Evaluation of Pulmonary Nodules by Radiologists vs. Radiomics in Stand-Alone and Complementary CT and MRI.

Increased attention has been given to MRI in radiation-free screening for malignant nodules in recent years. Our objective was to compare the performance of human readers and radiomic feature analysis based on stand-alone and complementary CT and MRI imaging in classifying pulmonary nodules. This single-center study comprises patients with CT findings of pulmonary nodules who underwent additional lung MRI and whose nodules were classified as benign/malignant by resection. For radiomic features analysis, 2D segmentation was performed for each lung nodule on axial CT, T2-weighted (T2w), and diffusion (DWI) images. The 105 extracted features were reduced by iterative backward selection. The performance of radiomics and human readers was compared by calculating accuracy with Clopper-Pearson confidence intervals. Fifty patients (mean age 63 +/- 10 years) with 66 pulmonary nodules (40 malignant) were evaluated. ACC values for radiomic features analysis vs. radiologists based on CT alone (0.68; 95%CI: 0.56, 0.79 vs. 0.59; 95%CI: 0.46, 0.71), T2w alone (0.65; 95%CI: 0.52, 0.77 vs. 0.68; 95%CI: 0.54, 0.78), DWI alone (0.61; 95%CI:0.48, 0.72 vs. 0.73; 95%CI: 0.60, 0.83), combined T2w/DWI (0.73; 95%CI: 0.60, 0.83 vs. 0.70; 95%CI: 0.57, 0.80), and combined CT/T2w/DWI (0.83; 95%CI: 0.72, 0.91 vs. 0.64; 95%CI: 0.51, 0.75) were calculated. This study is the first to show that by combining quantitative image information from CT, T2w, and DWI datasets, pulmonary nodule assessment through radiomics analysis is superior to using one modality alone, even exceeding human readers' performance.

Photon-counting versus Dual-Source CT of Congenital Heart Defects in Neonates and Infants: Initial Experience.

Background Photon-counting CT (PCCT) has been shown to improve cardiovascular CT imaging in adults. Data in neonates, infants, and young children under the age of 3 years are missing. Purpose To compare image quality and radiation dose of ultrahigh-pitch PCCT with that of ultrahigh-pitch dual-source CT (DSCT) in children suspected of having congenital heart defects. Materials and Methods This is a prospective analysis of existing clinical CT studies in children suspected of having congenital heart defects who underwent contrast-enhanced PCCT or DSCT in the heart and thoracic aorta between January 2019 and October 2022. CT dose index and dose-length product were used to calculate effective radiation dose. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated by standardized region-of-interest analysis. SNR and CNR dose ratios were calculated. Visual image quality was assessed by four independent readers on a five-point scale: 5, excellent or absent; 4, good or minimal; 3, moderate; 2, limited or substantial; and 1, poor or massive. Results Contrast-enhanced PCCT (n = 30) or DSCT (n = 84) was performed in 113 children (55 female and 58 male participants; median age, 66 days [IQR, 15-270]; median height, 56 cm [IQR, 52-67]; and median weight, 4.5 kg [IQR, 3.4-7.1]). A diagnostic image quality score of at least 3 was obtained in 29 of 30 (97%) with PCCT versus 65 of 84 (77%) with DSCT. Mean overall image quality ratings were higher for PCCT versus DSCT (4.17 vs 3.16, respectively; P < .001). SNR and CNR were higher for PCCT versus DSCT with SNR (46.3 ± 16.3 vs 29.9 ± 15.3, respectively; P = .007) and CNR (62.0 ± 50.3 vs 37.2 ± 20.8, respectively; P = .001). Mean effective radiation doses were similar for PCCT and DSCT (0.50 mSv vs 0.52 mSv; P = .47). Conclusion At a similar radiation dose, PCCT offers a higher SNR and CNR and thus better cardiovascular imaging quality than DSCT in children suspected of having cardiac heart defects. © RSNA, 2023.

A Radiomics Approach to Predict the Emergence of New Hepatocellular Carcinoma in Computed Tomography for High-Risk Patients with Liver Cirrhosis.

Liver cirrhosis poses a major risk for the development of hepatocellular carcinoma (HCC). This retrospective study investigated to what extent radiomic features allow the prediction of emerging HCC in patients with cirrhosis in contrast-enhanced computed tomography (CECT). A total of 51 patients with liver cirrhosis and newly detected HCC lesions (n = 82) during follow-up (FU-CT) after local tumor therapy were included. These lesions were not to have been detected by the radiologist in the chronologically prior CECT (PRE-CT). For training purposes, segmentations of 22 patients with liver cirrhosis but without HCC-recurrence were added. A total of 186 areas (82 HCCs and 104 cirrhotic liver areas without HCC) were analyzed. Using univariate analysis, four independent features were identified, and a multivariate logistic regression model was trained to classify the outlined regions as "HCC probable" or "HCC improbable". In total, 60/82 (73%) of segmentations with later detected HCC and 84/104 (81%) segmentations without HCC were classified correctly (AUC of 81%, 95% CI 74-87%), yielding a sensitivity of 72% (95% CI 57-83%) and a specificity of 86% (95% CI 76-96%). In conclusion, the model predicted the occurrence of new HCCs within segmented areas with an acceptable sensitivity and specificity in cirrhotic liver tissue in CECT.

