•A computer-aided diagnosis (CAD) system was proposed to diagnose breast cancer in ultrasound images.•In this study, we propose a CAD system for tumor diagnosis using an image fusion method combined ...with different image content representations and ensemble different CNN architectures on US images.•The results of our CAD system in the SNUH dataset show that the accuracy, sensitivity, specificity, precision, F1 score, and the AUC of the proposed method were 91.10%, 85.14%, 95.77%, 94.03%, 89.36%, and 0.9697, respectively. The results of our CAD system in the open dataset (BUSI) show that the accuracy, sensitivity, specificity, precision, F1 score, and the AUC of the proposed method were 94.62%, 92.31%, 95.60%, 90%, 91.14%, and 0.9711, respectively.
Breast ultrasound and computer aided diagnosis (CAD) has been used to classify tumors into benignancy or malignancy. However, conventional CAD software has some problems (such as handcrafted features are hard to design; conventional CAD systems are difficult to confirm overfitting problems, etc.). In our study, we propose a CAD system for tumor diagnosis using an image fusion method combined with different image content representations and ensemble different CNN architectures on US images. The CNN-based method proposed in this study includes VGGNet, ResNet, and DenseNet. In our private dataset, there was a total of 1687 tumors that including 953 benign and 734 malignant tumors. The accuracy, sensitivity, specificity, precision, F1 score and the AUC of the proposed method were 91.10%, 85.14%, 95.77%, 94.03%, 89.36%, and 0.9697 respectively. In the open dataset (BUSI), there was a total of 697 tumors that including 437 benign lesions, 210 malignant tumors, and 133 normal images. The accuracy, sensitivity, specificity, precision, F1 score, and the AUC of the proposed method were 94.62%, 92.31%, 95.60%, 90%, 91.14%, and 0.9711. In conclusion, the results indicated different image content representations that affect the prediction performance of the CAD system, more image information improves the prediction performance, and the tumor shape feature can improve the diagnostic effect.
Patients who have residual invasive breast cancer after receiving neoadjuvant chemotherapy plus human epidermal growth factor receptor 2 (HER2)-targeted therapy have a worse prognosis than those who ...have no residual cancer. Trastuzumab emtansine (T-DM1), an antibody-drug conjugate of trastuzumab and the cytotoxic agent emtansine (DM1), a maytansine derivative and microtubule inhibitor, provides benefit in patients with metastatic breast cancer that was previously treated with chemotherapy plus HER2-targeted therapy.
We conducted a phase 3, open-label trial involving patients with HER2-positive early breast cancer who were found to have residual invasive disease in the breast or axilla at surgery after receiving neoadjuvant therapy containing a taxane (with or without anthracycline) and trastuzumab. Patients were randomly assigned to receive adjuvant T-DM1 or trastuzumab for 14 cycles. The primary end point was invasive disease-free survival (defined as freedom from ipsilateral invasive breast tumor recurrence, ipsilateral locoregional invasive breast cancer recurrence, contralateral invasive breast cancer, distant recurrence, or death from any cause).
At the interim analysis, among 1486 randomly assigned patients (743 in the T-DM1 group and 743 in the trastuzumab group), invasive disease or death had occurred in 91 patients in the T-DM1 group (12.2%) and 165 patients in the trastuzumab group (22.2%). The estimated percentage of patients who were free of invasive disease at 3 years was 88.3% in the T-DM1 group and 77.0% in the trastuzumab group. Invasive disease-free survival was significantly higher in the T-DM1 group than in the trastuzumab group (hazard ratio for invasive disease or death, 0.50; 95% confidence interval, 0.39 to 0.64; P<0.001). Distant recurrence as the first invasive-disease event occurred in 10.5% of patients in the T-DM1 group and 15.9% of those in the trastuzumab group. The safety data were consistent with the known safety profile of T-DM1, with more adverse events associated with T-DM1 than with trastuzumab alone.
Among patients with HER2-positive early breast cancer who had residual invasive disease after completion of neoadjuvant therapy, the risk of recurrence of invasive breast cancer or death was 50% lower with adjuvant T-DM1 than with trastuzumab alone. (Funded by F. Hoffmann-La Roche/Genentech; KATHERINE ClinicalTrials.gov number, NCT01772472 .).
