A Challenge for Emphysema Quantification Using a Deep Learning Algorithm With Low-dose Chest Computed Tomography

Choi, Hyewon; Kim, Hyungjin; Jin, Kwang Nam; Jeong, Yeon Joo; Chae, Kum Ju; Lee, Kyung Hee; Yong, Hwan Seok; Gil, Bomi; Lee, Hye Jeong; Lee, Ki Yeol; Jeon, Kyung Nyeo; Yi, Jaeyoun; Seo, Sola; Ahn, Chulkyun; Lee, Joonhyung; Oh, Kyuhyup; Goo, Jin Mo

doi:10.1097/rti.0000000000000647

Cited by 8 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Iterative reconstruction techniques synthesize projections by modelling the data collection process based on the noise properties of the imaged objects to allow dose reductions of 32~65% without increasing noise in the reconstructed images that are produced. Recently, one study evaluated the performance of various deep learning-based algorithms for emphysema quantification using a dataset with different low dose CT protocols and showed that intraclass correlation coefficients of emphysema index between standard-dose CT and converted low-dose CT scans using deep learning-based algorithms ranged from 0.85 to 0.94 [ 22 ]. Although deep learning-based algorithms can improve emphysema quantification from low-dose CT with heterogenous CT protocols, it is not clear whether this also applies to emphysema quantification for ultra-low-dose CT scans.…”

Section: Discussionmentioning

confidence: 99%

Emphysema Quantification Using Ultra-Low-Dose Chest CT: Efficacy of Deep Learning-Based Image Reconstruction

et al. 2022

View full text Add to dashboard Cite

Background and Objectives: Although reducing the radiation dose level is important during diagnostic computed tomography (CT) applications, effective image quality enhancement strategies are crucial to compensate for the degradation that is caused by a dose reduction. We performed this prospective study to quantify emphysema on ultra-low-dose CT images that were reconstructed using deep learning-based image reconstruction (DLIR) algorithms, and compared and evaluated the accuracies of DLIR algorithms versus standard-dose CT. Materials and Methods: A total of 32 patients were prospectively enrolled, and all underwent standard-dose and ultra-low-dose (120 kVp; CTDIvol < 0.7 mGy) chest CT scans at the same time in a single examination. A total of six image datasets (filtered back projection (FBP) for standard-dose CT, and FBP, adaptive statistical iterative reconstruction (ASIR-V) 50%, DLIR-low, DLIR-medium, DLIR-high for ultra-low-dose CT) were reconstructed for each patient. Image noise values, emphysema indices, total lung volumes, and mean lung attenuations were measured in the six image datasets and compared (one-way repeated measures ANOVA). Results: The mean effective doses for standard-dose and ultra-low-dose CT scans were 3.43 ± 0.57 mSv and 0.39 ± 0.03 mSv, respectively (p < 0.001). The total lung volume and mean lung attenuation of five image datasets of ultra-low-dose CT scans, emphysema indices of ultra-low-dose CT scans reconstructed using ASIR-V 50 or DLIR-low, and the image noise of ultra-low-dose CT scans that were reconstructed using DLIR-low were not different from those of standard-dose CT scans. Conclusions: Ultra-low-dose CT images that were reconstructed using DLIR-low were found to be useful for emphysema quantification at a radiation dose of only 11% of that required for standard-dose CT.

show abstract

Section: Discussionmentioning

confidence: 99%

Emphysema Quantification Using Ultra-Low-Dose Chest CT: Efficacy of Deep Learning-Based Image Reconstruction

et al. 2022

View full text Add to dashboard Cite

show abstract

“…2, 3). The algorithm was based on a 2.5-dimensional U-net architecture and was trained with 468 pairs of LDCT and standard-dose CT images obtained from patients at 9 different institutions using various scanners 20 . The detailed information regarding the development of the kernel adaptation algorithm is described in a previous literature 20 .…”

Section: Methodsmentioning

confidence: 99%

“…Reduction of noise in CT images obtained using lower radiation dose is a representative application of these artificial intelligence algorithms 16–18 . Generation of images mimicking standard-dose, low-frequency kernel CT images from low-dose, high-frequency kernel CT images may help in better quantitative evaluation of pulmonary emphysema and prediction of long-term outcomes of individuals undergoing LDCTs 19,20 …”

mentioning

confidence: 99%

Deep Learning–Based Kernel Adaptation Enhances Quantification of Emphysema on Low-Dose Chest CT for Predicting Long-Term Mortality

