HER2-negative Breast Cancer Research Articles

LightweightUNet: Multimodal Deep Learning with GAN-Augmented Imaging Data for Efficient Breast Cancer Detection

Breast cancer ranks as the second most prevalent cancer globally and is the most frequently diagnosed cancer among women; therefore, early, automated, and precise detection is essential. Most AI-based techniques for breast cancer detection are complex and have high computational costs. Hence, to overcome this challenge, we have presented the innovative LightweightUNet hybrid deep learning (DL) classifier for the accurate classification of breast cancer. The proposed model boasts a low computational cost due to its smaller number of layers in its architecture, and its adaptive nature stems from its use of depth-wise separable convolution. We have employed a multimodal approach to validate the model’s performance, using 13,000 images from two distinct modalities: mammogram imaging (MGI) and ultrasound imaging (USI). We collected the multimodal imaging datasets from seven different sources, including the benchmark datasets DDSM, MIAS, INbreast, BrEaST, BUSI, Thammasat, and HMSS. Since the datasets are from various sources, we have resized them to the uniform size of 256 × 256 pixels and normalized them using the Box-Cox transformation technique. Since the USI dataset is smaller, we have applied the StyleGAN3 model to generate 10,000 synthetic ultrasound images. In this work, we have performed two separate experiments: the first on a real dataset without augmentation and the second on a real + GAN-augmented dataset using our proposed method. During the experiments, we used a 5-fold cross-validation method, and our proposed model obtained good results on the real dataset (87.16% precision, 86.87% recall, 86.84% F1-score, and 86.87% accuracy) without adding any extra data. Similarly, the second experiment provides better performance on the real + GAN-augmented dataset (96.36% precision, 96.35% recall, 96.35% F1-score, and 96.35% accuracy). This multimodal approach, which utilizes LightweightUNet, enhances the performance by 9.20% in precision, 9.48% in recall, 9.51% in F1-score, and a 9.48% increase in accuracy on the combined dataset. The LightweightUNet model we proposed works very well thanks to a creative network design, adding fake images to the data, and a multimodal training method. These results show that the model has a lot of potential for use in clinical settings.

Predictive and prognostic value of 18F-FES PET/CT for patients with recurrent or metastatic breast cancer treated with endocrine therapy plus cyclin-dependent kinase 4/6 inhibitors.

Estrogen receptor (ER) expression and heterogeneity affect endocrine therapy efficacy. 18F-fluoroestradiol (18F-FES) PET/CT is an effective non-invasive method to analyze systemic ER expression. This study aimed to examine the predictive/prognostic value of 18F-FES PET/CT for patients treated with endocrine therapy plus cyclin-dependent kinase 4/6 (CDK4/6) inhibitors. Patients were identified from a prospective cohort for post-marketing surveillance of 18F-FES enrolled between April 2021 and April 2023 at Asan Medical Center. In this retrospective analysis, patients with ER-positive, HER2-negative recurrent/metastatic breast cancer who underwent CDK4/6 inhibitor-based endocrine therapy and pre-treatment 18F-FES PET/CT were included. A total of 127 women were included. The endocrine therapy used was aromatase inhibitors in 96 patients (76%) and fulvestrant in 31 patients (24%). There were 25 (20%) and 102 (80%) patients in the "with FES-negative" (3 completely negative, 22 mixed) and "FES-positive" groups, respectively. 18F-FES status correlated with progression-free survival (PFS) following endocrine therapy with CDK4/6 inhibitors and overall survival (OS) ("with FES-negative" group: hazard ratio for PFS, 3.9, p < 0.001; for OS, 3.7, p = 0.008). Reduced benefit from endocrine treatment in the "with FES-negative" group was consistent across subgroups including menopausal status, endocrine sensitivity, and treatment regimen. ER expression determined by 18F-FES PET/CT predicted the efficacy of CDK4/6 inhibitor-based endocrine therapy and was prognostic for survival in recurrent/metastatic ER-positive, HER2-negative breast cancer.

Exploration of Novel Therapeutic Targets for Breast Carcinoma and Molecular Docking Studies of Anticancer Compound Libraries with Cyclin-dependent Kinase 4/6 (CDK4/6): A Comprehensive Study of Signalling Pathways for Drug Repurposing.