MONARCH 2 is a global, randomized, double‐blind, phase 3 study of abemaciclib/placebo + fulvestrant in patients with hormone receptor positive, human epidermal growth factor receptor 2‐negative ...advanced breast cancer. The East Asian population comprised 212 (31.7%) of the 669 intent‐to‐treat population in the MONARCH 2 trial. Consistent with the primary analysis, this subpopulation analysis of East Asian patients indicated progression‐free survival benefit in the abemaciclib arm. The median overall survival was not reached in the abemaciclib arm and was 48.9 months in the placebo arm (hazard ratio 0.80; 95% confidence interval 0.52–1.24; p = 0.377). In addition, other efficacy endpoints, including time to chemotherapy, chemotherapy free survival, and time to second disease progression, indicated benefit in the abemaciclib arm. This analysis found no new safety concerns with longer follow‐up. These findings support the positive benefit–risk balance of the MONARCH 2 regimen in East Asian patients with hormone receptor positive, human epidermal growth factor receptor 2‐negative advanced breast cancer.
MONARCH 2 is a randomized, double‐blind, phase 3 study of abemaciclib/placebo + fulvestrant in patients with hormone receptor positive, human epidermal growth factor receptor 2‐negative advanced breast cancer. We analyzed on OS, PFS, safety, time to chemotherapy, chemotherapy free survival, and time to second disease progression. This subpopulation analysis of East Asian patients indicated the positive benefit‐risk balance of the abemaciclib arm therapy.
Abstract
Background
The incidence of breast cancer among younger East Asian women has been increasing rapidly over recent decades. This international collaborative study systemically compared the ...differences in age-specific incidences and pathological characteristics of breast cancer in East Asian women and women of predominantly European ancestry.
Methods
We excerpted analytic data from six national cancer registries (979 675 cases) and eight hospitals (18 008 cases) in East Asian countries and/or regions and, for comparisons, from the US Surveillance, Epidemiology, and End Results program database. Linear regression analyses of age-specific incidences of female breast cancer and logistic regression analyses of age-specific pathological characteristics of breast cancer were performed. All statistical tests were two-sided.
Results
Unlike female colorectal cancer, the age-specific incidences of breast cancer among East Asian women aged 59 years and younger increased disproportionally over recent decades relative to rates in US contemporaries. For years 2010–2014, the estimated age-specific probability of estrogen receptor positivity increased with age in American patients, whereas that of triple-negative breast cancer (TNBC) declined with age. No similar trends were evident in East Asian patients; their probability of estrogen receptor positivity at age 40–49 years was statistically significantly higher (odd ratio OR = 1.50, 95% confidence interval CI = 1.36 to 1.67, P < .001) and of TNBC was statistically significantly lower (OR = 0.79, 95% CI = 0.71 to 0.88, P < .001), whereas the probability of ER positivity at age 50–59 years was statistically significantly lower (OR = 0.88, 95% CI = 0.828 to 0.95, P < .001). Subgroup analyses of US Surveillance, Epidemiology, and End Results data showed similarly distinct patterns between East Asian American and white American patients.
Conclusions
Contrasting age-specific incidences and pathological characteristics of breast cancer between East Asian and American women, as well as between East Asian Americans and white Americans, suggests racial differences in the biology.
An improvement in progression-free survival was shown with trastuzumab deruxtecan versus trastuzumab emtansine in patients with HER2-positive metastatic breast cancer in the progression-free survival ...interim analysis of the DESTINY-Breast03 trial. The aim of DESTINY-Breast03 was to compare the efficacy and safety of trastuzumab deruxtecan versus trastuzumab emtansine.
This open-label, randomised, multicentre, phase 3 trial was done in 169 study centres in North America, Asia, Europe, Australia, and South America. Eligible patients were aged 18 or older, had HER2-positive unresectable or metastatic breast cancer previously treated with trastuzumab and a taxane, had an Eastern Cooperative Oncology Group performance status 0–1, and at least one measurable lesion per Response Evaluation Criteria in Solid Tumours version 1.1. Patients were randomly assigned (1:1) to receive trastuzumab deruxtecan 5·4 mg/kg or trastuzumab emtansine 3·6 mg/kg, both administered by intravenous infusion every 3 weeks. Randomisation was stratified by hormone receptor status, previous treatment with pertuzumab, and history of visceral disease, and was managed through an interactive web-based system. Within each stratum, balanced block randomisation was used with a block size of four. Patients and investigators were not masked to the treatment received. The primary endpoint was progression-free survival by blinded independent central review. The key secondary endpoint was overall survival and this prespecified second overall survival interim analysis reports updated overall survival, efficacy, and safety results. Efficacy analyses were performed using the full analysis set. Safety analyses included all randomly assigned patients who received at least one dose of study treatment. This study is registered with ClinicalTrials.gov, NCT03529110.
