ABSTRACT
Objective To investigate the clinical value of radiomics nomogram,which is established by 18F-fluorodeoxyglucose (FDG) PET/CT radiomics signature combined with clinical-pathologic risk factors,in predicting the prognosis of patients with postoperative gastric carcinoma.Methods 18F-FDG PET/CT data of 207 patients (143 males,64 females,age range:20-85 years) with postoperative gastric carcinoma from January 2008 to August 2015 was reviewed retrospectively.Patients were divided into training group (n=104) and validation group (n =103),and the clinicopathologic information and disease-free survival (DFS) data were acquired.Significant textural features were selected from PET/CT images,and radiomics score (RS) for individual patient was calculated based on the radiomics signatures.The relationship between RS and DFS was analyzed.Cox regression analysis was performed to determine the risk factors ofDFS.The radiomics nomo-gram,obtained from combination of RS with clinicopathologic risk factors,was established and further evaluated in predictive value for recurrence or metastasis of postoperative gastric carcinoma,and the concordance index (C-index) was calculated.Results Cox regression analysis demonstrated that RS,tumor location,depth of invasion,lymph node metastasis,and distant metastasis were the significant risk factors for DFS (hazard ratios:2.148-2.828,all P＜0.05).The radiomics nomogram combined with RS and 4 clinicopathologic risk factors had a better prediction for the estimated DFS,comparing to RS alone.C-index of radiomics nomogram and RS were 0.830 and 0.700 in training group,and 0.776 and 0.681 in validation group,respectively.Conclusion Radiomics nomogram which is established by radiomics signatures and clinicopathologic risk factors may be better for predicting DFS of patients with postoperative gastric carcinoma.
ABSTRACT
Objective To evaluate the diagnostic performance of digital breast tomosynthesis (DBT) breast X-ray photography image texture characteristics based deep learning classification model on differentiating malignant masses. Methods Retrospectively collected 132 cases with simplex breast lesions (89 benign lesions and 43 malignant lesions) which were confirmed by pathology and DBT during January 2016 to December 2016 in Nanfang Hospital. DBT was performed before biopsy and surgery. Image of cranio-caudal view (CC) and medio-lateral oblique (MLO) were captured. The lesion area was segmented to acquire ROI by ITK-SNAP software. Then the processed images were input into MATLAB R2015b to establish a feature model for extracting texture features. The characteristics with high correlation was analyzed from Fisher score and one sample t test. We built up support vector machine (SVM) classification model based on extracted texture and added neural network model (CNN) for deep learning classification model. We randomly assigned collected cases into training group and validation group. The diagnosis of benign and malignant lesions were served as the reference. The efficiency was evaluated by ROC classification model. Result We extracted 82 texture characteristics from 132 images of leisure (132 images of CC and 132 images of MLO) by establishing deep learning classification model of breast lesions. We randomly chose and combined characteristics from 15 texture characteristics with statistical significance, then differentiated benign and malignant by SVM classification model. After 50 iterations on each combination of characteristics, the average diagnostic efficacy was compared to obtained the one with higher efficacy. Nine of CC and 8 of MLO was selected. The result showed that the sensitivity, specificity, accuracy and area under curve (AUC) of the model to differentiate simplex breast lesions for CC were 0.68, 0.77, 0.74 and 0.74, for MLO were 0.71, 0.71, 0.71 and 0.76. Conclusions MLO has better diagnostic performance for the diagnosis than CC. The deep learning classification model on breast lesions which was built upon DBT image texture characteristics on MLO could differentiate malignant masses effectively.