This study aims to identify and evaluate promising therapeutic proteins and compounds for breast cancer treatment through a comprehensive database search and molecular docking analysis. Breast cancer (BC), primarily originating from the terminal ductal-lobular unit of the breast, is the most prevalent form of cancer globally. In 2020, an estimated 2.3 million new cases were reported, resulting in approximately 685,000 deaths. Mutations in the BRCA1 and BRCA2 genes are well-established in hereditary breast cancer. The identification of effective therapeutic proteins for BC remains a complex and evolving area of research. This study aims to identify and evaluate promising therapeutic proteins and compounds specific to breast cancer through a comprehensive database search and molecular docking analysis. A rigorous search was conducted within the National Cancer Institute (NCI), NCI Metathesaurus, SIGnaling Network Open Resource (SIGNOR), Human Protein Atlas (HPA), and the Human Phenotype Ontology (HPO) to shortlist proteins linked to BC (CUI C0678222). Recent studies were reviewed to understand the administration of CDK4/6 inhibitors (palbociclib, ribociclib, abemaciclib) combined with endocrine therapy for HR-positive and HER2-negative breast cancer. Anticancer compound libraries available at ZINC and PubChem were analyzed. Compounds were evaluated based on their binding energies with CDK4 protein, a rationally selected druggable target. Key proteins linked to breast cancer were identified through database searches. Proliferation, apoptosis, and G1/S transition pathways were frequently found dysregulated in breast cancer. ZINC13152284 exhibited the strongest binding energy at -10.9 Kcal/mol, followed by ZINC05492794 with a binding energy of -10.4 Kcal/mol. Preexisting drugs showed lower binding energies with the CDK4 protein. The study highlights the importance of drug repurposing as a strategy for the safe and effective treatment of breast cancer. Synthetic inhibitors often cause severe side effects, emphasizing the need for novel targets and compounds with better therapeutic profiles. Molecular docking identified promising compounds from the ZINC database, suggesting potential new avenues for breast cancer therapy.

Physics-informed hybrid models for enhanced precision in breast cancer classification

Breast cancer poses a significant health and safety risk for women globally, making early detection vital for effective treatment. Artificial intelligence (AI) can enhance early detection by differentiating between cancerous and non-cancerous breast tissues. Existing AI approaches for breast cancer detection face limitations, including overfitting, the need for fine-tuning, and loss of fine details. This research introduces an adaptive hybrid model infused with physics insights framework to address these challenges. The transformed dynamic and adaptive filter is proposed for data preprocessing and achieving a balance between noise reduction and edge preservation, thereby retaining critical image structures. Then, robotic physics informed model is proposed which contains diffusion convolution, batch normalization layers, activation layers, pooling layers, optimization layer and ends with a classification layer. The proposed approach compared with the baseline AOADL-HBCC, DTLRO-HCBC, Inception v3, Inception v3 Long Short Term Memory, Inception v3 Bi-directional Long Short Term Memory, VGG-16, and Residual Network such as 96.77%, 93.52%, 81.67%, 91.46%, 92.05%, 80.15%, and 82.18%, respectively. The accuracy of the proposed approach is 99.56%. This demonstrates our model’s superior performance and effectiveness in breast cancer detection.

Neutropenia and Palbociclib in Advanced Luminal HER2-Negative Breast Cancer: Experience of the Mohammed VI Oncology Center at CHU IBN ROCHD, Casablanca, Morocco

