Evolving standards of care and new challenges in the management of HER2-positive breast cancer.

The management of human epidermal growth factor receptor (HER2)-positive breast cancer (BC) has rapidly evolved over the last 20 years. Major advances have led to US Food and Drug Administration approval of 7 HER2-targeted therapies for the treatment of early-stage and/or advanced-stage disease. Although oncologic outcomes continue to improve, most patients with advanced HER2-positive BC ultimately die of their disease because of primary or acquired resistance to therapy, and patients with HER2-positive early BC who have residual invasive disease after preoperative systemic therapy are at a higher risk of distant recurrence and death. The concept of treatment de-escalation and escalation is increasingly important to optimally tailor therapy for patients with HER2-positive BC and is a major focus of the current review. Research efforts in this regard are discussed as well as updates regarding the evolving standard of care in the (neo)adjuvant and metastatic settings, including the use of novel combination therapies. The authors also briefly discuss ongoing challenges in the management of HER2-positive BC (eg, intrinsic vs acquired drug resistance, the identification of predictive biomarkers, the integration of imaging techniques to guide clinical practice), and the treatment of HER2-positive brain metastases. Research aimed at superseding these challenges will be imperative to ensure continued progress in the management of HER2-positive BC going forward.

Fatigue and vigilance in medical experts detecting breast cancer.

An abundance of laboratory-based experiments has described a vigilance decrement of reducing accuracy to detect targets with time on task, but there are few real-world studies, none of which have previously controlled the environment to control for bias. We describe accuracy in clinical practice for 360 experts who examined >1 million women's mammograms for signs of cancer, whilst controlling for potential biases. The vigilance decrement pattern was not observed. Instead, test accuracy improved over time, through a reduction in false alarms and an increase in speed, with no significant change in sensitivity. The multiple-decision model explains why experts miss targets in low prevalence settings through a change in decision threshold and search quit threshold and propose it should be adapted to explain these observed patterns of accuracy with time on task. What is typically thought of as standard and robust research findings in controlled laboratory settings may not directly apply to real-world environments and instead large, controlled studies in relevant environments are needed.

International evaluation of an AI system for breast cancer screening.

Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.

Postoperative radiotherapy omission in selected patients with early breast cancer following preoperative breast MRI (PROSPECT): primary results of a prospective two-arm study.

BACKGROUND: Adjuvant breast radiotherapy as a standard component of breast-conserving treatment for early cancer can overtreat many women. Breast MRI is the most sensitive modality to assess local tumour burden. The aim of this study was to determine whether a combination of MRI and pathology findings can identify women with truly localised breast cancer who can safely avoid radiotherapy. METHODS: PROSPECT is a prospective, multicentre, two-arm, non-randomised trial of radiotherapy omission in patients selected using preoperative MRI and postoperative tumour pathology. It is being conducted at four academic hospitals in Australia. Women aged 50 years or older with cT1N0 non-triple-negative breast cancer were eligible. Those with apparently unifocal cancer had breast-conserving surgery (BCS) and, if pT1N0 or N1mi, had radiotherapy omitted (group 1). Standard treatment including excision of MRI-detected additional cancers was offered to the others (group 2). All were recommended systemic therapy. The primary outcome was ipsilateral invasive recurrence rate (IIRR) at 5 years in group 1. Primary analysis occurred after the 100th group 1 patient reached 5 years follow-up. Quality-adjusted life-years (QALYs) and cost-effectiveness of the PROSPECT pathway were analysed. This study is registered with the Australian New Zealand Clinical Trials Registry (ACTRN12610000810011). FINDINGS: Between May 17, 2011, and May 6, 2019, 443 patients with breast cancer underwent MRI. Median age was 63·0 years. MRI detected 61 malignant occult lesions separate from the index cancer in 48 patients (11%). Of 201 group 1 patients who had BCS without radiotherapy, the IIRR at 5 years was 1·0% (upper 95% CI 5·4%). In group 1, one local recurrence occurred at 4·5 years and a second at 7·5 years. In group 2, nine patients had mastectomy (2% of total cohort), and the 5-year IIRR was 1·7% (upper 95% CI 6·1%). The only distant metastasis in the entire cohort was genetically distinct from the index cancer. The PROSPECT pathway increased QALYs by 0·019 (95% CI 0·008-0·029) and saved AU$1980 (95% CI 1396-2528) or £953 (672-1216) per patient. INTERPRETATION: PROSPECT suggests that women with unifocal breast cancer on MRI and favourable pathology can safely omit radiotherapy. FUNDING: Breast Cancer Trials, National Breast Cancer Foundation, Cancer Council Victoria, the Royal Melbourne Hospital Foundation, and the Breast Cancer Research Foundation.

