Diagnosis Of Breast Cancer Research Articles

Enhancing Breast Cancer Collagen Segmentation with Improved Swim Transformation Algorithm

The precise segmentation of collagen fibres in breast tissue is essential for an efficient diagnostic and treatment strategy because breast cancer is still a major worldwide health concern. By better separating fibers from the background, the Swim Transformation (SWT) algorithm has demonstrated potential to improve collagen fiber segmentation. Unfortunately, the resilience and accuracy of the original SWT method are limited because to its susceptibility to noise and distortions. This work suggests an updated version of the SWT algorithm that includes multiple improvements to maximize collagen segmentation in breast cancer tissues, thereby addressing these constraints. The novel method improves the detection of collagen fibers by introducing a noise reduction pre-processing step and adaptive thresholding. It also incorporates an extra post-processing phase to eliminate segmentation mistakes and improve the overall outcomes. Using a dataset of microscopic pictures of breast cancer tissue, the suggested method's effectiveness was assessed and contrasted with that of the original SWT algorithm and other cutting-edge segmentation techniques. The enhanced SWT algorithm achieves greater segmentation accuracy, sensitivity, and precision, according to experimental data. In addition, the study expands on previous research by using a deep learning framework that classifies breast cancer cells based on segmented collagen properties. This framework uses Long Short-Term Memory (LSTM) and Bidirectional LSTM models. The promise of deep learning for automated cancer detection was demonstrated when the model was trained on segmented collagen pictures to identify the presence of malignant cells. The suggested method provides a notable enhancement in the segmentation of collagen, yielding more dependable outcomes that aid medical professionals in diagnosing breast cancer and developing treatment plans.

Digital breast tomosynthesis for early detection of malignant breast microcalcification: A hospital-based cross-sectional study

Background: Breast cancer is the leading cause of cancer-related deaths in women. Early detection by screening is crucial for improved survival. Digital breast tomosynthesis (DBT) may offer better visibility than conventional screening. This study aims to assess the diagnostic accuracy of DBT in detecting malignant breast microcalcifications compared to histopathological findings. Methods: This cross-sectional study was done at the Department of Radiology and Imaging, Bangabandhu Sheikh Mujib Medical University, Dhaka, from July 2022 to June 2023 and enrolled 35 women suspected of having breast cancer. Each patient underwent DBT and histopathology tests. The diagnostic accuracy of DBT in detecting malignant breast microcalcifications was assessed compared to the gold standard of histopathology. Results: The average age of the participants was 48.6 years. Palpable breast lumps (91.4%) were the most common clinical presentation. Among them, 80% had malignant microcalcifications diagnosed by DBT, primarily with linear (40.0%) and segmental (28.6%) distribution. Histopathology identified 80% of cases as malignant, with ductal carcinoma in situ (34.3%) being the most prevalent type. DBT demonstrated high sensitivity (100%) and specificity (85.7%) in detecting malignant microcalcifications, resulting in an overall accuracy of 97.1%. Conclusions: DBT has high diagnostic accuracy for detecting malignant breast microcalcifications and can be considered a valid tool for the early detection of breast microcalcifications, particularly in the context of diagnosing breast cancer.

