HER2-negative Breast Cancer Research Articles

High Mechanical Conditioning by Tumor Extracellular Matrix Stiffness Is a Predictive Biomarker for Antifibrotic Therapy in HER2-Negative Breast Cancer.

Tumor progression has been linked to stiffening of the extracellular matrix caused by fibrosis. Cancer cells can be mechanically conditioned by stiff extracellular matrix, exhibiting a 1,004-gene signature [mechanical conditioning (MeCo) score]. Nintedanib has demonstrated antifibrotic activity in idiopathic pulmonary fibrosis. This study explores nintedanib's antifibrotic effect on breast cancer outcomes. We present long-term follow-up and analysis of a neoadjuvant randomized phase II trial in early HER2-negative breast cancer. Patients (N = 130) underwent a baseline biopsy and received 12 paclitaxel courses alone (control arm) or in combination with nintedanib (experimental arm). The tumor MeCo score was determined by RNA sequencing. The primary aim was to assess nintedanib's impact on event-free survival based on MeCo scores. Follow-up data were retrieved from 111 patients; 75 baseline and 24 post-run-in phase samples were sequenced. After median follow-up of 9.67 years, median event-free survival was not statistically different between arms (P = 0.37). However, in the control arm, high- versus low-MeCo patients had a statistically higher relapse risk: HR = 0.21; P = 0.0075. This risk was corrected by nintedanib in the experimental arm: HR = 0.37; P = 0.16. Nintedanib demonstrated pharmacodynamic engagement, reducing the MeCo score by 25% during the run-in phase (P < 0.01). Patients with low MeCo after run-in had the best long-term prognosis (HR = 0.087; P = 0.03). High MeCo is predictive of poor outcomes in HER2-negative early breast cancer, although this risk can be mitigated by nintedanib, which is able to specifically reduce MeCo.

An updated overview of radiomics-based artificial intelligence (AI) methods in breast cancer screening and diagnosis.

Current imaging methods for diagnosing breast cancer (BC) are associated with limited sensitivity and specificity and modest positive predictive power. The recent progress in image analysis using artificial intelligence (AI) has created great promise to improve BC diagnosis and subtype differentiation. In this case, novel quantitative computational methods, such as radiomics, have been developed to enhance the sensitivity and specificity of early BC diagnosis and classification. The potential of radiomics in improving the diagnostic efficacy of imaging studies has been shown in several studies. In this review article, we discuss the radiomics workflow and current handcrafted radiomics methods in the diagnosis and classification of BC based on the most recent studies on different imaging modalities, e.g., MRI, mammography, contrast-enhanced spectral mammography (CESM), ultrasound imaging, and digital breast tumosynthesis (DBT). We also discuss current challenges and potential strategies to improve the specificity and sensitivity of radiomics in breast cancer to help achieve a higher level of BC classification and diagnosis in the clinical setting. The growing field of AI incorporation with imaging information has opened a great opportunity to provide a higher level of care for BC patients.

A plain language summary of the CAPItello-291 study: Capivasertib in hormone receptor-positive advanced breast cancer.

This is a summary of the article discussing the results of the CAPItello-291 study. In the study, participants had advanced breast cancer that could not be completely removed with surgery, and that was diagnosed as a type of breast cancer where tumor cells had hormone receptors (HR-positive) but did not have HER2 receptors (HER2-negative). All participants were also required to have previously received treatment with a type of therapy called an aromatase inhibitor (with or without a CDK4/6 inhibitor), but over time their cancer cells had still grown or spread. The CAPItello-291 study researchers wanted to find out if a treatment combination of the medications capivasertib plus fulvestrant worked better than placebo plus fulvestrant. Capivasertib is a drug that blocks the activity of a protein called AKT, which is found inside breast cancer cells. The main finding was that participants who took capivasertib plus fulvestrant lived longer without their disease getting worse (progressing) compared with those treated with placebo plus fulvestrant. This is called progression-free survival. This result was seen across all participants (median progression-free survival of 7.2months with capivasertib plus fulvestrant vs 3.6months with placebo plus fulvestrant). It was also seen in participants whose tumors had detectable genetic alterations in genes called PIK3CA, AKT1, and/ or PTEN (median progression-free survival of 7.3months with capivasertib plus fulvestrant vs 3.1months with placebo plus fulvestrant). The most common side effects experienced by participants included diarrhea and different types of rash. These were as expected (given how capivasertib works). The CAPItello-291 study is still ongoing, and more results are expected to be released in the future. Results from the CAPItello-291 study showed that capivasertib plus fulvestrant compared with placebo plus fulvestrant improved progression-free survival in participants with HR-positive/ HER2-negative advanced breast cancer whose cancer had grown or spread despite hormone therapy (with/without a CDK4/6 inhibitor).Clinical Trial Registration: NCT04305496 (CAPItello-291) (ClinicalTrials.gov).

