Journal of Thoracic Imaging最新文献

Purpose: Pulmonary embolism (PE) is a significant cause of mortality in the United States. The objective of this study is to implement deep learning (DL) models using computed tomography pulmonary angiography (CTPA), clinical data, and PE Severity Index (PESI) scores to predict PE survival.

Materials and methods: In total, 918 patients (median age 64 y, range 13 to 99 y, 48% male) with 3978 CTPAs were identified via retrospective review across 3 institutions. To predict survival, an AI model was used to extract disease-related imaging features from CTPAs. Imaging features and clinical variables were then incorporated into independent DL models to predict survival outcomes. Cross-modal fusion CoxPH models were used to develop multimodal models from combinations of DL models and calculated PESI scores. Five multimodal models were developed as follows: (1) using CTPA imaging features only, (2) using clinical variables only, (3) using both CTPA and clinical variables, (4) using CTPA and PESI score, and (5) using CTPA, clinical variables, and PESI score. Performance was evaluated using the concordance index (c-index). Kaplan-Meier analysis was performed to stratify patients into high-risk and low-risk groups. Additional factor-risk analysis was conducted to account for right ventricular (RV) dysfunction.

Results: For both data sets, the multimodal models incorporating CTPA features, clinical variables, and PESI score achieved higher c-indices than PESI alone. Following the stratification of patients into high-risk and low-risk groups by models, survival outcomes differed significantly (both P<0.001). A strong correlation was found between high-risk grouping and RV dysfunction.

Conclusions: Multiomic DL models incorporating CTPA features, clinical data, and PESI achieved higher c-indices than PESI alone for PE survival prediction.

Purpose: To investigate the clinical and computed tomography (CT) features of nodular pulmonary amyloidosis (NPA) to enhance our understanding of the disease and improve the ability to differentiate it from other similar conditions.

Materials and methods: A retrospective analysis was conducted on the clinical data, chest CT imaging findings, and pathologic characteristics of 13 patients with NPA in our hospital from April 2014 to April 2024. All 13 patients underwent chest CT plain scan examination. The basic data, medical history, clinical manifestations, and lung lesion features on chest CT imaging were analyzed and summarized.

Results: Among the 13 patients, there were 3 males (23.08%) and 10 females (76.92%). Their ages ranged from 37 to 68 years, with a mean age of (57.85±8.40) years and a median age of 59 years. Three (23.08%) patients had cough and sputum, while the others (76.92%) had no clinical symptoms. Before surgery, 6 patients underwent chest CT scans, and NPA changes in size, shape, and density were observed. Six cases (46.15%) were located in the left lung (4 in the upper lobe and 2 in the lower lobe), and 7 cases (53.85%) in the right lung (3 in the upper lobe, 2 in the middle lobe, and 2 in the lower lobe). Seven cases (53.85%) of NPA were round or oval, while 6 cases (46.15%) were irregularly shaped. Out of the NPA cases, 11 (84.62%) were solid nodules with well-defined boundaries, including 2 cases of solid nodules with surrounding calcification. In addition, 2 cases presented as solid nodules with cavities. Ten cases (76.92%) had multiple cystic lesions in the bilateral lungs, in which 7 cases had more than 10 cysts with obvious cyst walls, and 1 case showed a solid nodule on the cyst wall. During the postoperative follow-up, 1 patient experienced an increase in the size of the original nodule and the appearance of new solid nodules. Subsequent surgery revealed mucosal-associated lymphoid tissue lymphoma (MALT). The remaining patients were followed up regularly, and their conditions remained stable.

Conclusions: NPA is more common in middle-aged and elderly people and is more likely to occur in women. Most cases are asymptomatic, and bilateral lungs can be involved. For nodules with multiple pulmonary cysts found by chest CT, the possibility of NPA should be considered, and further histopathologic examination is needed to confirm the diagnosis. Most patients with NPA have a good long-term prognosis after surgical resection, but some patients require further investigation and close follow-up due to underlying causes.

Background: Bronchial arterial chemoembolization (BACE), as a safe and effective minimally invasive treatment method, is increasingly being accepted by more and more patients with advanced nonsmall-cell lung cancer (NSCLC). In recent years, drug-eluting beads (DEB)-BACE has also been applied in the field of lung cancer. It is still unclear which is more recommended due to the limited number of comparative studies between conventional BACE (C-BACE) and DEB-BACE.