VascuViz: a multimodality and multiscale imaging and visualization pipeline for vascular systems biology.

Despite advances in imaging, image-based vascular systems biology has remained challenging because blood vessel data are often available only from a single modality or at a given spatial scale, and cross-modality data are difficult to integrate. Therefore, there is an exigent need for a multimodality pipeline that enables ex vivo vascular imaging with magnetic resonance imaging, computed tomography and optical microscopy of the same sample, while permitting imaging with complementary contrast mechanisms from the whole-organ to endothelial cell spatial scales. To achieve this, we developed 'VascuViz'-an easy-to-use method for simultaneous three-dimensional imaging and visualization of the vascular microenvironment using magnetic resonance imaging, computed tomography and optical microscopy in the same intact, unsectioned tissue. The VascuViz workflow permits multimodal imaging with a single labeling step using commercial reagents and is compatible with diverse tissue types and protocols. VascuViz's interdisciplinary utility in conjunction with new data visualization approaches opens up new vistas in image-based vascular systems biology.

Conditional probabilistic diffusion model driven synthetic radiogenomic applications in breast cancer.

This study addresses the heterogeneity of Breast Cancer (BC) by employing a Conditional Probabilistic Diffusion Model (CPDM) to synthesize Magnetic Resonance Images (MRIs) based on multi-omic data, including gene expression, copy number variation, and DNA methylation. The lack of paired medical images and genomics data in previous studies presented a challenge, which the CPDM aims to overcome. The well-trained CPDM successfully generated synthetic MRIs for 726 TCGA-BRCA patients, who lacked actual MRIs, using their multi-omic profiles. Evaluation metrics such as Frechet's Inception Distance (FID), Mean Square Error (MSE), and Structural Similarity Index Measure (SSIM) demonstrated the CPDM's effectiveness, with an FID of 2.02, an MSE of 0.02, and an SSIM of 0.59 based on the 15-fold cross-validation. The synthetic MRIs were used to predict clinical attributes, achieving an Area Under the Receiver-Operating-Characteristic curve (AUROC) of 0.82 and an Area Under the Precision-Recall Curve (AUPRC) of 0.84 for predicting ER+/HER2+ subtypes. Additionally, the MRIs served to accurately predicted BC patient survival with a Concordance-index (C-index) score of 0.88, outperforming other baseline models. This research demonstrates the potential of CPDMs in generating MRIs based on BC patients' genomic profiles, offering valuable insights for radiogenomic research and advancements in precision medicine. The study provides a novel approach to understanding BC heterogeneity for early detection and personalized treatment.

Resting state functional connectome in breast cancer patients with fear of cancer recurrence.

This study aimed to investigate network-level brain functional changes in breast cancer patients and their relationship with fear of cancer recurrence (FCR). Resting-state functional MRI was collected from 43 patients with breast cancer and 40 healthy controls (HCs). Graph theory analyses, whole-brain voxel-wise functional connectivity strength (FCS) analyses and seed-based functional connectivity (FC) analyses were performed to identify connection alterations in breast cancer patients. Correlations between brain functional connections (i.e. FCS and FC) and FCR level were assessed to further reveal the neural mechanisms of FCR in breast cancer patients. Graph theory analyses indicated a decreased clustering coefficient in breast cancer patients compared to HCs (P = 0.04). Patients with breast cancer exhibited significantly higher FCS in both higher-order function networks (frontoparietal, default mode, and dorsal attention systems) and primary somatomotor networks. Among the hyperconnected regions in breast cancer, the left inferior frontal operculum demonstrated a significant positive correlation with FCR. Our findings suggest that breast cancer patients exhibit less segregation of brain function, and the left inferior frontal operculum is a key region associated with FCR. This study offers insights into the neural mechanisms of FCR in breast cancer patients at the level of brain connectome.