6931 Weight Trends and Predictors of Weight Gain in Breast Cancer Survivors

Abstract Disclosure: M.D. Hurtado: None. E. Tama: None. D. Hodge: None. A. Weston: None. S. Fahad: None. K. Ruddy: None. J. Olson: None. F. Coach: None. R. Carter: None. S. D'Andre: None. A. Acosta: Consulting Fee; Self; Amgen Inc. Grant Recipient; Self; Vivus USA, Novo Nordisk. C. Shufelt: None. Background: Breast cancer (BC) is the most common cancer in women. Weight gain after treatment for early-stage BC is associated with a higher risk of recurrence. Excess adiposity is also a major risk factor for cardiovascular disease, the leading cause of non-BC related death in BC survivors. This study aimed to describe weight trends in a large cohort of BC survivors and to identify predictors of weight gain after BC diagnosis. Methods: This was a retrospective study of BC survivors from the prospectively consented Mayo Clinic Breast Cancer Registry, which has enrolled >10,000 patients seen at least once at Mayo Clinic Rochester for a BC diagnosed within the prior year. We extracted data on weights at baseline, and years 1, 4, and 6 after BC diagnosis to generate longitudinal weight trajectory curves on the change from baseline. Weights were either reported by patients in the registry questionnaires or extracted from the electronic health records. We identified BC survivors with weight gain >10% from baseline weight at years 1, 4, and 6. We then conducted univariable logistic regression analyses to identify predictors of >10% weight gain. Variables considered included: demographics, anthropometrics, BC clinical and pathologic characteristics, BRCA 1 and 2 genetic mutation status, and treatment (surgery, neoadjuvant or adjuvant chemotherapy, and/or radiotherapy). Results: We included 4744 BC survivors, mostly white (95%) and non-Hispanic (91%), with a mean age and weight at BC diagnosis of 58 ± 13 years and 76 ± 18 kg. Most patients had clinical stage I (43%) and ER+ and PR+ BC (83% and 76%, respectively). Most patients underwent breast preserving surgery (62%), half received radiation (54%), one third (36%) received systemic chemotherapy, and two thirds (61%) received endocrine therapy. At one year after BC diagnosis the average weight change was negligible compared to baseline (mean difference -0.2 ± 8 kg), but there were small but significant average increases by years 4 and 6 (0.5 ± 9 kg, p=0.002; and 0.8 ± 10 kg, p<0.001; respectively). At years 1, 4, and 6, the percentage of BC survivors gaining >10% of their baseline weight was 10%, 15%, and 18%, respectively. Baseline characteristics associated with >10% weight gain at 6 years included lower baseline weight (p<0.001), younger age at BC diagnosis (p<0.001), more advanced clinical and pathologic BC stage (p=0.008), ER+ and PR+ tumor biology (p=0.02 for both), BRCA2 mutation (p<0.001), mastectomy (compared to breast preserving surgeries, p=0.008), the use of systemic chemotherapy treatment (p<0.001), and the use of endocrine therapy (p=0.03). Conclusion: While most BC survivors do not experience weight gain after survivorship, 1 out 5 may experience excessive weight gain of more than 10%. Baseline anthropometric and BC-related variables are associated with excessive weight gain and could be used as predictors of weight gain in this population. Presentation: 6/3/2024

6550 National Statin Prescription Trends in Patients With Breast Cancer and Diabetes for Primary Cardiovascular Disease Prevention

Abstract Disclosure: A.B. Yang: None. G. Mhango: None. C. Kong: None. J.J. Lin: None. J.P. Wisnivesky: Consulting Fee; Self; Sanofi, Banook, PPD. Grant Recipient; Self; Sanofi, Regeneron Pharmaceuticals, Axella, Arnold Consultants. A. Leiter: None. Background: Cardiovascular disease (CVD) is the leading cause of death in older early-stage breast cancer (BC) survivors. Due to cardiotoxic BC treatments such as chemotherapy and radiation, patients with BC and diabetes (DM) are at increased risk of CVD. In patients with BC and DM, statins decrease CVD mortality. Since 2013, many clinical guidelines broadened statin indications for primary CVD prevention in patients with DM, making >85% of patients eligible. Little is known about statin prescription (Rx) patterns in older BC survivors with DM, a group at high risk of CVD. Hypothesis: We hypothesized that statin Rxs increased over time, but were less likely in BC survivors with more advanced locoregional BC and lower comorbidity burden. Methods: A population-based, retrospective cohort study was conducted using Surveillance, Epidemiology and End Results (SEER) cancer registry data linked to Medicare claims. We identified women with preexisting DM who were diagnosed with stage 0-III primary BC between 2008-17. We excluded patients with prior CVD who died <1 year after BC diagnosis. Statin Rx (atorvastatin, pravastatin, rosuvastatin, simvastatin, fluvastatin, lovastatin) was defined as ≥1 statin pharmacy claim <1 year after BC diagnosis. Comorbidity burden was assessed with a modified Charlson Comorbidity Index (CCI). We compared patient demographic and clinical characteristics by statin Rx status using the chi-square test. Using a multivariate logistic regression adjusting for age, race, CCI, BC stage, and diagnosis year, independent predictors of statin Rx were identified. Results: Of 8,423 BC patients with pre-existing DM, 5,698 (68%) had a statin Rx. Statin Rx increased over time (BC diagnosis year 2008-10: 66%, 2011-13: 66%, 2014-15: 69%, 2016-17: 70%; p=0.01) and differed by age (66-69: 66%, 70-74: 70%, 75-79: 69%, ≥80: 65%; p<0.01) and race (White: 68%, Black: 62%, Latinx: 66%, Other: 72%; p<0.01). Statin Rx did not differ by comorbidity burden (CCI 0: 68%, 1-2: 67%, ≥3: 67%; p=0.87) and declined with higher BC stage (0: 73%, I: 70%, II: 65%, III: 63%; p<0.01). In adjusted analyses, more recent BC diagnosis (2016-17 vs. 2008-10: odds ratio [OR]: 1.19, 95% confidence interval [CI]: 1.04-1.38), age group (70-74 vs. 66-69: OR: 1.24, 95% CI: 1.09-1.41), race (Black vs. White: OR 0.77, 95% CI: 0.66-0.89) and higher BC stages (II vs. 0: OR: 0.76, 95% CI: 0.58-1.00; III vs. 0: OR: 0.72, 95% CI: 0.54-0.97) remained predictors of statin Rx. Conclusions: In a nationally representative cohort analysis of older early-stage BC patients, statin Rx increased between 2008-17 and varied by age, race, and BC stage. Elucidating gaps in statin Rx can potentially improve guideline-concordant Rx in a group at high risk for CVD and reduce disparities. Presentation: 6/2/2024

Race and ethnicity and self-reported racial/ethnic discrimination in breast cancer patient interactions with providers in the Pathways Study.