Between July 20, 2018, and June 23, 2020, 699 patients were screened for eligibility, 524 of whom were enrolled and randomly assigned to receive trastuzumab deruxtecan (n=261) or trastuzumab emtansine (n=263). Median duration of study follow-up was 28·4 months (IQR 22·1–32·9) with trastuzumab deruxtecan and 26·5 months (14·5–31·3) with trastuzumab emtansine. Median progression-free survival by blinded independent central review was 28·8 months (95% CI 22·4–37·9) with trastuzumab deruxtecan and 6·8 months (5·6–8·2) with trastuzumab emtansine (hazard ratio HR 0·33 95% CI 0·26–0·43; nominal p<0·0001). Median overall survival was not reached (95% CI 40·5 months–not estimable), with 72 (28%) overall survival events, in the trastuzumab deruxtecan group and was not reached (34·0 months–not estimable), with 97 (37%) overall survival events, in the trastuzumab emtansine group (HR 0·64 95% CI 0·47–0·87; p=0·0037). The number of grade 3 or worse treatment-emergent adverse events was similar in patients who received trastuzumab deruxtecan versus trastuzumab emtansine (145 56% patients versus 135 52% patients). Adjudicated drug-related interstitial lung disease or pneumonitis occurred in 39 (15%) patients treated with trastuzumab deruxtecan and eight (3%) patients treated with trastuzumab emtansine, with no grade 4 or 5 events in either group.
Trastuzumab deruxtecan showed a significant improvement in overall survival versus trastuzumab emtansine in patients with HER2-positive metastatic breast cancer, as well as the longest reported median progression-free survival, reaffirming trastuzumab deruxtecan as the standard of care in the second-line setting. A manageable safety profile of trastuzumab deruxtecan was confirmed with longer treatment duration.
Daiichi Sankyo and AstraZeneca.
This paper performs a comprehensive study on the deep-learning-based computer-aided diagnosis (CADx) for the differential diagnosis of benign and malignant nodules/lesions by avoiding the potential ...errors caused by inaccurate image processing results (e.g., boundary segmentation), as well as the classification bias resulting from a less robust feature set, as involved in most conventional CADx algorithms. Specifically, the stacked denoising auto-encoder (SDAE) is exploited on the two CADx applications for the differentiation of breast ultrasound lesions and lung CT nodules. The SDAE architecture is well equipped with the automatic feature exploration mechanism and noise tolerance advantage, and hence may be suitable to deal with the intrinsically noisy property of medical image data from various imaging modalities. To show the outperformance of SDAE-based CADx over the conventional scheme, two latest conventional CADx algorithms are implemented for comparison. 10 times of 10-fold cross-validations are conducted to illustrate the efficacy of the SDAE-based CADx algorithm. The experimental results show the significant performance boost by the SDAE-based CADx algorithm over the two conventional methods, suggesting that deep learning techniques can potentially change the design paradigm of the CADx systems without the need of explicit design and selection of problem-oriented features.
Abstract Purpose Recognizing molecular markers is helpful for guiding treatment plans for breast cancer. This study correlated estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), ...and triple-negative breast cancer (TNBC) statuses to the degree of heterogeneity on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Materials and Methods A total of 102 biopsy-proven cancers from 102 patients between October 2010 and December 2012 were used in this study, including ER (59 positive, 43 negative), HER2 (47 positive, 55 negative), and TNBC (22 TNBC, 80 non-TNBC). At first, the tumor region was segmented by using a region growing method. Then, the region-based features were extracted by the proposed regionalization method to quantify intra-tumoral heterogeneity on breast DCE-MRI. The three-dimensional morphological features (texture features and shape feature) and the pharmacokinetic model were also extracted from the segmented tumor region. After feature extraction, a logistic regression was used to classify ER, HER2, and TNBC statuses respectively. The performances were evaluated by using receiver operating characteristic curve (ROC) curve analysis. Results The proposed region-based features achieved the accuracy of 73.53%, 82.35%, and 77.45% for ER, HER2, and TNBC classification. The corresponding area under the ROC curves (Az) achieves 0.7320, 0.8458, and 0.8328 that were better than those of texture features, shape features, and Tofts pharmacokinetic model. Conclusion The intra-tumoral heterogeneity quantified by the region-based features can be used to reflect the vasculature complexity of different molecular markers and to provide prediction information of cell surface receptors on clinical examination.
