Objective:To explore the value of salivary gland imaging based on deep learning and Delta radiomics in assessing salivary gland injury after 131I treatment in post-thyroidectomy thyroid cancer patients. Methods:A retrospective analysis on 223 patients (46 males, 177 females, age(47.7±14.0) years ) with papillary thyroid cancer, who underwent total thyroidectomy and 131I treatment in Affiliated Hospital of Guilin Medical University between December 2019 and January 2022, was conducted. All patients underwent salivary gland 99Tc mO 4- imaging before and after 131I therapy. The patients were categorized according to salivary gland function based on 99Tc mO 4- imaging results (normal salivary gland vs salivary gland injury), and divided into training and test sets in a ratio of 7∶3. A ResNet-34 neural network model was trained using images at the time of maximum salivary gland radioactivity and those based on background radioactivity counts for structured image feature data. The Delta radiomics approach was then used to subtract the image feature values of the two periods, followed by feature selection through t-test, correlation analysis, and the least absolute shrinkage and selection operator( LASSO) algorithm, to develop logistic regression (LR), support vector machine (SVM), and K-nearest neighbor (KNN) predictive models. The diagnostic performance of 3 models for salivary gland function on the test set was compared with that of the manual interpretation. The AUCs of the 3 models on the test set were compared (Delong test). Results:Among the 67 cases of the test set, the diagnostic accuracy of 3 physicians were 89.6%(60/67), 83.6%(56/67), and 82.1%(55/67) respectively, with the time required for diagnosis of 56, 74 and 55 min, respectively. The accuracies of LR, SVM, and KNN models were 91.0%(61/67), 86.6%(58/67), and 82.1%(55/67), with the required times of 12.5, 15.3 and 17.9 s, respectively. All 3 radiomics models demonstrated good classification and predictive capabilities, with AUC values for the training set of 0.972, 0.965, and 0.943, and for the test set of 0.954, 0.913, and 0.791, respectively. There were no significant differences among the AUC values for the test set ( z values: 0.72, 1.18, 1.82, all P>0.05). Conclusion:The models based on deep learning and Delta radiomics possess high predictive value in assessing salivary gland injury following 131I treatment after surgery in patients with thyroid cancer.

Objective To observe the value of 18F-FDG PET/CT semi-quantitative parameters for predicting spread through air spaces(STAS)of clinical stage Ⅰa—Ⅲa lung adenocarcinoma.Methods Data of 85 patients with clinical stage Ⅰa—Ⅲ a lung adenocarcinoma who underwent preoperative 18F-FDG PET/CT were retrospectively analyzed.The patients were divided into positive group(n=23)or negative group(n=62)according to whether pathology showed STAS or not.Clinical and PET/CT data were compared between groups,and logistic analysis was performed to explore the efficacy of each parameter for predicting STAS.Results Significant differences of gender,carcinoma embryonic antigen,clinical stage,pathological grade,micropapillary growth and proportion were found between groups(all P＜0.05).The maximum,the mean,the peak standard uptake value(SUVmax,SUVmean,SUVpeak),as well as the maximum,the mean and the peak standard uptake value normalized by lean body mass(SULmax,SULmean,SULpeak),also the total lesion glycolysis(TLG)in positive group were all significantly higher than those in negative group(all P＜0.05).Patients'gender,proportion of micropapillary growth,SUVmax and SULmax were all independent risk factors of STAS of clinical stage Ⅰa—Ⅲa lung adenocarcinoma.The area under the curve(AUC)of the above parameters for predicting STAS was 0.666,0.912,0.839 and 0.842,respectively,and of the combination was 0.957.Conclusion 18 F-FDG PET/CT semi-quantitative parameters SUVmax and SULmax were helpful for predicting STAS of clinical stage Ⅰa—Ⅲ a lung adenocarcinoma,and further combination of gender and proportion of micropapillary growth could improve diagnostic efficacy.