast Surgery, Gifu University Hospital. YOLOv3 (object detection models) was used to detect lesions on US images. A graphical user interface (GUI) was developed to predict an AI server. A smartphone application was also developed for capturing US images displayed on the HIS monitor with its camera and displaying the prediction results received from the AI server. The sensitivity and specificity of the prediction performed on the AI server and via the smartphone were calculated using 60 images spared from the training.
RESULTS: The established AI showed 100% sensitivity and 75% specificity for malignant lesions and took 0.2 s per prediction with the AI sever. Prediction using a smartphone required 2 s per prediction and showed 100% sensitivity and 97.5% specificity for malignant lesions.
CONCLUSIONS: Good-quality predictions were obtained using the AI server. Moreover, the quality of the prediction via the smartphone was slightly better than that on the AI server, which can be safely and inexpensively introduced into HISs.

OBJECTIVE: Artificial intelligence (AI) systems have been increasingly applied to breast ultrasonography. They are expected to decrease the workload of radiologists and to improve diagnostic accuracy. The aim of this study is to evaluate the performance of an AI system for the BI-RADS category assessment in breast masses detected on breast ultrasound. MATERIALS AND METHODS: A total of 715 masses detected in 530 patients were analyzed. Three breast imaging centers of the same institution and nine breast radiologists participated in this study. Ultrasound was performed by one radiologist who obtained two orthogonal views of each detected lesion. These images were retrospectively reviewed by a second radiologist blinded to the patient\'s clinical data. A commercial AI system evaluated images. The level of agreement between the AI system and the two radiologists and their diagnostic performance were calculated according to dichotomic BI-RADS category assessment.
RESULTS: This study included 715 breast masses. Of these, 134 (18.75%) were malignant, and 581 (81.25%) were benign. In discriminating benign and probably benign from suspicious lesions, the agreement between AI and the first and second radiologists was moderate statistically. The sensitivity and specificity of radiologist 1, radiologist 2, and AI were calculated as 98.51% and 80.72%, 97.76% and 75.56%, and 98.51% and 65.40%, respectively. For radiologist 1, the positive predictive value (PPV) was 54.10%, the negative predictive value (NPV) was 99.58%, and the accuracy was 84.06%. Radiologist 2 achieved a PPV of 47.99%, NPV of 99.32%, and accuracy of 79.72%. The AI system exhibited a PPV of 39.64%, NPV of 99.48%, and accuracy of 71.61%. Notably, none of the lesions categorized as BI-RADS 2 by AI were malignant, while 2 of the lesions classified as BI-RADS 3 by AI were subsequently confirmed as malignant. By considering AI-assigned BI-RADS 2 as safe, we could potentially avoid 11% (18 out of 163) of benign lesion biopsies and 46.2% (110 out of 238) of follow-ups.
CONCLUSIONS: AI proves effective in predicting malignancy. Integrating it into the clinical workflow has the potential to reduce unnecessary biopsies and short-term follow-ups, which, in turn, can contribute to sustainability in healthcare practices.