Background: To develop an artificial intelligence (AI) model with radiomics and deep learning (DL) features extracted from CT images to distinguish benign from malignant ovarian tumors. Methods: We enrolled 149 patients with pathologically confirmed ovarian tumors. A total of 185 tumors were included and divided into training and testing sets in a 7:3 ratio. All tumors were manually segmented from preoperative contrast-enhanced CT images. CT image features were extracted using radiomics and DL. Five models with different combinations of feature sets were built. Benign and malignant tumors were classified using machine learning (ML) classifiers. The model performance was compared with five radiologists on the testing set. Results: Among the five models, the best performing model is the ensemble model with a combination of radiomics, DL, and clinical feature sets. The model achieved an accuracy of 82%, specificity of 89% and sensitivity of 68%. Compared with junior radiologists averaged results, the model had a higher accuracy (82% vs 66%) and specificity (89% vs 65%) with comparable sensitivity (68% vs 67%). With the assistance of the model, the junior radiologists achieved a higher average accuracy (81% vs 66%), specificity (80% vs 65%), and sensitivity (82% vs 67%), approaching to the performance of senior radiologists. Conclusions: We developed a CT-based AI model that can differentiate benign and malignant ovarian tumors with high accuracy and specificity. This model significantly improved the performance of less-experienced radiologists in ovarian tumor assessment, and may potentially guide gynecologists to provide better therapeutic strategies for these patients.

Central obesity in relation to insulin resistance is strongly linked to the development of type 2 diabetes. However, data regarding the association between pericardial and peri-aortic adiposity, a potential estimate of visceral adipose tissue burden, and pre-diabetes status remains unclear.

Thoracic cancer treatment presents dosimetric difficulties due to respiratory motion and lung inhomogeneity. Monte Carlo and deformable image registration techniques have been proposed to be used in four-dimensional (4D) dose calculations to overcome the difficulties. This study validates the 4D Monte Carlo dosimetry with measurement, compares 4D dosimetry of different tumor sizes and tumor motion ranges, and demonstrates differences of dose-volume histograms (DVH) with the number of respiratory phases that are included in 4D dosimetry. BEAMnrc was used in dose calculations while an optical flow algorithm was used in deformable image registration and dose mapping. Calculated and measured doses of a moving phantom agreed within 3% at the center of the moving gross tumor volumes (GTV). 4D CT image sets of lung cancer cases were used in the analysis of 4D dosimetry. For a small tumor (12.5 cm³) with motion range of 1.5 cm, reduced tumor volume coverage was observed in the 4D dose with a beam margin of 1 cm. For large tumors and tumors with small motion range (around 1 cm), the 4D dosimetry did not differ appreciably from the static plans. The dose-volume histogram (DVH) analysis shows that the inclusion of only extreme respiratory phases in 4D dosimetry is a reasonable approximation of all-phase inclusion for lung cancer cases similar to the ones studied, which reduces the calculation in 4D dosimetry.

To reduce positron emission tomography (PET) and computed tomography (CT) misalignments and standardized uptake value (SUV) errors, cine average CT (CACT) has been proposed to replace helical CT (HCT) for attenuation correction (AC). A new method using interpolated average CT (IACT) for AC is introduced to further reduce radiation dose with similar image quality. Six patients were recruited in this study. The end-inspiration and -expiration phases from cine CT were used as the two original phases. Deformable image registration was used to generate the interpolated phases. The IACT was calculated by averaging the original and interpolated phases. The PET images were then reconstructed with AC using CACT, HCT and IACT, respectively. Their misalignments were compared by visual assessment, mutual information, correlation coefficient and SUV. The doses from different CT maps were analyzed. The misalignments were reduced for CACT and IACT as compared to HCT. The maximum SUV difference between the use of IACT and CACT was similar to 3%, and it was similar to 20% between the use of HCT and CACT. The estimated dose for IACT was 0.38 mSv. The radiation dose using IACT could be reduced by 85% compared to the use of CACT. IACT is a good low-dose approximation of CACT for AC.

The aims of this study were to investigate the image quality and radiation exposure of pediatric protocols for cardiac CT angiography (CTA) in infants under one year of age. Cardiac CTA examinations were performed using an anthropomorphic phantom representing a 1-year-old child scanned with non-electrocardiogram-gated (NG), retrospectively electrocardiogram-gated helical (RGH) and prospectively electrocardiogram-gated axial (PGA) techniques in 64-slice and 256-slice CT scanners. The thermoluminescent dosimeters (TLD) were used for direct organ dose measurement, while dose-length product and effective mAs were also used to estimate the patient dose. For image quality, noise and signal-to-noise-ratio (SNR) were assessed based on regions-of-interest drawn on the reconstructed CT images, and were compared with the proposed cardiac image quantum index (CIQI). Estimated dose results were in accordant to the measured doses. The NG scan showed the best image quality in terms of noise and SNR. The PGA scan had better image quality than the RGH scan with 83.70% dose reduction. Noise and SNR were also corresponded to the proposed CIQI. The PGA scan protocol was a good choice in balancing radiation exposure and image quality for infant cardiac CTA. We also suggested that the effective mAs and the CIQI were suitable in assessing the tradeoffs between radiation dose and image quality for cardiac CTA in infants. These results are useful for future implementation of dose reduction strategies in pediatric cardiac CTA protocols.