OBJECTIVES:To characterise longitudinal changes in chest computed tomography (CT) features and to investigate the relationship between quantitative CT and pulmonary functions in patients with anti-synthetase syndrome-associated interstitial lung disease (ASyS-ILD). METHODS:This retrospective study included 60 newly diagnosed patients with ASyS-ILD (April 2014-December 2022), who were positive for anti-synthetase antibodies and had undergone at least two chest CT examinations. Clinical, serological, pulmonary function test, and CT data were analysed. CT abnormalities and imaging patterns were assessed visually and quantitatively using semi-quantitative CT scoring and automated quantitative CT software. Patients were stratified according to clinical outcomes (regression, stability, or deterioration) and baseline disease severity. RESULTS:Median follow-up duration was 25 months, during which 404 CT scans were reviewed. At baseline, ground-glass opacities, linear opacities, and consolidations were the predominant imaging findings. Over time, traction bronchiectasis showed significant progression (p<0.001), whereas consolidation, pleural thickening, and organising pneumonia (OP) patterns decreased significantly (p<0.05). Fibrotic patterns increased overall, particularly in the anti-PL-12 (100%), anti-Jo-1 (77.4%), and anti-EJ (77.8%) subgroups. Baseline traction bronchiectasis was more frequently observed in the stability and deterioration groups, whereas OP pattern and consolidation were more common in the regression group. Both CT scores and quantitative CT parameters, including mean lung density (MLD) and high-attenuation volume percentage (HAV%), showed strong correlations with FVC%, FEV1%, TLC, and VC, and moderate correlations with DLco%. Compared with the less advanced group, the more advanced group exhibited significantly higher CT scores (13.0±2.1 vs. 9.2±2.4, p<0.001), higher MLD values (-696±58 vs. -768±61, p=0.001) and HAV% (6.3±1.6 vs. 4.3±2.1, p=0.002), as well as lower low-attenuation volume percentage (LAV%) (5.6±8.0 vs. 11.3±10.1, p=0.049). CONCLUSIONS:CT assessments in patients with ASyS-ILD demonstrate a progressive shift toward fibrotic patterns over time. Both CT scores and quantitative CT parameters are strongly associated with pulmonary function and reflect disease severity,supporting their potential value inindividualised clinical evaluation.

Abstract Purpose To compare intrapulmonary vessel volume (IPVV) on computed tomography pulmonary angiography (CTPA) between vasculitis patients with pulmonary vascular involvement and CTPA-negative subjects. Methods This study included 207 vasculitis patients with pulmonary vascular involvement between March 2019 and November 2024 and 202 CTPA-negative subjects between February 2019 and February 2025. A computer-aided pulmonary vascular segmentation algorithm was employed to automatically measure total intrapulmonary vessel volume (TIPVV), intrapulmonary arterial vessel volume (IPVVa) and intrapulmonary venous vessel volume (IPVVv). Additionally, IPVVs were analyzed and compared within five specific vessel diameter groups: 0.8–1.6 mm, 1.6–2.4 mm, 2.4–3.2 mm, 3.2–4.0 mm, and > 4.0 mm. Results TIPVV and IPVVv showed no significant differences between groups. The IPVVa measured in CTPA-negative subjects was 47.79 (42.48, 54.10) mL·m− 2, while that in vasculitis patients with pulmonary vascular involvement was 44.86 (39.33, 52.58) mL·m− 2. The IPVVa in vasculitis patients with pulmonary vascular involvement was significantly lower than that in CTPA-negative subjects (p < 0.01). In pulmonary arteries with diameters of 0.8–1.6 mm and 2.4–3.2 mm, the IPVVa in vasculitis patients with pulmonary vascular involvement was lower than that in CTPA-negative subjects (p < 0.05). In pulmonary veins with diameters of 1.6–2.4 mm and 3.2–4.0 mm, the IPVVv in vasculitis patients with pulmonary vascular involvement was higher than that in CTPA-negative subjects (p < 0.05). Conclusions The computer-aided pulmonary vascular segmentation algorithm can automatically measure IPVV, enabling quantitative assessment of small pulmonary vessel involvement in vasculitis.

