Central Role of CT in Management of Pulmonary Fibrosis

With the approval of antifibrotic medications to treat patients with idiopathic pulmonary fibrosis and progressive pulmonary fibrosis, radiologists have an integral role in diagnosing these entities and guiding treatment decisions. CT features of early pulmonary fibrosis include irregular thickening of interlobular septa, pleura, and intralobular linear structures, with subsequent progression to reticular abnormality, traction bronchiectasis or bronchiolectasis, and honeycombing. CT patterns of fibrotic lung disease can often be reliably classified on the basis of the CT features and distribution of the condition. Accurate identification of usual interstitial pneumonia (UIP) or probable UIP patterns by radiologists can obviate the need for a tissue sample-based diagnosis. Other entities that can appear as a UIP pattern must be excluded in multidisciplinary discussion before a diagnosis of idiopathic pulmonary fibrosis is made. Although the imaging findings of nonspecific interstitial pneumonia and fibrotic hypersensitivity pneumonitis can overlap with those of a radiologic UIP pattern, these entities can often be distinguished by paying careful attention to the radiologic signs. Diagnostic challenges may include misdiagnosis of fibrotic lung disease due to pitfalls such as airspace enlargement with fibrosis, paraseptal emphysema, recurrent aspiration, and postinfectious fibrosis. The radiologist also plays an important role in identifying complications of pulmonary fibrosis-pulmonary hypertension, acute exacerbation, infection, and lung cancer in particular. In cases in which there is uncertainty regarding the clinical and radiologic diagnoses, surgical biopsy is recommended, and a multidisciplinary discussion among clinicians, radiologists, and pathologists can be used to address diagnosis and management strategies. This review is intended to help radiologists diagnose and manage pulmonary fibrosis more accurately, ultimately aiding in the clinical management of affected patients. ©RSNA, 2024 Supplemental material is available for this article.

BranchLabelNet: Anatomical Human Airway Labeling Approach using a Dividing-and-Grouping Multi-Label Classification

Anatomical airway labeling is crucial for precisely identifying airways displaying symptoms such as constriction, increased wall thickness, and modified branching patterns, facilitating the diagnosis and treatment of pulmonary ailments. This study introduces an innovative airway labeling methodology, BranchLabelNet, which accounts for the fractal nature of airways and inherent hierarchical branch nomenclature. In developing this methodology, branch-related parameters, including position vectors, generation levels, branch lengths, areas, perimeters, and more, are extracted from a dataset of 1000 chest computed tomography (CT) images. To effectively manage this intricate branch data, we employ an n-ary tree structure that captures the complicated relationships within the airway tree. Subsequently, we employ a divide-and-group deep learning approach for multi-label classification, streamlining the anatomical airway branch labeling process. Additionally, we address the challenge of class imbalance in the dataset by incorporating the Tomek Links algorithm to maintain model reliability and accuracy. Our proposed airway labeling method provides robust branch designations and achieves an impressive average classification accuracy of 95.94% across fivefold cross-validation. This approach is adaptable for addressing similar complexities in general multi-label classification problems within biomedical systems.

Deep Learning Classification of Usual Interstitial Pneumonia Predicts Outcomes

Rationale: Computed tomography (CT) enables noninvasive diagnosis of usual interstitial pneumonia (UIP), but enhanced image analyses are needed to overcome the limitations of visual assessment. Objectives: Apply multiple instance learning (MIL) to develop an explainable deep learning algorithm for prediction of UIP from CT and validate its performance in independent cohorts. Methods: We trained an MIL algorithm using a pooled dataset (n = 2,143) and tested it in three independent populations: data from a prior publication (n = 127), a single-institution clinical cohort (n = 239), and a national registry of patients with pulmonary fibrosis (n = 979). We tested UIP classification performance using receiver operating characteristic analysis, with histologic UIP as ground truth. Cox proportional hazards and linear mixed-effects models were used to examine associations between MIL predictions and survival or longitudinal FVC. Measurements and Main Results: In two cohorts with biopsy data, MIL improved accuracy for histologic UIP (area under the curve, 0.77 [n = 127] and 0.79 [n = 239]) compared with visual assessment (area under the curve, 0.65 and 0.71). In cohorts with survival data, MIL-UIP classifications were significant for mortality (n = 239, mortality to April 2021: unadjusted hazard ratio, 3.1; 95% confidence interval [CI], 1.96-4.91; P < 0.001; and n = 979, mortality to July 2022: unadjusted hazard ratio, 3.64; 95% CI, 2.66-4.97; P < 0.001). Individuals classified as UIP positive by the algorithm had a significantly greater annual decline in FVC than those classified as UIP negative (-88 ml/yr vs. -45 ml/yr; n = 979; P < 0.01), adjusting for extent of lung fibrosis. Conclusions: Computerized assessment using MIL identifies clinically significant features of UIP on CT. Such a method could improve confidence in radiologic assessment of patients with interstitial lung disease, potentially enabling earlier and more precise diagnosis.

Measurement Variability of Same-Day CT Quantification of Interstitial Lung Disease: A Multicenter Prospective Study

Purpose To investigate quantitative CT (QCT) measurement variability in interstitial lung disease (ILD) on the basis of two same-day CT scans. Materials and Methods Participants with ILD were enrolled in this multicenter prospective study between March and October 2022. Participants underwent two same-day CT scans at an interval of a few minutes. Deep learning-based texture analysis software was used to segment ILD features. Fibrosis extent was defined as the sum of reticular opacity and honeycombing cysts. Measurement variability between scans was assessed with Bland-Altman analyses for absolute and relative differences with 95% limits of agreement (LOA). The contribution of fibrosis extent to variability was analyzed using a multivariable linear mixed-effects model while adjusting for lung volume. Eight readers assessed ILD fibrosis stability with and without QCT information for 30 randomly selected samples. Results Sixty-five participants were enrolled in this study (mean age, 68.7 years ± 10 [SD]; 47 [72%] men, 18 [28%] women). Between two same-day CT scans, the 95% LOA for the mean absolute and relative differences of quantitative fibrosis extent were -0.9% to 1.0% and -14.8% to 16.1%, respectively. However, these variabilities increased to 95% LOA of -11.3% to 3.9% and -123.1% to 18.4% between CT scans with different reconstruction parameters. Multivariable analysis showed that absolute differences were not associated with the baseline extent of fibrosis (P = .09), but the relative differences were negatively associated (β = -0.252, P < .001). The QCT results increased readers' specificity in interpreting ILD fibrosis stability (91.7% vs 94.6%, P = .02). Conclusion The absolute QCT measurement variability of fibrosis extent in ILD was 1% in same-day CT scans. Keywords: CT, CT-Quantitative, Thorax, Lung, Lung Diseases, Interstitial, Pulmonary Fibrosis, Diagnosis, Computer Assisted, Diagnostic Imaging Supplemental material is available for this article. © RSNA, 2024.

