Generative Adversarial Network-Based Image Conversion Among Different Computed Tomography Protocols and Vendors: Effects on Accuracy and Variability in Quantifying Regional Disease Patterns of Interstitial Lung Disease

Objective@#To assess whether computed tomography (CT) conversion across different scan parameters and manufacturers using a routable generative adversarial network (RouteGAN) can improve the accuracy and variability in quantifying interstitial lung disease (ILD) using a deep learning-based automated software. @*Materials and Methods@#This study included patients with ILD who underwent thin-section CT. Unmatched CT images obtained using scanners from four manufacturers (vendors A-D), standard- or low-radiation doses, and sharp or medium kernels were classified into groups 1–7 according to acquisition conditions. CT images in groups 2–7 were converted into the target CT sty le (Group 1: vendor A, standard dose, and sharp kernel) using a RouteGAN. ILD was quantified on original and converted CT images using a deep learning-based software (Aview, Coreline Soft). The accuracy of quantification was analyzed using the dice similarity coefficient (DSC) and pixel-wise overlap accuracy metrics against manual quantification by a radiologist. Five radiologists evaluated quantification accuracy using a 10-point visual scoring system. @*Results@#Three hundred and fifty CT slices from 150 patients (mean age: 67.6 ± 10.7 years; 56 females) were included. The overlap accuracies for quantifying total abnormalities in groups 2–7 improved after CT conversion (original vs. converted: 0.63vs. 0.68 for DSC, 0.66 vs. 0.70 for pixel-wise recall, and 0.68 vs. 0.73 for pixel-wise precision; P < 0.002 for all). The DSCs of fibrosis score, honeycombing, and reticulation significantly increased after CT conversion (0.32 vs. 0.64, 0.19 vs. 0.47, and 0.23 vs. 0.54, P < 0.002 for all), whereas those of ground-glass opacity, consolidation, and emphysema did not change significantly or decreased slightly. The radiologists’ scores were significantly higher (P < 0.001) and less variable on converted CT. @*Conclusion@#CT conversion using a RouteGAN can improve the accuracy and variability of CT images obtained using different scan parameters and manufacturers in deep learning-based quantification of ILD.

Computer-Aided Classification of Visual Ventilation Patterns in Patients with Chronic Obstructive Pulmonary Disease at Two-Phase Xenon-Enhanced CT

OBJECTIVE: To evaluate the technical feasibility, performance, and interobserver agreement of a computer-aided classification (CAC) system for regional ventilation at two-phase xenon-enhanced CT in patients with chronic obstructive pulmonary disease (COPD). MATERIALS AND METHODS: Thirty-eight patients with COPD underwent two-phase xenon ventilation CT with resulting wash-in (WI) and wash-out (WO) xenon images. The regional ventilation in structural abnormalities was visually categorized into four patterns by consensus of two experienced radiologists who compared the xenon attenuation of structural abnormalities with that of adjacent normal parenchyma in the WI and WO images, and it served as the reference. Two series of image datasets of structural abnormalities were randomly extracted for optimization and validation. The proportion of agreement on a per-lesion basis and receiver operating characteristics on a per-pixel basis between CAC and reference were analyzed for optimization. Thereafter, six readers independently categorized the regional ventilation in structural abnormalities in the validation set without and with a CAC map. Interobserver agreement was also compared between assessments without and with CAC maps using multirater kappa statistics. RESULTS: Computer-aided classification maps were successfully generated in 31 patients (81.5%). The proportion of agreement and the average area under the curve of optimized CAC maps were 94% (75/80) and 0.994, respectively. Multirater kappa value was improved from moderate (kappa = 0.59; 95% confidence interval [CI], 0.56-0.62) at the initial assessment to excellent (kappa = 0.82; 95% CI, 0.79-0.85) with the CAC map. CONCLUSION: Our proposed CAC system demonstrated the potential for regional ventilation pattern analysis and enhanced interobserver agreement on visual classification of regional ventilation.

Imaging Characteristics of Stage I Non-Small Cell Lung Cancer on CT and FDG-PET: Relationship with Epidermal Growth Factor Receptor Protein Expression Status and Survival

OBJECTIVE: To identify CT and FDG-PET features associated with epidermal growth factor receptor (EGFR) protein overexpression, and to evaluate whether imaging features and EGFR-overexpression can help predict clinical outcome. MATERIALS AND METHODS: In 214 patients (M : F = 129 : 85; mean age, 63.2) who underwent curative resection of stage I non-small cell lung cancer, EGFR protein expression status was determined through immunohistochemical analysis. Imaging characteristics on CT and FDG-PET was assessed in relation to EGFR-overexpression. Imaging features and EGFR-overexpression were also evaluated for clinical outcome by using the Cox proportional hazards model. RESULTS: EGFR-overexpression was found in 51 patients (23.8%). It was significantly more frequent in tumors with an SUVmax > 5.0 (p 2.43 cm (p 5.0 (OR, 3.113; 95% CI, 1.375-7.049; p = 0.006) and diameter > 2.43 cm (OR, 2.799; 95% CI, 1.285-6.095; p = 0.010) were independent predictors of EGFR overexpression. Multivariate analysis showed that SUVmax > 4.0 (hazard ratio, 10.660; 95% CI, 1.370-82.966; p = 0.024), and the presence of cavitation within a tumor (hazard ratio, 3.122; 95% CI, 1.143-8.532; p = 0.026) were factors associated with poor prognosis. CONCLUSION: EGFR-overexpression is associated with high SUVmax, large tumor diameter, and small GGO proportion. CT and FDG-PET findings, which are closely related to EGFR overexpression, can be valuable in the prediction of clinical outcome.

Camurati-Engelmann's Disease on (99m)Tc-MDP Bone Scan / 핵의학분자영상

A 24 year-old female presented for a (99m)Tc-methylene diphosphonatae (MDP) whole body bone scan due to chronic pain in the bilateral lower extremities that has aggravated since 2002. She was diagnosed with Camurati-Engelmann disease (CED) based on the clinical and radiological findings in 2002, and she re-visited our institute to evaluate disease status at this time. CED is a rare autosomal dominant type of bone dysplasia characterized by progressive cortical thickening of long bones, and narrowing of medullary cavity, and thus presents with typical clinical symptoms and signs such as chronic pain in the extremities, muscle weakness, and waddling gait. On the (99m)Tc-MDP bone scan performed to evaluate disease status, intense increased uptake was seen in the skull, facial bones, bilateral scapulae, bilateral long bones, and bilateral pelvic bones, which clearly demonstrated the extent of CED involvement.

Multislice CT of a Persistent Left Superior Vena Cava Coursing Anterior to the Right Ventricle: A Case Report

EKG-gated cardiac CT revealed a variant vein in a 44-year-old man that was misinterpreted as a mass on echocardiography. The variant vein was an extension of the confluence of the left internal jugular vein and left subclavian vein and coursed anterior to the right ventricle. It connected to the right atrium directly at the inferior surface of the heart. The variant vein was likely a persistent left superior vena cava, a variant that has never been reported.