Background: Cyclin-dependent kinase 4/6 (CDK4/6) inhibitors, including palbociclib, are approved for treating advanced hormone receptor (HR)-positive/HER2-negative breast cancer. Although these agents are generally safe and effective, their use is associated with high rates of hematological adverse events, particularly neutropenia, compared to hormone therapy alone. Dose reductions and adjustments are recommended for managing these toxicities. We evaluated the neutropenia profiles, dose management of palbociclib, and clinical responses after dose reductions. Methodology: This retrospective study included 93 patients with advanced HR-positive/HER2-negative breast cancer treated with palbociclib and hormone therapy at the Mohammed VI Cancer Center, CHU IBN ROCHD, Casablanca, over three years (January 2021 to December 2023). Results: Ninety-three patients received at least one dose of palbociclib with hormone therapy. The mean patient age was 56 years, and 13 had visceral disease. The frequencies of neutropenia of any grade/grade 3/grade 4 were 81.72%/60.22%/7.53%. Twenty-nine patients required a dose reduction from 125 to 100 mg of palbociclib, and three patients required further reduction to 75 mg. The incidence of neutropenia of any grade and grade 3/4 decreased after dose reduction. No cases of febrile neutropenia or permanent treatment discontinuation were reported. Conclusion: Palbociclib combined with hormone therapy was well tolerated. Neutropenia, the most frequently reported adverse event in women with advanced HR-positive/HER2-negative breast cancer, was primarily transient and manageable through dose adjustments for patients experiencing grade ≥3 neutropenia, without compromising efficacy. Keywords: Advanced breast cancer; Cyclin-dependent kinase; Palbociclib; Neutropenia; Dose reduction.

The tRF-33/IGF1 Axis Dysregulates Mitochondrial Homeostasis in HER2-Negative Breast Cancer.

Transfer RNA-derived small RNAs (tsRNAs), a recently identified non-coding RNA subset, are mainly classified into tRNA-derived small RNA fragments (tRFs) and tRNA-derived stress-induced RNAs (tiRNAs). tsRNAs dysregulation is frequently observed in numerous cancer types, suggesting involvement in tumorigenesis. However, their functions in breast cancer (BC) remain to be fully understood. Here, it was discovered that tRF-33-MEF91SS2PMFI0Q (tRF-33), derived from mature tRNA-LysTTT, was markedly upregulated in HER2-negative BC cells and tissue samples. tRF-33 stimulated the proliferation, migration, and invasiveness of BC cells in vitro and facilitated tumor progression in vivo. Mechanistically, tRF-33 was found for the first time to bind directly to the 3'-UTR of IGF1, resulting in downregulation of both its mRNA and protein and thus affecting mitochondrial homeostasis and progression of BC. These results demonstrate a novel tsRNA modulatory mechanism and a potential direction for treating HER2-negative BC.

GradeDiff-IM: An Ensembles Model-based Grade Classification of Breast Cancer.

Cancer grade classification is a challenging task identified from the cell structure of healthy and abnormal tissues. The partitioner learns about the malignant cell through the grading and plans the treatment strategy accordingly. A major portion of researchers used DL models for grade classification. However, the behavior of DL models is hidden type, it is unknown which features contribute to the accuracy and how the features are chosen for grading. To address the issue the study proposes a Grade Differentiation Integrated&#xD; Model (GradeDiff-IM) to classify the grades G1, G2, and G3. In GradeDiff-IM, different ML models, are used for grade classification from clinical and pathological reports. The biological-significant features with ranking technique prioritize influential features are used&#xD; to identify grades G. Subsequently, histopathological images are used by DL models for grade classification and compared with ML models. Instead of employing a single ML model, the GradeDiff-IM model uses the stack-ensembled approach to improve the grade&#xD; G classification performance. The maximum accuracy is attained by stacking G1-98.2, G2-97.6, and G3-97.5. The proposed study shows that the ML ensemble model is more accurate than the DL models. As a result, the proposed model achieved higher accuracy&#xD; for G by implementing the stacking technique than the other state-of-the-art models.

Recent advances of antibody-drug conjugates in treating breast cancer with different HER2 status.

Despite the availability of multiple treatment options for breast cancer, challenges such as adverse events, drug resistance, and disease progression persist for patients. The identification of human epidermal growth factor receptor 2 (HER2) as an oncogenic driver in a subset of breast cancers, alongside the development of HER2-targeted therapies, has significantly improved the prognosis of HER2-amplified breast cancers. However, therapeutic options remain limited for HER2-overexpressing or HER2-negative breast cancers. In response to this gap, antibody-drug conjugates (ADCs) have emerged as a promising approach. ADCs combine the specificity of monoclonal antibodies with the cytotoxic effects of chemotherapy, which allows for the targeted delivery of a cytotoxic payload to cancer cells. ADCs have been used as adjuvant chemotherapeutic treatments and salvage therapies across various breast cancer subtypes, which have greatly improved the prognosis of breast cancer patients. Numerous ongoing clinical trials seek to optimize dosing strategies and identify patient populations that would benefit most from ADCs. This review presents an updated and comprehensive overview of emerging investigational ADCs for treating breast cancer patients with various HER2 subtypes. These ADCs are spearheading a new era in targeted cancer therapy, promising to innovate treatment paradigms for both HER2-positive and HER2-low breast cancers.