Neutrophil-to-lymphocyte ratio at the end of treatment with CDK4/6 inhibitors is an independent prognostic factor for ER-positive HER2-negative advanced breast cancer.

The aim of this study was to elucidate the clinical significance of peripheral blood biomarkers, including absolute lymphocyte count (ALC) and neutrophil-to-lymphocyte ratio (NLR), at the end of treatment (EOT) with CDK4/6 inhibitors abemaciclib and palbociclib in patients with estrogen receptor-positive human epidermal growth factor receptor 2-negative advanced breast cancer. We included 67 patients treated with fulvestrant plus abemaciclib or palbociclib. Overall survival (OS) since the EOT with CDK/4/6 inhibitors was compared in relation to the levels of ALC and NLR. The cut-off values of ALC and NLR were set at 1000/μL and 3, respectively. Patients with a high ALC at EOT showed significantly longer OS than those with a low ALC (p = 0.0358). Moreover, patients with a low NLR at EOT showed significantly longer OS than those with a high NLR at EOT (p = 0.0044). Looking at the changes of ALC and NLR between baseline and the EOT, patients with a high ALC both at baseline and at the EOT showed significantly longer OS than others (p = 0.0201). Similarly, patients with a low NLR both at baseline and at the EOT showed significantly longer OS after EOT than others (p = 0.0136). Multivariable analysis revealed that the NLR at EOT (low vs. high) and changes in NLR (low at baseline to low at EOT vs. others) were significant and independent prognostic factors for OS after EOT (p = 0.0337, p = 0.0039, respectively). NLR at EOT with CDK4/6 inhibitors is a significant and independent prognostic marker for patients with ER-positive HER2-negative advanced breast cancer.

Statin use and risks of breast cancer recurrence and mortality.

Preclinical evidence suggests improved breast cancer survival associated with statin use, but findings from observational studies are conflicting and remain inconclusive. The objective of this study was to assess the association between statin use after cancer diagnosis and cancer outcomes among breast cancer patients. In this retrospective cohort study, 38,858 women aged ≥66 years who were diagnosed with localized and regional stage breast cancer from 2008 through 2017 were identified from the linked Surveillance, Epidemiology, and End Results Medicare database. Statin use was ascertained from Medicare Part D pharmacy claims data. Multivariable Cox proportional hazards models were used to estimate hazard ratios (HRs) and 95% confidence intervals (CIs) for the association between post-diagnosis statin use and risks of breast cancer recurrence and breast cancer-specific mortality. Over a median follow-up of 2.9 years for recurrence and 3.7 years for mortality, 1446 women experienced a recurrence, and 2215 died from breast cancer. The mean duration of post-diagnosis statin use was 2.2 years. Statin use post-diagnosis was not associated with recurrence risk (HR, 1.05; 95% CI, 0.91-1.21), but was associated with a reduced risk of cancer-specific mortality (HR, 0.85; 95% CI, 0.75-0.96). The reduction was more pronounced in women with hormone receptor-positive/human epidermal growth factor receptor 2-negative breast cancer (HR, 0.71; 95% CI, 0.57-0.88). These findings suggest that post-diagnosis statin use is associated with improved cancer-specific survival in women with breast cancer and should be confirmed in randomized trials of statin therapy in breast cancer patients.