In women aged 45 to 75 y, opt-out vs. opt-in breast cancer screening outreach did not increase mammography rates.

SOURCE CITATION: Marcotte LM, Deeds S, Wheat C, et al. Automated opt-out vs opt-in patient outreach strategies for breast cancer screening: a randomized clinical trial. JAMA Intern Med. 2023;183:1187-1194. 37695621.

Association Between False-Positive Results and Return to Screening Mammography in the Breast Cancer Surveillance Consortium Cohort.

BACKGROUND: False-positive results on screening mammography may affect women's willingness to return for future screening. OBJECTIVE: To evaluate the association between screening mammography results and the probability of subsequent screening. DESIGN: Cohort study. SETTING: 177 facilities participating in the Breast Cancer Surveillance Consortium (BCSC). PATIENTS: 3 529 825 screening mammograms (3 184 482 true negatives and 345 343 false positives) performed from 2005 to 2017 among 1 053 672 women aged 40 to 73 years without a breast cancer diagnosis. MEASUREMENTS: Mammography results (true-negative result or false-positive recall with a recommendation for immediate additional imaging only, short-interval follow-up, or biopsy) from 1 or 2 screening mammograms. Absolute differences in the probability of returning for screening within 9 to 30 months of false-positive versus true-negative screening results were estimated, adjusting for race, ethnicity, age, time since last mammogram, BCSC registry, and clustering within women and facilities. RESULTS: Women were more likely to return after a true-negative result (76.9% [95% CI, 75.1% to 78.6%]) than after a false-positive recall for additional imaging only (adjusted absolute difference, -1.9 percentage points [CI, -3.1 to -0.7 percentage points]), short-interval follow-up (-15.9 percentage points [CI, -19.7 to -12.0 percentage points]), or biopsy (-10.0 percentage points [CI, -14.2 to -5.9 percentage points]). Asian and Hispanic/Latinx women had the largest decreases in the probability of returning after a false positive with a recommendation for short-interval follow-up (-20 to -25 percentage points) or biopsy (-13 to -14 percentage points) versus a true negative. Among women with 2 screening mammograms within 5 years, a false-positive result on the second was associated with a decreased probability of returning for a third regardless of the first screening result. LIMITATION: Women could receive care at non-BCSC facilities. CONCLUSION: Women were less likely to return to screening after false-positive mammography results, especially with recommendations for short-interval follow-up or biopsy, raising concerns about continued participation in routine screening among these women at increased breast cancer risk. PRIMARY FUNDING SOURCE: National Cancer Institute.

USPSTF recommends biennial mammography for breast cancer screening in women aged 40 to 74 y.

SOURCE CITATION: US Preventive Services Task Force; Nicholson WK, Silverstein M, Wong JB, et al. Screening for breast cancer: US Preventive Services Task Force recommendation statement. JAMA. 2024;331:1918-1930. 38687503.

Mammography Screening Preferences Among Screening-Eligible Women in Their 40s : A National U.S. Survey.

BACKGROUND: The U.S. Preventive Services Task Force (USPSTF) recently changed its recommendation for mammography screening from informed decision making to biennial screening for women aged 40 to 49 years. Although many women welcome this change, some may prefer not to be screened at age 40 years. OBJECTIVE: To conduct a national probability-based U.S. survey to investigate breast cancer screening preferences among women aged 39 to 49 years. DESIGN: Pre-post survey with a breast cancer screening decision aid (DA) intervention. (ClinicalTrials.gov: NCT05376241). SETTING: Online national U.S. survey. PARTICIPANTS: 495 women aged 39 to 49 years without a history of breast cancer or a known BRCA1/2 gene mutation. INTERVENTION: A mammography screening DA providing information about screening benefits and harms and a personalized breast cancer risk estimate. MEASUREMENTS: Screening preferences (assessed before and after the DA), 10-year Gail model risk estimate, and whether the information was surprising and different from past messages. RESULTS: Before viewing the DA, 27.0% of participants preferred to delay screening (vs. having mammography at their current age), compared with 38.5% after the DA. There was no increase in the number never wanting mammography (5.4% before the DA vs. 4.3% after the DA). Participants who preferred to delay screening had lower breast cancer risk than those who preferred not to delay. The information about overdiagnosis was surprising for 37.4% of participants versus 27.2% and 22.9% for information about false-positive results and screening benefits, respectively. LIMITATION: Respondent preferences may have been influenced by the then-current USPSTF guideline. CONCLUSION: There are women in their 40s who would prefer to have mammography at an older age, especially after being informed of the benefits and harms of screening. Women who wanted to delay screening were at lower breast cancer risk than women who wanted screening at their current age. Many found information about the benefits and harms of mammography surprising. PRIMARY FUNDING SOURCE: National Cancer Institute.