Purpose: To compare the safety and efficacy of C-BACE (BACE with gelfoam particles) and DEB-BACE for advanced NSCLC.

Materials and methods: From January 2021 to April 2023, 48 consecutive patients (37 males and 11 females) with advanced NSCLC treated with DEB-BACE (group A) or C-BACE (group B) at our center were collected retrospectively in this study. There were 18 patients in group A and 30 patients in group B. The technical success rate, adverse events, objective response rate (ORR), disease control rate (DCR), progression-free survival (PFS), and overall survival (OS) were compared between the 2 groups.

Results: The technical success rate in both groups was 100%. The median OS times were 19.5 months and 12.5 months in group A and group B, respectively (P=0.0062). The median PFS times were 13 months and 7 months in group A and group B, respectively (P=0.0072). The ORRs at 6 months were 72.2% and 46.7% in group A and group B, respectively (P=0.084). The DCRs at 6 months were 88.9% and 63.3% in group A and group B, respectively (P=0.043). Grade 1 adverse events like chest pain, and cough were common, while serious adverse events did not occur.

Conclusions: BACE with DEB or gelfoam particles were equally safe. The DEB-BACE showed better survival and tumor response than C-BACE for advanced NSCLC.

Purpose: To describe the spectrum of computed tomography (CT) findings in various chronic pulmonary aspergillosis (CPA) subtypes.

Material and methods: This retrospective study analyzed the CT scans of consecutively diagnosed CPA cases. Two radiologists independently evaluated the CT findings (both qualitatively and quantitatively) to characterize the lung cavities, intracavitary contents, pericavitary opacities and fibrosis, mediastinal shift, pleural thickening, and underlying structural lung disease. Patients were then classified into CPA subtypes, and between-group differences were assessed using the sample t test, Wilcoxon test, χ2 test, and Fisher exact test.

Results: Among 103 patients with CPA (mean age: 47.26 ± 1.98 y; 69 men), 77.7%, 15.5%, and 6.8% were categorized as chronic cavitary pulmonary aspergillosis, chronic fibrosing pulmonary aspergillosis (CFPA), and single/simple aspergilloma, respectively. The mean symptom duration was 2.7 ± 3.96 years, with cough being the most common symptom (86.4%). Underlying post-tubercular lung abnormalities were observed in 97.1% of the patients. Cavities were observed in all patients (100%), most commonly in the left upper lobe (68.0%). The difference in cavity number among CPA subtypes was statistically significant (P = 0.003), with 87.5% CFPA and 41.5% chronic cavitary pulmonary aspergillosis cases showing multiple cavities. The overall median cavity wall thickness was 6 mm (interquartile range: 2.8), with the highest value in the CFPA. Pericavitary fibrosis was observed in 70.9% of overall cases and in 100% of CFPA cases (P < 0.001). Intracavitary contents were identified in 89.3% of patients. The median pleural thickness was 8 mm (interquartile range: 4), which was significantly different among CPA subtypes (P = 0.001). There was excellent interobserver agreement (k = 0.94) between the two readers. Posterior intercostal lymph nodes were identified in 66%, a novel CPA observation.

Conclusion: Comprehensive qualitative and quantitative assessment of CT findings improves the characterization of the CPA subtypes. The number and size of lung cavities, mediastinal shift, and pleural thickness, among other quantitative parameters, vary significantly across CPA subtypes, facilitating more accurate differentiation between them.

Acute pulmonary injury can occur in response to any number of inciting factors. The body's response to these insults is much less diverse and usually categorizable as one of several patterns of disease defined by histopathology, with corresponding patterns on chest CT. Common patterns of acute injury include diffuse alveolar damage, organizing pneumonia, acute eosinophilic pneumonia, and hypersensitivity pneumonitis. The ultimate clinical diagnosis is multidisciplinary, requiring a detailed history and relevant laboratory investigations from referring clinicians, identification of injury patterns on imaging by radiologists, and sometimes tissue evaluation by pathologists. In this review, several clinical diagnoses will be explored, grouped by imaging pattern, with a representative clinical presentation, a review of the current literature, and a discussion of typical imaging findings. Additional information on terminology and disambiguation will be provided to assist with comprehension and standardization of descriptions. The focus will be on the acute phase of illness from presentation to diagnosis; treatment methods and chronic sequela of acute disease are beyond the scope of this review.