Summary Background Findings from the randomised phase 3 NeoALTTO trial in women with HER2-positive early breast cancer showed that the combination of lapatinib and trastuzumab significantly improved ...rates of pathological complete response compared with either drug alone. Here, we report data for the prespecified secondary endpoints of event-free and overall survival, and assess the association between these outcomes and pathological complete response. Methods We enrolled women with HER2-positive early breast cancer and randomly assigned them to receive oral lapatinib (1500 mg), intravenous trastuzumab (4 mg/kg loading dose followed by 2 mg/kg), or lapatinib (1000 mg) plus trastuzumab (same dose as for single agent) in combination for 6 weeks, followed by an additional 12 weeks of the assigned anti-HER2 therapy in combination with weekly paclitaxel (80 mg/m2 ). Definitive surgery was done 4 weeks after the last dose of paclitaxel. After surgery, women received three cycles of FEC (fluorouracil 500 mg/m2 plus epirubicin 100 mg/m2 plus cyclophosphamide 500 mg/m2 ) given intravenously every 3 weeks, followed by 34 weeks of the same assigned neoadjuvant anti-HER2 therapy. The primary endpoint was pathological complete response. Secondary endpoints included event-free and overall survival (intention-to-treat analysis), and the association between pathological complete response and event-free or overall survival (analysed by landmark analysis at 30 weeks after randomisation). Follow-up is ongoing, and the trial is registered with ClinicalTrials.gov , number NCT00553358. Findings 455 patients were enrolled: 154 (34%) were assigned to the lapatinib group, 149 (33%) to the trastuzumab group, and 152 (33%) to the lapatinib plus trastuzumab group. At an event follow-up of 3·77 years (IQR 3·50–4·22), 3-year event-free survival was 78% (95% CI 70–84) in the lapatinib group, 76% (68–82) in the trastuzumab group, and 84% (77–89) in the combination group. Event-free survival did not differ between the lapatinib and trastuzumab groups (HR 1·06, 95% CI 0·66–1·69, p=0·81), nor between the combination and trastuzumab groups (0·78, 0·47–1·28, p=0·33). Median survival follow-up was 3·84 years (IQR 3·60–4·24), and 3-year overall survival was 93% (95% CI 87–96) for lapatinib, 90% (84–94) for trastuzumab, and 95% (90–98) for combination therapy. Overall survival did not significantly differ between the lapatinib and trastuzumab groups (HR 0·86, 95% CI 0·45–1·63, p=0·65), nor between the combination and trastuzumab groups (0·62, 0·30–1·25, p=0·19). Landmark analyses showed that 3-year event-free survival was significantly improved for women who achieved pathological complete response compared with those who did not (HR 0·38, 95% CI 0·22–0·63, p=0·0003), as was 3-year overall survival (0·35, 0·15–0·70, p=0·005). Adverse events occurred in 149 (99%) patients receiving lapatinib, 142 (96%) patients receiving trastuzumab, and 147 (99%) patients receiving combination therapy. The most common adverse events were diarrhoea, rash or erythema, hepatic adverse events, and neutropenia (not related to FEC administration), and were consistent with known safety profiles of lapatinib and trastuzumab. Three primary and eight secondary cardiac events occurred, with no significant difference in incidence between treatment groups for primary or any cardiac events. Interpretation Although event-free survival or overall survival did not differ between treatment groups, findings from our study confirm that patients who achieve pathological complete response after neoadjuvant anti-HER2 therapy have longer event-free and overall survival than do patients without pathological complete response. Funding GlaxoSmithKline.