Background:Pulmonary artery involvement (PAI) in Takayasu arteritis (TA) is often diagnosed late and may lead to pulmonary hypertension (PH). Quantitative imaging biomarkers that could aid early detection are currently lacking. This study aimed to quantify pulmonary arterial volumes (PAVs) in TA-PAI using computed tomography pulmonary angiography (CTPA) and to compare imaging features between PAI patients and age-/sex-matched controls, as well as between PAI subgroups with and without PH. Methods:This single-center retrospective study (April 2022-March 2024) included 90 patients [median age 33 years; interquartile range (IQR), 27-43 years; 91.1% female] meeting modified Ishikawa criteria and 47 age- and sex-matched controls with normal pulmonary arteries on CTPA. PAVs were measured in six non-overlapping diameter (D) strata (D ≤0.8, 0.8< D ≤1.6, 1.6< D ≤2.4, 2.4< D ≤3.2, 3.2< D ≤4.0, D >4.0 mm) using a deep learning-based segmentation method implemented on the AZE Virtual Place workstation. Cumulative threshold-based volumes and the proportional contribution of each stratum to total intraparenchymal PAV were then analyzed. Qualitative features (stenosis, occlusion, dilation, aneurysm, wall thickening, thrombosis) were recorded. PH was defined by echocardiography according to the European Society of Cardiology/European Respiratory Society (ESC/ERS) PH guidelines. Continuous variables were compared using the t-test or Mann-Whitney U test, and categorical variables using the χ2 or Fisher's exact test, with Bonferroni correction (P<0.05). Results:Compared with the control group, the patient group showed significantly lower cumulative volumes (mL) for arteries with diameters of ≤3.2 mm [52.8 (IQR, 45.8-57.7) vs. 56.6±11.2 mL; P=0.047] and ≤4.0 mm [59.5 (IQR, 52.2-65.0) vs. 63.7±11.6 mL; P=0.028]. The proportional contribution of each non-overlapping diameter stratum to total intraparenchymal PAV was lower in patients than in controls for the 1.6< D ≤2.4 mm (patients vs. controls: 26.1%±5.5% vs. 28.6%±6.3%; P=0.021) and 2.4< D ≤3.2 mm (21.6%±3.5% vs. 23.6%±3.4%; P=0.001). Compared with non-PH patients (n=73), the PH subgroup (n=17) had larger main pulmonary artery diameters (32.3±5.4 vs. 26.9±5.3 mm; P<0.001) and higher rates of stenosis (88% vs. 63%; P=0.045), dilation (71% vs. 29%; P=0.001), and aneurysm (24% vs. 4%; P=0.007), but cumulative PAVs did not differ significantly. Conclusions:CTPA-based PAV quantification reveals marked volume loss in mid-sized pulmonary arteries in TA-PAI. PAV might be beneficial for detecting TA. However, PAV showed no significant difference between groups according to PH status, despite severe pulmonary arterial structural changes.

To characterize lobar and segmental airway volume differences between systemic lupus erythematosus (SLE) patients with interstitial lung disease (ILD) and those without ILD (non-ILD) using a deep learning-based approach on non-contrast chest high-resolution CT (HRCT). Methods: A retrospective analysis was conducted on 106 SLE patients (27 SLE-ILD, 79 SLE-non-ILD) who underwent HRCT. A customized deep learning framework based on the U-Net architecture was developed to automatically segment airway structures at the lobar and segmental levels via HRCT. Volumetric measurements of lung lobes and segments derived from the segmentations were statistically compared between the two groups using two-sample t-tests (significance threshold: p < 0.05). Results: At lobar level, significant airway volume enlargement in SLE-ILD patients was observed in the right upper lobe (p=0.009) and left upper lobe (p=0.039) compared to SLE-non-ILD. At the segmental level, significant differences were found in segments including R1 (p=0.016), R3 (p<0.001), and L3 (p=0.038), with the most marked changes in the upper lung zones, while lower zones showed non-significant trends. Conclusion: Our study demonstrates that an automated deep learning-based approach can effectively quantify airway volumes on HRCT scans and reveal significant, region-specific airway dilation in patients with SLE-ILD compared to those without ILD. The pattern of involvement, predominantly affecting the upper lobes and specific segments, highlights a distinct topographic phenotype of SLE-ILD and implicates airway structural alterations as a potential biomarker for disease presence. This AI-powered quantitative imaging biomarker holds promise for enhancing the early detection and monitoring of ILD in the SLE population, ultimately contributing to more personalized patient management.