Refining breast cancer classification: Customized attention integration approaches with dense and residual networks for enhanced detection.

Breast cancer detection is critical for timely and effective treatment, and automatic detection systems can significantly reduce human error and improve diagnosis speed. This study aims to develop an accurate and robust framework for classifying breast cancer into benign and malignant categories using a novel machine learning architecture. We propose a dense-ResNet attention integration (DRAI) architecture that combines DenseNet and ResNet models with three attention mechanisms to enhance feature extraction from the BreakHis dataset. The attention mechanisms focus on regionally important features, improving classification accuracy. A triple-level ensemble (TLE) method combines the performance of multiple models, further enhancing prediction accuracy. The proposed DRAI architecture with TLE achieves an accuracy of 99.58% in classifying breast cancer into benign and malignant categories, surpassing existing methodologies. This high accuracy demonstrates the effectiveness of the fusion architecture and its ability to reduce manual errors in breast cancer diagnosis. The DRAI architecture with TLE provides a robust, automated framework for breast cancer classification. Its exceptional accuracy lays a solid foundation for future advancements in automated diagnostics and offers a reliable method for aiding early breast cancer detection.

Transfer Learning Based Breast Cancer Detection and Classification using AG2Convnet and Adap-BI Magnification

Transfer Learning Based Breast Cancer Detection and Classification using AG2Convnet and Adap-BI Magnification

LARSE: Level-Based Associated Residual Network with Squeeze-and-Excitation for Breast Cancer Detection and Classification

LARSE: Level-Based Associated Residual Network with Squeeze-and-Excitation for Breast Cancer Detection and Classification

Rad4XCNN: A new agnostic method for post-hoc global explanation of CNN-derived features by means of Radiomics.

In recent years, machine learning-based clinical decision support systems (CDSS) have played a key role in the analysis of several medical conditions. Despite their promising capabilities, the lack of transparency in AI models poses significant challenges, particularly in medical contexts where reliability is a mandatory aspect. However, it appears that explainability is inversely proportional to accuracy. For this reason, achieving transparency without compromising predictive accuracy remains a key challenge. This paper presents a novel method, namely Rad4XCNN, to enhance the predictive power of CNN-derived features with the inherent interpretability of radiomic features. Rad4XCNN diverges from conventional methods based on saliency maps, by associating intelligible meaning to CNN-derived features by means of Radiomics, offering new perspectives on explanation methods beyond visualization maps. Using a breast cancer classification task as a case study, we evaluated Rad4XCNN on ultrasound imaging datasets, including an online dataset and two in-house datasets for internal and external validation. Some key results are: (i) CNN-derived features guarantee more robust accuracy when compared against ViT-derived and radiomic features; (ii) conventional visualization map methods for explanation present several pitfalls; (iii) Rad4XCNN does not sacrifice model accuracy for their explainability; (iv) Rad4XCNN provides a global explanation enabling the physician to extract global insights and findings. Our method can mitigate some concerns related to the explainability-accuracy trade-off. This study highlighted the importance of proposing new methods for model explanation without affecting their accuracy.

Complication Rates After Mastectomy and Reconstruction in Breast Cancer Patients Treated with Hypofractionated Radiation Therapy Compared to Conventional Fractionation: A Single Institutional Analysis.