Human-airway surface mesh smoothing based on graph convolutional neural networks

BACKGROUND AND OBJECTIVE

A detailed representation of the airway geometry in the respiratory system is critical for predicting precise airflow and pressure behaviors in computed tomography (CT)-image-based computational fluid dynamics (CFD). The CT-image-based geometry often contains artifacts, noise, and discontinuities due to the so-called stair step effect. Hence, an advanced surface smoothing is necessary. The existing smoothing methods based on the Laplacian operator drastically shrink airway geometries, resulting in the loss of information related to smaller branches. This study aims to introduce an unsupervised airway-mesh-smoothing learning (AMSL) method that preserves the original geometry of the three-dimensional (3D) airway for accurate CT-image-based CFD simulations.

METHOD

The AMSL method jointly trains two graph convolutional neural networks (GCNNs) defined on airway meshes to filter vertex positions and face normal vectors. In addition, it regularizes a combination of loss functions such as reproducibility, smoothness and consistency of vertex positions, and normal vectors. The AMSL adopts the concept of a deep mesh prior model, and it determines the self-similarity for mesh restoration without using a large dataset for training. Images of the airways of 20 subjects were smoothed by the AMSL method, and among them, the data of two subjects were used for the CFD simulations to assess the effect of airway smoothing on flow properties.

RESULTS

In 18 of 20 benchmark problems, the proposed smoothing method delivered better results compared with the conventional or state-of-the-art deep learning methods. Unlike the traditional smoothing, the AMSL successfully constructed 20 smoothed airways with airway diameters that were consistent with the original CT images. Besides, CFD simulations with the airways obtained by the AMSL method showed much smaller pressure drop and wall shear stress than the results obtained by the traditional method.

CONCLUSIONS

The airway model constructed by the AMSL method reproduces branch diameters accurately without any shrinkage, especially in the case of smaller airways. The accurate estimation of airway geometry using a smoothing method is critical for estimating flow properties in CFD simulations.

Colon cancer: the 2023 Korean clinical practice guidelines for diagnosis and treatment

Colorectal cancer is the third most common cancer in Korea and the third leading cause of death from cancer. Treatment outcomes for colon cancer are steadily improving due to national health screening programs with advances in diagnostic methods, surgical techniques, and therapeutic agents.. The Korea Colon Cancer Multidisciplinary (KCCM) Committee intends to provide professionals who treat colon cancer with the most up-to-date, evidence-based practice guidelines to improve outcomes and help them make decisions that reflect their patients' values and preferences. These guidelines have been established by consensus reached by the KCCM Guideline Committee based on a systematic literature review and evidence synthesis and by considering the national health insurance system in real clinical practice settings. Each recommendation is presented with a recommendation strength and level of evidence based on the consensus of the committee.

Structural and functional features of asthma participants with fixed airway obstruction using CT imaging and 1D computational fluid dynamics: A feasibility study

Asthma with fixed airway obstruction (FAO) is associated with significant morbidity and rapid decline in lung function, making its treatment challenging. Quantitative computed tomography (QCT) along with data postprocessing is a useful tool to obtain detailed information on airway structure, parenchymal function, and computational flow features. In this study, we aim to identify the structural and functional differences between asthma with and without FAO. The FAO group was defined by a ratio of forced expiratory volume in 1 s (FEV1 ) to forced vital capacity (FVC), FEV1 /FVC <0.7. Accordingly, we obtained two sets of QCT images at inspiration and expiration of asthma subjects without (N = 24) and with FAO (N = 12). Structural and functional QCT-derived airway variables were extracted, including normalized hydraulic diameter, normalized airway wall thickness, functional small airway disease, and emphysema percentage. A one-dimensional (1D) computational fluid dynamics (CFD) model considering airway deformation was used to compare the pressure distribution between the two groups. The computational pressures showed strong correlations with the pulmonary function test (PFT)-based metrics. In conclusion, asthma participants with FAO had worse lung functions and higher-pressure drops than those without FAO.

Chronic Lung Injury after COVID-19 Pneumonia: Clinical, Radiologic, and Histopathologic Perspectives

With the COVID-19 pandemic having lasted more than 3 years, concerns are growing about prolonged symptoms and respiratory complications in COVID-19 survivors, collectively termed post-COVID-19 condition (PCC). Up to 50% of patients have residual symptoms and physiologic impairment, particularly dyspnea and reduced diffusion capacity. Studies have also shown that 24%-54% of patients hospitalized during the 1st year of the pandemic exhibit radiologic abnormalities, such as ground-glass opacity, reticular opacity, bronchial dilatation, and air trapping, when imaged more than 1 year after infection. In patients with persistent respiratory symptoms but normal results at chest CT, dual-energy contrast-enhanced CT, xenon 129 MRI, and low-field-strength MRI were reported to show abnormal ventilation and/or perfusion, suggesting that some lung injury may not be detectable with standard CT. Histologic patterns in post-COVID-19 lung disease include fibrosis, organizing pneumonia, and vascular abnormality, indicating that different pathologic mechanisms may contribute to PCC. Therefore, a comprehensive imaging approach is necessary to evaluate and diagnose patients with persistent post-COVID-19 symptoms. This review will focus on the long-term findings of clinical and radiologic abnormalities and describe histopathologic perspectives. It also addresses advanced imaging techniques and deep learning approaches that can be applied to COVID-19 survivors. This field remains an active area of research, and further follow-up studies are warranted for a better understanding of the chronic stage of the disease and developing a multidisciplinary approach for patient management.