Purpose: To develop and validate an accurate computed tomography-based radiomics model for predicting high-grade (micropapillary/solid) patterns in T1-stage lung invasive adenocarcinoma (IAC) after propensity score matching (PSM).

Materials and methods: We enrolled 546 participants from 2 cohorts with histologically diagnosed lung IAC after complete surgical resection between January 2020 and August 2021. The patients were divided into high-grade and non-high-grade groups and matched using PSM. Matched patient HRCT images were used to delineate regions of interest from tumors and extract radiomics features, and the random forest method was used to construct a radiomics model. The area under the receiver operating characteristic curve (area under the curve) was used to evaluate the model's performance, and external validation was performed to assess the model's generalizability.

Results: Before PSM, there was no statistically significant difference in age between the two groups, though nodule type and sex exhibited significant differences (P < 0.05) in both cohorts. After PSM, we matched 176 and 97 pairs of patients in the 2 cohorts. In both cohorts, sex and nodule type were equal between the two groups, with a higher percentage of males and solid nodules in both groups. Our model exhibited moderate predictive performance after PSM, with area under the curve values of 0.75 (95% CI: 0.70-0.80) and 0.71 (95% CI: 0.63-0.80) for the development and external validation cohorts, respectively.

Conclusion: Although the nodule type compromised the validity of the model's performance, our results suggest that our acute computed tomography-based radiomics model could preoperatively predict micropapillary/solid patterns in patients with stage I lung IAC after PSM.

Purpose: To assess the performance of a newly introduced deep learning-based reconstruction algorithm, namely the artificial intelligence iterative reconstruction (AIIR), in reducing the dose of pediatric chest CT by using the image data of below 3-year-old patients with congenital heart disease (CHD).

Materials and methods: The lung image available from routine-dose cardiac CT angiography (CTA) on below 3 years patients with CHD was employed as a reference for evaluating the paired low-dose chest CT. A total of 191 subjects were prospectively enrolled, where the dose for chest CT was reduced to ~0.1 mSv while the cardiac CTA protocol was kept unchanged. The low-dose chest CT images, obtained with the AIIR and the hybrid iterative reconstruction (HIR), were compared in image quality, ie, overall image quality and lung structure depiction, and in diagnostic performance, ie, severity assessment of pneumonia and airway stenosis.

Results: Compared with the reference, lung image quality was not found significantly different on low-dose AIIR images (all P>0.05) but obviously inferior with the HIR (all P<0.05). Compared with the HIR, low-dose AIIR images also achieved a closer pneumonia severity index (AIIR 4.32±3.82 vs. Ref 4.37±3.84, P>0.05; HIR 5.12±4.06 vs. Ref 4.37±3.84, P<0.05) and airway stenosis grading (consistently graded: AIIR 88.5% vs. HIR 56.5% ) to the reference.

Conclusions: AIIR has the potential for large dose reduction in chest CT of patients below 3 years of age while preserving image quality and achieving diagnostic results nearly equivalent to routine dose scans.

Purpose: To investigate the left ventricular (LV) trabecular complexity and evaluate its relationship with LV cardiac function and especially myocardial strain in patients with hypertrophic cardiomyopathy (HCM).

Materials and methods: A total of 100 patients were retrospectively recruited in the study, including 50 obstructive hypertrophic cardiomyopathy (HOCM) and 50 nonobstructive HCM (NOHCM). Fifty age-matched and sex-matched healthy participants were also enrolled. The global and regional LV fractal dimensions (FDs), the global radial, circumferential, and longitudinal strain (GRS, GCS, and GLS) for LV were measured. FDs and myocardial strain parameters among 3 groups with post hoc paired comparisons. Correlations analysis and receiver operating characteristic analysis were performed.