Radiation therapy plays an important role in the treatment of localized breast cancer. Hypofractionated (HF) radiation therapy has emerged as a promising alternative to conventional fractionation (CF) schedules, offering comparable efficacy with reduced treatment duration and costs. However, concerns remain regarding its safety and rate of toxicity, particularly in patients undergoing mastectomy with breast reconstruction. This study aimed to assess the implant-related complications in breast cancer patients receiving HF post-mastectomy radiation therapy (PMRT) and reconstruction compared to CF PMRT. A retrospective study was conducted on 59 breast cancer patients who underwent mastectomy and breast reconstruction between 2013 and 2021 and received adjuvant PMRT. Patient demographics, treatment characteristics, and implant-related complications were analyzed. Statistical tests including chi-square, Fischer's exact test, and multivariable Cox regression were employed for analysis. Of the 59 patients, 29 received HF PMRT and 30 received CF PMRT. At a median follow-up of 23.4 months, there was no significant difference in major implant-related complications between the two groups (24.1% in HF vs. 33.3% in CF, p = 0.436). Most complications in the HF group occurred within the first two years post-radiation. Age over 40 was identified as a significant predictor for higher implant-related complications (p = 0.029). Our findings indicate that HF PMRT and reconstruction does not increase the risk of major implant-related complications compared to CF PMRT. These results align with the existing literature, supporting the safety of HF radiation in breast cancer patients who underwent mastectomy with reconstruction.

Large Unstained Cells (LUC): A Novel Predictor of CDK4/6 Inhibitor Outcomes in HR+ HER2-Negative Metastatic Breast Cancer.

Background: Although CDK4/6 inhibitors combined with endocrine therapies have improved outcomes in HR+ HER2-negative metastatic breast cancer, predictive biomarkers for treatment response and adverse effects remain limited. This study assessed the prognostic and predictive value of large unstained cells (LUC), a subset of white blood cells that may reflect immune status or treatment response. Methods: A retrospective analysis of 210 patients with HR+ HER2-negative metastatic breast cancer treated with CDK 4/6 inhibitors between 2021 and 2024 was conducted. Clinical data, including demographics, tumor characteristics, and treatment regimens, were analyzed. Based on LUC levels, progression-free survival (PFS), overall survival (OS), and adverse events were evaluated. Results: The cohort had a median age of 57, of which 78% were postmenopausal. Common metastatic sites included bone (67%) and liver (24%). At a median follow-up of 18.5 months, the PFS and OS rates were 65% and 83%. Patients with low LUC levels had significantly shorter PFS (OR: 1.91; p = 0.014) and OS (OR: 2.39; p = 0.012), while high LUC levels correlated with a lower incidence of grade 3 neutropenia (OR: 0.49; p = 0.017). Liver metastasis and prior treatments were also linked to shorter survival. Conclusions: LUC levels emerge as a promising biomarker for predicting survival outcomes and the risk of neutropenia in HR+ HER2-negative metastatic breast cancer patients treated with CDK 4/6 inhibitors and endocrine therapy, showing their potential to guide personalized treatment approaches.

RAD51 testing in patients with early HER2-negative breast cancer and homologous recombination deficiency: post-hoc analysis of the GeparOla trial.

The randomized GeparOla trial reported comparable pathological complete response (pCR) rates with neoadjuvant containing olaparib vs. carboplatin treatment. Here, we evaluate the association between functional homologous repair deficiency (HRD) by RAD51 foci and pCR, and the potential of improving patient selection by combining RAD51 and stromal tumor infiltrating lymphocytes (sTILs). This is a post-hoc blinded, biomarker analysis from the randomized GeparOla trial. Patients with early-stage HER2-negative breast cancer and HRD assessed by Myriad myChoice or BRCA1/BRCA2 mutation were randomized 1:1 to receive i) paclitaxel plus olaparib or ii) paclitaxel plus carboplatin, both followed by epirubicin/cyclophosphamide. Functional HRD was predefined as a RAD51 score ≤10% (RAD51-low). Overall, 90/97 (92.8%) samples were evaluable for RAD51 testing and 72/90 (80.0%) were RAD51-low. The pCR rate in patients with RAD51-low tumors was 66.7% (48/72), while it decreased to 22.2% (4/18) in those with RAD51-high. In the multivariable model including clinicopathological factors and treatment, the RAD51 score remained significantly associated with pCR (OR=12.03, 95%CI 2.60-55.73, p=0.002). Patients with RAD51-low and high sTILs in their tumors achieved a pCR rate of 75.0% (27/36). Similar results were observed for olaparib or carboplatin. In the exploratory DFS analysis, no differences were observed between RAD51 groups (high vs. low: HR=0.85, 95% CI 0.25-2.97). In a pre-selected population with HRD according to a genetic test, RAD51 testing identifies patients with different pCR rates under PARPi or platinum-based therapies. Future biomarker-driven studies should consider this information to refine stratification factors and to improve patient selection.