Giant Fibrovascular Polyp Mimicking Esophageal Malignancy on 18 F-FDG PET/CT

ABSTRACT

A 52-year-old man presented with continuous dull pain from the throat to the epigastric region with dysphagia. Initial endoscopy misdiagnosed a subepithelial tumor causing external compression of the esophagus. A CT scan visualized a 14.0 × 4.0-cm pedunculated mass inside the esophagus. Subsequent 18 F-FDG PET/CT identified an intense FDG-avid area in the mass, which strongly suggested esophageal cancer. Total mass excision was performed, and fibrovascular polyp with chronic ulcerative inflammation was finally confirmed on histologic examination.

External validation of deep learning-based automated detection algorithm for chest radiograph: practical issues in outpatient clinic

BACKGROUND

There have been no reports on diagnostic performance of deep learning-based automated detection (DLAD) for thoracic diseases in real-world outpatient clinic.

PURPOSE

To validate DLAD for use at an outpatient clinic and analyze the interpretation time for chest radiographs.

MATERIAL AND METHODS

This is a retrospective single-center study. From 18 January 2021 to 18 February 2021, 205 chest radiographs with DLAD and paired chest CT from 205 individuals (107 men and 98 women; mean ± SD age: 63 ± 8 years) from an outpatient clinic were analyzed for external validation and observer performance. Two radiologists independently reviewed the chest radiographs by referring to the paired chest CT and made reference standards. Two pulmonologists and two thoracic radiologists participated in observer performance tests, and the total amount of time taken during the test was measured.

RESULTS

The performance of DLAD (area under the receiver operating characteristic curve [AUC] = 0.920) was significantly higher than that of pulmonologists (AUC = 0.756) and radiologists (AUC = 0.782) without assistance of DLAD. With help of DLAD, the AUCs were significantly higher for both groups (pulmonologists AUC = 0.853; radiologists AUC = 0.854). A greater than 50% decrease in mean interpretation time was observed in the pulmonologist group with assistance of DLAD compared to mean reading time without aid of DLAD (from 67 s per case to 30 s per case). No significant difference was observed in the radiologist group (from 61 s per case to 61 s per case).

CONCLUSION

DLAD demonstrated good performance in interpreting chest radiographs of patients at an outpatient clinic, and was especially helpful for pulmonologists in improving performance.

Erratum: Correction of Affiliations in the Article "Establishment of a Nationwide Korean Imaging Cohort of Coronavirus Disease 2019"

This corrects the article on p. e413 in vol. 35, PMID: 33258333.

Correction: Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study

[This corrects the article DOI: 10.2196/42717.].

Quantitative CT Analysis Based on Smoking Habits and Chronic Obstructive Pulmonary Disease in Patients with Normal Chest CT

PURPOSE

To assess normal CT scans with quantitative CT (QCT) analysis based on smoking habits and chronic obstructive pulmonary disease (COPD).

MATERIALS AND METHODS

From January 2013 to December 2014, 90 male patients with normal chest CT and quantification analysis results were enrolled in our study [non-COPD never-smokers (n = 38) and smokers (n = 45), COPD smokers (n = 7)]. In addition, an age-matched cohort study was performed for seven smokers with COPD. The square root of the wall area of a hypothetical bronchus of internal perimeter 10 mm (Pi10), skewness, kurtosis, mean lung attenuation (MLA), and percentage of low attenuation area (%LAA) were evaluated.

RESULTS

Among patients without COPD, the Pi10 of smokers (4.176 ± 0.282) was about 0.1 mm thicker than that of never-smokers (4.070 ± 0.191, p = 0.047), and skewness and kurtosis of smokers (2.628 ± 0.484 and 6.448 ± 3.427) were lower than never-smokers (2.884 ± 0.624, p = 0.038 and 8.594 ± 4.944, p = 0.02). The Pi10 of COPD smokers (4.429 ± 0.435, n = 7) was about 0.4 mm thicker than never-smokers without COPD (3.996 ± 0.115, n = 14, p = 0.005). There were no significant differences in MLA and %LAA between groups (p > 0.05).

CONCLUSION

Even on normal CT scans, QCT showed that the airway walls of smokers are thicker than never-smokers regardless of COPD and it preceded lung parenchymal changes.

Interstitial Lung Abnormalities at CT in the Korean National Lung Cancer Screening Program: Prevalence and Deep Learning-based Texture Analysis

Background Interstitial lung abnormalities (ILAs) are associated with worse clinical outcomes, but ILA with lung cancer screening CT has not been quantitatively assessed. Purpose To determine the prevalence of ILA at CT examinations from the Korean National Lung Cancer Screening Program and define an optimal lung area threshold for ILA detection with CT with use of deep learning-based texture analysis. Materials and Methods This retrospective study included participants who underwent chest CT between April 2017 and December 2020 at two medical centers participating in the Korean National Lung Cancer Screening Program. CT findings were classified by three radiologists into three groups: no ILA, equivocal ILA, and ILA (fibrotic and nonfibrotic). Progression was evaluated between baseline and last follow-up CT scan. The extent of ILA was assessed visually and quantitatively with use of deep learning-based texture analysis. The Youden index was used to determine an optimal cutoff value for detecting ILA with use of texture analysis. Demographics and ILA subcategories were compared between participants with progressive and nonprogressive ILA. Results A total of 3118 participants were included in this study, and ILAs were observed with the CT scans of 120 individuals (4%). The median extent of ILA calculated by the quantitative system was 5.8% for the ILA group, 0.7% for the equivocal ILA group, and 0.1% for the no ILA group (P < .001). A 1.8% area threshold in a lung zone for quantitative detection of ILA showed 100% sensitivity and 99% specificity. Progression was observed in 48% of visually assessed fibrotic ILAs (15 of 31), and quantitative extent of ILA increased by 3.1% in subjects with progression. Conclusion ILAs were detected in 4% of the Korean lung cancer screening population. Deep learning-based texture analysis showed high sensitivity and specificity for detecting ILA with use of a 1.8% lung area cutoff value. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Egashira and Nishino in this issue.

An unsupervised image registration method employing chest computed tomography images and deep neural networks

BACKGROUND

Deformable image registration is crucial for multiple radiation therapy applications. Fast registration of computed tomography (CT) lung images is challenging because of the large and nonlinear deformation between inspiration and expiration. With advancements in deep learning techniques, learning-based registration methods are considered efficient alternatives to traditional methods in terms of accuracy and computational cost.

