Journal of Thoracic Imaging最新文献

Purpose: Compare the impact of photon-counting detector computed tomography (PCD-CT) to conventional CT on an interstitial lung disease (ILD) quantitative machine learning (QML) model.

Materials and methods: A QML model analyzed 52 CT exams from patients who underwent same-day conventional and PCD-CT for suspected ILD. Lin's concordance correlation coefficient (CCC) assessed agreement between conventional and PCD-CT QML results. A CCC >0.90 was regarded as excellent, 0.9 to 0.8 as good, and <0.80 as a poor concordance. Spearman rank correlation evaluated the association between pulmonary function test results (PFT) and QML features (reticulation [R], honeycombing [HC], ground glass [GG], interstitial lung disease [ILD], and vessel-related structures [VRS]). Correlations were statistically significant if the 95% CI did not include 0.00 and P value <0.05.

Results: Conventional and PCD-CT QML results had good to excellent concordance (CCC ≥0.8) except for total HC (CCC <0.8), likely related to better PCD-CT honeycombing delineation. Overall, compared with conventional CT, PCD-CT had consistently more statistically significant correlation with PFT for HC (9 PCD vs. 2 conventional of 28 total and regional associations), similar correlation for R (20 PCD vs. 18 conventional of 28 associations) and VRS (19 PCD vs. 23 conventional of 28 associations), and less correlation for GG extent (12 PCD vs. 20 conventional associations).

Conclusions: There is strong agreement between conventional and PCD-CT QML ILD features except for HC. PCD-CT improved HC but decreased GG extent correlation with PFT. Therefore, even though most quantitative features were not impacted by the newer PCD-CT technology, model adjustment is necessary.

Drug-induced acute lung injury is a significant yet often underrecognized clinical challenge, associated with a wide range of therapeutic agents, including chemotherapy drugs, antibiotics, anti-inflammatory drugs, and immunotherapies. This comprehensive review examines the pathophysiology, clinical manifestations, and radiologic findings of drug-induced acute lung injury across different drug categories. Common imaging findings are highlighted to aid radiologists and clinicians in early recognition and diagnosis. The review emphasizes the importance of immediate cessation of the offending drug and supportive care, which may include corticosteroids. Understanding these patterns is crucial for prompt diagnosis and management, potentially improving patient outcomes.

Purpose: This study was designed to construct progressive binary classification models based on radiomics and deep learning to predict the presence of epidermal growth factor receptor (EGFR) and TP53 mutations and to assess the models' capacities to identify patients who are suitable for TKI-targeted therapy and those with poor prognoses.

Materials and methods: A total of 267 patients with lung adenocarcinomas who underwent genetic testing and noncontrast chest computed tomography from our hospital were retrospectively included. Clinical information and imaging characteristics were gathered, and high-throughput feature acquisition on all defined regions of interest (ROIs) was carried out. We selected features and constructed clinical models, radiomics models, deep learning models, and ensemble models to predict EGFR status with all patients and TP53 status with EGFR-positive patients, respectively. The validity and reliability of each model were expressed as the area under the curve (AUC), sensitivity, specificity, accuracy, precision, and F1 score.

Results: We constructed 7 kinds of models for 2 different dichotomies, namely, the clinical model, the radiomics model, the DL model, the rad-clin model, the DL-clin model, the DL-rad model, and the DL-rad-clin model. For EGFR- and EGFR+, the DL-rad-clin model got the highest AUC value of 0.783 (95% CI: 0.677-0.889), followed by the rad-clin model, the DL-clin model, and the DL-rad model. In the group with an EGFR mutation, for TP53- and TP53+, the rad-clin model got the highest AUC value of 0.811 (95% CI: 0.651-0.972), followed by the DL-rad-clin model and the DL-rad model.

Conclusion: Our progressive binary classification models based on radiomics and deep learning may provide a good reference and complement for the clinical identification of TKI responders and those with poor prognoses.

Purpose: To perform a systematic review and meta-analysis of relevant studies to assess the diagnostic accuracy and safety outcomes of ultrasound (US)-guided transthoracic needle biopsy (TTNB) for peripheral lung and pleural lesions.

Materials and methods: A search was performed through Medline, Embase, Web of Science, and Cochrane Central from inception up to September 23, 2022 for diagnostic accuracy studies reporting US-guided TTNB (Prospero registration: CRD42021225168). The primary outcome was diagnostic accuracy, which was assessed by sensitivity, specificity, likelihood ratios (LR), and diagnostic odds ratio. Sensitivity and subgroup analyses were performed to evaluate inter-study heterogeneity. The secondary outcome was the frequency of complications. Random-effects models were used for the analyses. The risk of bias and the applicability of the included studies were assessed using the QUADAS-2 tool. Publication bias was assessed by testing the association between the natural logarithm of the diagnostic odds ratio and the effective sample size.

