Effect of New Model-Based Iterative Reconstruction on Quantitative Analysis of Airway Tree by Computer-Aided Detection Software in Chest Computed Tomography.
- 作者列表："Jia Y","Zhai B","He T","Yu Y","Yu N","Duan H","Yang C","Li JY
OBJECTIVE:Compared the performance of computer-aided detection (CAD) software for quantitative analysis of airway using computed tomography (CT) images reconstructed with versions of model-based iterative reconstruction (MBIR) that either balances spatial and density resolution (MBIRSTND) or prefers spatial resolution (MBIRRP20), and adaptive statistical iterative reconstruction (ASIR) with lung kernel. METHODS:Thirty patients were included who were scanned for pulmonary disease using a routine dose multidetector CT system. Data were reconstructed with ASIR, MBIRSTND, and MBIRRP20. Airway dimensions from the 3 reconstructions were measured using an automated, quantitative CAD software designed to segment and quantify the bronchial tree automatically using a skeletonization algorithm. For each patient and reconstruction algorithm, the right middle lobe bronchus was selected as a representative for measuring the bronchial length of the matched airways. Two radiologists used a semiquantitative 5-point scale to rate the subjective image quality of MBIRSTND and MBIRRP20 reconstructions on airway trees analysis. RESULTS:Algorithm impacts the measurement variability of bronchus length in chest CT, MBIRRP20 were the best, whereas ASIR were the worst (P < 0.05). In addition, the optimal reconstruction algorithm was found to be MBIRSTND for the airway trees being assessed about subjective noise and MBIRRP20 about bronchial end shows, and there were no significant differences in the continuity and completeness of bronchial wall, whereas ASIR performed inferiorly compared with them (P < 0.05). CONCLUSIONS:Compared with ASIR, MBIRSTND, and MBIRRP20 from MBIRn algorithm potentially allow the desired airway quantification accuracy to be achieved on the performance of CAD, especially for MBIRRP20.
目的: 比较计算机辅助检测 (CAD) 软件的性能，利用计算机断层扫描 (CT) 图像与基于模型的迭代重建 (MBIR) 版本进行气道定量分析即平衡空间和密度分辨率 (MBIRSTND) 或偏好空间分辨率 (MBIRRP20)，以及具有肺核的自适应统计迭代重建 (ASIR)。 方法: 采用常规剂量多排螺旋ct 对 30 例肺部疾病患者进行扫描。用 ASIR 、 MBIRSTND 和 mbirrp20 重建数据。使用自动定量 cad软件测量 3 次重建的气道尺寸，该软件旨在使用骨骼化算法自动分割和定量支气管树。对于每个患者和重建算法，选择右中叶支气管作为测量匹配气道支气管长度的代表。两名放射科医生使用半定量 5 点量表对 MBIRSTND 和 MBIRRP20 重建的主观图像质量进行气道树分析。 结果: 算法影响胸部 CT 支气管长度的测量变异性，MBIRRP20 最好，ASIR 最差 (P
METHODS:Background Dye localization is a useful method for the resection of unidentifiable small pulmonary lesions. This study compares the transbronchial route with augmented fluoroscopic bronchoscopy (AFB) and conventional transthoracic CT-guided methods for preoperative dye localization in thoracoscopic surgery. Methods Between April 2015 and March 2019, a total of 231 patients with small pulmonary lesions who received preoperative dye localization via AFB or percutaneous CT-guided technique were enrolled in the study. A propensity-matched analysis, incorporating preoperative variables, was used to compare localization and surgical outcomes between the two groups. Results After matching, a total of 90 patients in the AFB group ( N = 30) and CT-guided group ( N = 60) were selected for analysis. No significant difference was noted in the demographic data between both the groups. Dye localization was successfully performed in 29 patients (96.7%) and 57 patients (95%) with AFB and CT-guided method, respectively. The localization duration (24.1 ± 8.3 vs. 21.4 ± 12.5 min, p = 0.297) and equivalent dose of radiation exposure (3.1 ± 1.5 vs. 2.5 ± 2.0 mSv, p = 0.130) were comparable in both the groups. No major procedure-related complications occurred in either group; however, a higher rate of pneumothorax (0 vs. 16.7%, p = 0.029) and focal intrapulmonary hemorrhage (3.3 vs. 26.7%, p = 0.008) was noted in the CT-guided group. Conclusion AFB dye marking is an effective alternative for the preoperative localization of small pulmonary lesions, with a lower risk of procedure-related complications than the conventional CT-guided method.
