RESUMO
Objective:To explore the value of mammography-based radiomics for preoperative prediction of axillary lymph node metastasis in breast carcinoma.Methods:The clinical and X-ray data of female patients with pathologically confirmed breast cancer in Henan People′s Hospital from June 2013 to July 2017 were analyzed retrospectively. A total of 214 patients, aged 30-85 (53±11) years, were randomly divided into training set ( n=153) and verification set ( n=61) according to the ratio of 3∶1. According to pathological findings of the axillary lymph node metastasis, 99 cases were divided into positive group and 115 cases into negative group. The lesions were segmented and extracted in X-ray images of mediolateral oblique (MLO) and cranial caudal (CC). Three, nine and seven axillary lymph node metastasis related histologic features were selected from the high dimensional features of CC, MLO and CC combined MLO images by lasso regression model. According to the characteristics of imaging and clinical characteristics, the prediction model was constructed. The prediction ability of the model was verified by 10% cross validation. Results:The lymph node in positive group was larger than negative groups, the difference was statistically significant ( t=2.611, P<0.05). In the validation set, the area under curve (AUC) values of CC, MLO, CC combined with MLO images, clinical features and clinical features combined with CC and MLO images were 0.680, 0.723, 0.740, 0.558 and 0.714, respectively. Among them, CC combined with MLO images had the highest prediction efficiency, and AUC values were higher than CC alone, MLO images and CC combined with MLO images. Conclusions:Quantitative radiomics features of breast tumor extracted from digital mammograms are helpful for preoperatively predicting axillary lymph node metastasis. Future larger studies are needed to further evaluate these findings.
RESUMO
In order to solve the pathological grading of hepatocellular carcinomas (HCC) which depends on biopsy or surgical pathology invasively, a quantitative analysis method based on radiomics signature was proposed for pathological grading of HCC in non-contrast magnetic resonance imaging (MRI) images. The MRI images were integrated to predict clinical outcomes using 328 radiomics features, quantifying tumour image intensity, shape and text, which are extracted from lesion by manual segmentation. Least absolute shrinkage and selection operator (LASSO) were used to select the most-predictive radiomics features for the pathological grading. A radiomics signature, a clinical model, and a combined model were built. The association between the radiomics signature and HCC grading was explored. This quantitative analysis method was validated in 170 consecutive patients (training dataset: = 125; validation dataset, = 45), and cross-validation with receiver operating characteristic (ROC) analysis was performed and the area under the ROC curve (AUC) was employed as the prediction metric. Through the proposed method, AUC was 0.909 in training dataset and 0.800 in validation dataset, respectively. Overall, the prediction performances by radiomics features showed statistically significant correlations with pathological grading. The results showed that radiomics signature was developed to be a significant predictor for HCC pathological grading, which may serve as a noninvasive complementary tool for clinical doctors in determining the prognosis and therapeutic strategy for HCC.