METHOD

In this study, an unsupervised lung registration network (LRN) with cycle-consistent training is proposed to align two acquired CT-derived lung datasets during breath-holds at inspiratory and expiratory levels without utilizing any ground-truth registration results. Generally, the LRN model uses three loss functions: image similarity, regularization, and Jacobian determinant. Here, LRN was trained on the CT datasets of 705 subjects and tested using 10 pairs of public CT DIR-Lab datasets. Furthermore, to evaluate the effectiveness of the registration technique, target registration errors (TREs) of the LRN model were compared with those of the conventional algorithm (sum of squared tissue volume difference; SSTVD) and a state-of-the-art unsupervised registration method (VoxelMorph).

RESULTS

The results showed that the LRN with an average TRE of 1.78 ± 1.56 mm outperformed VoxelMorph with an average TRE of 2.43 ± 2.43 mm, which is comparable to that of SSTVD with an average TRE of 1.66 ± 1.49 mm. In addition, estimating the displacement vector field without any folding voxel consumed less than 2 s, demonstrating the superiority of the learning-based method with respect to fiducial marker tracking and the overall soft tissue alignment with a nearly real-time speed.

CONCLUSIONS

Therefore, this proposed method shows significant potential for use in time-sensitive pulmonary studies, such as lung motion tracking and image-guided surgery.

Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study

BACKGROUND

An artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19.

OBJECTIVE

We aimed to develop and validate a prediction model using CXR based on an AI model and clinical variables to predict clinical outcomes in patients with COVID-19.

METHODS

This retrospective longitudinal study included patients hospitalized for COVID-19 at multiple COVID-19 medical centers between February 2020 and October 2020. Patients at Boramae Medical Center were randomly classified into training, validation, and internal testing sets (at a ratio of 8:1:1, respectively). An AI model using initial CXR images as input, a logistic regression model using clinical information, and a combined model using the output of the AI model (as CXR score) and clinical information were developed and trained to predict hospital length of stay (LOS) ≤2 weeks, need for oxygen supplementation, and acute respiratory distress syndrome (ARDS). The models were externally validated in the Korean Imaging Cohort of COVID-19 data set for discrimination and calibration.

RESULTS

The AI model using CXR and the logistic regression model using clinical variables were suboptimal to predict hospital LOS ≤2 weeks or the need for oxygen supplementation but performed acceptably in the prediction of ARDS (AI model area under the curve [AUC] 0.782, 95% CI 0.720-0.845; logistic regression model AUC 0.878, 95% CI 0.838-0.919). The combined model performed better in predicting the need for oxygen supplementation (AUC 0.704, 95% CI 0.646-0.762) and ARDS (AUC 0.890, 95% CI 0.853-0.928) compared to the CXR score alone. Both the AI and combined models showed good calibration for predicting ARDS (P=.079 and P=.859).

CONCLUSIONS

The combined prediction model, comprising the CXR score and clinical information, was externally validated as having acceptable performance in predicting severe illness and excellent performance in predicting ARDS in patients with COVID-19.

Prevalence and Long-term Outcomes of CT Interstitial Lung Abnormalities in a Health Screening Cohort

Background The association between interstitial lung abnormalities (ILAs) and long-term outcomes has not been reported in Asian health screening populations. Purpose To investigate ILA prevalence in an Asian health screening cohort and determine rates and risks for ILA progression, lung cancer development, and mortality within the 10-year follow-up. Materials and Methods This observational, retrospective multicenter study included patients aged 50 years or older who underwent chest CT at three health screening centers over a 4-year period (2007-2010). ILA status was classified as none, equivocal ILA, and ILA (nonfibrotic or fibrotic). Progression was evaluated from baseline to the last follow-up CT examination, when available. The log-rank test was performed to compare mortality rates over time between ILA statuses. Multivariable Cox proportional hazards models were used to assess factors associated with hazards of ILA progression, lung cancer development, and mortality. Results Of the 2765 included patients (mean age, 59 years ± 7 [SD]; 2068 men), 94 (3%) had a finding of ILA (35 nonfibrotic and 59 fibrotic ILA) and 119 (4%) had equivocal ILA. The median time for CT follow-up and the entire observation was 8 and 12 years, respectively. ILA progression was observed in 80% (48 of 60) of patients with ILA over 8 years. Those with fibrotic and nonfibrotic ILA had a higher mortality rate than those without ILA (P < .001 and P = .01, respectively) over 12 years. Fibrotic ILA was independently associated with ILA progression (hazard ratio [HR], 10.3; 95% CI: 6.4, 16.4; P < .001), lung cancer development (HR, 4.4; 95% CI: 2.1, 9.1; P < .001), disease-specific mortality (HR, 6.7; 95% CI: 3.7, 12.2; P < .001), and all-cause mortality (HR, 2.5; 95% CI: 1.6, 3.8; P < .001) compared with no ILA. Conclusion The prevalence of interstitial lung abnormalities (ILAs) in an Asian health screening cohort was approximately 3%, and fibrotic ILA was an independent risk factor for ILA progression, lung cancer development, and mortality. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Hatabu and Hata in this issue.

A Radiomics Approach on Chest CT Distinguishes Primary Lung Cancer from Solitary Lung Metastasis in Colorectal Cancer Patients

PURPOSE

This study utilized a radiomics approach combined with a machine learning algorithm to distinguish primary lung cancer (LC) from solitary lung metastasis (LM) in colorectal cancer (CRC) patients with a solitary pulmonary nodule (SPN).

MATERIALS AND METHODS

In a retrospective study, 239 patients who underwent chest computerized tomography (CT) at three different institutions between 2011 and 2019 and were diagnosed as primary LC or solitary LM were included. The data from the first institution were divided into training and internal testing datasets. The data from the second and third institutions were used as an external testing dataset. Radiomic features were extracted from the intra and perinodular regions of interest (ROI). After a feature selection process, Support vector machine (SVM) was used to train models for classifying between LC and LM. The performances of the SVM classifiers were evaluated with both the internal and external testing datasets. The performances of the model were compared to those of two radiologists who reviewed the CT images of the testing datasets for the binary prediction of LC versus LM.