Neratinib enhances the efficacy of CDK4/6 inhibitor plus endocrine therapy in HR+/HER2-low breast cancer cell line ZR-75-1 via hsa-miR-23a-5p

HR+/HER2-low breast cancer is a significant subgroup of conventional HR+/HER2-negative breast cancer, and combination of CDK4/6 inhibitor and endocrine therapy is the standard first-line and second-line treatments for advanced HR+/HER2-low breast cancer. Nevertheless, it remains uncertain whether HER2 signaling affects the effectiveness of CDK4/6 inhibitor administered in combination with endocrine therapy for HR+/HER2-low breast cancer and suitable intervention measures. This study revealed poor efficacy for CDK4/6 inhibitor combined with endocrine therapy for HR+/HER2-low breast cancer in vitro and in vivo models. Secondly, suppression of HER2 gene expression in HR+/HER2-low breast cancer cells resulted in significantly improved efficacy for CDK4/6 inhibitor combined with endocrine therapy. Furthermore, the anti-HER inhibitor neratinib was administered to enhance the effectiveness of CDK4/6 inhibitor combined with endocrine therapy in HR+/HER2-low breast cancer by inhibiting the HER2 pathway and lowering HER2 mRNA expression. Strikingly, neratinib reversed the efficacy of CDK4/6 inhibitor and endocrine therapy by reducing HER2 mRNA stability in HR+/HER2-low breast cancer through the interaction of HER2 3’-UTR region with hsa-miR-23a-5p. Even after reducing neratinib dosage to the standard 1/2 dose (20 mg/kg), it remained highly effective and well-tolerated. This study provides a viable and well-tolerated triple combination therapy for clinical HR+/HER2-low breast cancer.

Antibody-drug conjugate review in breast cancer: A targeted approach

Antibody-drug conjugates (ADCs) provide specificity for cytotoxic drugs as well as monoclonal antibodies (mAbs) and represent an important step in the treatment of breast cancer. This review summarizes the current status, efficacy, safety, and future prospects of ADCs in the treatment of breast cancer. mAbs enable drug delivery by detecting specific antigens on cancer cells. Cytotoxic payloads cause cell death upon internalization. The linker binds the mAb to the payload and influences drug release. All three components together form an ADC. Transtuzumab Emtansine 1 (T-DM1) (Kadcyla) targets human epidermal growth factor receptor 2 (HER2)-positive breast cancer and has shown activity against both metastatic and early disease. Fam-trastuzumab deruxtecan (T-DXd; Enhertu) has shown improved progression-free survival and overall survival for T-DM1 in HER2-positive metastatic breast cancer. Sacituzumab govitecan (SG) targets the Trophoblast Antigen 2 (TROP2) receptor and has been shown to be effective in triple-negative breast cancer and hormone receptor-positive, HER2-negative advanced breast cancer. Fatigue, nausea, and diarrhea are the most common. Some ADCs have their own side effects. T-DXd, which can cause interstitial lung disease, and SG, which increases the risk of diarrhea. Monitoring and controlling these adverse events is important to achieve good patient outcomes. There are ongoing issues with ADC use including drug-related and other issues. The drug-related issues include side effects and ADCs drug resistance. This resistance can be due to a variety of reasons including downregulation of the target antigen, reduced internalization, increased drug efflux, and reduced burden. Strategies to reduce resistance include the use of combination therapies, early detection of resistance, and the development of more effective products. Second-generation ADCs with improved structure and potency are under development. There is ongoing research focusing on novel targets beyond HER2, such as Trop-2 and Claudin-18.2. Non-drug-related issues include tumor heterogeneity, patient selection, manufacturing issues, and increased costs. In conclusion, ADCs are a huge improvement over conventional chemotherapy for breast cancer treatment. The importance and use of ADCs in cancer treatment is bound to increase. The future of ADCs in breast cancer treatment looks promising with ongoing research into new targets, new therapeutic agents, and advances in drug resistance leading to mediated and effective methods.