To examine the association of race and ethnicity groups with self-reported racial/ethnic discrimination in patient-provider interactions during the diagnosis and treatment for breast cancer. We analyzed data from the Pathways Study, a prospective cohort of women diagnosed with breast cancer from 2006-2013 in the Kaiser Permanente Northern California Health Care System. Racial/ethnic discrimination in patient-provider interactions was assessed with two questions from the Interpersonal Processes of Care survey at baseline and 6-months and 24-months post-diagnosis. Logistic regression was performed to compare women who self-identified as racial or ethnic minorities with Non-Hispanic White (NHW) women. Covariates included age at diagnosis, country of origin, education level, income, marital status, and medical provider's race/ethnicity. Our sample included 1836 participants: 1350 NHW women and 486 women (87 Black, 208 Asian American, 153 Hispanic, 38 American Indian/Alaskan Native/Pacific Islander [AIANPI]) from racial or ethnic minority groups. In multivariate analysis, minority women were more likely to report racial/ethnic discrimination in patient-provider interactions than NHW women (adjusted odds ratio [aOR]: 4.73; 95% confidence interval [CI] 3.45-6.50). Specifically, Black women were most likely to self-report racial/ethnic discrimination in patient-provider interactions (aOR: 9.65; 95% CI 5.92-15.70), followed by Asian (aOR: 5.39; 95% CI 3.46-8.40), Hispanic (aOR: 2.55; 95% CI 1.54-4.14), and AIANPI (aOR: 1.74; 95% CI 0.58-4.25) women, compared with NHW women. Racial/ethnic discrimination was more likely self-reported from minority women diagnosed with breast cancer. Additional studies are needed to understand the mechanisms and impact of racial/ethnic discrimination in patient-provider interactions on disparities.

Ensemble approach of deep learning models for binary and multiclass classification of histopathological images for breast cancer

Breast cancer (BC) is the most frequently occurring cancer disease observed in women after lung cancer. Out of different stages, invasive ductal BC causes maximum deaths in women. In this work, three deep learning (DL) models such as Vision Transformer (ViT), Convmixer, and Visual Geometry Group-19 (VGG-19) are implemented for the detection and classification of different breast cancer tumors with the help of Breast cancer histopathological (Break His) image database. The performance of each model is evaluated using an 80:20 training scheme and measured in terms of accuracy, precision, recall, loss, F1-score, and area under the curve (AUC). From the simulation result, ViT showed the best performance for binary classification of breast cancer tumors with accuracy, precision, recall, and F1-score of 99.89 %, 98.29 %, 98.29 %, and 98.29 %, respectively. Also, ViT showed the best performance in terms of accuracy (98.21 %), average Precision (89.84 %), recall (89.97 %), and F1-score (88.75) for eight class classifications. Moreover, we have also ensemble the ViT-Convmixer model and observed that the performance of the ensemble model is reduced as compared to the ViT model. We have also compared the performance of the proposed best model with other existing models reported by several research groups. The study will help find suitable models that will increase accuracy in early diagnoses of BC. We hope the study will also help to minimize human errors in the early diagnosis of this fatal disease and administer appropriate treatment. The proposed model may also be implemented for the detection of other diseases with improved accuracy.

7326 Breast and Ovarian Cancer are Increased in Women with Primary Ovarian Insufficiency and Early Menopause and Cancer is Increased in Family Members