Construction of a Spatial-Confined Self-Stacking Catalytic Circuit for Rapid and Sensitive Imaging of Piwi-Interacting RNA in Living Cells.

Piwi-interacting RNAs (piRNAs) are small noncoding RNAs that repress transposable elements to maintain genome integrity. The canonical catalytic hairpin assembly (CHA) circuit relies on random collisions of free-diffused reactant probes, which substantially slow down reaction efficiency and kinetics. Herein, we demonstrate the construction of a spatial-confined self-stacking catalytic circuit for rapid and sensitive imaging of piRNA in living cells based on intramolecular and intermolecular hybridization-accelerated CHA. We rationally design a 3WJ probe that not only accelerates the reaction kinetics by increasing the local concentration of reactant probes but also eliminates background signal leakage caused by cross-entanglement of preassembled probes. This strategy achieves high sensitivity and good specificity with shortened assay time. It can quantify intracellular piRNA expression at a single-cell level, discriminate piRNA expression in tissues of breast cancer patients and healthy persons, and in situ image piRNA in living cells, offering a new approach for early diagnosis and postoperative monitoring.

Three-Dimensional Visualization of Breast Cancer Pathology Evolution in Clinical Patient Tissues with NIR-II Imaging.

Breast cancer (BC) is the most common tumor worldwide and requires crucial molecular typing for treatment and prognosis assessment. Currently, approaches like pathological staining, immunohistochemistry (IHC), and immunofluorescence (IF) face limitations due to the low signal-to-background ratio (SBR) and high tumor heterogeneity, resulting in a high misdiagnosis rate. Fluorescent assay in the second near-infrared region (NIR-II, 1000-1700 nm) exhibits ultrahigh SBR owing to diminished scattering and tissue autofluorescence. Here, we present a NIR-II strategy for accurate BC molecular typing and three-dimensional (3D) visualization based on the atomically precise fluorescent Au24Pr1 clusters. Single-atom Pr doping results in 3.9-fold fluorescence enhancement and long-term photostability. The Au24Pr1 clusters possess high fluorescence centered at ∼1100 nm and the SBR on pathological section diagnosis was 4 times higher than that of NIR-I imaging. This enables high spatial resolution 3D visualization of biopsy specimens, which can surmount tissue heterogeneity for clinical diagnosis of BC.

DNA-Mediated Magnetic-Dimer Assembly for Fault-Free Ultra-High-Field Magnetic Resonance Imaging of Tumors.

Ultra-high-field (UHF) magnetic resonance imaging (MRI) stands as a pivotal cornerstone in biomedical imaging, yet the challenge of false imaging persists, constraining its full potential. Despite the development of dual-mode contrast agents improving conventional MRI, their effectiveness in UHF remains suboptimal due to the high magnetic moment, resulting in diminished T1 relaxivity and excessively enhanced T2 relaxivity. Herein, we report a DNA-mediated magnetic-dimer assembly (DMA) of iron oxide nanoparticles that harnesses UHF-tailored nanomagnetism for fault-free UHF-MRI. DMA exhibits a dually enhanced longitudinal relaxivity of 4.42 mM-1·s-1 and transverse relaxivity of 26.23 mM-1·s-1 at 9 T, demonstrating a typical T1-T2 dual-mode UHF-MRI contrast agent. Importantly, DMA leverages T1-T2 dual-modality image fusion to achieve artifact-free breast cancer visualization, effectively filtering interference from hundred-micrometer-level false-positive signals with unprecedented precision. The UHF-tailored T1-T2 dual-mode DMA contrast agents hold promise for elevating the accuracy of MR imaging in disease diagnosis.