RESULTS

The SVM classifier trained with the radiomic features from the intranodular ROI and achieved the sensitivity/specificity of 0.545/0.828 in the internal test dataset, and 0.833/0.964 in the external test dataset, respectively. The SVM classifier trained with the combined radiomic features from the intra- and perinodular ROIs achieved the sensitivity/specificity of 0.545/0.966 in the internal test dataset, and 0.833/1.000 in the external test data set, respectively. Two radiologists demonstrated the sensitivity/specificity of 0.545/0.966 and 0.636/0.828 in the internal test dataset, and 0.917/0.929 and 0.833/0.929 in the external test dataset, which were comparable to the performance of the model trained with the combined radiomics features.

CONCLUSION

Our results suggested that the machine learning classifiers trained using radiomics features of SPN in CRC patients can be used to distinguish the primary LC and the solitary LM with a similar level of performance to radiologists.

A Rare Case of Familial Schwannomatosis Showing Intrafamilial Variability with Identification of a Shared Novel Germline SMARCB1 Mutation

Schwannomatosis is characterized by the presence of multiple schwannomas without landmarks of NF2. It is considered the rarest form of neurofibromatosis (NF). Here, we report the first case of familial schwannomatosis with regard to the segmental/generalized phenotype, in which the proband and the daughter present a distinct phenotype in this classification. The proband presents a generalized, painless, extradural type of schwannomatosis, while the daughter shows a segmental, painful, intradural type of schwannomatosis. Whole-exome sequencing of the affected individuals revealed a shared novel SMARCB1 gene mutation (c.92A > G, p.Glu31Gly) despite the clinical variability. We thus suggest two points in the diagnosis of familial schwannomatosis: The identified novel germline SMARCB1 variant can be reflective of a phenotypical progression from a segmental to a generalized type of schwannomatosis, or an intrafamilial variability in inherited schwannomatosis, which was not reported in previous literature. The specific combination of somatic NF2 mutations may be a major factor in regulating the severity and scope of the resulting phenotype in schwannomatosis.

Invasive Hypervirulent Klebsiella pneumoniae Syndrome Originating from an Anorectal Abscess as Opposed to a Pyogenic Liver Abscess

An immunocompetent 49-year-old man presented with swelling and pain in the lower region of his left leg that had lasted for 4 weeks. The diagnosis was severe pyomyositis and osteomyelitis in the lower left leg caused by hypervirulent Klebsiella pneumoniae (hvKP) along with multiple metastatic infections in the kidneys, lungs, and brain originating from an anorectal abscess. A virulence-gene analysis revealed that the isolated K. pneumoniae harbored rmpA, entB, ybtS, kfu, iutA, mrkD, and allS-virulence genes and belonged to the K1 capsular serotype. After repeated abscess drainage procedures, intravenous ceftriaxone was administered for more than 10 weeks, and the patient's infection was controlled. We focused on the clinical features of hvKP originating from an anorectal abscess without a pyogenic liver abscess. We suggest that hvKP be considered a causative pathogen of pyomyositis and osteomyelitis resulting in multiple metastatic infections in an immunocompetent patient, and more information on the unexpected multiple metastatic infections should be obtained from a virulence analysis of K. pneumoniae.

CT-based lung motion differences in patients with usual interstitial pneumonia and nonspecific interstitial pneumonia

We applied quantitative CT image matching to assess the degree of motion in the idiopathic ILD such as usual interstitial pneumonia (UIP) and nonspecific interstitial pneumonia (NSIP). Twenty-one normal subjects and 42 idiopathic ILD (31 UIP and 11 NSIP) patients were retrospectively included. Inspiratory and expiratory CT images, reviewed by two experienced radiologists, were used to compute displacement vectors at local lung regions matched by image registration. Normalized three-dimensional and two-dimensional (dorsal-basal) displacements were computed at a sub-acinar scale. Displacements, volume changes, and tissue fractions in the whole lung and the lobes were compared between normal, UIP, and NSIP subjects. The dorsal-basal displacement in lower lobes was smaller in UIP patients than in NSIP or normal subjects (p = 0.03, p = 0.04). UIP and NSIP were not differentiated by volume changes in the whole lung or upper and lower lobes (p = 0.53, p = 0.12, p = 0.97), whereas the lower lobe air volume change was smaller in both UIP and NSIP than normal subjects (p = 0.02, p = 0.001). Regional expiratory tissue fractions and displacements showed positive correlations in normal and UIP subjects but not in NSIP subjects. In summary, lung motionography quantified by image registration-based lower lobe dorsal-basal displacement may be used to assess the degree of motion, reflecting limited motion due to fibrosis in the ILD such as UIP and NSIP.

Relationship between Incidental Abnormalities on Screening Thoracic Computed Tomography and Mortality: A Long-Term Follow-Up Analysis

OBJECTIVE

The present study aimed to assess the relationship between incidental abnormalities on thoracic computed tomography (CT) and mortality in a general screening population using a long-term follow-up analysis.

MATERIALS AND METHODS

We retrospectively collected the medical records and CT images of 840 participants (mean age ± standard deviation [SD], 58.5 ± 6.7 years; 564 male) who underwent thoracic CT at a single health promotion center between 2007 and 2010. Two thoracic radiologists independently reviewed all CT images and evaluated any incidental abnormalities (interstitial lung abnormality [ILA], emphysema, coronary artery calcification [CAC], aortic valve [AV] calcification, and pulmonary nodules). Kaplan-Meier analysis with log-rank and z-tests was performed to assess the relationship between incidental CT abnormalities and all-cause mortality in the subsequent follow-up. Cox proportional hazards regression was performed to further identify risk factors of all-cause mortality among the incidental CT abnormalities and clinical factors.

RESULTS

Among the 840 participants, 55 (6%), 171 (20%), 288 (34%), 396 (47%), and 97 (11%) had findings of ILA, emphysema, CAC, pulmonary nodule, and AV calcification, respectively, on initial CT. The participants were followed up for a mean period ± SD of 10.9 ± 1.4 years. All incidental CT abnormalities were associated with all-cause mortality in univariable analysis (p < 0.05). However, multivariable analysis further revealed fibrotic ILA as an independent risk factor for all-cause mortality (hazard ratio, 2.52 [95% confidence interval, 1.02-6.22], p = 0.046). ILA were also identified as an independent risk factor for lung cancer or respiratory disease-related deaths.

