This study aimed to explore the ability of radiomics derived from both MRI and 18F-fluorodeoxyglucose positron emission tomography (18F-FDG-PET) images to differentiate glioblastoma (GBM) from solitary brain metastases (SBM) and to investigate the combined application of multiple models. The imaging data of 100 patients with brain tumours (50 GBMs and 50 SBMs) were retrospectively analysed. Three model sets were built on MRI, 18F-FDG-PET, and MRI combined with 18F-FDG-PET using five feature selection methods and five classification algorithms. The model set with the highest average AUC value was selected, in which some models were selected and divided into Groups A, B, and C. Individual and joint voting predictions were performed in each group for the entire data. The model set based on MRI combined with 18F-FDG-PET had the highest average AUC compared with isolated MRI or 18F-FDG-PET. Joint voting prediction showed better performance than the individual prediction when all models reached an agreement. In conclusion, radiomics derived from MRI and 18F-FDG-PET could help differentiate GBM from SBM preoperatively. The combined application of multiple models can provide greater benefits.

BackgroundCyclin‐dependent kinase inhibitor 2A/B (CDKN2A/B) homozygous deletion has been verified as an independent and critical biomarker of negative prognosis and short survival in isocitrate dehydrogenase (IDH)‐mutant astrocytoma. Therefore, noninvasive and accurate discrimination of CDKN2A/B homozygous deletion status is essential for the clinical management of IDH‐mutant astrocytoma patients.PurposeTo develop a noninvasive, robust preoperative model based on MR image features for discriminating CDKN2A/B homozygous deletion status of IDH‐mutant astrocytoma.Study TypeRetrospective.PopulationTwo hundred fifty‐one patients: 107 patients with CDKN2A/B homozygous deletion and 144 patients without CDKN2A/B homozygous deletion.Field Strength/Sequence:3.0 T/1.5 TContrast‐enhanced T1‐weighted spin‐echo inversion recovery sequence (CE‐T1WI) and T2‐weighted fluid‐attenuation spin‐echo inversion recovery sequence (T2FLAIR).AssessmentA total of 1106 radiomics and 1000 deep learning features extracted from CE‐T1WI and T2FLAIR were used to develop models to discriminate the CDKN2A/B homozygous deletion status. Radiomics models, deep learning‐based radiomics (DLR) models and the final integrated model combining radiomics features with deep learning features were developed and compared their preoperative discrimination performance.Statistical TestingPearson chi‐square test and Mann Whitney U test were used for assessing the statistical differences in patients' clinical characteristics. The Delong test compared the statistical differences of receiver operating characteristic (ROC) curves and area under the curve (AUC) of different models. The significance threshold is P < 0.05.ResultsThe final combined model (training AUC = 0.966; validation AUC = 0.935; test group: AUC = 0.943) outperformed the optimal models based on only radiomics or DLR features (training: AUC = 0.916 and 0.952; validation: AUC = 0.886 and 0.912; test group: AUC = 0.862 and 0.902).Data ConclusionWhether based on a single sequence or a combination of two sequences, radiomics and DLR models have achieved promising performance in assessing CDKN2A/B homozygous deletion status. However, the final model combining both deep learning and radiomics features from CE‐T1WI and T2FLAIR outperformed the optimal radiomics or DLR model.Evidence Level4Technical EfficacyStage 2

Purpose Noninvasive coronary CT angiography (CCTA) was used to retrospectively analyze the characteristics of coronary artery disease (CAD) in patients with thoracic tumors and the impact of the results on clinical surgery decision-making, thus increasing the understanding of perioperative cardiac risk evaluation. Method A total of 779 patients (age 68.6 ± 6.6 years) with thoracic tumor (lung, esophageal, and mediastinal tumor) scheduled for non-cardiac surgery were retrospectively enrolled. Patients were divided into two groups: accepted or canceled surgery. Clinical data and CCTA results were compared between the two groups, and multivariate logistic regression analysis was performed to determine predictors of the events of cancellations of scheduled surgeries. Results 634 patients (81.4%) had non-significant CAD and 145 patients (18.6%) had significant CAD. Single‑, 2‑, and 3‑ vessel disease was found in 173 (22.2%), 93 (11.9%) and 50 (6.4%) patients, respectively. 500 (64.2%), 96 (12.3%), 96 (12.3%), 56 (7.2%) and 31 (4.0%) patients were rated as CACS 0, 1–99, 100–399, 400–999 and > 1000, respectively. Cancellations of scheduled procedures continue to increase based on the severity of the stenosis and the number of major coronary artery stenosis. The degree of stenosis and the number of vascular stenosis were independent predictors of cancelling scheduled surgery. Conclusions For patients with thoracic tumors scheduled for non-cardiac surgery, the results suggested by CCTA significantly influenced surgery planning and facilitated to reduce perioperative cardiovascular events.