Abstract Disclosure: K.L. Allen-Brady: None. L. Verrilli: None. M. Alvord: None. M. Kern: None. N. Camp: None. K. Kelley: Consulting Fee; Self; Immunogen. J. Letourneau: None. L. Cannon-Albright: None. E.B. Johnstone: Stock Owner; Self; Abbott Laboratories, Abbvie. C.K. Welt: None. Introduction: Next generation sequencing in women with primary ovarian insufficiency (POI) identified deleterious variants in DNA damage repair and transcription fidelity genes. Based on underlying genetics, we hypothesized that a subset of women with POI may also be predisposed to reproductive or hormonally influenced cancers and that family members may be at risk. Methods: Women with POI (≤40 years) and early menopause >40 and <45 years) were identified using ICD9 and 10 codes in electronic medical records (1995-2021) from two major healthcare systems in Utah and reviewed for accuracy. Women with POI and their relatives were linked to genealogy information using the Utah Population Database (UPDB) and to cancer diagnoses (breast, ovarian, endometrial, colon, testicular and prostate) using the Utah Cancer Registry. The relative risk (RR) of cancer in women with POI and in relatives was estimated by comparison to population rates matched by age, sex, and birthplace. We also identified POI pedigrees with an excess number of observed cancer cases compared to the expected number in population controls. Results: We identified 613 women with POI and 165 women with early menopause. Of these, 416 women with POI had at least three generations of genealogical data with 2,405 first-degree relatives, 6,798 second-degree relatives and 17,666 third-degree relatives. Breast cancer was significantly increased in women with POI (OR [95%CI] 1.89 [1.20, 2.84]; p=0.0056) and there was a borderline increase in ovarian cancer. Probands were 36.5±4.3 years when diagnosed with POI and 59.5±12.7 years (range 43-80 years) at the time of breast cancer diagnosis and only 2 women took hormone replacement therapy after age 50 years. When women with early menopause were added, breast cancer risk remained increased and ovarian cancer was also nominally significant (3.38 [1.15, 8.65]; p=0.032). There was no increased risk of endometrial cancer and there were no cases of colon cancer. Among second-degree relatives of women with POI and 3 generations of family members, there was a significantly increased risk of breast (1.28 [1.08, 1.71]; p=0.0078) and colon cancer (1.50 [1.14, 1.94]; p=0.0036). Prostate cancer was increased in first- (1.64 [1.18, 2.23]; p=0.0026), second- (1.54 [1.32, 1.79]; p<0.001), and third-degree relatives (1.33 [1.20, 1.48]; p<0.001). There were 27 POI pedigrees that were high risk for these reproductive or hormonally influenced cancer diagnoses. Conclusions: Our data suggest common risk factors for POI and reproductive or hormonally influenced cancers. Therefore, clinicians need tools to predict cancer risk and comorbid disease in women with POI and early menopause to adequately counsel about future health risk. This understanding may change recommendations for hormone replacement based on the underlying genetic cause of POI for an individual. Presentation: 6/3/2024

A comparative performance assessment of artificial intelligence based classifiers and optimized feature reduction technique for breast cancer diagnosis

Breast cancer (BC) is a catastrophic global health concern that causes numerous fatalities worldwide. Early detection of breast cancer may mitigate death rates; however, the prevailing diagnostic procedure for the malignancy necessitates numerous multifaceted laboratory tests that must be performed by medical professionals. In this article machine learning, a branch of Artificial Intelligence (AI), has been employed to improve cancer diagnosis, prognoses and survival rates while reducing the vulnerability of humans. Support Vector Machine (SVM), K-nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF) and Grey Wolf Optimizer (GWO) are implemented to prognosticate breast cancer. Comprehensive insights into the efficacy of these approaches for breast cancer prognosis are provided by the performance assessment that is accomplished using the confusion matrix, Receiver Operating Characteristic (ROC) curves and parallel coordinate plots. Both UCI (University of California Irvine) and SEER (Surveillance, Epidemiology and End Results) datasets have been utilized to confirm the investigation's findings and ensure their generalizability across diverse data sources. The results conclusively demonstrate that SVM is the cohort's most accurate classifier. With a stupendous accuracy rate of 99.1 %, the GWO-SVM compares favorably to all other algorithms. Furthermore, feature reduction approaches such as Minimum Redundancy Maximum Relevance (mRMR), ReliefF and Principal Component Analysis (PCA) are utilized. ReliefF has demonstrated exceptional effectiveness with a maximum accuracy of 98.2 %.

Applications of AI (Artificial Intelligence) In Diagnosis of Breast Cancer

Breast cancer is a leading cause of cancer-related deaths worldwide. Early detection and accurate diagnosis are crucial for improving patient outcomes. Artificial intelligence (AI) has emerged as a promising tool in the fight against breast cancer. This research report explores the potential applications of AI in various stages of breast cancer management, including early detection, diagnosis, treatment planning, and prognosis prediction. AI algorithms can analyze mammograms and other imaging data to identify suspicious lesions with greater accuracy than traditional methods. Additionally, AI-powered tools can assist in the classification of breast tumors, helping to determine the most appropriate course of treatment. Furthermore, AI can be used to predict the likelihood of recurrence and metastasis, enabling personalized monitoring and follow-up care. This research report presents a comprehensive review of the current state of AI in breast cancer research and highlights the potential benefits and challenges associated with its implementation. By leveraging the power of AI, healthcare providers can improve breast cancer outcomes and enhance the quality of life for patients.