Pulmonary segment segmentation is crucial for cancer localization and surgical planning. The voxel-wise annotation of pulmonary segments is laborious, as the boundaries between segments are indistinguishable. To this end, we propose Anatomy-Hierarchy Supervised Learning (AHSL), a novel weakly supervised learning method. It incorporates anatomical priors into pulmonary segment segmentation through hierarchical supervision. Specifically, AHSL adopts a dual-level supervision paradigm at both the lobe and segment levels. At the lobe level, supervision constrains pulmonary segments to remain within their corresponding lobes. At the segment level, sparse bronchovascular annotations are used to enforce spatial correspondence between each segment and its associated bronchovascular tree. In addition, we introduce a consistency loss based on the L1 norm of the Laplacian to encourage smooth segmental boundaries, along with a new evaluation metric designed to measure the smoothness of the boundaries. Furthermore, we introduce a two-stage segmentation strategy. Specifically, the first stage identifies bronchovascular information, which is then utilized in the second stage to guide the segmentation of the pulmonary segments. Quantitative evaluations on the internal dataset demonstrate that our method outperforms the state-of-the-art methods. AHSL achieves a Dice coefficient of 0.923/0.933 for the mapped artery and 0.924/0.934 for the mapped bronchus on computed tomography pulmonary angiography and non-contrast computed tomography, respectively. In the visual assessments on an independent external dataset, AHSL receives scores of 3.71 and 3.69 on a five-point rating system from two radiologists, respectively, indicating the accurate segmentation with excellent generalization and clinical validity. The proposed AHSL achieves superior performance in pulmonary segment segmentation by integrating hierarchical supervision, consistency loss, and a two-stage segmentation strategy, all without requiring voxel-wise pulmonary segment annotations.

Timely intervention of interstitial lung disease (ILD) was promising for attenuating the lung function decline and improving clinical outcomes. The prone position HRCT is essential for early diagnosis of ILD, but limited by its high radiation exposure. This study was aimed to explore whether deep learning reconstruction (DLR) could keep the image quality and reduce the radiation dose compared with hybrid iterative reconstruction (HIR) in prone position scanning for patients of early-stage ILD. This study prospectively enrolled 21 patients with early-stage ILD. All patients underwent high-resolution CT (HRCT) and low-dose CT (LDCT) scans. HRCT images were reconstructed with HIR using standard settings, and LDCT images were reconstructed with DLR (lung/bone kernel) in a mild, standard, or strong setting. Overall image quality, image noise, streak artifacts, and visualization of normal and abnormal ILD features were analysed. The effective dose of LDCT was 1.22 ± 0.09 mSv, 63.7

Background: Multiple spectral images can be extrapolated from Spectral Detector CT (SDCT), ED, and OED images. ED and OED images are highly sensitive to moisture-rich tissues. Moreover, they have the potential to detect pulmonary artery thrombi in non-enhanced chest CT images. Objective: The objective of this study was to assess the sensitivity, specificity, and accuracy of ED and OED images obtained using SDCT for the detection of pulmonary embolism on non-enhanced images. Aims: This study aimed to evaluate the utility of unenhanced spectral imaging, Electron Density (ED), and Overlay Electron Density (OED) images for assessing pulmonary embolisms in patients with suspected or confirmed Acute Pulmonary Embolism (APE). Methods: Seventy-nine patients who underwent unenhanced and Computed Tomography Pulmonary Angiography (CTPA) using dual-layer spectral detector CT to evaluate APE between November, 2021 and April, 2022 were enrolled in this retrospective study. Based on unenhanced spectral and CTPA images, two radiologists identified areas of high density in the main, lobar, and segmental pulmonary arteries on ED and OED images and detected Pulmonary Embolism (PE) on enhanced images using a consultative approach. CTPA results were considered the gold standard. The diagnostic performance of ED and OED in detecting PE was analyzed. Results: PE was detected in 40 patients (40/79), and 17, 69, and 20 PEs were detected in the main, lobar, and segmental arteries, respectively. The PE detection sensitivity on ED images was 69.7–94.7%, and the specificity was 58.5–98.2% for the individual, main, lobe, and segmental pulmonary arteries. The sensitivity and specificity for OED images were 94.1–95.2% and 80.0–98.1%, respectively. The positive predictive value (PPV) and negative predictive value (NPV) were 53.6–87.7% and 69.7–95.9% for ED images and 48.5–88.9% and 94.1–98.9% for OED images, respectively. The accuracy was 76.0–98.9% and 87.3–96.2% when using ED and OED images, respectively. The research identified that whether it was main, lobar, or segmental pulmonary arteries with blood clots, EDW values ranged from 108.1–108.8%EDW, which were 3.9–4.2%EDW higher than those of arteries without emboli. Pulmonary arteries with emboli standardised ED values were 103.6-104.3%EDW. Conclusion: ED and OED images using spectral CT without contrast media demonstrated high diagnostic performance and could improve the visualization of PE.