Employing Raman Spectroscopy and Machine Learning for the Identification of Breast Cancer

BackgroundBreast cancer poses a significant health risk to women worldwide, with approximately 30% being diagnosed annually in the United States. The identification of cancerous mammary tissues from non-cancerous ones during surgery is crucial for the complete removal of tumors.ResultsOur study innovatively utilized machine learning techniques (Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN)) alongside Raman spectroscopy to streamline and hasten the differentiation of normal and late-stage cancerous mammary tissues in mice. The classification accuracy rates achieved by these models were 94.47% for RF, 96.76% for SVM, and 97.58% for CNN, respectively. To our best knowledge, this study was the first effort in comparing the effectiveness of these three machine-learning techniques in classifying breast cancer tissues based on their Raman spectra. Moreover, we innovatively identified specific spectral peaks that contribute to the molecular characteristics of the murine cancerous and non-cancerous tissues.ConclusionsConsequently, our integrated approach of machine learning and Raman spectroscopy presents a non-invasive, swift diagnostic tool for breast cancer, offering promising applications in intraoperative settings.

Unraveling the causal links and novel molecular classification of Crohn’s disease in breast Cancer: a two-sample mendelian randomization and transcriptome analysis with prognostic modeling

BackgroundCrohn’s disease (CD), a prominent manifestation of chronic gastrointestinal inflammation, and breast cancer (BC), seemingly disparate in the medical domain, exhibit a shared characteristic. This convergence arises from their involvement in chronic inflammation and immune responses, an aspect that has progressively captivated the attention of investigators but remain controversial.MethodsWe used two-sample Mendelian Randomization (MR) and transcriptomics to explore the relationship between CD and BC. MR assessed causality of CD on different BC subtypes and reverse causality of BC on CD. We identified CD-related differentially expressed genes and their prognostic impact on BC, and developed a new molecular BC classification based on these key genes.ResultsMR revealed a causal link between CD and increased BC risk, especially in estrogen receptor-positive (ER+) patients, but not in ER-negative (ER-) cases. BC showed no causal effect on CD. Transcriptomics pinpointed genes like B4GALNT2 and FGF19 that affected BC prognosis in CD patients. A nomogram based on these genes predicted BC outcomes with high accuracy. Using these genes, a new molecular classification of BC patients was proposed.ConclusionsCD is a risk factor for ER + BC but not for ER- BC. BC does not causally affect CD. Our prognostic model and new BC molecular classifications offer insights for personalized treatment strategies.

Neoadjuvant Chemotherapy with Concurrent Letrozole for Estrogen Receptor-Positive and HER2-Negative Breast Cancer: An Open-Label, Single-Center, Nonrandomized Phase II Study (NeoCHAI).

The role of combining neoadjuvant endocrine therapy with conventional chemotherapy remains unclear; therefore, we conducted an open-label, single-center, nonrandomized phase II trial to assess the effect of this combination. Patients with previously untreated stage II or III HR-positive, HER2-negative breast cancer received concurrent letrozole 2.5 mg with standard neoadjuvant chemotherapy. The primary endpoint was pathologic complete response (pCR) at the time of surgery. We used Simon's minimax two-stage design; a pCR rate > 6% was necessary at the first stage to continue. Between November 2017 and November 2020, 53 women were enrolled in the first stage of the trial. Their median age was 49 years (range, 33-63), and 60% of them were premenopausal. Subsequently, 66% and 34% of patients with clinical stages II and III, respectively, were included; 93% had clinically node-positive disease. Two patients (4%) achieved pCR after neoadjuvant chemo-endocrine treatment, which did not satisfy the criteria for continuing to the second stage. The overall response rate was 83%. During the median follow-up of 53.7 months, the 3-year disease-free survival and overall survival rates were 87% and 98%, respectively. Neutropenia was the most common grade 3/4 adverse event (40%), but rarely led to febrile neutropenic episodes (4%). Myalgia (32%), nausea (19%), constipation (17%), heartburn (11%), oral mucositis (9%), and sensory neuropathy (9%) were frequently observed, but classified as grade 1 or 2. No deaths occurred during preoperative treatment. The addition of letrozole to standard neoadjuvant chemotherapy was safe and beneficial in terms of overall response rate, but did not provide a higher pCR rate in locally advanced HR-positive, HER2-negative breast cancer. Further research is needed to enhance neoadjuvant treatment strategies for this cancer subtype.

