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.

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.

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.

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.

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.

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.

Development of a machine learning-based radiomics signature for estimating breast cancer TME phenotypes and predicting anti-PD-1/PD-L1 immunotherapy response.

BACKGROUNDS: Since breast cancer patients respond diversely to immunotherapy, there is an urgent need to explore novel biomarkers to precisely predict clinical responses and enhance therapeutic efficacy. The purpose of our present research was to construct and independently validate a biomarker of tumor microenvironment (TME) phenotypes via a machine learning-based radiomics way. The interrelationship between the biomarker, TME phenotypes and recipients' clinical response was also revealed. METHODS: In this retrospective multi-cohort investigation, five separate cohorts of breast cancer patients were recruited to measure breast cancer TME phenotypes via a radiomics signature, which was constructed and validated by integrating RNA-seq data with DCE-MRI images for predicting immunotherapy response. Initially, we constructed TME phenotypes using RNA-seq of 1089 breast cancer patients in the TCGA database. Then, parallel DCE-MRI images and RNA-seq of 94 breast cancer patients obtained from TCIA were applied to develop a radiomics-based TME phenotypes signature using random forest in machine learning. The repeatability of the radiomics signature was then validated in an internal validation set. Two additional independent external validation sets were analyzed to reassess this signature. The Immune phenotype cohort (n = 158) was divided based on CD8 cell infiltration into immune-inflamed and immune-desert phenotypes; these data were utilized to examine the relationship between the immune phenotypes and this signature. Finally, we utilized an Immunotherapy-treated cohort with 77 cases who received anti-PD-1/PD-L1 treatment to evaluate the predictive efficiency of this signature in terms of clinical outcomes. RESULTS: The TME phenotypes of breast cancer were separated into two heterogeneous clusters: Cluster A, an "immune-inflamed" cluster, containing substantial innate and adaptive immune cell infiltration, and Cluster B, an "immune-desert" cluster, with modest TME cell infiltration. We constructed a radiomics signature for the TME phenotypes ([AUC] = 0.855; 95% CI 0.777-0.932; p < 0.05) and verified it in an internal validation set (0.844; 0.606-1; p < 0.05). In the known immune phenotypes cohort, the signature can identify either immune-inflamed or immune-desert tumor (0.814; 0.717-0.911; p < 0.05). In the Immunotherapy-treated cohort, patients with objective response had higher baseline radiomics scores than those with stable or progressing disease (p < 0.05); moreover, the radiomics signature achieved an AUC of 0.784 (0.643-0.926; p < 0.05) for predicting immunotherapy response. CONCLUSIONS: Our imaging biomarker, a practicable radiomics signature, is beneficial for predicting the TME phenotypes and clinical response in anti-PD-1/PD-L1-treated breast cancer patients. It is particularly effective in identifying the "immune-desert" phenotype and may aid in its transformation into an "immune-inflamed" phenotype.

Contrast-enhanced ultrasound to predict malignant upgrading of atypical ductal hyperplasia.

BACKGROUND: A malignancy might be found at surgery in cases of atypical ductal hyperplasia (ADH) diagnosed via US-guided core needle biopsy (CNB). The objective of this study was to investigate the diagnostic performance of contrast-enhanced ultrasound (CEUS) in predicting ADH diagnosed by US-guided CNB that was upgraded to malignancy after surgery. METHODS: In this retrospective study, 110 CNB-diagnosed ADH lesions in 109 consecutive women who underwent US, CEUS, and surgery between June 2018 and June 2023 were included. CEUS was incorporated into US BI-RADS and yielded a CEUS-adjusted BI-RADS. The diagnostic performance of US BI-RADS and CEUS-adjusted BI-RADS for ADH were analyzed and compared. RESULTS: The mean age of the 109 women was 49.7 years ± 11.6 (SD). The upgrade rate of ADH at CNB was 48.2% (53 of 110). The sensitivity, specificity, positive predictive value, and negative predictive value of CEUS for identification of malignant upgrading were 96.2%, 66.7%,72.9%, and 95.0%, respectively, based on BI-RADS category 4B threshold. The two false-negative cases were low-grade ductal carcinoma in situ. Compared with the US, CEUS-adjusted BI-RADS had better specificity for lesions smaller than 2 cm (76.7% vs. 96.7%, P = 0.031). After CEUS, 16 (10 malignant and 6 nonmalignant) of the 45 original US BI-RADS category 4A lesions were up-classified to BI-RADS 4B, and 3 (1 malignant and 2 nonmalignant) of the 41 original US BI-RADS category 4B lesions were down-classified to BI-RADS 4A. CONCLUSIONS: CEUS is helpful in predicting malignant upgrading of ADH, especially for lesions smaller than 2 cm and those classified as BI-RADS 4A and 4B on ultrasound.