Xpert Breast Cancer STRAT4 Assay using fine-needle aspiration biopsy samples in a resource-constrained setting: a prospective diagnostic accuracy study

Use of fine-needle aspiration biopsy (FNAB) specimens on Xpert Breast Cancer STRAT4 Assay (STRAT4; Cepheid, Sunnyvale, CA, USA), a CE-marked in-vitro diagnostic medical device, could potentially increase access to breast cancer biomarker testing in resource-constrained settings. We aimed to assess the performance of a research use-only version of STRAT4 using FNAB specimens in Tanzania. In this prospective diagnostic accuracy study, patients aged 18 years or older with palpable breast masses presenting to the FNAB Clinic at Muhimbili National Hospital (Dar es Salaam, Tanzania) were recruited consecutively. Patients who were pregnant, lactating, or had a previous diagnosis of breast cancer were excluded. STRAT4 testing was performed on off-label FNAB samples using four protocols: the 1 × protocol (using the standard lysate method) on FNAB smears (1 × FNAB), quick lysis and Maui protocols (both on FNAB smears), and the 1 × protocol on formalin-fixed paraffin-embedded (FFPE) cell block material (1 × cell block). For 1 × FNAB and 1 × cell block, tissue was processed using FFPE lysis reagent, incubated at 80°C with proteinase K, and followed by addition of 95% or higher ethanol. Quick lysis was processed using FFPE lysis reagent and 95% or higher ethanol, whereas Maui was processed using a proprietary research-use only lysis reagent. The primary outcomes were overall concordance, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of STRAT4 as compared with immunohistochemistry or immunohistochemistry plus fluorescence in-situ hybridisation performed on cell blocks using clinically validated protocols in a Clinical Laboratory Improvement Amendments-accredited laboratory at the University of California, San Francisco (San Francisco, CA, USA). Between Nov 29, 2017, and Dec 17, 2020, 208 patients were enrolled. Of 208 cases, 51 (25%) were excluded from analysis because of insufficient tissue in the cell block or absent cell blocks, leaving 157 participants (all female) for analysis. For oestrogen receptor, 1 × FNAB had the best performance, with an overall concordance of 95% (95% CI 90-100), sensitivity of 94% (85-100), specificity of 97% (90-100), and AUC of 0·96 (0·81-1·00). For progesterone receptor, 1 × cell block had the best overall performance (overall concordance 89% [95% CI 84-95], sensitivity 91% [82-99], and specificity 89% [81-97], with an AUC of 0·93 [0·89-0·99]) and 1 × FNAB performed the best among the smear protocols, with a concordance of 84% (95% CI 74-93), sensitivity of 63% (43-82), specificity of 97% (92-100), and AUC of 0·91 (0·72-0·97). For HER2, Maui had the highest agreement, with an overall concordance of 93% (95% CI 89-98), sensitivity of 96% (88-100), specificity of 92% (87-98), and AUC of 0·95 (0·98-1·00). For Ki67, Maui had the best performance of smear protocols, with a concordance of 73% (95% CI 64-82), sensitivity of 70% (58-81), specificity of 81% (66-96), and AUC of 0·80 (0·54-0·82). Processing FNAB samples with STRAT4 is feasible in Tanzania, and performance for the oestrogen receptor is robust. Further optimisation of STRAT4 for FNAB has the potential to improve timely access to breast cancer diagnostics in resource-constrained settings. US National Institutes of Health; UCSF Global Cancer Program, Helen Diller Family Comprehensive Cancer Center; UCSF Department of Pathology; and Cepheid.

A study on breast cancer image classification based on particle swarm algorithm and transfer learning

Breast cancer is a major disease that poses a serious threat to the lives and health of women. A new framework was proposed to address the common challenges of high dimensional and data imbalances in image classification. This framework integrates particle swarm optimization (PSO) and transfer learning into a convolutional neural network model based on the ResNet34 architecture. The respective strengths complement each other to enhance the performance and efficiency of the classification model. Through parameter optimization and functional selection of PSO, the global search of the model has been improved. Transfer learning lets the model use large pre-trained datasets to learn more quickly on small sample datasets, which is especially helpful in areas where there are a lot of images that don’t have labels. Experimental findings reveal that our framework attains a 97.83% accuracy rate on the dataset and notably shortens the training cycle, demonstrating its effectiveness in improving breast cancer diagnosis performance with small sample sizes.

Study on Bionic Design and Tissue Manipulation of Breast Interventional Robot.

Minimally invasive interventional surgery is commonly used for diagnosing and treating breast cancer, but the high fluidity and deformability of breast tissue reduce intervention accuracy. This study proposes a bionic breast interventional robot that mimics the scorpion's predation process, actively manipulating tissue deformation to control target displacement and enhance accuracy. The robot's structure is designed using a modular method, and its kinematics and workspace are analyzed and solved. To address the nonlinear breast tissue deformation problem, a hierarchical tissue method is proposed to simplify the three-dimensional problem into a two-dimensional one. A two-dimensional tissue deformation solver is established based on the minimum energy method for quick resolution. The problem is treated as quasi-static, deriving the displacement relationship between external manipulation points and internal tissue targets. The method of active manipulation of tissue deformation is simulated using MATLAB (2019-b) software to verify the feasibility of the method. Results show maximum errors of 1.7 mm for prostheses and 2.5 mm for in vitro tissues in the X and Y directions. This method improves intervention accuracy in breast surgery and offers a new solution for breast cancer diagnosis and treatment.