Multi-omics-based Machine Learning for the Subtype Classification of Breast Cancer

AbstractCancer is a complicated disease that produces deregulatory changes in cellular activities (such as proteins). Data from these levels must be integrated into multi-omics analyses to better understand cancer and its progression. Deep learning approaches have recently helped with multi-omics analysis of cancer data. Breast cancer is a prevalent form of cancer among women, resulting from a multitude of clinical, lifestyle, social, and economic factors. The goal of this study was to predict breast cancer using several machine learning methods. We applied the architecture for mono-omics data analysis of the Cancer Genome Atlas Breast Cancer datasets in our analytical investigation. The following classifiers were used: random forest, partial least squares, Naive Bayes, decision trees, neural networks, and Lasso regularization. They were used and evaluated using the area under the curve metric. The random forest classifier and the Lasso regularization classifier achieved the highest area under the curve values of 0.99 each. These areas under the curve values were obtained using the mono-omics data employed in this investigation. The random forest and Lasso regularization classifiers achieved the maximum prediction accuracy, showing that they are appropriate for this problem. For all mono-omics classification models used in this paper, random forest and Lasso regression offer the best results for all metrics (precision, recall, and F1 score). The integration of various risk factors in breast cancer prediction modeling can aid in early diagnosis and treatment, utilizing data collection, storage, and intelligent systems for disease management. The integration of diverse risk factors in breast cancer prediction modeling holds promise for early diagnosis and treatment. Leveraging data collection, storage, and intelligent systems can further enhance disease management strategies, ultimately contributing to improved patient outcomes.

High-dose chemotherapy for patients with stage III breast cancer with homologous recombination deficiency: a discrete choice experiment among healthcare providers.

High-dose chemotherapy with autologous stem cell rescue (HDCT) is currently under investigation as a potential therapy for patients with stage III HER2-negative breast cancer with homologous recombination deficiency (HRD). In addition to survival, the impact on short- and long-term side effects might influence the uptake of HDCT by healthcare professionals. As part of the SUBITO trial, we investigated healthcare professionals' treatment (outcome) preferences for patients with HRD stage III HER2-negative breast cancer and established how healthcare professionals make trade-offs between these treatment outcomes. We conducted a discrete choice experiment in which healthcare professionals were asked to choose repeatedly between scenarios with two treatment options (HDCT or standard of care (SOC)) that varied in outcome with respect to 10-year overall survival (OS), short-term toxicity, long-term cognitive impairment, and premature menopause. We analysed treatment preferences, relative importance, and trade-offs using a multinomial logistic model. Thirty-five of the 151 dedicated breast cancer professionals with extensive experience in treating breast cancer patients completed the survey. The 10-year OS and long-term cognitive impairment were the most important attributes. The results indicate a requirement of 10.4% and 25.1% absolute additional improvement in the 10-year survival rate to justify accepting moderate or severe long-term cognitive impairment as a trade-off, respectively. Therefore, we found in our dataset that healthcare professionals expected a large improvement in 10-year OS to accept moderate to severe cognitive impairment. This information calls for further research into chemotherapy-related cognitive impairment, shared decision-making, and treatment preferences for patients with stage III breast cancer.

Prosigna Assay for Treatment Decisions in Early Breast Cancer: A Decision Impact Study.

Introduction: Therapeutic decisions in early breast cancer are based on clinico-pathological features which are subject to intra- and inter-observer variability. This single-center decision impact study aimed to evaluate the effects of the Prosigna assay on physicians' adjuvant treatment choices. Methods: Between 09/2017 and 02/2018, formalin-fixed tumor samples from 52 newly diagnosed, postmenopausal, hormone receptor-positive, HER2-negative breast cancer (T1-T2; pN0-N1a) patients were analyzed. Pre-test clinical judgements and Prosigna test results were compared. Results: The mean age was 59 (42-77). Invasive ductal carcinoma (79.2%), grade 2 (52.8%) and T1c-N0 tumors (43.4%) were represented. There was 40.4% discordance between the pre- and post-test risk of recurrences. No significant change was observed in the clinical intermediate risk category, while there was a net reclassification of low-risk patients into a high Prosigna recurrence risk group. In addition, clinically determined intrinsic subtypes were 34.6% discordant with the Prosigna results, which is largely driven by the reclassification of the luminal A tumors into the Prosigna-assessed luminal B group. Before the Prosigna test, endocrine treatment was the primary choice in 20 patients (39.2%), and chemotherapy was recommended to 31 patients (60.8%). Overall, the Prosigna assay led to a change in treatment choice for one patient. Conclusions: Although conventional risk assessment methods are relatively inexpensive with shorter turnaround times, their accuracy and value for risk reduction are suboptimal. According to our results, the Prosigna assay was found to be a relevant tool for the clinical decision making process. Long-term follow-up of these patients will elucidate the potential benefits of using multigene molecular tests as biomarkers for treatment.

