Search

Qianqing Ma,1,&ast; Chunyun Shen,2,&ast; Yankun Gao,3,&ast; Yayang Duan,1 Wanyan Li,4 Gensheng Lu,5 Xiachuan Qin,1 Chaoxue Zhang,1 Junli Wang2 1Department of Ultrasound, the First Affiliated Hospital of Anhui Medical University, Hefei, People’s Republic of China; 2Department of Ultrasound, Wuhu No. 2 People’s Hospital, Wuhu, People’s Republic of China; 3Department of Radiology, the First Affiliated Hospital of Anhui Medical University, Hefei, People’s Republic of China; 4Department of Ultrasound, Linquan Country People’s Hospital, Fuyang, People’s Republic of China; 5Department of Pathology, Wuhu No. 2 People’s Hospital, Wuhu, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Junli Wang, Department of Ultrasound, Wuhu No. 2 People’s Hospital, No. 259 Jiuhuashan Road, Jinghu District, Wuhu, Anhui, 241001, People’s Republic of China, Tel +86 18055317022, Email wjl980134@163.com Chaoxue Zhang, Department of Ultrasound, the First Affiliated Hospital of Anhui Medical University, No. 218 Jixi Road, Shushan District, Hefei, Anhui, 230022, People’s Republic of China, Tel +86 13955158023, Email zcxay@163.comBackground: Breast cancer is the most common tumor globally. Automated Breast Volume Scanner (ABVS) and strain elastography (SE) can provide more useful breast information. The use of radiomics combined with ABVS and SE images to predict breast cancer has become a new focus. Therefore, this study developed and validated a radiomics analysis of breast lesions in combination with coronal plane of ABVS and SE to improve the differential diagnosis of benign and malignant breast diseases.Patients and Methods: 620 pathologically confirmed breast lesions from January 2017 to August 2021 were retrospectively analyzed and randomly divided into a training set (n=434) and a validation set (n=186). Radiomic features of the lesions were extracted from ABVS, B-ultrasound, and strain elastography (SE) images, respectively. These were then filtered by Gradient Boosted Decision Tree (GBDT) and multiple logistic regression. The ABVS model is based on coronal plane features for the breast, B+SE model is based on features of B-ultrasound and SE, and the multimodal model is based on features of three examinations. The evaluation of the predicted performance of the three models used the receiver operating characteristic (ROC) and decision curve analysis (DCA).Results: The area under the curve, accuracy, specificity, and sensitivity of the multimodal model in the training set are 0.975 (95% CI:0.959– 0.991),93.78%, 92.02%, and 96.49%, respectively, and 0.946 (95% CI:0.913 − 0.978), 87.63%, 83.93%, and 93.24% in the validation set, respectively. The multimodal model outperformed the ABVS model and B+SE model in both the training (P < 0.001, P = 0.002, respectively) and validation sets (P < 0.001, P = 0.034, respectively).Conclusion: Radiomics from the coronal plane of the breast lesion provide valuable information for identification. A multimodal model combination with radiomics from ABVS, B-ultrasound, and SE could improve the diagnostic efficacy of breast masses.Keywords: radiomics, automated breast volume scanner, strain elastography, ultrasound, breast cancer

To develop and validate a nomogram for predicting the risk of malignancy of breast imaging reporting and data system (BI-RADS) 4A lesions to reduce unnecessary invasive examinations.From January 2017 to July 2021, 190 cases of 4A lesions included in this study were divided into training and validation sets in a ratio of 8:2. Radiomics features were extracted from sonograms by Automatic Breast Volume Scanner (ABVS) and B-ultrasound. We constructed the radiomics model and calculated the rad-scores. Univariate and multivariate logistic regressions were used to assess demographics and lesion elastography values (virtual touch tissue image, shear wave velocity) and to develop clinical model. A clinical radiomics model was developed using rad-score and independent clinical factors, and a nomogram was plotted. Nomogram performance was evaluated using discrimination, calibration, and clinical utility.The nomogram included rad-score, age, and elastography, and showed good calibration. In the training set, the area under the receiver operating characteristic curve (AUC) of the clinical radiomics model (0.900, 95% confidence interval (CI): 0.843-0.958) was superior to that of the radiomics model (0.860, 95% CI: 0.799-0.921) and clinical model (0.816, 95% CI: 0.735-0.958) (p = 0.024 and 0.008, respectively). The decision curve analysis showed that the clinical radiomics model had the highest net benefit in most threshold probability ranges.ABVS and B-ultrasound-based radiomics nomograms have satisfactory performance in differentiating benign and malignant 4A lesions. This can help clinicians make an accurate diagnosis of 4A lesions and reduce unnecessary biopsy.

Prediction of microvascular invasion (MVI) status of hepatocellular carcinoma (HCC) holds clinical significance for decision-making regarding the treatment strategy and evaluation of patient prognosis. We developed a deep learning (DL) model based on contrast-enhanced ultrasound (CEUS) to predict MVI of HCC.We retrospectively analyzed the data for single primary HCCs that were evaluated with CEUS 1 week before surgical resection from December 2014 to February 2022. The study population was divided into training (n = 198) and test (n = 54) cohorts. In this study, three DL models (Resnet50, Resnet50+BAM, Resnet50+SE) were trained using the training cohort and tested in the test cohort. Tumor characteristics were also evaluated by radiologists, and multivariate regression analysis was performed to determine independent indicators for the development of predictive nomogram models. The performance of the three DL models was compared to that of the MVI prediction model based on radiologist evaluations.The best-performing model, ResNet50+SE model achieved the ROC of 0.856, accuracy of 77.2, specificity of 93.9%, and sensitivity of 52.4% in the test group. The MVI prediction model based on a combination of three independent predictors showed a C-index of 0.729, accuracy of 69.4, specificity of 73.8%, and sensitivity of 62%.The DL algorithm can accurately predict MVI of HCC on the basis of CEUS images, to help identify high-risk patients for the assist treatment.