CONCLUSION

Incidental abnormalities on screening thoracic CT were associated with increased mortality during the long-term follow-up. Among incidental CT abnormalities, fibrotic ILA were independently associated with increased mortality. Appropriate management and surveillance may be required for patients with fibrotic ILA on thoracic CT obtained for general screening purposes.

Structural and functional alterations of subjects with cement dust exposure: A longitudinal quantitative computed tomography-based study

Cement dust exposure (CDE) can be a risk factor for pulmonary disease, causing changes in segmental airways and parenchymal lungs. This study investigates longitudinal alterations in quantitative computed tomography (CT)-based metrics due to CDE. We obtained CT-based airway structural and lung functional metrics from CDE subjects with baseline CT and follow-up CT scans performed three years later. From the CT, we extracted wall thickness (WT) and bifurcation angle (θ) at total lung capacity (TLC) and functional residual capacity (FRC), respectively. We also computed air volume (V_air), tissue volume (V_tissue), global lung shape, percentage of emphysema (Emph%), and more. Clinical measures were used to associate with CT-based metrics. Three years after their baseline, the pulmonary function tests of CDE subjects were similar or improved, but there were significant alterations in the CT-based structural and functional metrics. The follow-up CT scans showed changes in θ at most of the central airways; increased WT at the subgroup bronchi; smaller V_air at TLC at all except the right upper and lower lobes; smaller V_tissue at all lobes in TLC and FRC except for the upper lobes in FRC; smaller global lung shape; and greater Emph% at the right upper and lower lobes. CT-based structural and functional variables are more sensitive to the early identification of CDE subjects, while most clinical lung function changes were not noticeable. We speculate that the significant long-term changes in CT are uniquely observed in CDE subjects, different from smoking-induced structural changes.

Prognosis and recurrence patterns in patients with early stage lung cancer: a multi-state model approach

Background

We aimed to assess whether recurrence patterns affect survival and to use a multi-state model to predict the prognosis of early stage non-small cell lung cancer in patients who underwent surgical resection.

Methods

Patients with early stage non-small cell lung cancer who underwent surgical resection at two tertiary medical centers between 2010 and 2015 were retrospectively analyzed. A multi-state model was employed with one initial state (surgery), two intermediate states (locoregional recurrence, distant metastasis), and one absorbing state (death), comprising five transitions: surgery to locoregional recurrence, surgery to distant metastasis, surgery to death without recurrence, locoregional recurrence to death, and distant metastasis to death. Cox proportional hazards models stratified for these transitions were performed with the risk factors; transition probabilities for each patient were predicted.

Results

A total of 949 patients were identified [median age: 67 years, male: 614 (64.6%)]. Recurrence occurred in 194 (20.4%) patients (locoregional recurrence: 7.3%, distant metastasis: 13.1%). Hazard ratios for distant metastasis after surgery were higher for older age (hazard ratio: 1.03, 95% confidence interval: 1.01–1.06) and adenocarcinoma (hazard ratio: 1.67, 95% confidence interval: 1.06–2.61). Lower lobe location exhibited a higher hazard ratio for death after surgery without recurrence (hazard ratio: 1.59, 95% confidence interval: 1.00–2.53). Stage IIB lung cancer showed a higher probability of transition to distant metastasis after surgery than other stages. Cumulative transition hazards rapidly increased in both recurrence patterns until approximately two years after surgery (locoregional recurrence: 0.052; distant metastasis: 0.104). Patients with distant metastasis were more likely to die within 5 years of surgery than those with locoregional recurrence (6.8% and 2.6%, respectively).

Conclusions

With the multi-state model, risk factors and post-relapse survival probabilities differed between locoregional recurrence and distant metastasis. These findings may enable clinicians to establish personalized follow-up strategies for patients undergoing curative resection for early stage non-small cell lung cancer.

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

PURPOSE

We aimed to identify clinically relevant deep learning algorithms for emphysema quantification using low-dose chest computed tomography (LDCT) through an invitation-based competition.

MATERIALS AND METHODS

The Korean Society of Imaging Informatics in Medicine (KSIIM) organized a challenge for emphysema quantification between November 24, 2020 and January 26, 2021. Seven invited research teams participated in this challenge. In total, 558 pairs of computed tomography (CT) scans (468 pairs for the training set, and 90 pairs for the test set) from 9 hospitals were collected retrospectively or prospectively. CT acquisition followed the hospitals' protocols to reflect the real-world clinical setting. Using the training set, each team developed an algorithm that generated converted LDCT by changing the pixel values of LDCT to simulate those of standard-dose CT (SDCT). The agreement between SDCT and LDCT was evaluated using the intraclass correlation coefficient (ICC; 2-way random effects, absolute agreement, and single rater) for the percentage of low-attenuated area below -950 HU (LAA-950 HU), κ value for emphysema categorization (LAA-950 HU, <5%, 5% to 10%, and ≥10%) and cosine similarity of LAA-950 HU.

RESULTS

The mean LAA-950 HU of the test set was 14.2%±10.5% for SDCT, 25.4%±10.2% for unconverted LDCT, and 12.9%±10.4%, 11.7%±10.8%, and 12.4%±10.5% for converted LDCT (top 3 teams). The agreement between the SDCT and converted LDCT of the first-place team was 0.94 (95% confidence interval: 0.90, 0.97) for ICC, 0.71 (95% confidence interval: 0.58, 0.84) for categorical agreement, and 0.97 (interquartile range: 0.94 to 0.99) for cosine similarity.

CONCLUSIONS

Emphysema quantification with LDCT was feasible through deep learning-based CT conversion strategies.