MRI-guided optimisation of neoadjuvant chemotherapy duration in stage II-III HER2-positive breast cancer (TRAIN-3): a multicentre, single-arm, phase 2 study.

BACKGROUND: Patients with stage II-III HER2-positive breast cancer have good outcomes with the combination of neoadjuvant chemotherapy and HER2-targeted agents. Although increasing the number of chemotherapy cycles improves pathological complete response rates, early complete responses are common. We investigated whether the duration of chemotherapy could be tailored on the basis of radiological response. METHODS: TRAIN-3 is a single-arm, phase 2 study in 43 hospitals in the Netherlands. Patients with stage II-III HER2-positive breast cancer aged 18 years or older and a WHO performance status of 0 or 1 were enrolled. Patients received neoadjuvant chemotherapy consisting of paclitaxel (80 mg/m2 of body surface area on day 1 and 8 of each 21 day cycle), trastuzumab (loading dose on day 1 of cycle 1 of 8 mg/kg bodyweight, and then 6 mg/kg on day 1 on all subsequent cycles), and carboplatin (area under the concentration time curve 6 mg/mL per min on day 1 of each 3 week cycle) and pertuzumab (loading dose on day 1 of cycle 1 of 840 mg, and then 420 mg on day 1 of each subsequent cycle), all given intravenously. The response was monitored by breast MRI every three cycles and lymph node biopsy. Patients underwent surgery when a complete radiological response was observed or after a maximum of nine cycles of treatment. The primary endpoint was event-free survival at 3 years; however, follow-up for the primary endpoint is ongoing. Here, we present the radiological and pathological response rates (secondary endpoints) of all patients who underwent surgery and the toxicity data for all patients who received at least one cycle of treatment. Analyses were done in hormone receptor-positive and hormone receptor-negative patients separately. This trial is registered with ClinicalTrials.gov, number NCT03820063, recruitment is closed, and the follow-up for the primary endpoint is ongoing. FINDINGS: Between April 1, 2019, and May 12, 2021, 235 patients with hormone receptor-negative cancer and 232 with hormone receptor-positive cancer were enrolled. Median follow-up was 26·4 months (IQR 22·9-32·9) for patients who were hormone receptor-negative and 31·6 months (25·6-35·7) for patients who were hormone receptor-positive. Overall, the median age was 51 years (IQR 43-59). In 233 patients with hormone receptor-negative tumours, radiological complete response was seen in 84 (36%; 95% CI 30-43) patients after one to three cycles, 140 (60%; 53-66) patients after one to six cycles, and 169 (73%; 66-78) patients after one to nine cycles. In 232 patients with hormone receptor-positive tumours, radiological complete response was seen in 68 (29%; 24-36) patients after one to three cycles, 118 (51%; 44-57) patients after one to six cycles, and 138 (59%; 53-66) patients after one to nine cycles. Among patients with a radiological complete response after one to nine cycles, a pathological complete response was seen in 147 (87%; 95% CI 81-92) of 169 patients with hormone receptor-negative tumours and was seen in 73 (53%; 44-61) of 138 patients with hormone receptor-positive tumours. The most common grade 3-4 adverse events were neutropenia (175 [37%] of 467), anaemia (75 [16%]), and diarrhoea (57 [12%]). No treatment-related deaths were reported. INTERPRETATION: In our study, a third of patients with stage II-III hormone receptor-negative and HER2-positive breast cancer had a complete pathological response after only three cycles of neoadjuvant systemic therapy. A complete response on breast MRI could help identify early complete responders in patients who had hormone receptor negative tumours. An imaging-based strategy might limit the duration of chemotherapy in these patients, reduce side-effects, and maintain quality of life if confirmed by the analysis of the 3-year event-free survival primary endpoint. Better monitoring tools are needed for patients with hormone receptor-positive and HER2-positive breast cancer. FUNDING: Roche Netherlands.

Recent advancements in artificial intelligence for breast cancer: Image augmentation, segmentation, diagnosis, and prognosis approaches.