Development of a novel prediction model for carriage of BRCA1/2 pathogenic variant in Japanese patients with breast cancer based on Japanese organization of hereditary breast and ovarian cancer registry data.

With the increasing demand for BRCA genetic testing, most existing prediction models were developed using data from individuals of European descent. This study aimed to identify clinicopathological factors of hereditary breast and ovarian cancer (HBOC) syndrome and develop the first Japanese-specific prediction model for BRCA pathogenic variant carriers in Japan. We utilized data from 3072 Japanese patients with breast cancer aggregated by the Japanese Organization of Hereditary Breast and Ovarian Cancer registry. Prediction models were developed using 70% of the overall dataset and validated using the remaining 30%. Factors associated with the BRCA pathogenic variant status were identified using logistic univariate analysis, and significant factors were further analyzed using logistic multivariate analysis to develop prediction models for BRCA1/2 (BRCA1 and/or BRCA2), BRCA1, and BRCA2 pathogenic variants. BRCA1 showed associations with aggressive clinicopathological factors such as triple-negative breast cancer and nuclear grade 3. Moreover, the prediction model showed a high area under the curve (AUC) of 0.879. By contrast, BRCA2 exhibited fewer characteristic associated factors, and the AUC of the model was 0.669. Common factors shared by BRCA1/2, BRCA1, and BRCA2 were the age at diagnosis of breast cancer and the youngest age of relatives with breast cancer. Consistent with previous research, early-onset breast cancer appeared to be strongly associated with HBOC. We successfully developed prediction models for BRCA1/2, BRCA1, and BRCA2 pathogenic variants. By accurately stratifying patients' risk and guiding targeted screening and preventative interventions, these models will contribute to improved management and outcomes of HBOC.

A Lightweight Method for Breast Cancer Detection Using Thermography Images with Optimized CNN Feature and Efficient Classification.

Breast cancer is a prominent cause of death among women worldwide. Infrared thermography, due to its cost-effectiveness and non-ionizing radiation, has emerged as a promising tool for early breast cancer diagnosis. This article presents a hybrid model approach for breast cancer detection using thermography images, designed to process and classify these images into healthy or cancerous categories, thus supporting disease diagnosis. Multiple pre-trained convolutional neural networks are employed for image feature extraction, and feature filter methods are proposed for feature selection, with diverse classifiers utilized for image classification. Evaluating the DRM-IR test set revealed that the combination of ResNet34, Chi-square ( ) filter, and SVM classifier demonstrated superior performance, achieving the highest accuracy at . Furthermore, the highest accuracy improvement obtained was when using the SVM classifier and Chi-square filter compared to regular convolutional neural networks. The results confirmed that the proposed method, with its high accuracy and lightweight model, outperforms state-of-the-art breast cancer detection from thermography image methods, making it a good choice for computer-aided diagnosis.

Disparities in mental health screening for veteran women with a new diagnosis of breast cancer.

222 Background: Compared to the general population, mental health disorders, including depression, are higher for Veteran women. Breast cancer (BC) is the most commonly diagnosed cancer in this population and up to 50% of women will experience depressive symptoms after diagnosis, associated with poor prognosis and survival. An increasing number of Veteran women live in rural areas, where access to behavioral health care may be limited. This study sought to evaluate rural disparities in mental health screening and follow-up evaluation after a new BC diagnosis. Methods: Women Veterans with a new BC diagnosis were identified between 2017 and 2021. Data for mental health screenings [Patient Health Questionnaire (PHQ)-2, PHQ-9, General Anxiety Disorder-7] were collected subsequent to the first BC diagnosis. Rurality was defined per the USDA Rural-Urban Commuting Area (RUCA) codes framework to determine rurality based on population density and commuting patterns. Data were abstracted from several large VA and non-VA datasets, including the Corporate Data Warehouse (CDW) Outpatient files, non-VA Care Medical and Pharmacy System files, Program Integrity Tool, and VA Informatics and Computing Infrastructure for Oncology. Rurality data was specified using CDW designations combined with ZIP-code-level USDA RUCA information. All categorical variables were analyzed using chi-square tests. Means were tested using t-tests. Results: 14,225 Veteran women with a new BC diagnosis were identified. The mean age was 63.4 (SD 11.7). The most common documented race was White (30.6%), followed by Black (15.7%). 59.6% lived in an urban setting as opposed to rural setting (40.4%). In the entire population, only 14% had a mental health screening within 3 months of a cancer diagnosis. Veteran women living in an urban setting were more likely to be screened compared to those living in a rural setting (17.4% vs 9.2%, p < 0.001). For women screened within 3 months, most screened negative, regardless of rurality (76.1% rural, 75.7% urban). Of women who had a positive mental health screen within 3 months, only approximately one-third (31.8% rural, 34.2% urban) had additional screening regardless of rurality. However, for those with a negative initial screen, urban Veterans were more likely to have any additional screening (17% vs 10.2%, p = 0.001). PHQ-2 was the most common mental health screening tool used (73.8%) followed by a combination of PHQ-9 and GAD-7 (9.6%). Conclusions: Mental health screening within 3 months of breast cancer diagnosis is low for Veteran women. There is a significant difference in screening between rural and urban populations. It is critical to both improve mental health screening overall in this population and bridge the disparity gap between screening in rural and urban Veteran women. This may impact not only mental health but also breast cancer outcomes during the period encompassing treatment and survivorship.