Objective: This study aimed to compare automated three-dimensional Intrapulmonary Vessel Volume (IPVV) differences between lung and mediastinal windows in healthy individuals using quantitative measurements obtained from chest Computed Tomography (CT) plain scans. Methods: A total of 258 participants (aged 21–83 years) with negative chest CT scans from routine physical examinations conducted between January to November 2023 were retrospectively enrolled. For each healthy participant, an algorithm was used to automatically extract total lung IPVVs as well as IPVVs for vessels of specific diameter. Differences in IPVVs were then compared between those extracted using the lung window and those extracted using the mediastinal window. Results: The IPVVs for the entire lung, intrapulmonary arteries, intrapulmonary veins, and small pulmonary vessels (categorized by different diameters) extracted from the lung window were significantly higher than those extracted from the mediastinal window (p<0.01). No significant sex-based differences in IPVV were observed for pulmonary arteries and veins with diameters between 0.8 and 1.6 mm, as well as pulmonary veins with diameters between 2.4 and 3.2 mm. However, in pulmonary arteries and veins with diameters between 1.6 and 2.4 mm, females had significantly higher IPVVs than males. In all other cases, IPVVs were larger in males than in females. Conclusion: This method of automatic IPVV extraction and quantitative assessment has been proven to be feasible. Automated IPVV expression effectively identified morphological characteristics of intrapulmonary vessels. The study has concluded IPVVs extracted from the lung window to be generally larger than those extracted from the mediastinal window.

Accurate segmentation of pulmonary vessels plays a very critical role in diagnosing and assessing various lung diseases. Currently, many automated algorithms are primarily targeted at CTPA (Computed Tomography Pulmonary Angiography) types of data. However, the segmentation precision of these methods is insufficient, and support for NCCT (Non-Contrast Computed Tomography) types of data is also a requirement in some clinical scenarios. In this study, we propose a 3D image segmentation algorithm for automated pulmonary vessel segmentation from both contrast-enhanced and non-contrast CT images. In the network, we designed a Vessel Lumen Structure Optimization Module (VLSOM), which extracts the centerline (Cl) of vessels and adjusts the weights based on the positional information and adds a Cl-Dice Loss to supervise the stability of the vessels structure. We used 427 sets of high-precision annotated CT data from multiple vendors and countries to train the model and achieved Cl-DICE, Cl-Recall, and Recall values of 0.892, 0.861, 0.924 for CTPA data and 0.925, 0.903, 0.949 for NCCT data. This shows that our model has achieved good performance in both accuracy and completeness of pulmonary vessel segmentation. We finally conducted a clinical visual assessment on an independent external test dataset. The average score for accuracy and robustness, branch abundance, assistance for diagnosis and vascular continuity are 4.26, 4.17, 4.33, 3.83 respectively while the full score is 5. These results highlight the great potential of this method in clinical application.

Abstract Purpose To examine whether there is a significant difference in image quality between the deep learning reconstruction (DLR [AiCE, Advanced Intelligent Clear-IQ Engine]) and hybrid iterative reconstruction (HIR [AIDR 3D, adaptive iterative dose reduction three dimensional]) algorithms on the conventional enhanced and CE-boost (contrast-enhancement-boost) images of indirect computed tomography venography (CTV) of lower extremities. Materials and methods In this retrospective study, seventy patients who underwent CTV from June 2021 to October 2022 to assess deep vein thrombosis and varicose veins were included. Unenhanced and enhanced images were reconstructed for AIDR 3D and AiCE, AIDR 3D-boost and AiCE-boost images were obtained using subtraction software. Objective and subjective image qualities were assessed, and radiation doses were recorded. Results The CT values of the inferior vena cava (IVC), femoral vein ( FV), and popliteal vein (PV) in the CE-boost images were approximately 1.3 (1.31–1.36) times higher than in those of the enhanced images. There were no significant differences in mean CT values of IVC, FV, and PV between AIDR 3D and AiCE, AIDR 3D-boost and AiCE-boost images. Noise in AiCE, AiCE-boost images was significantly lower than in AIDR 3D and AIDR 3D-boost images ( P < 0.05). The SNR (signal-to-noise ratio), CNR (contrast-to-noise ratio), and subjective scores of AiCE-boost images were the highest among 4 groups, surpassing AiCE, AIDR 3D, and AIDR 3D-boost images (all P < 0.05). Conclusion In indirect CTV of the lower extremities images, DLR with the CE-boost technique could decrease the image noise and improve the CT values, SNR, CNR, and subjective image scores. AiCE-boost images received the highest subjective image quality score and were more readily accepted by radiologists.