EP283 - Sentinel Lymph Node Biopsy Should Not Be Withheld In Patients With Early Breast Cancer Over 70 Years Of Age

Abstract Introduction North American Choosing Wisely guidelines currently state patients with hormone receptor (HR) positive, HER2 negative early breast cancer over 70 [EBC] should avoid sentinel lymph node biopsy (SLNB). Methods Data was collected over a 2-year period in patients over 70 years with EBC. Results 22 patients, mean age 77.0, (70-89). Dual tracer was attempted in all cases. There was no significant difference in age, tumour size or BMI between dual lymphatic mapping vs single tracer success (unpaired t test, p = 0.80, 0.61 and 0.31). SLNB failed in one patient (EBC, breast cancer surgery with axillary dissection 15 years before). SNLB success rate 97.5% Positive nodes at SLNB were found in 5 EBC patients (22.7%), mean age 79.2 years (74-86), mean tumour size 27.8mm (11-78mm); mean number of sentinel nodes removed was 5.8 (range 4-9), mean number of positive nodes 1.8 (range 1-4). In the 5 patients with lymph node disease, 3 had metastasis, two micrometastasis), 4 nodes were retrieved at SLNB in all 3 cases, positive node range 1-4. All 5 patients with positive nodes were HR positive, HER negative. All had adjuvant treatment, 4 out of the 5 had tumours less than 1.5cm in size. Mean survival after surgery 63.5 months (40-87 months), mean follow up 71.4 months (50-90 months). Conclusion Our study indicates contrary to current Choosing Wisely guidelines, there is benefit for SLNB in over 70s, even with small HR positive, tumours, usually thought to be at low risk of metastasis. We found SLNB safe and effective. To accurately identify positive nodes, up to 4 sentinel nodes should be retrieved.

New treatment strategy for early hormone receptor-positive HER2-negative breast cancer: updated results of adjuvant abemaciclib trial in operable and locally advanced breast cancer

Abemaciclib is an oral inhibitor 4 and 6 (CDK4/6). Abemaciclib differs from other drugs in this group in suppression spectrum of cyclin-dependent kinases and is proven to improve survival rates in different treatment lines of metastatic breast cancer. In randomized clinical trials 3rd phase in patients with early hormone-dependent HR+ HER2 negative breast cancer high risk of progression abemaciclib in conjunction with hormone therapy significantly improves invasive disease-free survival (IDFS) and distant relapse-free survival (DRFS). Long- term outcome studies monarchE with 5 – year follow – up of patients showed that abemaciclib adding to ET increases 5-year IDFS from 76 to 83.6% (HR0.680; 95% CI 0.599 to 0.772; p &lt;0.001) and 5-year DRFS from 79.2% to 86.0% (HR0.675; 95% CI 0.588 to 0.774; p &lt;0.001). Adverse events of 3rd degree and higher are registrated in 45.5% of patients in abemaciclib group and in 12,7% in control group and mainly presented by neutropenia (18.6 and 0.7%) and diarrhea (7,6 and 0.1%). Toxicity profile was expected and controlled. The reasonable dose reduction of abemaciclib did not lead to deterioration of long-term treatment result.

Mass Spectrometry-Based Proteomics for Classification and Treatment Optimisation of Triple Negative Breast Cancer.