Results: Of the 7841 citations identified, 83 independent cohorts (11,767 patients) were included in the analysis. The pooled sensitivity of US-TTNB was 88% (95% CI: 86%-91%, 80 studies). Pooled specificity was 100% (95% CI: 99%-100%, 72 studies), resulting in positive LR, negative LR, and diagnostic odds ratio of 946 (-743 to 2635), 0.12 (0.09 to 0.14), and 8141 (1344 to 49,321), respectively. Complications occurred in 4% (95% CI: 3%-5%) of the procedures, with pneumothorax being the most frequent (3%; 95% CI: 2%-3%, 72 studies) and resulting in chest tube placement in 0.4% (95% CI: 0.2%-0.7%, 64 studies) of the procedures.

Conclusions: US-TTNB is an effective and safe procedure for pleural lesions and peripheral lung lesions.

Purpose: Bronchiectasis is associated with loss of lung function, substantial use of health care resources, and increased morbidity and mortality in people with cardiopulmonary diseases. We assessed the frequency of progression or new development of bronchiectasis and predictors of progression in participants in low-dose computed tomography (CT) screening programs.

Materials and methods: We reviewed our prospectively enrolled screening cohort in the Early Lung and Cardiac Action Program cohort of smokers, aged 40 to 90, between 2010 and 2019, and medical records to assess the progression of bronchiectasis after five or more years of follow-up after baseline low-dose CT. Logistic and multivariate-analysis-of-covariance regression analyses were used to examine factors associated with bronchiectasis progression.

Results: Among 2182 baseline screening participants, we identified 534 (mean age: 65±9 y; 53.6% women) with follow-up screening of 5+ years (median follow-up: 103.2 mo). Of the 534 participants, 34 (6.4%) participants had progressed (25/126, 19.8%) or newly developed (9/408, 2.2%) bronchiectasis. Significant predictors of progression (progressed+newly developed) were: age (P=0.03), pack-years of smoking (P=0.004), baseline components of the ELCAP Bronchiectasis Score, including the severity of bronchial dilatation (P=0.01), its extent (P=0.01), bronchial wall thickening (P=0.04), and mucoid impaction (P<0.001).

Conclusions: Assuming similar progression rates, ~136 out of 2182 participants are expected to progress on follow-up screening. This study sheds light on bronchiectasis progression and its significant predictors in a low-dose CT screening program. We recommend reporting bronchiectasis as participants who have smoked are at increased risk, and continued assessment over the entire period of participation in the low-dose CT screening program would allow for the identification of possible causes, early warning, and even early treatment.

Purpose: To investigate and compare the diagnostic performance of 10 different large language models (LLMs) and 2 board-certified general radiologists in thoracic radiology cases published by The Society of Thoracic Radiology.

Materials and methods: We collected publicly available 124 "Case of the Month" from the Society of Thoracic Radiology website between March 2012 and December 2023. Medical history and imaging findings were input into LLMs for diagnosis and differential diagnosis, while radiologists independently visually provided their assessments. Cases were categorized anatomically (parenchyma, airways, mediastinum-pleura-chest wall, and vascular) and further classified as specific or nonspecific for radiologic diagnosis. Diagnostic accuracy and differential diagnosis scores (DDxScore) were analyzed using the χ2, Kruskal-Wallis, Wilcoxon, McNemar, and Mann-Whitney U tests.

Results: Among the 124 cases, Claude 3 Opus showed the highest diagnostic accuracy (70.29%), followed by ChatGPT 4/Google Gemini 1.5 Pro (59.75%), Meta Llama 3 70b (57.3%), ChatGPT 3.5 (53.2%), outperforming radiologists (52.4% and 41.1%) and other LLMs (P<0.05). Claude 3 Opus DDxScore was significantly better than other LLMs and radiologists, except ChatGPT 3.5 (P<0.05). All LLMs and radiologists showed greater accuracy in specific cases (P<0.05), with no DDxScore difference for Perplexity and Google Bard based on specificity (P>0.05). There were no significant differences between LLMs and radiologists in the diagnostic accuracy of anatomic subgroups (P>0.05), except for Meta Llama 3 70b in the vascular cases (P=0.040).

Conclusions: Claude 3 Opus outperformed other LLMs and radiologists in text-based thoracic radiology cases. LLMs hold great promise for clinical decision systems under proper medical supervision.

Purpose: To evaluate the accuracy of ultra-low dose (ULD) chest computed tomography (CT), with a radiation exposure equivalent to a 2-view chest x-ray, for pulmonary nodule detection using deep learning image reconstruction (DLIR).

Material and methods: This prospective cross-sectional study included 60 patients referred to our institution for assessment or follow-up of solid pulmonary nodules. All patients underwent low-dose (LD) and ULD chest CT within the same examination session. LD CT data were reconstructed using Adaptive Statistical Iterative Reconstruction-V (ASIR-V), whereas ULD CT data were reconstructed using DLIR and ASIR-V. ULD CT images were reviewed by 2 readers and LD CT images were reviewed by an experienced thoracic radiologist as the reference standard. Quantitative image quality analysis was performed, and the detectability of pulmonary nodules was assessed according to their size and location.