METHODS:Background The use of artificial intelligence, including machine learning, is increasing in medicine. Use of machine learning is rising in the prediction of patient outcomes. Machine learning may also be able to enhance and augment anesthesia clinical procedures such as airway management. In this study, we sought to develop a machine learning algorithm that could classify vocal cords and tracheal airway anatomy real-time during video laryngoscopy or bronchoscopy as well as compare the performance of three novel convolutional networks for detecting vocal cords and tracheal rings. Methods Following institutional approval, a clinical dataset of 775 video laryngoscopy and bronchoscopy videos was used. The dataset was divided into two categories for use for training and testing. We used three convolutional neural networks (CNNs): ResNet, Inception and MobileNet. Backpropagation and a mean squared error loss function were used to assess accuracy as well as minimize bias and variance. Following training, we assessed transferability using the generalization error of the CNN, sensitivity and specificity, average confidence error, outliers, overall confidence percentage, and frames per second for live video feeds. After the training was complete, 22 models using 0 to 25,000 steps were generated and compared. Results The overall confidence of classification for the vocal cords and tracheal rings for ResNet, Inception and MobileNet CNNs were as follows: 0.84, 0.78, and 0.64 for vocal cords, respectively, and 0.69, 0.72, 0.54 for tracheal rings, respectively. Transfer learning following additional training resulted in improved accuracy of ResNet and Inception for identifying the vocal cords (with a confidence of 0.96 and 0.93 respectively). The two best performing CNNs, ResNet and Inception, achieved a specificity of 0.985 and 0.971, respectively, and a sensitivity of 0.865 and 0.892, respectively. Inception was able to process the live video feeds at 10 FPS while ResNet processed at 5 FPS. Both were able to pass a feasibility test of identifying vocal cords and tracheal rings in a video feed. Conclusions We report the development and evaluation of a CNN that can identify and classify airway anatomy in real time. This neural network demonstrates high performance. The availability of artificial intelligence may improve airway management and bronchoscopy by helping to identify key anatomy real time. Thus, potentially improving performance and outcomes during these procedures. Further, this technology may theoretically be extended to the settings of airway pathology or airway management in the hands of experienced providers. The researchers in this study are exploring the performance of this neural network in clinical trials.
METHODS:BACKGROUND:The optimal mode of delivering topical anesthesia during flexible bronchoscopy remains unknown. This article compares the efficacy and safety of nebulized lignocaine, lignocaine oropharyngeal spray, or their combination. METHODS:Consecutive subjects were randomized 1:1:1 to receive nebulized lignocaine (2.5 mL of 4% solution, group A), oropharyngeal spray (10 actuations of 10% lignocaine, group B), or nebulization (2.5 mL, 4% lignocaine) and two actuations of 10% lignocaine spray (group C). The primary outcome was the subject-rated severity of cough according to a visual analog scale. The secondary outcomes included bronchoscopist-rated severity of cough and overall procedural satisfaction on a visual analog scale, total lignocaine dose, subject's willingness to undergo a repeat procedure, adverse reactions to lignocaine, and others. RESULTS:A total of 1,050 subjects (median age, 51 years; 64.8% men) were included. The median (interquartile range) score for subject-rated cough severity was significantly lower in group B compared to group C or group A (4 [1-10] vs 11 [4-24] vs 13 [5-30], respectively; P < .001). The bronchoscopist-rated severity of cough was also the least (P < .001), and the overall satisfaction was highest in group B (P < .001). The cumulative lignocaine dose administered was the least in group B (P < .001). A significantly higher proportion of subjects (P < .001) were willing to undergo a repeat bronchoscopy in group B (73.7%) than in groups A (49.1%) and C (59.4%). No lignocaine-related adverse events were observed. CONCLUSIONS:Ten actuations of 10% lignocaine oropharyngeal spray were superior to nebulized lignocaine or their combination for topical anesthesia during diagnostic flexible bronchoscopy. TRIAL REGISTRY:ClinicalTrials.gov; No.: NCT03109392; URL: www.clinicaltrials.gov.