CT radiomic ground-glass and solid features from part-solid nodules predicted invasiveness of lung adenocarcinoma better than conventional Brock, clinical-semantic, volumetric, and radiomics gross ... Background Solid components of part-solid nodules (PSNs) at CT are reflective of invasive adenocarcinoma, but studies describing radiomic features of PSNs and the perinodular region are lacking. Pu...

As a promising method in artificial intelligence, deep learning has been proven successful in several domains ranging from acoustics and images to natural language processing. With medical imaging becoming an important part of disease screening and diagnosis, deep learning-based approaches have emerged as powerful techniques in medical image areas. In this process, feature representations are learned directly and automatically from data, leading to remarkable breakthroughs in the medical field. Deep learning has been widely applied in medical imaging for improved image analysis. This paper reviews the major deep learning techniques in this time of rapid evolution and summarizes some of its key contributions and state-of-the-art outcomes. The topics include classification, detection, and segmentation tasks on medical image analysis with respect to pulmonary medical images, datasets, and benchmarks. A comprehensive overview of these methods implemented on various lung diseases consisting of pulmonary nodule diseases, pulmonary embolism, pneumonia, and interstitial lung disease is also provided. Lastly, the application of deep learning techniques to the medical image and an analysis of their future challenges and potential directions are discussed.

Solitary cystic lung cancer has malignant features of nonuniform walls, septations, wall nodules, and irregular margins that help to distinguish this entity from benign cystic airspace on CT images. There are increasing reports of a type of lung cancer that manifests as solitary cystic airspaces. The purpose of this case series was to identify the CT features and possible mechanisms of solitary cystic lung cancer, on the basis of CT observations and pathologic characteristics. The clinical, imaging, and pathologic data of 106 patients with solitary cystic lung cancer were collected and analyzed between January 2011 and December 2017. CT images were reviewed independently by three radiologists who were blinded to pathologic findings. Demographic data and clinical and smoking status were extracted from the medical records. The mean age was 58.8 years ± 10.6 (standard deviation) (range, 30–82 years). CT features in the 106 patients included nonuniform cystic walls in 96 (90.6%) patients, cyst septations in 62 (58.5%) patients, nodular walls in 58 (54.7%) patients, ground-glass opacity around the cyst in 53 patients (50.0%), and irregular margins in 42 (39.6%) patients. At histologic examination, the maj...

Background: Genotype status of glioma have important significance to clinical treatment and prognosis. At present, there are few studies on the prediction of multiple genotype status in glioma by method of multi-sequence radiomics. The purpose of the study is to compare the performance of clinical features (age, sex, WHO grade, MRI morphological features etc.), radiomics features from multi MR sequence (T2WI, T1WI, DWI, ADC, CE-MRI (contrast enhancement)), and a combined multiple features model in predicting biomarker status (IDH, MGMT, TERT, 1p/19q of glioma.Methods: In this retrospective analysis, 81 glioma patients confirmed by histology were enrolled in this study. Five MRI sequences were used for radiomic feature extraction. Finally, 107 features were extracted from each sequence on Pyradiomics software, separately. These included 18 first-order metrics, such as the mean, standard deviation, skewness, and kurtosis etc., 14 shape features and second-order metrics including 24 grey level run length matrix (GLCM), 16 grey level run length matrix (GLRLM), 16 grey level size zone matrix (GLSZM), 5 neighboring gray tone difference matrix (NGTDM), and 14 grey level dependence matrix (GLDM). Then, Univariate analysis and LASSO (Least absolute shrinkage and selection operator regression model were used to data dimension reduction, feature selection, and radiomics signature building. Significant features (p < 0.05 by multivariate logistic regression were retained to establish clinical model, T1WI model, T2WI model, T1 + C (T1WI contrast enhancement model, DWI model and ADC model, multi sequence model. Clinical features were combined with multi sequence model to establish a combined model. The predictive performance was validated by receiver operating characteristic curve (ROC analysis and decision curve analysis (DCA).Results: The combined model showed the better performance in some groups of genotype status among some models (IDH AUC = 0.93, MGMT AUC = 0.88, TERT AUC = 0.76). Multi sequence model performed better than single sequence model in IDH, MGMT, TERT. There was no significant difference among the models in predicting 1p/19q status. Decision curve analysis showed combined model has higher clinical benefit than multi sequence model.Conclusion: Multi sequence model is an effective method to identify the genotype status of cerebral glioma. Combined with clinical models can better distinguish genotype status of glioma.Key Points: The combined model showed the higher performance compare with other models in predicting genotype status of IDH, MGMT, TERT. Multi sequence model showed a better predictive model than that of a single sequence model. Compared with other models, the combined model and multi sequence model show no advantage in prediction of 1p/19q status.

Objectives: Develop a CT-based radiomics model and combine it with frozen section (FS) and clinical data to distinguish invasive adenocarcinomas (IA) from preinvasive lesions/minimally invasive adenocarcinomas (PM). Methods: This multicenter study cohort of 623 lung adenocarcinomas was split into training (n = 331), testing (n = 143), and external validation dataset (n = 149). Random forest models were built using selected radiomics features, results from FS, lesion volume, clinical and semantic features, and combinations thereof. The area under the receiver operator characteristic curves (AUC) was used to evaluate model performances. The diagnosis accuracy, calibration, and decision curves of models were tested. Results: The radiomics-based model shows good predictive performance and diagnostic accuracy for distinguishing IA from PM, with AUCs of 0.89, 0.89, and 0.88, in the training, testing, and validation datasets, respectively, and with corresponding accuracies of 0.82, 0.79, and 0.85. Adding lesion volume and FS significantly increases the performance of the model with AUCs of 0.96, 0.97, and 0.96, and with accuracies of 0.91, 0.94, and 0.93 in the three datasets. There is no significant difference in AUC between the FS model enriched with radiomics and volume against an FS model enriched with volume alone, while the former has higher accuracy. The model combining all available information shows minor non-significant improvements in AUC and accuracy compared with an FS model enriched with radiomics and volume. Conclusions: Radiomics signatures are potential biomarkers for the risk of IA, especially in combination with FS, and could help guide surgical strategy for pulmonary nodules patients. Key Points: • A CT-based radiomics model may be a valuable tool for preoperative prediction of invasive adenocarcinoma for patients with pulmonary nodules. • Radiomics combined with frozen sections could help in guiding surgery strategy for patients with pulmonary nodules.