Journal of Thoracic Imaging最新文献

Purpose: Pulmonary hamartomas (HAs) and neuroendocrine neoplasms (NENs) are often impossible to discriminate using high-resolution computed tomography (CT) as they share morphologic features. This challenge makes differential diagnosis crucial as HAs are invariably benign, whereas NENs must be considered malignant, thus requiring them to be evaluated for surgical excision.Our aim was, therefore, to develop a simple method to discriminate between pulmonary "fat-poor" HAs and NENs using contrast-enhanced CT (CECT).

Materials and methods: Between September 2015 and December 2021, 95 patients with a histologically proven diagnosis of lung NENs (74) and HAs (21) and who underwent a preoperative CECT scan were initially identified through a review of our pathologic and radiologic databases. Among these, 55 cases (18 HAs and 37 NENs), which have been studied with biphasic CECT, were ultimately selected and reviewed by 3 radiologists with different levels of experience, analyzing their morphologic and enhancement features.The enhancement analysis was performed by placing a region of interest within the lesion in noncontrast (NCp), postcontrast (PCp, 55 to 65 s after intravenous contrast injection), and delayed phases (Dp, 180 to 300 s). A subgroup of 35 patients who underwent 18FDG-PET/CT was evaluated in a secondary analysis.

Results: HU values were significantly different between NENs and HAs in the PCp ( P <0.001). NCp and Dp attenuation values did not show significant differences in the 2 groups. Differences in values of HUs in PCp and Dp allowed to discriminate between NENs and HAs.

Conclusion: Wash-out analysis, ΔHU (PCp-Dp), can perfectly discriminate pulmonary "fat-poor" HAs from NENs.

Purpose: Reliable prediction of volume doubling time (VDT) is essential for the personalized management of pulmonary ground-glass nodules (GGNs). We aimed to determine the optimal VDT prediction method by comparing different machine learning methods only based on the baseline chest computed tomography (CT) images.

Materials and methods: Seven classical machine learning methods were evaluated in terms of their stability and performance for VDT prediction. The VDT, calculated by the preoperative and baseline CT, was divided into 2 groups with a cutoff value of 400 days. A total of 90 GGNs from 3 hospitals constituted the training set, and 86 GGNs from the fourth hospital served as the external validation set. The training set was used for feature selection and model training, and the validation set was used to evaluate the predictive performance of the model independently.

Results: The eXtreme Gradient Boosting showed the highest predictive performance (accuracy: 0.890±0.128 and area under the ROC curve (AUC): 0.896±0.134), followed by the neural network (NNet) (accuracy: 0.865±0.103 and AUC: 0.886±0.097). While regarding stability, the NNet showed the highest robustness against data perturbation (relative SDs [%] of mean AUC: 10.9%). Therefore, the NNet was chosen as the final model, achieving high accuracy of 0.756 in the external validation set.

Conclusion: The NNet is a promising machine learning method to predict the VDT of GGNs, which would assist in the personalized follow-up and treatment strategies for GGNs reducing unnecessary follow-up and radiation dose.

Purpose: To evaluate the role of quantitative features of intranodular vessels based on deep learning in distinguishing pulmonary adenocarcinoma invasiveness.

Materials and methods: This retrospective study included 512 confirmed ground-glass nodules from 474 patients with 241 precursor glandular lesions (PGL), 126 minimally invasive adenocarcinomas (MIA), and 145 invasive adenocarcinomas (IAC). The pulmonary blood vessels were reconstructed on noncontrast computed tomography images using deep learning-based region-segmentation and region-growing techniques. The presence of intranodular vessels was evaluated based on the automatic calculation of vessel prevalence, vascular categories, and vessel volume percentage. Further comparisons were made between different invasive groups by the Mantel-Haenszel χ 2 test, χ 2 test, and analysis of variance.

Results: The detection rate of intranodular vessels in PGL (33.2%) was significantly lower than that of MIA (46.8%, P = 0.011) and IAC (55.2%, P < 0.001), while the vascular categories were similar (all P > 0.05). Vascular changes were more common in IAC and MIA than in PGL, mainly in increased vessel volume percentage (12.4 ± 19.0% vs. 6.3 ± 13.1% vs. 3.9 ± 9.4%, P < 0.001). The average intranodular artery and vein volume percentage of IAC (7.5 ± 14.0% and 5.0 ± 10.1%) was higher than that of PGL (2.1 ± 6.9% and 1.7 ± 5.8%) and MIA (3.2 ± 9.1% and 3.1 ± 8.7%), with statistical significance (all P < 0.05).

Conclusions: The quantitative analysis of intranodular vessels on noncontrast computed tomography images demonstrated that the ground-glass nodules with increased internal vessel prevalence and volume percentages had higher possibility of tumor invasiveness.

Purpose: We aimed to investigate the impacts of age, gender, and race on aortic dimensions in healthy adults.

Methods: We analyzed data from 3 large population-based sample studies, including Chinese Echocardiographic Measurements in Normal Chinese Adults, Japanese the Normal Values for Echocardiographic Measurements Project, and European Normal Reference Ranges for Echocardiography, to compare the two-dimensional echocardiography-derived aortic diameters at different levels and to explore the effects of age, gender, and race on aortic measurements. We also compared the values corrected by body surface area (BSA) or height.