Virtual Monoenergetic Images (VMI+) in Dual-Source Dual-Energy CT Venography (DSDE-CTV) of the Lower Extremity Prior to Coronary Artery Bypass Graft (CABG): A Feasibility Study.

RATIONALE AND OBJECTIVES: To evaluate the image quality and suitability of Dual-Source Dual-Energy CT venography (DSDE-CTV) with asynchronous virtual monoenergetic images (VMI+) of the entire lower extremity in the context of pre-surgical assessment of complex cases prior to coronary bypass graft as a feasibility study. MATERIALS AND METHODS: Fifteen consecutive patients, consisting of 5 females and 10 males with an average age of 52 ± 17 years underwent DSDE-CTV from the pubic symphysis to the ankles after intravenous injection of an iodinated contrast medium. DSDE-CTV was acquired with tube voltages of 80 kVp and sn140 kVp. Single spectrum images (A - 80 kVp; B - 140 kVp) as well as a linearly blended mixed data set (M_0.6) were reconstructed. By postprocessing, an VMI+ dataset at 40 keV was generated. Objective image quality parameters of the deep and superficial veins of thigh, knee, and calves were measured separately for each location. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. Additionally, subjective image quality was assessed independently by two radiologists. RESULTS: Mean vascular attenuation was 73.9 ± 17.8 HU at B, 113.7 ± 42.2 HU at M_0.6, 119.4 ± 45.5 HU at A, and 201.0 ± 89.7 HU at VMI+. Mean CNR was 6.7 ± 2.0 at 140 keV, 9.25 ± 2.3 in the M_0.6 datasets, 8.7 ± 3.0 at 80 keV, and 12.9 ± 4.3 at 40 keV. Attenuation values were approximately doubled when compared to the reference standard (M_0.6) with significantly improved SNR and CNR (p < 0.05). Subjective image quality scores were highest for VMI+ datasets (4.1 ± 0.5) and lowest for B datasets (2.3 ± 0.37), however differences between VMI+ datasets and M_0.6 datasets did not reach statistical significance. CONCLUSION: Postprocessing of dual-energy CTV with VMI+ significantly increases attenuation of veins and markedly improves SNR and CNR values, thereby improving the diagnostic quality of CTV for the evaluation of deep and superficial veins of the entire lower limb prior to coronary bypass graft.

Leadless Cardiac Pacemaker (LCP) without Diagnostic Relevant Artifacts in DualSource and DualEnergy-CT Examinations in First- to Third-Generation DSCT Scanner.

RATIONALE AND OBJECTIVES: To identify the influence and artifact burden in cardiac CT imaging of a leadless cardiac pacemaker (LCP) performed with all three generations of DualSource CT (DSCT) Scanners. MATERIALS AND METHODS: The LCP was examined in DSCT scanners of the first to third generation using DualEnergy (DECT) and DSCT as well as alterations of the current-time product. For DECT examinations, virtual monoenergetic images were computed manually on a dedicated workstation. Virtual voltage was manually selected by subjective assessment of the lowest artifact burden. Systematic variations of the pacemaker angle to the gantry were assessed, too. The angle was successively increased by 10°, ranging from 0° to 90°. Artifact burden was quantified on a five-point Likert scale (1- no artifacts, 2- few artifacts, 3- moderate artifacts, 4- many artifacts, and 5- massive artifacts). Likert values of 1-3 were considered diagnostic and assessed by two board-certified radiologists in consensus. RESULTS: In total, 200 examinations were analyzed, a mean Likert value of 1.93 ± 0.61 was found overall. None of the images were assessed Likert value >3. The positioning evaluation showed a clear and significant reduction of artifact burden toward lower angles, (0°: 1.4 ± 0.5 vs. 90° 2.55 ± 0.51). At scanner level, second-generation DSCT performed significantly better (1.68 ± 0.47) than both other scanners. Comparison of technique (DECT vs. DSCT) revealed a significantly improved image quality in DSCT examinations. CONCLUSION: LCP can be safely examined in DSCT scanner of the first to third generation with the evaluated protocols and techniques, which are currently in use. Artifact burden can be significantly reduced by aligning or approaching the LCP's longitudinal axis toward the scanner's z-axis.