Quantitative Assessment of Airway Changes in Fibrotic Interstitial Lung Abnormality Patients by Chest CT According to Cumulative Cigarette Smoking

Purpose: The aim of this study was to evaluate the role of Pi10 in patients with fibrotic interstitial lung abnormality (fibrotic ILA) in a chest CT, according to cumulative cigarette smoking. Methods: We retrospectively assessed 54 fibrotic ILA patients and 18 healthy non-smokers (control) who underwent non-enhanced CT and pulmonary function tests. We quantitatively analyzed airway changes (the inner luminal area, airway inner parameter, airway wall thickness, Pi10, skewness, and kurtosis) in the chest CT of fibrotic ILA patients, and the fibrotic ILA patients were categorized into groups based on pack-years: light, moderate, heavy. Airway change data and pulmonary function tests among the three groups of fibrotic ILA patients were compared with those of the control group by one-way ANOVA. Results: Mean skewness (2.58 ± 0.36) and kurtosis (7.64 ± 2.36) in the control group were significantly different from those of the fibrotic ILA patients (1.89 ± 0.37 and 3.62 ± 1.70, respectively, p < 0.001). In fibrotic ILA group, only heavy smokers had significantly increased Pi10 (mean increase 0.04, p = 0.013), increased airway wall thickness of the segmental bronchi (mean increase 0.06 mm, p = 0.005), and decreased lung diffusing capacity for carbon monoxide (p = 0.023). Conclusion: Pi10, as a biomaker of quantitative CT in fibrotic ILA patients, can reveal that smoking affects airway remodeling.

Imaging and Clinical Features of COVID-19 Breakthrough Infections: A Multicenter Study

Background

Since vaccines against COVID-19 became available, rare breakthrough infections have been reported despite their high efficacies.

Purpose

To evaluate the clinical and imaging characteristics of patients with COVID-19 breakthrough infections and compare them with those of unvaccinated patients with COVID-19.

Materials and Methods

In this retrospective multicenter cohort study, the authors analyzed patient (aged ≥18 years) data from three centers that were registered in an open data repository for COVID-19 between June and August 2021. Hospitalized patients with baseline chest radiographs were divided into three groups according to their vaccination status. Differences between clinical and imaging features were analyzed using the Pearson χ² test, Fisher exact test, and analysis of variance. Univariable and multivariable logistic regression analyses were used to evaluate associations between clinical factors, including vaccination status and clinical outcomes.

Results

Of the 761 hospitalized patients with COVID-19, the mean age was 47 years and 385 (51%) were women; 47 patients (6%) were fully vaccinated (breakthrough infection), 127 (17%) were partially vaccinated, and 587 (77%) were unvaccinated. Of the 761 patients, 412 (54%) underwent chest CT during hospitalization. Among the patients who underwent CT, the proportions without pneumonia were 22% of unvaccinated patients (71 of 326), 30% of partially vaccinated patients (19 of 64), and 59% of fully vaccinated patients (13 of 22) (P < .001). Fully vaccinated status was associated with a lower risk of requiring supplemental oxygen (odds ratio [OR], 0.24 [95% CI: 0.09, 0.64; P = .005]) and lower risk of intensive care unit admission (OR, 0.08 [95% CI: 0.09, 0.78; P = .02]) compared with unvaccinated status.

Conclusion

Patients with COVID-19 breakthrough infections had a significantly higher proportion of CT scans without pneumonia compared with unvaccinated patients. Vaccinated patients with breakthrough infections had a lower likelihood of requiring supplemental oxygen and intensive care unit admission.

© RSNA, 2022

Online supplemental material is available for this article.

See also the editorial by Schiebler and Bluemke in this issue.

Radiologic-pathologic correlation of interstitial lung abnormalities and predictors for progression and survival

OBJECTIVES

To evaluate radiologic and histologic correlations for interstitial lung abnormalities (ILAs) and to investigate radiologic or pathologic features contributing to disease progression and mortality.

METHODS

From 268 patients who underwent surgical lung biopsy between January 2004 and April 2019, 45 patients with incidentally detected ILA and normal pulmonary function were retrospectively included. CT features were classified as subpleural fibrotic or non-fibrotic, and changes in ILA over at least 2 years of follow-up were evaluated. Histologic findings were categorized as definite, probable, indeterminate, or alternative diagnosis for usual interstitial pneumonia (UIP) patterns. Overall and progression-free survival were calculated using the Kaplan-Meier method, and the Cox proportional hazard method was used to examine predictors for ILA progression and survival.

RESULTS

Among 36 subpleural fibrotic ILA subjects, 25 (69%) showed definite or probable UIP patterns, and 89% (8/9) of subpleural non-fibrotic ILA subjects showed an indeterminate or alternative diagnosis for UIP pattern on histopathology. On the radiologic-pathologic correlation, reticular opacity of fibrotic ILA was correlated with patchy involvement of fibrosis, and ground-glass attenuation of non-fibrotic ILA corresponded to diffuse interstitial thickening. The median progression time of ILA was 54 months, and fibrotic ILA increased the likelihood of progression (hazard ratio, 2.42; p = 0.017). The median survival time of ILA subjects was 123 months, and fibrotic ILA was associated with an increased risk of death (hazard ratio, 9.22; p = 0.025).

CONCLUSIONS

Subpleural fibrotic ILAs are associated with pathologic UIP patterns, and it is important to recognize subpleural fibrotic ILA on CT to predict disease progression and mortality.

KEY POINTS

• In total, 69% of subpleural fibrotic ILA showed definite or probable UIP patterns, while 11% of subpleural non-fibrotic ILA showed definite or probable UIP patterns. • Subpleural fibrotic ILA was associated with an increased rate of progression (hazard ratio, 2.42; p = 0.017), and the median progression-free time was 40 months. • Subpleural fibrotic ILA had an increased risk of death (hazard ratio, 9.22; p = 0.025), and the median survival time was 86 months.

Quantitative computed tomography imaging-based classification of cement dust-exposed subjects with an artificial neural network technique

BACKGROUND AND OBJECTIVE

Cement dust exposure is likely to affect the structural and functional alterations in segmental airways and parenchymal lungs. This study develops an artificial neural network (ANN) model for identifying cement dust-exposed (CDE) subjects using quantitative computed tomography-based airway structural and functional features.

METHODS

We obtained the airway features in five central and five sub-grouped segmental regions and the lung features in five lobar regions and one total lung region from 311 CDE and 298 non-CDE (NCDE) subjects. The five-fold cross-validation method was adopted to train the following classification models:ANN, support vector machine (SVM), logistic regression (LR), and decision tree (DT). For all the classification models, linear discriminant analysis (LDA) and genetic algorithm (GA) were applied for dimensional reduction and hyperparameterization, respectively. The ANN model without LDA was also optimized by the GA method to observe the effect of the dimensional reduction.

