Search

ObjectivesTo build and evaluate a deep learning radiomics nomogram (DLRN) for preoperative prediction of lung metastasis (LM) status in patients with soft tissue sarcoma (STS).MethodsIn total, 242 patients with STS (training set, n=116; external validation set, n=126) who underwent magnetic resonance imaging were retrospectively enrolled in this study. We identified independent predictors for LM-status and evaluated their performance. The minimum redundancy maximum relevance (mRMR) method and least absolute shrinkage and selection operator (LASSO) algorithm were adopted to screen radiomics features. Logistic regression, decision tree, random forest, support vector machine (SVM), and adaptive boosting classifiers were compared for their ability to predict LM. To overcome the imbalanced distribution of the LM data, we retrained each machine-learning classifier using the synthetic minority over-sampling technique (SMOTE). A DLRN combining the independent clinical predictors with the best performing radiomics prediction signature (mRMR+LASSO+SVM+SMOTE) was established. Area under the receiver operating characteristics curve (AUC), calibration curves, and decision curve analysis (DCA) were used to assess the performance and clinical applicability of the models.ResultComparisons of the AUC values applied to the external validation set revealed that the DLRN model (AUC=0.833) showed better prediction performance than the clinical model (AUC=0.664) and radiomics model (AUC=0.799). The calibration curves indicated good calibration efficiency and the DCA showed the DLRN model to have greater clinical applicability than the other two models.ConclusionThe DLRN was shown to be an accurate and efficient tool for LM-status prediction in STS.

Background: Alkylating agents are critical therapeutic options for melanoma, while dacarbazine (DTIC)-based chemotherapy showed poor sensitivity in clinical trials. Long non-coding RNAs (lncRNAs) were highlighted in the progression of malignant tumors in recent years, whereas little was known about their involvement in melanoma.Methods: The functional role and molecular mechanism of lncRNA POU3F3 were evaluated on DTIC-resistant melanoma cells. Further studies analyzed its clinical role in the disease progression of melanoma.Results: We observed elevated the expression of lncRNA POU3F3 in the DTIC-resistant melanoma cells. Gain-of-function assays showed that the overexpression of lncRNA POU3F3 maintained cell survival with DTIC treatment, while the knockdown of lncRNA POU3F3 restored cell sensitivity to DTIC. A positive correlation of the expression O6-methylguanine-DNA-methyltransferase (MGMT) was observed with lncRNA POU3F3 in vitro and in vivo. Bioinformatic analyses predicted that miR-650 was involved in the lncRNA POU3F3-regulated MGMT expression. Molecular analysis indicated that lncRNA POU3F3 worked as a competitive endogenous RNA to regulate the levels of miR-650, and the lncRNA POU3F3/miR-650 axis determined the transcription of MGMT in melanoma cells to a greater extent. Further clinical studies supported that lncRNA POU3F3 was a risk factor for the disease progression of melanoma.Conclusion: LncRNA POU3F3 upregulated the expression of MGMT by sponging miR-650, which is a crucial way for DTIC resistance in melanoma. Our results indicated that lncRNA POU3F3 was a valuable biomarker for the disease progression of melanoma.

PurposeTo establish various radiomics models based on conventional CT scan images and enhanced CT images, explore their value in the classification of pheochromocytoma (PHEO) and lipid-poor adrenal adenoma (LPA) and screen the most parsimonious and efficient modelMethodsThe clinical and imaging data of 332 patients (352 lesions) with PHEO or LPA confirmed by surgical pathology in the Affiliated Hospital of Qingdao University were retrospectively analyzed. The region of interest (ROI) on conventional and enhanced CT images was delineated using ITK-SNAP software. Different radiomics signatures were constructed from the radiomics features extracted from conventional and enhanced CT images, and a radiomics score (Rad score) was calculated. A clinical model was established using demographic features and CT findings, while radiomics nomograms were established using multiple logistic regression analysis.The predictive efficiency of different models was evaluated using the area under curve (AUC) and receiver operating characteristic (ROC) curve. The Delong test was used to evaluate whether there were statistical differences in predictive efficiency between different models.ResultsThe radiomics signature based on conventional CT images showed AUCs of 0.97 (training cohort, 95% CI: 0.95∼1.00) and 0.97 (validation cohort, 95% CI: 0.92∼1.00). The AUCs of the nomogram model based on conventional scan CT images and enhanced CT images in the training cohort and the validation cohort were 0.97 (95% CI: 0.95∼1.00) and 0.97 (95% CI: 0.94~1.00) and 0.98 (95% CI: 0.97∼1.00) and 0.97 (95% CI: 0.94∼1.00), respectively. The prediction efficiency of models based on enhanced CT images was slightly higher than that of models based on conventional CT images, but these differences were statistically insignificant(P>0.05).ConclusionsCT-based radiomics signatures and radiomics nomograms can be used to predict and identify PHEO and LPA. The model established based on conventional CT images has great identification and prediction efficiency, and it can also enable patients to avoid harm from radiation and contrast agents caused by the need for further enhancement scanning in traditional image examinations.

ObjectiveTo establish a radiomics signature and a nomogram model based on enhanced CT images to predict the Ki-67 index of lung cancer.MethodsFrom January 2014 to December 2018, 282 patients with lung cancer who had undergone enhanced CT scans and Ki-67 examination within 2 weeks were retrospectively enrolled and analyzed. The clinical data of the patients were collected, such as age, sex, smoking history, maximum tumor diameter and serum tumor markers. Our primary cohort was randomly divided into a training group (n=197) and a validation group (n=85) at a 7:3 ratio. A Ki-67 index ≤ 40% indicated low expression, and a Ki-67 index > 40% indicated high expression. In total, 396 radiomics features were extracted using AK software. Feature reduction and selection were performed using the lasso regression model. Logistic regression analysis was used to establish a multivariate predictive model to identify high and low Ki-67 expression in lung cancer. A nomogram integrating the radiomics score was established based on multiple logistic regression analysis. Area under the curve (AUC) was used to evaluate the prediction efficiency of the radiomics signature and nomogram.ResultsThe AUC,sensitivity, specificity and accuracy of the radiomics signature in the training and validation groups were 0.88 (95% CI: 0.82~0.93),79.2%,84.3%,81.2% and 0.86 (95% CI: 0.78~0.94),74.6%,88.1%,79.8%, respectively. A nomogram combining radiomics features and clinical risk factors (smoking history and NSE) was developed. The AUC, sensitivity, specificity and accuracy were 0.87 (95% CI: 0.80~0.95), 75.0%, 90.2% and 83.5% in the validation group, respectively.ConclusionThe radiomics signature and nomogram based on enhanced CT images provide a way to predict the Ki-67 expression level in lung cancer.