To explore the performance of low-dose computed tomography (LDCT) with deep learning reconstruction (DLR) for the improvement of image quality and assessment of lung parenchyma. Sixty patients underwent chest regular-dose CT (RDCT) followed by LDCT during the same examination. RDCT images were reconstructed with hybrid iterative reconstruction (HIR) and LDCT images were reconstructed with HIR and DLR, both using lung algorithm. Radiation exposure was recorded. Image noise, signal-to-noise ratio, and subjective image quality of normal and abnormal CT features were evaluated and compared using the Kruskal–Wallis test with Bonferroni correction. The effective radiation dose of LDCT was significantly lower than that of RDCT (0.29 ± 0.03 vs 2.05 ± 0.65 mSv, p < 0.001). The mean image noise ± standard deviation was 33.9 ± 4.7, 39.6 ± 4.3, and 31.1 ± 3.2 HU in RDCT, LDCT HIR-Strong, and LDCT DLR-Strong, respectively (p < 0.001). The overall image quality of LDCT DLR-Strong was significantly better than that of LDCT HIR-Strong (p < 0.001) and comparable to that of RDCT (p > 0.05). LDCT DLR-Strong was comparable to RDCT in evaluating solid nodules, increased attenuation, linear opacity, and airway lesions (all p > 0.05). The visualization of subsolid nodules and decreased attenuation was better with DLR than with HIR in LDCT but inferior to RDCT (all p < 0.05). LDCT DLR can effectively reduce image noise and improve image quality. LDCT DLR provides good performance for evaluating pulmonary lesions, except for subsolid nodules and decreased lung attenuation, compared to RDCT-HIR. The study prospectively evaluated the contribution of DLR applied to chest low-dose CT for image quality improvement and lung parenchyma assessment. DLR can be used to reduce radiation dose and keep image quality for several indications. • DLR enables LDCT maintaining image quality even with very low radiation doses. • Chest LDCT with DLR can be used to evaluate lung parenchymal lesions except for subsolid nodules and decreased lung attenuation. • Diagnosis of pulmonary emphysema or subsolid nodules may require higher radiation doses.

Objective:To explore the value of high-resolution CT (HRCT) visual scores and quantitative analysis in assessing pulmonary Langerhans cell histiocytosis (PLCH) in adults.Methods:In total 51 adult patients with PLCH confirmed by pathology in Peking Union Medical College Hospital from August 2014 to December 2021 were retrospectively analyzed. All patients underwent HRCT and pulmonary function tests (PFT). The involvement of the nodular and cystic lesions were evaluated by two experienced radiologists using CT visual scores. The cases were divided into three groups based on the nodular scores, and into four groups based on the cystic scores, respectively. Ratio of low attenuation areas (LAA%) was measured by an automatic post-processing software. Pulmonary function indices including forced expiratory volume in the first second (FEV 1), forced vital capacity (FVC), FEV 1/FVC, diffusion capacity for carbon monoxide of lung (D LCO), alveolar ventilation (V A), D LCO/V A, D LCO corrected for hemoglobin (D LCOc), D LCOc/V A were collected. FEV 1/FVC was expressed as measured values and other indices were expressed as percent predicted (%pred). Spearman correlation analysis was used to evaluate the correlation between HRCT visual scores, LAA% and PFT. The lung function indices among different nodular groups as well as among different cystic groups were compared using the Kruskal‐Wallis test. Results:Both nodular and cystic lesions were found on HRCT images of all 51 patients. There were no correlation between the visual scores of nodular lesions and lung function indices (all P>0.05). There were no significant differences in lung function indices among different nodular groups (all P>0.05). The visual scores of cystic lesions were negatively correlated with FEV 1/FVC, D LCO%pred, D LCO/V A%pred, D LCOc%pred, D LCOc/V A%pred ( r=-0.491, -0.347, -0.330, -0.373, -0.346, respectively, all P<0.05); the pulmonary function indices among different cystic groups had significant difference (all P<0.05). LAA% were negatively correlated with FEV 1/FVC, D LCO%pred, D LCO/V A%pred, D LCOc%pred, D LCOc/V A%pred ( r=-0.278, -0.378, -0.418, -0.395, -0.451, respectively, all P<0.05). Conclusion:HRCT visual scores of nodular lesions do not correlate with lung function in patients with PLCH. Visual scores and quantitative analysis of the cystic lesions can reflect the impairment degree of pulmonary ventilation and diffusion function to a certain extent, and may be used in assessment of patients with PLCH.