Breast cancer is a significant global health burden, with increasing morbidity and mortality worldwide. Early screening and accurate diagnosis are crucial for improving prognosis. Radiographic imaging modalities such as digital mammography (DM), digital breast tomosynthesis (DBT), magnetic resonance imaging (MRI), ultrasound (US), and nuclear medicine techniques, are commonly used for breast cancer assessment. And histopathology (HP) serves as the gold standard for confirming malignancy. Artificial intelligence (AI) technologies show great potential for quantitative representation of medical images to effectively assist in segmentation, diagnosis, and prognosis of breast cancer. In this review, we overview the recent advancements of AI technologies for breast cancer, including 1) improving image quality by data augmentation, 2) fast detection and segmentation of breast lesions and diagnosis of malignancy, 3) biological characterization of the cancer such as staging and subtyping by AI-based classification technologies, 4) prediction of clinical outcomes such as metastasis, treatment response, and survival by integrating multi-omics data. Then, we then summarize large-scale databases available to help train robust, generalizable, and reproducible deep learning models. Furthermore, we conclude the challenges faced by AI in real-world applications, including data curating, model interpretability, and practice regulations. Besides, we expect that clinical implementation of AI will provide important guidance for the patient-tailored management.

Are better AI algorithms for breast cancer detection also better at predicting risk? A paired case-control study.

BACKGROUND: There is increasing evidence that artificial intelligence (AI) breast cancer risk evaluation tools using digital mammograms are highly informative for 1-6 years following a negative screening examination. We hypothesized that algorithms that have previously been shown to work well for cancer detection will also work well for risk assessment and that performance of algorithms for detection and risk assessment is correlated. METHODS: To evaluate our hypothesis, we designed a case-control study using paired mammograms at diagnosis and at the previous screening visit. The study included n = 3386 women from the OPTIMAM registry, that includes mammograms from women diagnosed with breast cancer in the English breast screening program 2010-2019. Cases were diagnosed with invasive breast cancer or ductal carcinoma in situ at screening and were selected if they had a mammogram available at the screening examination that led to detection, and a paired mammogram at their previous screening visit 3y prior to detection when no cancer was detected. Controls without cancer were matched 1:1 to cases based on age (year), screening site, and mammography machine type. Risk assessment was conducted using a deep-learning model designed for breast cancer risk assessment (Mirai), and three open-source deep-learning algorithms designed for breast cancer detection. Discrimination was assessed using a matched area under the curve (AUC) statistic. RESULTS: Overall performance using the paired mammograms followed the same order by algorithm for risk assessment (AUC range 0.59-0.67) and detection (AUC 0.81-0.89), with Mirai performing best for both. There was also a correlation in performance for risk and detection within algorithms by cancer size, with much greater accuracy for large cancers (30 mm+, detection AUC: 0.88-0.92; risk AUC: 0.64-0.74) than smaller cancers (0 to < 10 mm, detection AUC: 0.73-0.86, risk AUC: 0.54-0.64). Mirai was relatively strong for risk assessment of smaller cancers (0 to < 10 mm, risk, Mirai AUC: 0.64 (95% CI 0.57 to 0.70); other algorithms AUC 0.54-0.56). CONCLUSIONS: Improvements in risk assessment could stem from enhancing cancer detection capabilities of smaller cancers. Other state-of-the-art AI detection algorithms with high performance for smaller cancers might achieve relatively high performance for risk assessment.

Improving lesion detection in mammograms by leveraging a Cycle-GAN-based lesion remover.