Pregnancy and Breast Cancer: A Challenge for the Multidisciplinary Team. A Single Center Experience and Narrative Review.

The diagnosis of breast cancer during pregnancy is a rare event, but it is more frequent in our daily clinical practice due to the progressing aging of pregnant women. The management of a woman affected by pregnancy-associated breast cancer (PABC) remains a challenge for the clinician as it is related to ethical and psychological decisions. Here, we retrospectively described 10 cases of PABC in women treated at our Institution. All cases were discussed in the multidisciplinary team. We reviewed available literature data on the topic. Nine out 10 patients were diagnosed with localized breast cancer. The remaining patients were presented with metastatic de novo disease. Median age was 37.5 years (range 26-42). Seven patients presented with grade 3 tumor and 9 patients had Ki-67 value higher than 30%. All but 2 patients received neoadjuvant chemotherapy consisting of sequential anthracyclines and cyclophosphamide followed by weekly paclitaxel during pregnancy. No safety concerns or complications during delivery for both the mothers and the babies were reported. Breast cancer during pregnancy is a challenging clinical situation and all the decisions need to consider both the patients and the fetus safety. Data from our series and from literature confirm the safety of standard chemotherapy approach starting from the second trimester of gestation. More research and effort are needed to offer these patients excellent outcomes and it is mandatory that cases should be closely followed up by a multidisciplinary team.

Optimization and correction of breast dynamic optical imaging projection data based on deep learning

Breast cancer poses a significant health threat to women, necessitating advancements in diagnostic technologies. Breast dynamic optical imaging (DOI) technology, recognized for its non-invasive and radiation-free properties, is extensively utilized for the early screening and quantitative analysis of breast tumors. The integration of deep learning, a robust technology for automatic image feature extraction, with breast DOI has the potential to enhance tumor detection and diagnosis significantly. This paper introduces a deep learning-enhanced image optimization approach to overcome challenges such as poor image quality and distorted projection data commonly encountered in existing DOI methods. The approach utilizes convolutional neural networks (CNNs) to extract features from raw images and employs generative adversarial networks (GANs) to enhance these images, thereby improving their quality and contrast. Additionally, a novel correction algorithm is developed to address projection data distortion, enabling the reconstruction and correction of this data for more accurate and reliable imaging results. Experimental findings confirm that the proposed method markedly enhances both image quality and projection data accuracy in breast DOI, offering a reliable foundation for clinical diagnosis. This study not only provides a new perspective and methodology for the early screening and diagnosis of breast cancer but also holds substantial clinical importance and prospective applications.

Defining the Need for Services for Patients at High Risk of Breast Cancer at a Safety-Net Hospital: An Approach to Narrowing the Disparities Gap.

The National Accreditation Program for Breast Cancer (NAPBC) standards were recently revised to promote breast cancer (BC) risk assessment and subsequent referral for high-risk services. This project sought to estimate the proportion of patients at high risk for BC in the authors' safety-net hospital system, gauge patient interest in high-risk services, and define resources for program development. Women presenting for breast imaging during 2 weeks in 2023 were surveyed. Thirty-five patients with a history or diagnosis of BC were excluded. The Tyrer-Cuzick (TC) model version 8 was used to calculate BC risk. High/intermediate risk was defined as a 10-year risk of 5% or more, a lifetime risk of 15% or more, or both. The criteria for genetic counseling and testing referral were based on National Comprehensive Cancer Network guidelines. A total of 257 patients had a TC risk assessment showing 14.8% (n = 38) with a 10-year BC risk of 5% or more (consideration of endocrine therapy), 6.2% (n = 16) with a lifetime BC risk of 20% or more (qualifying for annual screening MRI), and 10.5% (n = 27) with a lifetime BC risk of 15% or more (consideration of high-risk screening). The criteria for genetic counseling/testing were met by 61 (23.7%) of the 257 patients. Overall, 31.5% (n = 81) qualified for high/intermediate-risk screening, risk reduction, and/or genetic assessment/testing, 92.8% of whom were interested in referrals for additional information and care. In the authors' community, almost one third of patients undergoing breast imaging qualify for BC high-risk assessment and services. The majority of the patients expressed interest in pursuing such services. These data will be used in financial planning and resource allocation to develop a high-risk program at the authors' institution in line with NAPBC guidelines. They are hopeful that these efforts will improve oncologic outcomes and survival from BC in their community.

