A multicenter hospital-based diagnosis study of automated breast ultrasound system in detecting breast cancer among Chinese women

Objective： The automated breast ultrasound system（ABUS） is a potential method for breast cancer detection;however, its diagnostic performance remains unclear. We conducted a hospital-based multicenter diagnostic study to evaluate the clinical performance of the ABUS for breast cancer detection by comparing it to handheld ultrasound（HHUS） and mammography（MG）.Methods： Eligible participants underwent HHUS and ABUS testing; women aged 40–69 years additionally underwent MG. Images were interpreted using the Breast Imaging Reporting and Data System（BI-RADS）.Women in the BI-RADS categories 1–2 were considered negative. Women classified as BI-RADS 3 underwent magnetic resonance imaging to distinguish true-and false-negative results. Core aspiration or surgical biopsy was performed in women classified as BI-RADS 4–5, followed by a pathological diagnosis. Kappa values and agreement rates were calculated between ABUS, HHUS and MG.Results： A total of 1,973 women were included in the final analysis. Of these, 1,353（68.6%） and 620（31.4%）were classified as BI-RADS categories 1–3 and 4–5, respectively. In the older age group, the agreement rate and Kappa value between the ABUS and HHUS were 94.0% and 0.860（P〈0.001）, respectively; they were 89.2% and0.735（P〈0.001） between the ABUS and MG, respectively. Regarding consistency between imaging and pathology results, 78.6% of women classified as BI-RADS 4–5 based on the ABUS were diagnosed with precancerous lesions or cancer; which was 7.2% higher than that of women based on HHUS. For BI-RADS 1–2, the false-negative rates of the ABUS and HHUS were almost identical and were much lower than those of MG.Conclusions： We observed a good diagnostic reliability for the ABUS. Considering its performance for breast cancer detection in women with high-density breasts and its lower operator dependence, the ABUS is a promising option for breast cancer detection in China.

Automatic detection of breast lesions in automated 3D breast ultrasound with cross-organ transfer learning

Background Deep convolutional neural networks have garnered considerable attention in numerous machine learning applications,particularly in visual recognition tasks such as image and video analyses.There is a growing interest in applying this technology to diverse applications in medical image analysis.Automated three dimensional Breast Ultrasound is a vital tool for detecting breast cancer,and computer-assisted diagnosis software,developed based on deep learning,can effectively assist radiologists in diagnosis.However,the network model is prone to overfitting during training,owing to challenges such as insufficient training data.This study attempts to solve the problem caused by small datasets and improve model detection performance.Methods We propose a breast cancer detection framework based on deep learning(a transfer learning method based on cross-organ cancer detection)and a contrastive learning method based on breast imaging reporting and data systems(BI-RADS).Results When using cross organ transfer learning and BIRADS based contrastive learning,the average sensitivity of the model increased by a maximum of 16.05%.Conclusion Our experiments have demonstrated that the parameters and experiences of cross-organ cancer detection can be mutually referenced,and contrastive learning method based on BI-RADS can improve the detection performance of the model.

Early prediction of pathological outcomes to neoadjuvant chemotherapy in breast cancer patients using automated breast ultrasound

Objective： Early assessment of response to neoadjuvant chemotherapy （NAC） for breast cancer allows therapy to be individualized. The optimal assessment method has not been established. We investigated the accuracy of automated breast ultrasound （ABUS） to predict pathological outcomes after NAC. Methods： A total of 290 breast cancer patients were eligible for this study. Tumor response after 2 cycles of chemotherapy was assessed using the product change of two largest perpendicular diameters （PC） or the longest diameter change （LDC）. PC and LDC were analyzed on the axial and the coronal planes respectively. Receiver operating characteristic （ROC） curves were used to evaluate overall performance of the prediction methods. Youden＇s indexes were calculated to select the optimal cut-off value for each method. Sensitivity, specificity, positive and negative predictive values （PPV and NPV） and the area under the ROC curve （AUC） were calculated accordingly.Results： ypT0/is was achieved in 42 patients （14.5%） while ypT0 was achieved in 30 patients （10.3%） after NAC. All four prediction methods （PC on axial planes, LDC on axial planes, PC on coronal planes and LDC on coronal planes） displayed high AUCs （all〉0.82）, with the highest of 0.89 [95% confidence interval （95% CI）, 0.83-0.95] when mid-treatment ＆BUS was used to predict final pathological complete remission （pCR）. High sensitivities （85.7%-88.1%） were observed across all four prediction methods while high specificities （81.5%-85.1%） were observed in two methods used PC. The optimal cut-off values defined by our data replicate the WHO and the RECIST criteria. Lower AUCs were observed when mid-treatment ABUS was used to predict poor pathological outcomes. Conclusions：ABUS is a useful tool in early evaluation of pCR after NAC while less reliable when predicting poor pathological outcomes.