Results: The results are as follows: (1) Aortic diameters showed positive correlations with age (r=0.12-0.42, P<0.05), and there were significant inter-age group differences before and after indexing to BSA (P<0.05); (2) Men had greater measurements of aortic diameters than women, with the differences being the same when indexed to height. However, indexing to BSA reversed the differences; (3) The aortic diameters at annulus (Ao-a) and sinus (Ao-s) levels were very close with minor differences between the Chinese and Japanese regardless of whether BSA was used for correction; and (4) The aortic measurements at Ao-s and proximal ascending aorta (Ao-asc) levels in the Chinese were significantly lower than in the Europeans for both genders, with the differences remaining the same even after indexing to BSA or height (P<0.05).

Conclusion: Aortic dimensions vary with age and gender, and there are significant differences between races or ethnicities even when stratified by gender and age. The indexation by BSA or height cannot eliminate these differences. Therefore, age-specific, gender-specific, race-specific, and nationality-specific reference values may be more appropriate at present for clinical practice to avoid misdiagnosis and misclassification of aortic dilation.

Ischemic heart disease continues to be the leading cause of death and disability worldwide. For the diagnosis of ischemic heart disease, some form of cardiac stress test involving exercise or pharmacological stimulation continues to play an important role, despite advances within modalities like computer tomography for the noninvasive detection and characterization of epicardial coronary lesions. Among noninvasive stress imaging tests, cardiac magnetic resonance (CMR) combines several capabilities that are highly relevant for the diagnosis of ischemic heart disease: assessment of wall motion abnormalities, myocardial perfusion imaging, and depiction of replacement and interstitial fibrosis markers by late gadolinium enhancement techniques and T1 mapping. On top of these qualities, CMR is also well tolerated and safe in most clinical scenarios, including in the presence of cardiovascular implantable devices, while in the presence of renal disease, gadolinium-based contrast should only be used according to guidelines. CMR also offers outstanding viability assessment and prognostication of cardiovascular events. The last 2019 European Society of Cardiology guidelines for chronic coronary syndromes has positioned stress CMR as a class I noninvasive imaging technique for the diagnosis of coronary artery disease in symptomatic patients. In the present review, we present the current state-of-the-art assessment of myocardial ischemia by stress perfusion CMR, highlighting its advantages and current shortcomings. We discuss the safety, clinical, and cost-effectiveness aspects of gadolinium-based CMR-perfusion imaging for ischemic heart disease assessment.

Arterial plaque rupture and thrombosis is the primary cause of major cardiovascular and neurovascular events. The identification of atherosclerosis, especially high-risk plaques, is therefore crucial to identify high-risk patients and to implement preventive therapies. Computed tomography angiography has the ability to visualize and characterize vascular plaques. The standard methods for plaque evaluation rely on the assessment of plaque burden, stenosis severity, the presence of positive remodeling, napkin ring sign, and spotty calcification, as well as Hounsfield Unit (HU)-based thresholding for plaque quantification; the latter with multiple shortcomings. Semiautomated threshold-based segmentation techniques with predefined HU ranges identify and quantify limited plaque characteristics, such as low attenuation, non-calcified, and calcified plaque components. Contrary to HU-based thresholds, histologically validated plaque characterization, and quantification, an emerging Artificial intelligence-based approach has the ability to differentiate specific tissue types based on a biological correlate, such as lipid-rich necrotic core and intraplaque hemorrhage that determine plaque vulnerability. In this article, we review the relevance of plaque characterization and quantification and discuss the benefits and limitations of the currently available plaque assessment and classification techniques.

Approach to imaging ischemia in women Coronary artery disease in women tends to have a worse short- and long-term prognosis relative to men and remains the leading cause of mortality worldwide. Both clinical symptoms and diagnostic approach remain challenging in women due to lesser likelihood of women presenting with classic anginal symptoms on one hand and underperformance of conventional exercise treadmill testing in women on the other. Moreover, a higher proportion of women with signs and symptoms suggestive of ischemia are more likely to have nonobstructive coronary artery disease (CAD) that requires additional imaging and therapeutic considerations. New imaging techniques such as coronary computed tomography (CT) angiography, CT myocardial perfusion imaging, CT functional flow reserve assessment, and cardiac magnetic resonance imaging carry substantially better sensitivity and specificity for the detection of ischemia and coronary artery disease in women. Familiarity with various clinical subtypes of ischemic heart disease in women and with the major advantages and disadvantages of advanced imaging tests to ensure the decision to select one modality over another is one of the keys to successful diagnosis of CAD in women. This review compares the 2 major types of ischemic heart disease in women - obstructive and nonobstructive, while focusing on sex-specific elements of its pathophysiology.

Coronary computed tomographic angiography (CCTA) has emerged as a fast and robust tool with high sensitivity and excellent negative predictive value for the evaluation of coronary artery disease, but is unable to estimate the hemodynamic significance of a lesion. Advances in computed tomography (CT)-based diagnostic techniques, for example, CT-derived fractional flow reserve and CT perfusion, have helped transform CCTA primarily from an anatomic assessment tool to a technique that is able to provide both anatomic and functional information for a stenosis. With the results of the ISCHEMIA trial published in 2019, these advanced techniques can elevate CCTA into the role of a better gatekeeper for decision-making and can help guide referral for invasive management. In this article, we review the principles, limitations, diagnostic performance, and clinical utility of these 2 functional CT-based techniques in the evaluation of vessel-specific and lesion-specific ischemia.