Triple-negative breast cancer (TNBC) presents a significant medical challenge due to its highly invasive nature, high rate of metastasis, and lack of drug-targetable receptors, which together lead to poor prognosis and limited treatment options. The traditional treatment guidelines for early TNBC are based on a multimodal approach integrating chemotherapy, surgery, and radiation and are associated with low overall survival and high relapse rates. Therefore, the approach to treating early TNBC has shifted towards neoadjuvant treatment (NAC), given to the patient before surgery and which aims to reduce tumour size, reduce the risk of recurrence, and improve the pathological complete response (pCR) rate. However, recent studies have shown that NAC is associated with only 30% of patients achieving pCR. Thus, novel predictive biomarkers are essential if treatment decisions are to be optimised and chemotherapy toxicities minimised. Given the heterogeneity of TNBC, mass spectrometry-based proteomics technologies offer valuable tools for the discovery of targetable biomarkers for prognosis and prediction of toxicity. These biomarkers can serve as critical targets for therapeutic intervention. This review aims to provide a comprehensive overview of TNBC diagnosis and treatment, highlighting the need for a new approach. Specifically, it highlights how mass spectrometry-based can address key unmet clinical needs by identifying novel protein biomarkers to distinguish and early prognostication between TNBC patient groups who are being treated with NAC. By integrating proteomic insights, we anticipate enhanced treatment personalisation, improved clinical outcomes, and ultimately, increased survival rates for TNBC patients.

The choice of optimal therapy for ER+ HER2-metastatic breast cancer (PROMETHEUS): all-Russian analysis of physicians’ preferences – updated survey results

Cyclin-dependent kinase 4/6 inhibitors (iCDK4/6) are the generally accepted standard of care for the treatment of luminal HER2-negative metastatic breast cancer (ER+HER2- mBC). Data from randomized and observational studies have proven the high effectiveness of the combination of iCDK4/6 and endocrine therapy (ET) both in the 1st and in subsequent lines. The use of new drugs in real clinical practice is determined by a number of factors, including the awareness of doctors, their personal experience and subjective preferences, as well as financial support and availability in a particular region. To assess the frequency of prescription of CDK4/6, as well as other types of treatment in the 1st‑2nd line of therapy for ER+ HER2- mBC in real clinical practice in Russia, as well as to determine the factors and preferences of doctors influencing their choice, the National Association of Oncomammologists (NAOM) conducted a survey “Prometheus” of oncology specialists. From February 15 to August 30, 2023, a web survey of healthcare professionals who treat patients with mBC was conducted on the website anketolog.ru. An invitation to survey was sent out through the NAOM database, 112 questionnaires were received and processed. Earlier, in 2020, the “Prometheus” survey was conducted on the territory of the Russian Federation for a similar purpose. In this paper, we present the results of an updated and expanded survey and evaluate changes that have occurred over the past 3 years in actual clinical practice. The results of a 2023 survey conducted in the Russian Federation on the choice of early-line therapy for ER+HER2- mBC showed that, compared with the 2020 survey, the level of “trust” in iCDK4/6 has increased among practicing physicians, and the indications for their use have expanded, including visceral metastases (and even pending visceral crisis), the indications for prescribing chemotherapy in the 1st line have narrowed. When using monoET in the 1st line, the majority of respondents prescribe iCDK4/6 in the 2nd line. Obviously, the wider use of iCDK4/6 is associated not only with the accumulation of clinical knowledge and experience in the use of drugs, but also with improved drug supply. However, the main limitations to the use of iCDK4/6 are still insufficient funding and organizational difficulties. However, it should be noted that 1/5 of the respondents do not face any restrictions and widely prescribe combination therapy.

Comparative Study of Pre-Trained Models for Breast Cancer Classification: Challenges and Future Directions

Comparative Study of Pre-Trained Models for Breast Cancer Classification: Challenges and Future Directions

An Abscopal Effect on Lung Metastases in Canine Mammary Cancer Patients Induced by Neoadjuvant Intratumoral Immunotherapy with Cowpea Mosaic Virus Nanoparticles and Anti-Canine PD-1.