目的 探索深度学习算法提高超重肺间质性病变患者的低剂量CT（Low Dose CT,LDCT）及高分辨率CT（High Resolution CT,HRCT）扫描图像质量的应用效果。方法 前瞻性地纳入20例超重肺间质病（Interstitial Lung Disease,ILD）病例，其中5例为结缔组织病相关ILD，余15例病因不明。所有患者均接受HRCT扫描（120 kVp，自动管电流）和LDCT扫描（120 kVp,30 mAs）。HRCT扫描图像由混合迭代重建算法（Adaptive Iterative Dose Reduction 3-Dimensional, AIDR3D）处理，LDCT图像由深度学习重建算法（Advanced Intelligence Clear-IQ Engine,AiCE，肺/骨算法，mild/standard/strong重建）处理。两名放射科医师分别对图像的噪声、伪影、图像质量、正常结构以及ILD相关的特征表现进行评估，比较LDCT扫描组与HRCT扫描组的图像噪声与图像质量。结果 超重ILD患者应用LDCT扫描方案后，有效扫描剂量比HRCT扫描下降73%。其中，LDCT扫描中，应用肺算法（standard/strong重建）以及骨算法（mild/standard/strong重建）处理的图像噪声约降至HRCT扫描的34.5%～91.7%（P＜0.05），信噪比（范围：24.64～66.23）约为后者（平均值22.75）的1.1～2.9倍（P＜0.001）。两组扫描方案的重建图像主观评分（图像总体评分、伪影、正常结构观察如叶间裂、近端支气管及邻近肺血管、外周支气管及邻近肺血管、胸膜下血管等）均未表现出显著差异（P＞0.05）。在异常征象的评估中，LDCT扫描（肺算法，strong重建）对磨玻璃影的观察显著优于HRCT扫描（P=0.002），在其他异常特征（网格影、支气管扩张及蜂窝征）的观察中，两种方案的图像质量没有显著差异。结论 在超重ILD患者中，应用深度学习算法可以在有效降低辐射剂量的同时，保证图像质量。

Objective:To explore the effect of deep learning reconstruction (DLR) on radiation dosage reduction and image quality of CTPA compared with hybrid iterative reconstruction (HIR).Methods:A total of 100 patients with suspected pulmonary embolism (APE) or indications for CTPA due to other pulmonary artery diseases in Peking Union Medical College Hospital from December 2020 to April 2021 were prospectively enrolled and divided into HIR group and DLR group according to block randomization, with 50 cases in each group. The patient′s gender, age and body mass index (BMI) were recorded. HIR group and DLR group underwent standard deviation (SD)=8.8 and SD=15 CTPA protocols in combination with HIR and DLR algorithm respectively. Other scanning parameters and contrast medium injection plan were the same. The effective dose (ED) and size-specific dose estimate (SSDE) were calculated. Regions of interest (ROIs) were drawn in the lumen of Grade 1-3 pulmonary arteries and bilateral paravertebral muscles. The corresponding CT and SD values were recorded to acquire signal to noise ratio (SNR) and contrast noise ratio (CNR). Based on a double-blind method, two radiologists evaluated the subjective noise, visualization of pulmonary arteries, and diagnostic confidence of the two groups by 5-point Likert scales. The inconsistent results were judged comprehensively by the third radiologist. Independent samples t-test was used to compare the demographic data, radiation dosage and quantitative image quality of the two groups. Mann-Whitney U test was used to compare the subjective noise, visualization of pulmonary arteries and diagnostic confidence between the two groups. Linear weighted Kappa coefficient was calculated to analyze the consistency of the qualitative scores between the two radiologists. Results:There were no significant differences in gender, age and BMI between the two groups ( P>0.05). The CT values of Grade1-3 pulmonary arteries and paravertebral muscle had no significant differences ( P>0.05). Compared with HIR group, the ED and SSDE in DLR group decreased by about 35% to 1.3 mSv and 4.20 mGy respectively, while the SNR (30±5) and CNR (26±5) of CTPA images were higher in DLR group than those in HIR group (23±5 and 20±5, with t=-6.60 and -5.90, respectively, both P<0.001). The subjective noise score was higher in DLR group than that in HIR group ( Z=-7.34, P<0.001). In addition, two radiologists showed excellent interobserver agreement in DLR group (Kappa=0.847, 95%CI 0.553-1.000). No significant differences were found in visualization of pulmonary arteries and diagnostic confidence between the two groups ( P>0.05). Conclusion:DLR further reduced the radiation dosage and improved the image quality of CTPA, with no detriment to diagnostic confidence. Thus DLR is worthy of clinical promotion.