A prospective study on tumour response assessment methods after neoadjuvant endocrine therapy in early oestrogen receptor-positive breast cancer.

BACKGROUND: Neoadjuvant endocrine therapy (NET) in oestrogen receptor-positive (ER+) /HER2-negative (HER2-) breast cancer allows real-time evaluation of drug efficacy as well as investigation of the biological and molecular changes that occur after estrogenic deprivation. Clinical and pathological evaluation after NET may be used to obtain prognostic and predictive information of tumour response to decide adjuvant treatment. In this setting, clinical scales developed to evaluate response after neoadjuvant chemotherapy are not useful and there are not validated biomarkers to assess response to NET beyond Ki67 levels and preoperative endocrine prognostic index score (mPEPI). METHODS: In this prospective study, we extensively analysed radiological (by ultrasound scan (USS) and magnetic resonance imaging (MRI)) and pathological tumour response of 104 postmenopausal patients with ER+ /HER2- resectable breast cancer, treated with NET for a mean of 7 months prior to surgery. We defined a new score, tumour cellularity size (TCS), calculated as the product of the residual tumour cellularity in the surgical specimen and the tumour pathological size. RESULTS: Our results show that radiological evaluation of response to NET by both USS and MRI underestimates pathological tumour size (path-TS). Tumour size [mean (range); mm] was: path-TS 20 (0-80); radiological-TS by USS 9 (0-31); by MRI: 12 (0-60). Nevertheless, they support the use of MRI over USS to clinically assess radiological tumour response (rad-TR) due to the statistically significant association of rad-TR by MRI, but not USS, with Ki67 decrease (p = 0.002 and p = 0.3, respectively) and mPEPI score (p = 0.002 and p = 0.6, respectively). In addition, we propose that TCS could become a new tool to standardize response assessment to NET given its simplicity, reproducibility and its good correlation with existing biomarkers (such as ΔKi67, p = 0.001) and potential added value. CONCLUSION: Our findings shed light on the dynamics of tumour response to NET, challenge the paradigm of the ability of NET to decrease surgical volume and point to the utility of the TCS to quantify the scattered tumour response usually produced by endocrine therapy. In the future, these results should be validated in independent cohorts with associated survival data.

Optimising the diagnostic accuracy of First post-contrAst SubtracTed breast MRI (FAST MRI) through interpretation-training: a multicentre e-learning study, mapping the learning curve of NHS Breast Screening Programme (NHSBSP) mammogram readers using an enriched dataset.

BACKGROUND: Abbreviated breast MRI (FAST MRI) is being introduced into clinical practice to screen women with mammographically dense breasts or with a personal history of breast cancer. This study aimed to optimise diagnostic accuracy through the adaptation of interpretation-training. METHODS: A FAST MRI interpretation-training programme (short presentations and guided hands-on workstation teaching) was adapted to provide additional training during the assessment task (interpretation of an enriched dataset of 125 FAST MRI scans) by giving readers feedback about the true outcome of each scan immediately after each scan was interpreted (formative assessment). Reader interaction with the FAST MRI scans used developed software (RiViewer) that recorded reader opinions and reading times for each scan. The training programme was additionally adapted for remote e-learning delivery. STUDY DESIGN: Prospective, blinded interpretation of an enriched dataset by multiple readers. RESULTS: 43 mammogram readers completed the training, 22 who interpreted breast MRI in their clinical role (Group 1) and 21 who did not (Group 2). Overall sensitivity was 83% (95%CI 81-84%; 1994/2408), specificity 94% (95%CI 93-94%; 7806/8338), readers' agreement with the true outcome kappa = 0.75 (95%CI 0.74-0.77) and diagnostic odds ratio = 70.67 (95%CI 61.59-81.09). Group 1 readers showed similar sensitivity (84%) to Group 2 (82% p = 0.14), but slightly higher specificity (94% v. 93%, p = 0.001). Concordance with the ground truth increased significantly with the number of FAST MRI scans read through the formative assessment task (p = 0.002) but by differing amounts depending on whether or not a reader had previously attended FAST MRI training (interaction p = 0.02). Concordance with the ground truth was significantly associated with reading batch size (p = 0.02), tending to worsen when more than 50 scans were read per batch. Group 1 took a median of 56 seconds (range 8-47,466) to interpret each FAST MRI scan compared with 78 (14-22,830, p < 0.0001) for Group 2. CONCLUSIONS: Provision of immediate feedback to mammogram readers during the assessment test set reading task increased specificity for FAST MRI interpretation and achieved high diagnostic accuracy. Optimal reading-batch size for FAST MRI was 50 reads per batch. Trial registration (25/09/2019): ISRCTN16624917.