Neoadjuvant intratumoral (IT) therapy could amplify the weak responses to checkpoint blockade therapy observed in breast cancer (BC). In this study, we administered neoadjuvant IT anti-canine PD-1 therapy (IT acPD-1) alone or combined with IT cowpea mosaic virus therapy (IT CPMV/acPD-1) to companion dogs diagnosed with canine mammary cancer (CMC), a spontaneous tumor resembling human BC. CMC patients treated weekly with acPD-1 (n = 3) or CPMV/acPD-1 (n = 3) for four weeks or with CPMV/acPD-1 (n = 3 patients not candidates for surgery) for up to 11 weeks did not experience immune-related adverse events. We found that acPD-1 and CPMV/acPD-1 injections resulted in tumor control and a reduction in injected tumors in all patients and in noninjected tumors located in the ipsilateral and contralateral mammary chains of treated dogs. In two metastatic CMC patients, CPMV/acPD-1 treatments resulted in the control and reduction of established lung metastases. CPMV/acPD-1 treatments were associated with altered gene expression related to TLR1-4 signaling and complement pathways. These novel therapies could be effective for CMC patients. Owing to the extensive similarities between CMC and human BC, IT CPMV combined with approved anti-PD-1 therapies could be a novel and effective immunotherapy to treat local BC and suppress metastatic BC.

Mammography classification with multi-view deep learning techniques: Investigating graph and transformer-based architectures

The potential and promise of deep learning systems to provide an independent assessment and relieve radiologists’ burden in screening mammography have been recognized in several studies. However, the low cancer prevalence, the need to process high-resolution images, and the need to combine information from multiple views and scales still pose technical challenges. Multi-view architectures that combine information from the four mammographic views to produce an exam-level classification score are a promising approach to the automated processing of screening mammography. However, training such architectures from exam-level labels, without relying on pixel-level supervision, requires very large datasets and may result in suboptimal accuracy. Emerging architectures such as Visual Transformers (ViT) and graph-based architectures can potentially integrate ipsi-lateral and contra-lateral breast views better than traditional convolutional neural networks, thanks to their stronger ability of modeling long-range dependencies. In this paper, we extensively evaluate novel transformer-based and graph-based architectures against state-of-the-art multi-view convolutional neural networks, trained in a weakly-supervised setting on a middle-scale dataset, both in terms of performance and interpretability. Extensive experiments on the CSAW dataset suggest that, while transformer-based architecture outperform other architectures, different inductive biases lead to complementary strengths and weaknesses, as each architecture is sensitive to different signs and mammographic features. Hence, an ensemble of different architectures should be preferred over a winner-takes-all approach to achieve more accurate and robust results. Overall, the findings highlight the potential of a wide range of multi-view architectures for breast cancer classification, even in datasets of relatively modest size, although the detection of small lesions remains challenging without pixel-wise supervision or ad-hoc networks.

An integrated computer-aided diagnosis BCanD model for detection, segmentation and classification of breast cancer

A fully integrated Computer-Aided Diagnosis (CAD) system involves the integration of detection, segmentation, and classification, which makes it very useful for medical applications, particularly while dealing with the detection of breast mass and its classification into malignant and benign. The carried-out research work is intended to propose a Breast Cancer Detection (BCanD) model that is an integrated CAD system, where the system is capable enough for mass detection, its segmentation, and for the classification using mammograms. The proposed integrated system utilizes deep learning based YOLO model to detect the abnormality (mass) in the mammogram, where U-net is used for segmentation of the mass, as it has the capability to produce pixel level segmentation map, and at last stage that is the classification stage deep CNN is used for the classification. The proposed system is evaluated on open-source MIAS database. For the performance evaluation of the proposed BCanD, a three-fold cross-validation test was utilized. The mass detection accuracy of the BCanD is 98.99%, MCC is 97.96%, and F1-score is 98.87%. The model is evaluated with and without automated mass segmentation to study the impact of segmentation on the suggested CAD system. The best results was observed with the segmentation with the overall accuracy of 94.20%, F1-score (Dice) of 93.60%, MCC of 88.33%, and Jaccard of 88.08%. The proposed BCanD model surpasses the latest existing deep learning-based methodologies like fuzzy classifier, CNNI-BCC etc Hence, the proposed CAD system can be implemented and used by radiologists for all the stages from detection to diagnosis of breast mass.

266P Association of RAD51 and efficacy outcomes in patients with HER2-negative breast cancer (BC) and homologous recombination deficiency (HRD): Post-hoc analysis of the GeparOla trial

266P Association of RAD51 and efficacy outcomes in patients with HER2-negative breast cancer (BC) and homologous recombination deficiency (HRD): Post-hoc analysis of the GeparOla trial