BACKGROUND: The wide heterogeneity in the appearance of breast lesions and normal breast structures can confuse computerized detection algorithms. Our purpose was therefore to develop a Lesion Highlighter (LH) that can improve the performance of computer-aided detection algorithms for detecting breast cancer on screening mammograms. METHODS: We hypothesized that a Cycle-GAN based Lesion Remover (LR) could act as an LH, which can improve the performance of lesion detection algorithms. We used 10,310 screening mammograms from 4,832 women that included 4,942 recalled lesions (BI-RADS 0) and 5,368 normal results (BI-RADS 1). We divided the dataset into Train:Validate:Test folds with the ratios of 0.64:0.16:0.2. We segmented image patches (400 × 400 pixels) from either lesions marked by MQSA radiologists or normal tissue in mammograms. We trained a Cycle-GAN to develop two GANs, where each GAN transferred the style of one image to another. We refer to the GAN transferring the style of a lesion to normal breast tissue as the LR. We then highlighted the lesion by color-fusing the mammogram after applying the LR to its original. Using ResNet18, DenseNet201, EfficientNetV2, and Vision Transformer as backbone architectures, we trained three deep networks for each architecture, one trained on lesion highlighted mammograms (Highlighted), another trained on the original mammograms (Baseline), and Highlighted and Baseline combined (Combined). We conducted ROC analysis for the three versions of each deep network on the test set. RESULTS: The Combined version of all networks achieved AUCs ranging from 0.963 to 0.974 for identifying the image with a recalled lesion from a normal breast tissue image, which was statistically improved (p-value < 0.001) over their Baseline versions with AUCs that ranged from 0.914 to 0.967. CONCLUSIONS: Our results showed that a Cycle-GAN based LR is effective for enhancing lesion conspicuity and this can improve the performance of a detection algorithm.

Low-dose acetylsalicylic acid reduces local inflammation and tissue perfusion in dense breast tissue in postmenopausal women.

PURPOSE: One major risk factor for breast cancer is high mammographic density. It has been estimated that dense breast tissue contributes to ~ 30% of all breast cancer. Prevention targeting dense breast tissue has the potential to improve breast cancer mortality and morbidity. Anti-estrogens, which may be associated with severe side-effects, can be used for prevention of breast cancer in women with high risk of the disease per se. However, no preventive therapy targeting dense breasts is currently available. Inflammation is a hallmark of cancer. Although the biological mechanisms involved in the increased risk of cancer in dense breasts is not yet fully understood, high mammographic density has been associated with increased inflammation. We investigated whether low-dose acetylsalicylic acid (ASA) affects local breast tissue inflammation and/or structural and dynamic changes in dense breasts. METHODS: Postmenopausal women with mammographic dense breasts on their regular mammography screen were identified. A total of 53 women were randomized to receive ASA 160 mg/day or no treatment for 6 months. Magnetic resonance imaging (MRI) was performed before and after 6 months for a sophisticated and continuous measure breast density by calculating lean tissue fraction (LTF). Additionally, dynamic quantifications including tissue perfusion were performed. Microdialysis for sampling of proteins in vivo from breasts and abdominal subcutaneous fat, as a measure of systemic effects, before and after 6 months were performed. A panel of 92 inflammatory proteins were quantified in the microdialysates using proximity extension assay. RESULTS: After correction for false discovery rate, 20 of the 92 inflammatory proteins were significantly decreased in breast tissue after ASA treatment, whereas no systemic effects were detected. In the no-treatment group, protein levels were unaffected. Breast density, measured by LTF on MRI, were unaffected in both groups. ASA significantly decreased the perfusion rate. The perfusion rate correlated positively with local breast tissue concentration of VEGF. CONCLUSIONS: ASA may shape the local breast tissue microenvironment into an anti-tumorigenic state. Trials investigating the effects of low-dose ASA and risk of primary breast cancer among postmenopausal women with maintained high mammographic density are warranted. Trial registration EudraCT: 2017-000317-22.

Deep learning applications in breast cancer histopathological imaging: diagnosis, treatment, and prognosis.

Breast cancer is the most common malignant tumor among women worldwide and remains one of the leading causes of death among women. Its incidence and mortality rates are continuously rising. In recent years, with the rapid advancement of deep learning (DL) technology, DL has demonstrated significant potential in breast cancer diagnosis, prognosis evaluation, and treatment response prediction. This paper reviews relevant research progress and applies DL models to image enhancement, segmentation, and classification based on large-scale datasets from TCGA and multiple centers. We employed foundational models such as ResNet50, Transformer, and Hover-net to investigate the performance of DL models in breast cancer diagnosis, treatment, and prognosis prediction. The results indicate that DL techniques have significantly improved diagnostic accuracy and efficiency, particularly in predicting breast cancer metastasis and clinical prognosis. Furthermore, the study emphasizes the crucial role of robust databases in developing highly generalizable models. Future research will focus on addressing challenges related to data management, model interpretability, and regulatory compliance, ultimately aiming to provide more precise clinical treatment and prognostic evaluation programs for breast cancer patients.