Enhancing pathological complete response prediction in breast cancer: the role of dynamic characterization of DCE-MRI and its association with tumor heterogeneity.

BACKGROUND: Early prediction of pathological complete response (pCR) is important for deciding appropriate treatment strategies for patients. In this study, we aimed to quantify the dynamic characteristics of dynamic contrast-enhanced magnetic resonance images (DCE-MRI) and investigate its value to improve pCR prediction as well as its association with tumor heterogeneity in breast cancer patients. METHODS: The DCE-MRI, clinicopathologic record, and full transcriptomic data of 785 breast cancer patients receiving neoadjuvant chemotherapy were retrospectively included from a public dataset. Dynamic features of DCE-MRI were computed from extracted phase-varying radiomic feature series using 22 CAnonical Time-sereis CHaracteristics. Dynamic model and radiomic model were developed by logistic regression using dynamic features and traditional radiomic features respectively. Various combined models with clinical factors were also developed to find the optimal combination and the significance of each components was evaluated. All the models were evaluated in independent test set in terms of area under receiver operating characteristic curve (AUC). To explore the potential underlying biological mechanisms, radiogenomic analysis was implemented on patient subgroups stratified by dynamic model to identify differentially expressed genes (DEGs) and enriched pathways. RESULTS: A 10-feature dynamic model and a 4-feature radiomic model were developed (AUC = 0.688, 95%CI: 0.635-0.741 and AUC = 0.650, 95%CI: 0.595-0.705) and tested (AUC = 0.686, 95%CI: 0.594-0.778 and AUC = 0.626, 95%CI: 0.529-0.722), with the dynamic model showing slightly higher AUC (train p = 0.181, test p = 0.222). The combined model of clinical, radiomic, and dynamic achieved the highest AUC in pCR prediction (train: 0.769, 95%CI: 0.722-0.816 and test: 0.762, 95%CI: 0.679-0.845). Compared with clinical-radiomic combined model (train AUC = 0.716, 95%CI: 0.665-0.767 and test AUC = 0.695, 95%CI: 0.656-0.714), adding the dynamic component brought significant improvement in model performance (train p < 0.001 and test p = 0.005). Radiogenomic analysis identified 297 DEGs, including CXCL9, CCL18, and HLA-DPB1 which are known to be associated with breast cancer prognosis or angiogenesis. Gene set enrichment analysis further revealed enrichment of gene ontology terms and pathways related to immune system. CONCLUSION: Dynamic characteristics of DCE-MRI were quantified and used to develop dynamic model for improving pCR prediction in breast cancer patients. The dynamic model was associated with tumor heterogeniety in prognostic-related gene expression and immune-related pathways.

Deep learning of mammogram images to reduce unnecessary breast biopsies: a preliminary study.

BACKGROUND: Patients with a Breast Imaging Reporting and Data System (BI-RADS) 4 mammogram are currently recommended for biopsy. However, 70-80% of the biopsies are negative/benign. In this study, we developed a deep learning classification algorithm on mammogram images to classify BI-RADS 4 suspicious lesions aiming to reduce unnecessary breast biopsies. MATERIALS AND METHODS: This retrospective study included 847 patients with a BI-RADS 4 breast lesion that underwent biopsy at a single institution and included 200 invasive breast cancers, 200 ductal carcinoma in-situ (DCIS), 198 pure atypias, 194 benign, and 55 atypias upstaged to malignancy after excisional biopsy. We employed convolutional neural networks to perform 4 binary classification tasks: (I) benign vs. all atypia + invasive + DCIS, aiming to identify the benign cases for whom biopsy may be avoided; (II) benign + pure atypia vs. atypia-upstaged + invasive + DCIS, aiming to reduce excision of atypia that is not upgraded to cancer at surgery; (III) benign vs. each of the other 3 classes individually (atypia, DCIS, invasive), aiming for a precise diagnosis; and (IV) pure atypia vs. atypia-upstaged, aiming to reduce unnecessary excisional biopsies on atypia patients. RESULTS: A 95% sensitivity for the "higher stage disease" class was ensured for all tasks. The specificity value was 33% in Task I, and 25% in Task II, respectively. In Task III, the respective specificity value was 30% (vs. atypia), 30% (vs. DCIS), and 46% (vs. invasive tumor). In Task IV, the specificity was 35%. The AUC values for the 4 tasks were 0.72, 0.67, 0.70/0.73/0.72, and 0.67, respectively. CONCLUSION: Deep learning of digital mammograms containing BI-RADS 4 findings can identify lesions that may not need breast biopsy, leading to potential reduction of unnecessary procedures and the attendant costs and stress.