Objective:To evaluate the effectiveness of deep learning reconstruction (DLR) compared with hybrid iterative reconstruction (Hybrid IR) in improving the image quality in chest low-dose CT (LDCT).Methods:Seventy-seven patients who underwent LDCT scan for physical examination or regular follow-up in Peking Union Medical College Hospital from October 2020 to March 2021 were retrospectively included. The LDCT images were reconstructed with Hybrid IR at standard level (Hybrid IR Stand) and DLR at standard and strong level (DLR Stand and DLR Strong). Regions of interest were placed on pulmonary lobe, aorta, subscapularis muscle and axillary fat to measure the CT value and image noise. The signal to noise ratio (SNR) and contrast to noise ratio (CNR) were calculated. Subjective image quality was evaluated using Likert 5-score method by two experienced radiologists. The number and features of ground-glass nodule (GGN) were also assessed. If the scores of the two radiologists were inconsistent, the score was determined by the third radiologist. The objective and subjective image evaluation were compared using the Kruskal-Wallis test, and the Bonferroni test was used for multiple comparisons within the group.Results:Among Hybrid IR Stand, DLR Stand and DLR Strong images, the CT value of pulmonary lobe, aorta, subscapularis muscle and axillary fat had no significant differences (all P>0.05), but the image noise and SNR of pulmonary lobe, aorta, subscapularis muscle and axillary fat had significant differences(all P<0.05), and the CNR of images had significant difference( P<0.05), too. The CNR of Hybrid IR Stand images, DLR stand images and DLR strong images were 0.71 (0.49, 0.88), 1.06 (0.78, 1.32) and 1.14 (0.84, 1.48), respectively. Compared with Hybrid IR images, DLR images had lower objective and subjective image noise,higher SNR and CNR (all P<0.05). The scores of DLR images were superior to Hybrid IR images in identifying lung fissures, pulmonary vessels, trachea and bronchi, lymph nodes, pleura, pericardium and GGN (all P<0.05). Conclusions:DLR significantly reduced the image noise, and DLR images were superior to Hybrid IR images in identifying GGN in chest LDCT while maintaining superior image quality at relatively low radiation dose levels. Thus DLR images can improve the safety of lung cancer screening and pulmonary nodule follow-up by CT.

OBJECTIVES:To investigate whether deep learning reconstruction (DLR) could keep image quality and reduce radiation dose in interstitial lung disease (ILD) patients compared with HRCT reconstructed with hybrid iterative reconstruction (hybrid-IR).METHODS:Seventy ILD patients were prospectively enrolled and underwent HRCT (120 kVp, automatic tube current) and LDCT (120 kVp, 30 mAs) scans. HRCT images were reconstructed with hybrid-IR (Adaptive Iterative Dose Reduction 3-Dimensional [AIDR3D], standard-setting); LDCT images were reconstructed with DLR (Advanced Intelligence Clear-IQ Engine [AiCE], lung/bone, mild/standard/strong setting). Image noise, streak artifact, overall image quality, and visualization of normal and abnormal features of ILD were evaluated.RESULTS:The mean radiation dose of LDCT was 38% of HRCT. Objective image noise of reconstructed LDCT images was 33.6 to 111.3% of HRCT, and signal-to-noise ratio (SNR) was 0.9 to 3.1 times of the latter (p < 0.001). LDCT-AiCE was not significantly different from or even better than HRCT in overall image quality and visualization of normal lung structures. LDCT-AiCE (lung, mild/standard/strong) showed progressively better recognition of ground glass opacity than HRCT-AIDR3D (p < 0.05, p < 0.01, p < 0.001), and LDCT-AiCE (lung, mild/standard/strong; bone, mild) was superior to HRCT-AIDR3D in visualization of architectural distortion (p < 0.01, p < 0.01, p < 0.01; p < 0.05). LDCT-AiCE (bone, strong) was better than HRCT-AIDR3D in the assessment of bronchiectasis and/or bronchiolectasis (p < 0.05). LDCT-AiCE (bone, mild/standard/strong) was significantly better at the visualization of honeycombing than HRCT-AIDR3D (p < 0.05, p < 0.05, p < 0.01).CONCLUSION:Deep learning reconstruction could effectively reduce radiation dose and keep image quality in ILD patients compared to HRCT with hybrid-IR.KEY POINTS:• Deep learning reconstruction was a novel image reconstruction algorithm based on deep convolutional neural networks. It was applied in chest CT studies and received auspicious results. • HRCT plays an essential role in the whole process of diagnosis, treatment efficacy evaluation, and follow-ups for interstitial lung disease patients. However, cumulative radiation exposure could increase the risks of cancer. • Deep learning reconstruction method could effectively reduce the radiation dose and keep the image quality compared with HRCT reconstructed with hybrid iterative reconstruction in patients with interstitial lung disease.