2024

Self Cite

View full text Add to dashboard Cite

Objectives The aim of this study was to ascertain the predictive value of quantifying emphysema using low-dose computed tomography (LDCT) post deep learning–based kernel adaptation on long-term mortality. Materials and Methods This retrospective study investigated LDCTs obtained from asymptomatic individuals aged 60 years or older during health checkups between February 2009 and December 2016. These LDCTs were reconstructed using a 1- or 1.25-mm slice thickness alongside high-frequency kernels. A deep learning algorithm, capable of generating CT images that resemble standard-dose and low-frequency kernel images, was applied to these LDCTs. To quantify emphysema, the lung volume percentage with an attenuation value less than or equal to −950 Hounsfield units (LAA-950) was gauged before and after kernel adaptation. Low-dose chest CTs with LAA-950 exceeding 6% were deemed emphysema-positive according to the Fleischner Society statement. Survival data were sourced from the National Registry Database at the close of 2021. The risk of nonaccidental death, excluding causes such as injury or poisoning, was explored according to the emphysema quantification results using multivariate Cox proportional hazards models. Results The study comprised 5178 participants (mean age ± SD, 66 ± 3 years; 3110 males). The median LAA-950 (18.2% vs 2.6%) and the proportion of LDCTs with LAA-950 exceeding 6% (96.3% vs 39.3%) saw a significant decline after kernel adaptation. There was no association between emphysema quantification before kernel adaptation and the risk of nonaccidental death. Nevertheless, after kernel adaptation, higher LAA-950 (hazards ratio for 1% increase, 1.01; P = 0.045) and LAA-950 exceeding 6% (hazards ratio, 1.36; P = 0.008) emerged as independent predictors of nonaccidental death, upon adjusting for age, sex, and smoking status. Conclusions The application of deep learning for kernel adaptation proves instrumental in quantifying pulmonary emphysema on LDCTs, establishing itself as a potential predictive tool for long-term nonaccidental mortality in asymptomatic individuals.

show abstract

“…Pulmonary emphysema is de ned as abnormal permanent enlargement of airspaces distal to the terminal bronchioles [8,9] and results in low attenuated areas (LAA) in chest CT which are below -950 Hounse eld unit (HU). [3] Since the extent of emphysema in CT is associated with pulmonary function decline, [10] variables representing emphysema were evaluated.…”

Section: Variables Explanation and Outcome De Nitionmentioning

confidence: 99%

Predicting postoperative lung function in lung cancer patients by using imaging biomarkers

Kwon

Lee

Park

et al. 2023

Preprint

View full text Add to dashboard Cite

Background There were previous studies to predict postoperative lung function with pulmonary function test (PFT). Computing tomography (CT) can quantitatively measure small airway wall thickness, lung volume, pulmonary vessel volume, and emphysema area, which reflect the severity of respiratory diseases. These measurements are considered as imaging biomarkers. This study aimed to predict postoperative lung function with imaging biomarkers. Methods Retrospective analysis of 79 lung cancer patients who underwent lung surgery was completed. Postoperative lung function measured by forced expiratory volume in one second (FEV1) was defined as an outcome. Preoperative clinico-pathological parameters and imaging biomarkers representing airway wall thickness, severity of emphysema, total lung volume, and pulmonary vessel volume were measured quantitatively in chest CT by an automated segmentation software, AVIEW COPD. Logistic and linear regression were used to assess these variables. If the actual postoperative FEV1 was higher than the projected postoperative FEV1 by a formula, the group was considered to be preserved. Results Among 79 patients, 16 patients were grouped as a non-preserved group and 63 were grouped as a preserved group. Patients in the preserved FEV1 group had a higher vessel volume than the non-preserved group. Pi1 and Wafw were independent predictors of postoperative lung function. Conclusion Imaging biomarkers can be considered as significant variables in predicting postoperative lung function in patients with lung cancer.

show abstract

A Challenge for Emphysema Quantification Using a Deep Learning Algorithm With Low-dose Chest Computed Tomography

Cited by 8 publications

References 32 publications

Emphysema Quantification Using Ultra-Low-Dose Chest CT: Efficacy of Deep Learning-Based Image Reconstruction

Emphysema Quantification Using Ultra-Low-Dose Chest CT: Efficacy of Deep Learning-Based Image Reconstruction

Deep Learning–Based Kernel Adaptation Enhances Quantification of Emphysema on Low-Dose Chest CT for Predicting Long-Term Mortality

Predicting postoperative lung function in lung cancer patients by using imaging biomarkers

Contact Info

Product

Resources

About