Results: The effective radiation dose for ULD CT and LD CT were 0.13±0.01 and 1.16±0.6 mSv, respectively. Over the whole population, LD CT revealed 733 nodules. At ULD, DLIR images significantly exhibited better image quality than ASIR-V images. The overall sensitivity of DLIR reconstruction for the detection of solid pulmonary nodules from the ULD CT series was 93% and 82% for the 2 readers, with a good to excellent agreement with LD CT (ICC=0.82 and 0.66, respectively). The best sensitivities were observed in the middle lobe (97% and 85%, respectively).

Conclusions: At ULD, DLIR reconstructions, with minimal radiation exposure that could facilitate large-scale screening, allow the detection of pulmonary nodules with high sensitivity in an unrestricted BMI population.

Purpose: Lesion overlooking and late diagnostic workup can compromise the efficacy of low-dose CT (LDCT) screening of lung cancer (LC), implying more advanced and less curable disease stages. We hypothesized that the azygos esophageal recess (AER) of the right lower lobe (RLL) might be an area prone to lesion overlooking in LC screening.

Materials and methods: Two radiologists reviewed the LDCT examinations of all the screen-detected incident LCs observed in the active arm of 2 randomized clinical trials: ITALUNG and national lung screening trial. Those in the AER were compared with those in the remainder of the RLL for possible differences in diagnostic lag according to the Lung-RADS 1.1 recommendations, size, stage, and mortality.

Results: Six (11.7%) of 51 screen-detected incident LCs of the RLL were located in the AER. The diagnostic lag time was significantly longer (P=0.046) in the AER LC (mean 14±9 mo) than in the LC in the remaining RLL (mean 7.3±1 mo). Size and stage at diagnosis were not significantly different. All 6 subjects with LC in the AER and 16 (35.5%) of 45 subjects with LC in the remaining RLL (P=0.004) died of LC after a median follow-up of 12 years.

Conclusion: Our retrospective study indicates that AER might represent a lung region of the RLL prone to have early LC overlooked due to detection or interpretation errors with possible detrimental consequences for the subject undergoing LC screening.

Purpose: To compare texture-based analysis using convolutional neural networks (CNNs) against lung densitometry in detecting chest computed tomography (CT) image abnormalities.

Material and methods: A U-NET was used for lung segmentation, and an ensemble of 7 CNN architectures was trained for the classification of low-attenuation areas (LAAs; emphysema, cysts), normal-attenuation areas (NAAs; normal parenchyma), and high-attenuation areas (HAAs; ground-glass opacities, crazy paving/linear opacity, consolidation). Lung densitometry also computes (LAAs, ≤-950 HU), NAAs (-949 to -700 HU), and HAAs (-699 to -250 HU). CNN-based and densitometry-based severity indices (CNN and Dens, respectively) were calculated as (LAA+HAA)/(LAA+NAA+HAA) in 812 CT scans from 176 normal subjects, 343 patients with emphysema, and 293 patients with interstitial lung disease (ILD). The correlation between CNN-derived and densitometry-derived indices was analyzed, alongside a comparison of severity indices among patient subgroups with emphysema and ILD, using the Spearman correlation and ANOVA with Bonferroni correction.

Results: CNN-derived and densitometry-derived severity indices (SIs) showed a strong correlation (ρ=0.90) and increased with disease severity. CNN-SIs differed from densitometry SIs, being lower for emphysema and higher for moderate to severe ILD cases. CNN estimations for normal attenuation areas were higher than those from densitometry across all groups, indicating a potential for more accurate characterization of lung abnormalities.

Conclusions: CNN outputs align closely with densitometry in assessing lung abnormalities on CT scans, offering improved estimates of normal areas and better distinguishing similar abnormalities. However, this requires higher computing power.

Purpose: The aim of this study was to find the optimal strength level of QIR for ultra-high-resolution (UHR) PCCT of the lung.

Materials and methods: This retrospective study included 24 patients who had unenhanced chest CT with the novel UHR scan protocol on the PCCT scanner between March 24, 2023 and May 18, 2023. Two sets of reconstructions were made using different slice thicknesses: standard resolution (SR, 1 mm) and ultra-high-resolution (UHR, 0.2 mm), reconstructed with all strength levels of QIR (0 to 4). Attenuation of the lung parenchyma, noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were assessed as objective criteria of image quality. Two fellowship-trained radiologists compared image quality and noise level, sharpness of the images, and the airway details using a 5-point Likert scale. Wilcoxon signed-rank test was used for statistical analysis of reader scores, and one-way repeated measures analysis of variance for comparing the objective image quality scores.

Results: Objective image quality linearly improved with higher strength levels of QIR, reducing image noise by 66% from QIR-0 to QIR-4 (P<0.001). Subjective image noise was best for QIR-4 (P<0.001). Readers rated QIR-1 and QIR-2 best for SR, and QIR-2 and QIR-3 best for UHR in terms of subjective image sharpness and airway detail, without significant differences between them (P=0.48 and 0.56, respectively).

Conclusions: Higher levels of QIR provided excellent objective image quality, but readers' preference was for intermediate levels. Considering all metrics, we recommend QIR-3 for ultra-high-resolution PCCT of the lung.