HER2-targeted treatments have improved outcomes in patients with HER2-positive breast cancer in the neoadjuvant, adjuvant, and metastatic settings; however, some patients remain at risk of relapse or ...death for many years after treatment of early-stage disease. Therefore, new strategies are needed. We did a phase 3 trial to assess a neoadjuvant regimen for HER2-positive breast cancer that replaces traditional systemic chemotherapy with targeted treatment.
We did a randomised, open-label phase 3 KRISTINE trial in 68 Translational Research In Oncology centres (hospitals and specialty cancer centres in Asia, Europe, USA, and Canada). Eligible participants were aged 18 years or older with centrally confirmed HER2-positive stage II–III operable breast cancer (>2 cm tumour size), an Eastern Cooperative Oncology Group performance status of 0–1, and a baseline left ventricular ejection fraction of at least 55% (by echocardiogram or multiple-gated acquisition scan). We randomly assigned participants (1:1) to receive either trastuzumab emtansine plus pertuzumab or docetaxel, carboplatin, and trastuzumab plus pertuzumab. We did the randomisation via an interactive response system under a permuted block randomisation scheme (block size of four), stratified by hormone receptor status, stage at diagnosis, and geographical location. Patients received six cycles (every 3 weeks) of neoadjuvant trastuzumab emtansine plus pertuzumab (trastuzumab emtansine 3·6 mg/kg; pertuzumab 840 mg loading dose, 420 mg maintenance doses) or docetaxel, carboplatin, and trastuzumab plus pertuzumab (docetaxel 75 mg/m2; carboplatin area under the concentration–time curve 6 mg/mL × min; trastuzumab 8 mg/kg loading dose, 6 mg/kg maintenance doses) plus pertuzumab same dosing as in the other group). All treatments were administered intravenously. The primary objective was to compare the number of patients who achieved a pathological complete response (ypT0/is, ypN0), between groups in the intention-to-treat population (two-sided assessment), based on local evaluation of tumour samples taken at breast cancer surgery done between 14 days and 6 weeks after completion of neoadjuvant therapy. Safety was analysed in patients who received at least one dose of study medication. This trial is registered with ClinicalTrials.gov, number NCT02131064, and follow-up of the adjuvant phase is ongoing.
Between June 25, 2014, and June 15, 2015, we randomly assigned 444 patients to neoadjuvant treatment with trastuzumab emtansine plus pertuzumab (n=223) or docetaxel, carboplatin, and trastuzumab plus pertuzumab (n=221). A pathological complete response was achieved by 99 (44·4%) of 223 patients in the trastuzumab emtansine plus pertuzumab group and 123 (55·7%) of 221 patients in the docetaxel, carboplatin, and trastuzumab plus pertuzumab group (absolute difference −11·3 percentage points, 95% CI −20·5 to −2·0; p=0·016). During neoadjuvant treatment, compared with patients receiving docetaxel, carboplatin, and trastuzumab plus pertuzumab, fewer patients receiving trastuzumab emtansine plus pertuzumab had a grade 3–4 adverse event (29 13% of 223 vs 141 64% of 219) or a serious adverse event (11 5% of 223 vs 63 29% of 219). The most common grade 3–4 adverse events in the trastuzumab emtansine plus pertuzumab group were decreased platelet count (three 1% of 223 patients vs 11 5% of 219 with docetaxel, carboplatin, and trastuzumab plus pertuzumab), fatigue (three 1% vs seven 3%), alanine aminotransferase increase (three 1% vs four 2%), and hypokalaemia (three 1% vs five 2%). The most common grade 3–4 adverse events in the docetaxel, carboplatin, and trastuzumab plus pertuzumab group were neutropenia (55 25% of 219 vs one <1% of 223 with trastuzumab emtansine plus pertuzumab), diarrhoea (33 15% vs 2 <1%), and febrile neutropenia (33 15% vs 0). No deaths were reported during neoadjuvant treatment.
Traditional neoadjuvant systemic chemotherapy plus dual HER2-targeted blockade (docetaxel, carboplatin, and trastuzumab plus pertuzumab) resulted in significantly more patients achieving a pathological complete response than HER2-targeted chemotherapy plus HER2-targeted blockade (trastuzumab emtansine plus pertuzumab); however, numerically more grade 3–4 and serious adverse events occurred in the chemotherapy plus trastuzumab and pertuzumab group. Further efforts to improve the efficacy of chemotherapy without imparting more toxicity are warranted.
F Hoffmann-La Roche and Genentech.