Results: Mean global FD, max basal FD, and max apical FD were higher in patients with HCM compared with the healthy individuals (1.310 ± 0.046 vs 1.229 ± 0.027, 1.388 ± 0.089 vs 1.313 ± 0.039, 1.393 ± 0.108 vs 1.270 ± 0.041, all P < 0.001). Patients with HOCM showed significantly higher max apical FD than patients with NOHCM (1.432 ± 0.100 vs 1.355 ± 0.102, P < 0.001). The increased global FD was associated with reduced myocardial deformation across all 3 measures of global strain (GCS: r = 0.529, P < 0.001; GLS: r = 0.54, P < 0.001; GRS: r = -0.253, P = 0.002). Max apical FD yielded an area under the curve of 0.73 (95% CI: 0.63-0.83) for discriminating HOCM from NOHCM.

Conclusions: LV trabecular complexity is compensatively increased in patients with HCM and the max apical FD was more pronounced in patients with HOCM. The increased LV global trabecular complexity might be correlated with LV systolic dysfunction.

Purpose: To assess the accuracy of transaortic valve replacement (TAVR) planning CT examinations with a broad detector and a single dose of contrast media to diagnose CAD in a large patient cohort.

Materials and methods: In this retrospective study, consecutive patients who underwent a dedicated TAVR planning CT examination with a single contrast media dose and a 320-detector row between November 2017 and March 2021 were screened for inclusion. Inclusion criteria were a complete and correctly performed CT exam as well as an invasive coronary angiography (ICA). The scan consisted of 3 series: (1) ECG-triggered calcium score series over the heart. (2) ECG triggered i.v. CM scanning over the heart covering the entire cardiac cycle (0% to 100%). (3) non-ECG triggered scanning over the thoracic-abdominal area including subclavian and femoral arteries. For 2 and 3, a single i.v. CM bolus was used (300 mg iodine per kg total body weight of iodixanol, minimum 47 mL, maximum 75 mL at 100 kVp; 90 mL at 120 kVp). CT-derived CAD was defined as either free of obstructive CAD (<50%) or showing obstructive disease (>50%), further subclassified in moderate stenosis (50%-70%), or severe stenosis (>70%) for each vessel. ICA data were used as standard of reference.

Results: We studied 599 patients (78.6±7.5 y, 358 men). In ICA, 428 of 2396 coronary vessels (17.8%) demonstrated stenosis of 50% or more. In a per-patient analysis, CTA had a sensitivity of 97.6% and specificity of 84.3% for the detection of patients with at least one vessel with stenosis of 50% or more as well as a NPV and PPV of 97.8% and 82.2%, respectively. In a per-vessel analysis, CTA had 80.8% sensitivity and 88.1% specificity for the detection of stenosis of 50% or more, as well as an NPV and PPV of 95.5% and 59.6%, respectively.

Conclusions: Single-dose TAVR planning CT imaging with a wide detector has high sensitivity and NPV to exclude at least moderate CAD in TAVR candidates.

Purpose: Computed tomography (CT) is crucial in oncologic imaging for precise diagnosis and staging. Beam-hardening artifacts from contrast media in the superior vena cava can degrade image quality and obscure adjacent structures, complicating lymph node assessment. This study examines the use of virtual monoenergetic reconstruction with photon-counting detector CT (photon-counting CT) to mitigate these artifacts.

Materials and methods: The retrospective study included 50 patients who underwent thoracoabdominal scans. Virtual monoenergetic reconstructions at nine keV levels (60 to 140 keV) were analyzed for Hounsfield Unit (HU) stability, image noise, and artifact index in various regions of interest (ROIs): mediastinal adipose tissue (ROI 1 to 3) and vascular stations (ROI 4 to 6) were compared with reference tissue (ROI 7 to 8). The diagnostic image quality of the keV levels was assessed using a 5-point Likert Scale.

Results: Lower keV values (60 to 80) exhibited higher image noise and lower HU stability in mediastinal adipose tissue compared with higher energies, with optimal noise reduction observed at 130 keV (ROI 1 to 3). HU stability in vascular structures (ROI 4 to 6) significantly improved above 80 keV, with the best performance at 140 keV. Artifact levels decreased progressively from 60 to 140 keV. Visually, keV levels of 110 keV (96% Likert ≥4) and 120 keV (60% Likert 4) were rated most diagnostically valuable, consistent with technical findings.

Conclusion: Virtual monoenergetic reconstructions with photon-counting CT effectively reduce beam-hardening artifacts near the superior vena cava, enhancing the visualization of lymph nodes and adjacent structures. This technology advances oncologic imaging by improving diagnostic accuracy in areas previously affected by artifact-related image degradation.