Objective:To explore the computed tomography (CT) characteristics of small lung nodules and improve the diagnosis of pulmonary ground-glass nodules less than 10 mm in size.Methods:We retrospectively analyzed CT images of 161 pulmonary nodules (less than 10 mm in size) with spiculation, lobulation, vacuoles and pleural indentation and compared these images with pathological results or follow-up CT images. The relationships between the ground-glass nodules (GGNs) and blood vessels were observed. The GGN-vessel relationship were divided into four type, Type I (pass-by), Type II (pass-through), Type III (distorted/dilated), Type IV (complicated). The vessels traveling through a GGN were divided into three categories, category A (arteries), category B (veins), category C (arteries and veins).Results:One hundred sixty-one GGNs were divided into 3 groups(benign group, pre-invasive group and adenocarcinoma group) according to their pathological diagnosis. Significant differences in density of nodules were obser...

We aimed to detect acute aortic syndromes (AAS) on non-contrast computed tomography (NCCT) images using a radiomics-based machine learning model. A total of 325 patients who underwent aortic CT angiography (CTA) were enrolled retrospectively from 2 medical centers in China to form the internal cohort (230 patients, 60 patients with AAS) and the external testing cohort (95 patients with AAS). The internal cohort was divided into the training cohort (n = 135), validation cohort (n = 49), and internal testing cohort (n = 46). The aortic mask was manually delineated on NCCT by a radiologist. Least Absolute Shrinkage and Selection Operator regression (LASSO) was used to filter out nine feature parameters; the Support Vector Machine (SVM) model showed the best performance. In the training and validation cohorts, the SVM model had an area under the curve (AUC) of 0.993 (95% CI, 0.965–1); accuracy (ACC), 0.946 (95% CI, 0.877–1); sensitivity, 0.9 (95% CI, 0.696–1); and specificity, 0.964 (95% CI, 0.903–1). In the internal testing cohort, the SVM model had an AUC of 0.997 (95% CI, 0.992–1); ACC, 0.957 (95% CI, 0.945–0.988); sensitivity, 0.889 (95% CI, 0.888–0.889); and specificity, 0.973 (95% CI, 0.959–1). In the external testing cohort, the ACC was 0.991 (95% CI, 0.937–1). This model can detect AAS on NCCT, reducing misdiagnosis and improving examinations and prognosis.

This retrospective study aimed to predict the injury time of rib fractures in distinguishing fresh (30 days) or old (90 days) rib fractures. We enrolled 111 patients with chest trauma who had been scanned for rib fractures at our hospital between January 2018 and December 2018 using gemstone spectral imaging (GSI). The volume of interest of each broken end of the rib fractures was segmented using calcium-based material decomposition images derived from the GSI scans. The training and testing sets were randomly assigned in a 7:3 ratio. All cases were divided into groups distinguishing the injury time at 30 and 90 days. We constructed radiomics-based models to predict the injury time of rib fractures. The model performance was assessed by the area under the curve (AUC) obtained by the receiver operating characteristic analysis. We included 54 patients with 259 rib fracture segmentations (34 men; mean age, 52 years ± 12.02; and range, 19–72 years). Nine features were excluded by the least absolute shrinkage and selection operator logistic regression to build the radiomics signature. For distinguishing the injury time at 30 days, the Support Vector Machine (SVM) model and human–model collaboration resulted in an accuracy and AUC of 0.85 and 0.871 and 0.91 and 0.912, respectively, and 0.81 and 0.804 and 0.83 and 0.85, respectively, at 90 days in the testing set. The radiomics-based model displayed good accuracy in differentiating between the injury time of rib fractures at 30 and 90 days, and the human–model collaboration generated more accurate outcomes, which may help to add value to clinical practice and distinguish artificial injury in forensic medicine.

Purpose: Shortened injection durations are not recommended in step-and-shoot coronary computed tomography angiography (CCTA). We aimed to evaluate the image quality of CCTA performed using bodyweight-adjusted iodinated contrast media (ICM) with different injection durations to generate an optimized ICM administration protocol to acquire convincible image quality in step-and-shoot CCTA. Materials and Methods: A total of 200 consecutive patients with suspected coronary artery disease (CAD) were enrolled in group A (N=50, 350 mgI/mL, bodyweight×0.8 mL/kg with a 13-s injection duration), group B (N=50, 350 mgI/mL, bodyweight×0.9 mL/kg with a 13-s injection duration), group C (N=50, 350 mgI/mL, bodyweight×0.8 mL/kg with a 12-s injection duration), and group D (N=50, 320 mgI/mL, bodyweight×0.8 mL/kg with a 13-s injection duration). Patient characteristics, ICM administration protocols, quantitative computed tomography (CT) value measurements, and qualitative image scores were analyzed and compared among the groups. Results: Groups A and D achieved the lowest ICM volume, saline volume, injection flow rate, and total iodine and iodine injection rates among the groups. All the CT values of the coronary arteries in all groups were >300 HU. All the observers’ average scores exceeded three points. In group A, the CT values showed significant positive correlation with the iodine injection rate (r=0.226, P<0.001), whereas the signal-to-noise ratio (r=−0.004, P=0.927) and contrast-to-noise ratio (r=−0.006, P=0.893) values were not. Conclusions: Bodyweight×0.8 mL/kg with a 13-second injection duration is a comprehensive option for step-and-shoot CCTA with improved image quality, and a 350 mgI/mL iodine concentration is preferred.

To investigate the value of the deep learning method in predicting the invasiveness of early lung adenocarcinoma based on irregularly sampled follow-up computed tomography (CT) scans. In total, 351 nodules were enrolled in the study. A new deep learning network based on temporal attention, named Visual Simple Temporal Attention (ViSTA), was proposed to process irregularly sampled follow-up CT scans. We conducted substantial experiments to investigate the supplemental value in predicting the invasiveness using serial CTs. A test set composed of 69 lung nodules was reviewed by three radiologists. The performance of the model and radiologists were compared and analyzed. We also performed a visual investigation to explore the inherent growth pattern of the early adenocarcinomas. Among counterpart models, ViSTA showed the best performance (AUC: 86.4% vs. 60.6%, 75.9%, 66.9%, 73.9%, 76.5%, 78.3%). ViSTA also outperformed the model based on Volume Doubling Time (AUC: 60.6%). ViSTA scored higher than two junior radiologists (accuracy of 81.2% vs. 75.4% and 71.0%) and came close to the senior radiologist (85.5%). Our proposed model using irregularly sampled follow-up CT scans achieved promising accuracy in evaluating the invasiveness of the early stage lung adenocarcinoma. Its performance is comparable with senior experts and better than junior experts and traditional deep learning models. With further validation, it can potentially be applied in clinical practice.