First-line carboplatin-based chemotherapy may be beneficial for HER2-low advanced breast cancer: A retrospective analysis

For patients with human epidermal growth factor receptor 2 (HER2)-low advanced breast cancer who had failed to meet with anthracycline or taxane, the application of HER2-targeted antibody-drug conjugates as second-line therapy could improve patients' outcomes, but it is unclear whether carboplatin-based first-line therapy will benefit these patients. This retrospective study was designed to explore whether carboplatin based first-line treatment could improve outcomes in HER2-low advanced breast cancer, and to analyze potential factors affecting efficacy and prognosis. 103 patients with HER2-negative metastatic breast cancer were treated with carboplatin based first-line therapy. The differences in progression-free survival (PFS), objective response rate (ORR), and adverse events were analyzed in different HER2 expression subgroups. The risk ratio (HR) and 95% confidence interval (CI) for PFS were estimated using Cox proportional risk models. The ORR for the whole group was 42.72% and the median PFS (mPFS) was 7.93 months (m). The ORR of HER2-low patients was significantly higher than HER2-zero patients (56.4% vs 27.1%, P = .003), and HER2-zero was an independent risk factor of ORR (OR 3.478, 95%CI 1.516–7.977, P = .003), especially in the HR-negative subgroup. The mPFS was significantly longer in patients with low neutrophil-to-lymphocyte ratio (NLR) scores than those with high NLR scores (P &lt; .001). Multivariate analysis showed that young breast cancer (age &lt; 40) (P = .006) and high NLR values (P = .001) were prognostic risk factors affecting mPFS. The main grade 3 to 4 adverse reactions were neutropenia (15.53%), anemia (15.53%), and leukopenia (11.65%). The first-line carboplatin-based chemotherapy is quite active and tolerable in patients with HER2-low advanced breast cancer, that higher response rates can be achieved. In cases where CDK4/6 inhibitors are inappropriate for use due to resistance to endocrine therapy or the urgent need for short-term clinical response, chemotherapy remains important. When it is necessary to consider the accessibility of antibody-drug conjugates and the economics of patients, carboplatin-based chemotherapy may be provided to HER2-low patients as a more convenient, cost-effective and efficient option on the front line. Forecasting the efficacy and prognosis via inflammatory index such as NLR before the commencement of the treatment could enhance the precision and efficiency of carboplatin-based regimens.

A Real-World Comparison Between Adjuvant Docetaxel with Cyclophosphamide (TC) and Anthracycline–Taxane Chemotherapy in Early HER-2 Negative Breast Cancer

Background: Anthracycline–taxane chemotherapy is the gold standard in high-risk breast cancer (BC), despite the potential risk of congestive heart failure (CHF). A suitable alternative for anthracycline-sparing chemotherapy is through the combination of docetaxel and cyclophosphamide (TC). Methods: Through a retrospective study of stage I-III HER2-negative BC, using administrative databases, we analyzed a total of 10,634 women treated with adjuvant chemotherapy in Ontario, Canada, between 2009 and 2017. We compared TC versus standardized anthracycline–taxane chemotherapies (ACT and FEC-D). We investigated the overall survival (OS), and explored the incidence of CHF, emergency department (ED) visits and febrile neutropenia. Results: With a median follow-up of 5.5 years, the 5-year analysis showed an increased OS in patients treated with TC, versus those treated with ACT, HR 0.77 (0.63–0.95, p = 0.015). Among ER + BC, there was an increased OS in patients treated with ACT and FEC-D, versus those treated with TC, HR 0.70 (0.52–0.95, p = 0.021) and HR 0.71 (0.56–0.91, p = 0.007), respectively. There were no substantial differences in CHF, between TC and anthracycline-based treatments. Patients treated with TC and FEC-D had more ED visits, compared to those treated with ACT. Conclusion: Our study shows that anthracycline–taxane regimens were the most commonly prescribed adjuvant chemotherapy options in HER2-negative BC. Women who received ACT had the lowest OS, likely due to their unfavorable pathology.

A Comparative Analysis of CNN Architectures and Regularization Techniques for Breast Cancer Classification in Mammograms

A Comparative Analysis of CNN Architectures and Regularization Techniques for Breast Cancer Classification in Mammograms