Kernel Conversion for Robust Quantitative Measurements of Archived Chest Computed Tomography Using Deep Learning-Based Image-to-Image Translation

Chest computed tomography (CT) is used to screen for lung cancer and evaluate pulmonary and extra-pulmonary abnormalities such as emphysema and coronary artery calcification, particularly in smokers. In real-world practice, lung abnormalities are visually assessed using high-contrast thin-slice images which are generated from raw scan data using sharp reconstruction kernels with the sacrifice of increased image noise. In contrast, accurate CT quantification requires low-contrast thin-slice images with low noise, which are generated using soft reconstruction kernels. However, only sharp-kernel thin-slice images are archived in many medical facilities due to limited data storage space. This study aimed to establish deep neural network (DNN) models to convert sharp-kernel images to soft-kernel-like images with a final goal to reuse historical chest CT images for robust quantitative measurements, particularly in completed previous longitudinal studies. By using pairs of sharp-kernel (input) and soft-kernel (ground-truth) images from 30 patients with chronic obstructive pulmonary disease (COPD), DNN models were trained. Then, the accuracy of kernel conversion based on the established DNN models was evaluated using CT from independent 30 smokers with and without COPD. Consequently, differences in CT values between new images converted from sharp-kernel images using the established DNN models and ground-truth soft-kernel images were comparable with the inter-scans variability derived from repeated phantom scans (6 times), showing that the conversion error was the same level as the measurement error of the CT device. Moreover, the Dice coefficients to quantify the similarity between low attenuation voxels on given images and the ground-truth soft-kernel images were significantly higher on the DNN-converted images than the Gaussian-filtered, median-filtered, and sharp-kernel images (p < 0.001). There were good agreements in quantitative measurements of emphysema, intramuscular adipose tissue, and coronary artery calcification between the converted and the ground-truth soft-kernel images. These findings demonstrate the validity of the new DNN model for kernel conversion and the clinical applicability of soft-kernel-like images converted from archived sharp-kernel images in previous clinical studies. The presented method to evaluate the validity of the established DNN model using repeated scans of phantom could be applied to various deep learning-based image conversions for robust quantitative evaluation.

Comparison of Relapsing Polychondritis Patients with and Without Respiratory Involvement Based on Chest Computed Tomography: A Retrospective Cohort Study

Background Relapsing polychondritis (RP) patients with tracheal cartilage involvement are different from other patients. The objectives of this study were to compare the clinical features and disease patterns between respiratory involvement subgroup and non-respiratory involvement subgroup according to chest computed tomography. Method We performed a retrospective cohort study collected RP patients hospitalized at the Beijing Chao-Yang Hospital between January 2012 - August 2021. Results The incident of costochondritis was more frequent in RP patients with respiratory involvement(p=0.03), the incidence of inflammatory eye disease(p=0.001) and auricular chondritis(p=0.001) was less frequent in RP respiratory involvement patients, compared with those of RP patients without respiratory involvement. Correlation analysis showed that a negative correlation between respiratory involvement and auricular chondritis (r=-0.58, p < 0.01), and between respiratory involvement and inflammatory eye disease (r=-0.45, P < 0.01). Auricular chondritis was positively correlated with inflammatory eye disease (r=0.49, P < 0.01). Compared with non-respiratory involvement subgroup, the incidence of pulmonary infection marginally increased in respiratory involvement subgroup(p=0.06). Inflammatory indexes except for CAR were significantly higher in respiratory involvement subgroup, subgroup analysis found that there was no significant relationship between inflammatory indexes and pulmonary infection. Conclusion RP patients with respiratory involvement was characterized by higher rate of costochondritis and pulmonary infection, fewer inflammatory eye disease and auricular chondritis compared to non-respiratory involvement. Increase inflammatory indexes may suggested that patients with respiratory involvement had a higher disease activity index of RP. The probability of survival was not significant between two subgroups.

Uncommon cause of respiratory failure due to a bezoar in the hypopharynx: a case report

Background Trichotillomania and trichophagia cause trichobezoars, which are masses made of hair. The main presentation of this condition is abdominal pain. However, other complications include gastric outlet obstruction, nausea, vomiting, weight loss, malnutrition, hematemesis, diarrhea, and constipation. Case presentation A 57-year-old woman with trichotillomania was admitted to the Emergency Department with the chief complaints of dyspnea on exertion, shortness of breath, dysphagia, generalized weakness, and hoarseness. Spiral chest computed tomography (CT) scan did not reveal any parenchymal lesions Pulmonary CT angiography did not reveal pulmonary embolism. The patient was admitted to the Surgery Department for hand fasciotomy due to contrast leakage, and during laryngoscopy, a trichobezoar was detected that was removed with Magill forceps. Conclusions Rare cases of trichobezoars can be observed in humans with gastrointestinal and respiratory symptoms. Precise and timely diagnosis are key for the prevention of more invasive diagnostic procedures.

Rasmussen’s Aneurysm, Rare yet Acknowledged Cause of Massive Hemoptysis: Retrospective Review of 16 Cases

Objectives: Rasmussen’s aneurysm may cause life-threatening hemoptysis. We investigated the clinical characteristics and outcomes of patients with hemoptysis and Rasmussen’s aneurysm.Methods: We retrospectively investigated patients who clinically presented with hemoptysis and were diagnosed with a Rasmussen’s aneurysm on spiral chest computed tomography (CT).Results: Our study included 16 patients (men:women, 12:4; mean age, 65.25 ± 13.0 years). Massive hemoptysis was observed in nine patients (56%) and blood-tinged sputum in four patients (25%). Ten patients (62.5%) had a history of pulmonary tuberculosis, and three patients (18.7%) had underlying lung cancer. Chest CT revealed coexisting fungal balls in seven patients (43.7%). Bronchial artery embolization (BAE) was performed in 12 patients (75%). One patient died of uncontrolled massive hemoptysis.Conclusions: Patients with Rasmussen’s aneurysm showed hemoptysis during the course of the disease; however, bleeding can be controlled with conservative therapy and radiological interventions, such as BAE.