Objective:To investigate the feasibility of chest ultra-low dose CT (ULDCT) using deep learning reconstruction (DLR) for lung cancer screening, and to compare its image quality and nodule detection rate with ULDCT iterative reconstruction (Hybrid IR) and conventional dose CT (RDCT) Hybrid IR.Methods:The patients who underwent chest CT examination for pulmonary nodules in Peking Union Medical College Hospital from October 2020 to March 2021 were prospectively included and underwent chest RDCT (120 kVp, automatic tube current), followed by ULDCT (100 kVp, 20 mA). The RDCT images were reconstructed with Hybrid IR (adaptive iterative dose reduction 3D,AIDR 3D), and ULDCT was reconstructed with AIDR3D and DLR. Radiation dose parameters and nodule numbers were recorded. Image quality was assessed using objective noise, signal-to-noise ratio (SNR) of the main trachea and left upper lobe, subjective image scores of the lung and nodules. Subjective scores were scored by 2 experienced radiologists on a Likert 5-point scale. The difference of radiation dose was compared with paired t-test between ULDCT and RDCT.The differences of quantitative indexes, objective image noise and subjective scores of the three reconstruction methods were compared with one-way analysis of variance or Friedman test. Results:Forty-five patients were enrolled, including 17 males and 28 females, aged from 32 to 74 (55±11) years. The radiation dose of ULDCT was (0.17±0.01) mSv, which was significantly lower than that of RDCT [(1.35±0.41) mSv, t=15.46, P<0.001]. There were significant differences in the image noise and SNR in the trachea and lung parenchyma and in the CT value of the trachea among ULDCT-AICE, ULDCT-AIDR 3D and RDCT-AIDR 3D images ( P<0.05). Image noise in the trachea and lung parenchyma and CT value in the trachea of ULDCT-AICE were significantly lower than those of ULDCT-AIDR 3D ( P<0.05) and comparable to RDCT-AIDR 3D ( P>0.05). There were significant differences in subjective image scores of the lung and nodules among ULDCT-AICE, ULDCT-AIDR 3D and RDCT-AIDR 3D images (χ2=50.57,117.20, P<0.001). Subjective image scores of the lung and nodules for ULDCT-AICE were significantly higher than those of ULDCT-AIDR 3D ( P<0.05), and non-inferior to RDCT-ADIR 3D ( P>0.05). All 72 clinically significant nodules detected on RDCT-ADIR 3D were also noted on ULDCT-AICE and ULDCT-AIDR 3D images. Conclusions:Chest ULDCT using DLR can significantly reduce the radiation dose, and compared with Hybrid IR, it can effectively reduce the image noise and improve SNR, and display the pulmonary nodules well. The image quality and nodule detection are not inferior to RDCT Hybrid IR routinely used in clinical practice.

我国放射科住院医师规范化培训发展迅速, 在新型冠状病毒肺炎疫情防控期间, 大量教学内容转化为线上教育, 面临线上教学条件和资源不足, 在线课程互动不足等挑战, 为此, 我们需要加强线上课程资源建设, 增加线上课程的互动交流, 优化医学影像学人才的培养体系。

ObjectiveTo analyze surveys measuring the prevalence of burnout among Chinese doctors and reveal the overall prevalence, characteristics, timeline, and factors related to burnout.MethodsA comprehensive search was conducted on China National Knowledge Infrastructure, WANFANG, PubMed, EMBASE, PsycINFO and Cochrane Library databases from their inception to 28 February 2021. Random-effects meta-analyses, meta-regression and planned subgroup analyses were performed, and the standardized mean difference was adopted for comparisons between subgroups. Egger's and Begg's tests were performed to evaluate publication bias. Heterogeneity across the studies was tested using the I2 statistic. The study protocol was registered on PROSPERO (CRD42018104249).ResultsIn total, 3,210 records were reviewed; 64 studies including 48,638 Chinese doctors were eligible for meta-analysis. The prevalence of burnout increased continuously from 2008 to 2017 and decreased significantly from 2018 to 2020, a little increase from 2020 to 2021. The overall prevalence of burnout was 75.48% (95% CI, 69.20 to 81.26; I2 = 99.23%, P < 0.001), and high burnout was 9.37% (95% CI, 4.91 to 15.05, I2 = 98.88%, P < 0.001). The prevalence of emotional exhaustion was 48.64% (95% CI, 38.73 to 58.59; I2 = 99.53%, P < 0.001), depersonalization was 54.67% (95% CI, 46.95 to 62.27; I2 = 99.20%, P < 0.001), and reduced personal accomplishment was 66.53% (95% CI, 58.13 to 74.44; I2 = 99.37%, P < 0.001). Gender, marriage, professional title and specialty all influenced burnout.ConclusionsThe results showed that the total prevalence of doctor burnout in China is very high. The prevalence of burnout varies by location. Gender, marital status and professional title all affect burnout scores.