Tumor detection in breast cancer pathology patches using a Multi-scale Multi-head Self-attention Ensemble Network on Whole Slide Images

Breast cancer (BC) is the most common type of cancer among women globally and is one of the leading causes of cancer-related deaths among women. In the diagnosis of BC, histopathological assessment is the gold standard, where automated tumor detection technologies play a pivotal role. Utilizing Convolutional Neural Networks (CNNs) for automated analysis of image patches from Whole Slide Images (WSIs) enhances detection accuracy and alleviates the workload of pathologists. However, CNNs often face limitations in handling pathological patches due to a lack of sufficient contextual information and limited feature generation capabilities. To address this, we propose a novel Multi-scale Multi-head Self-attention Ensemble Network (MMSEN), which integrates a multi-scale feature generation module, a convolutional self-attention module, and an adaptive feature integration and output module, effectively optimizing the performance of classical CNNs. The design of MMSEN optimizes the capture of key information and the comprehensive integration of features in WSIs pathological patches, significantly enhancing the precision of tumor detection. Validation results from a five-fold cross-validation experiment on the PatchCamelyon (PCam) dataset demonstrate that MMSEN achieves a ROC-AUC of 99.01%±0.02%, an F1 Score of 98.00%±0.08%, a Balanced Accuracy (B-Acc) of 98.00%±0.08%, and a Matthews Correlation Coefficient (MCC) of 96.00%±0.16% (p<0.05). These results demonstrate the effectiveness and potential of MMSEN in detecting tumors from pathological patches in WSIs for BC.

Communicating a cancer diagnosis using a human centered design approach.

229 Background: Anticipating and getting "the call" communicating a cancer diagnosis is reportedly one of the most stressful times in a person’s life. If not pre-scheduled patients are often in unfortunate locations, doing distractive activities and are with unsympathetic companions. Additionally, patients ask for a single point of contact, impactful resources, and immediate next steps and appointments scheduling. Methods: Pilot/Study: 120 breast cancer patients: Control group: 30 positive, 30 negative DX Test group: 30 positive, 30 negative DX Test approach: co-designed with 10 patients, 5 physicians and 5 staff. Interviews: 7 care team roles. Data collection: customized patient interview assessment tool. Steady State: sustaining work done. Conducted: January 2019 through December 2022. Evaluation Methods -11 tests: t-Tests, One-Way ANOVA, and Capability. Changes Made: call be at a pre-scheduled time delivered by ongoing point of contact offering immediate next steps and appointment scheduling offering meaningful support and resources delivered with deep empathy/compassion. Results: The project was highly successful based on the results it achieved. Results: Improved by 64% (original goal of 30%) the composite measure of care satisfaction of patients receiving a breast cancer diagnosis call in Kaiser Permanente Maui, Hawaii. Composite: 1) 61% improvement in “satisfaction with your circumstance”, 2) 63% improvement in “satisfaction with the conversation”, and 3) 70% improvement in “feeling supported” using a local measurement tool. Conclusions: The 64% improvement in the patients' experience for cancer diagnosis communication was accomplished by understanding the needs of the patients and care team, establishing new communication protocols and resources, and ensuring the process empowered patients. The study showed that both patients and care teams want a communication process that included the elements in the test approach. This project was deemed a Kaiser Permanente best practice and is in consideration for spread. Improved by 64% (goal was 30%) the composite measure of care satisfaction of patients receiving a breast cancer diagnosis call in Kaiser Permanente Maui, Hawaii. Breast Cancer Diagnosis Communication - Key Improvement Metrics: Control Group Test Group Outcome Measure: the composite measure improvement 64% of care satisfaction of patients receiving a DX Results Call 2.39 3.93 Composite Measure 1: 61% improvement in “satisfaction with your circumstance” 2.35 3.78 Composite Measure 2: 63% improvement in “satisfaction with the conversation” 2.50 4.07 Composite Measure 3: 70% improvement in “feeling supported” 2.33 3.95 Process Measure: the error rate over time had a statistically significant difference between the Control and Test groups 30.3 8.90 Balancing Measure: Negative result patients have a similar experience as the Positive result patients No significant difference No significant difference