RESULTS

The genetically optimized ANN model without the LDA method was the best in terms of the classification accuracy. The accuracy, sensitivity, and specificity of the GA-ANN model with four layers were greater than those of the other classification models (i.e., ANN, SVM, LR, and DT using LDA and GA methods) in the five-fold cross-validation. The average values of accuracy, sensitivity, and specificity for the five-fold cross-validation were 97.0%, 98.7%, and 98.6%, respectively.

CONCLUSIONS

We demonstrated herein that a quantitative computed tomography-based ANN model could more effectively detect CDE subjects when compared to their counterpart models. By employing the model, the CDE subjects may be identified early for therapeutic intervention.

The Value of the Illness-Death Model for Predicting Outcomes in Patients with Non‒Small Cell Lung Cancer

Purpose

The illness-death model (IDM) is a comprehensive approach to evaluate the relationship between relapse and death. This study aimed to illustrate the value of the IDM for identifying risk factors and evaluating predictive probabilities for relapse and death in patients with non–small cell lung cancer (NSCLC) in comparison with the disease-free survival (DFS) model.

Materials and Methods

We retrospectively analyzed 612 NSCLC patients who underwent a curative operation. Using the IDM, the risk factors and predictive probabilities for relapse, death without relapse, and death after relapse were simultaneously evaluated and compared to those obtained from a DFS model.

Results

The IDM provided more detailed risk factors according to the patient’s disease course, including relapse, death without relapse, and death after relapse, in patients with resected lung cancer. In the IDM, history of malignancy (other than lung cancer) was related to relapse and smoking history was associated with death without relapse; both were indistinguishable in the DFS model. In addition, the IDM was able to evaluate the predictive probability and risk factors for death after relapse; this information could not be obtained from the DFS model.

Conclusion

Compared to the DFS model, we found that the IDM provides more comprehensive information on transitions between states and disease stages and provides deeper insights with respect to understanding the disease process among lung cancer patients.

Predictive Value of Interstitial Lung Abnormalities for Postoperative Pulmonary Complications in Elderly Patients with Early-stage Lung Cancer

Purpose

Identifying pretreatment interstitial lung abnormalities (ILAs) is important because of their predictive value for complications after lung cancer treatment. This study aimed to assess the predictive value of ILAs for postoperative pulmonary complications (PPCs) in elderly patients undergoing curative resection for early-stage non-small cell lung cancer (NSCLC).

Materials and Methods

Elderly patients (age ≥ 70 years) who underwent curative resection for pathologic stage I or II NSCLC with normal preoperative spirometry results (pre-bronchodilator forced expiratory volume in 1 s to forced vital capacity [FVC] ratio > 0.70 and FVC ≥ 80% of the predicted value) between January 2012 and December 2019 were retrospectively identified. Univariable and multivariable regression analyses were performed to assess risk factors for PPCs. The Kaplan-Meier method and log-rank test were used to analyze the relationship between ILAs and postoperative mortality. One-way analysis of variance was performed to assess the correlation between ILAs and hospital stay duration.

Results

A total of 262 patients (median age, 73 [interquartile range, 71-76] years; 132 male) were evaluated. A multivariable logistic regression model revealed that, among several relevant risk factors, fibrotic ILAs independently predicted both overall PPCs (adjusted odds ratio [OR], 4.84; 95% confidence interval [CI], 1.35-17.38; p=0.016) and major PPCs (adjusted OR, 8.72; 95% CI, 1.71-44.38; p=0.009). Fibrotic ILAs were significantly associated with higher postoperative mortality and longer hospital stay (F=5.21, p=0.006).

Conclusion

Pretreatment fibrotic ILAs are associated with PPCs, higher postoperative mortality, and longer hospital stay.

Quantitative CT Image-Based Structural and Functional Changes during Asthma Acute Exacerbations

Asthma acute exacerbations (AE) have been investigated using quantitative computed tomography (QCT)-based imaging metrics, but QCT has not yet been used to investigate a comprehensive set of imaging metrics during AE. This study aims to explore imaging features, captured both at segmental and parenchymal scales, during asthma AE, compared to stable asthma (SA). Two sets of the QCT images at total lung capacity (TLC) and functional residual capacity (FRC) were captured for 14 subjects during asthma AE and in SA phase, respectively. We calculated airway wall thickness (WT), hydraulic diameter (D_h), and airway circularity (Cr) of the 36 segmental airways, percentage of functional small airway disease (fSAD%), percentage of emphysema, tissue fraction (β_tiss), and coefficient of variation of β_tiss (CV of β_tiss). We performed Spearman correlation tests for changes in QCT metrics and pulmonary function tests, measured in AE and SA. During asthma AE, structural metrics, i.e., WT, D_h, and Cr, were not changed significantly. In functional metrics, CV of β_tiss at FRC indicating the heterogeneity of lung tissue distribution was significantly increased, while the mean of β_tiss at FRC did not change during AE. An increase of fSAD% during AE was most correlated with a decrease of forced expiratory volume in 1 second and forced vital capacity, especially in the lower lobes. This study demonstrates that the heterogeneous feature of β_tiss measured at lower lobes is more noticeable during asthma AE, compared with other traditional imaging metrics. This metric could be utilized to identify unique features during asthma AE.

CT-derived 3D-diaphragm motion in emphysema and IPF compared to normal subjects

Image registration-based local displacement analysis enables evaluation of respiratory motion between two computed tomography-captured lung volumes. The objective of this study was to compare diaphragm movement among emphysema, idiopathic pulmonary fibrosis (IPF) and normal subjects. 29 normal, 50 emphysema, and 51 IPF subjects were included. A mass preserving image registration technique was used to compute displacement vectors of local lung regions at an acinar scale. Movement of the diaphragm was assumed to be equivalent to movement of the basal lung within 5 mm from the diaphragm. Magnitudes and directions of displacement vectors were compared between the groups. Three-dimensional (3D) and apico-basal displacements were smaller in emphysema than normal subjects (P = 0.003, P = 0.002). Low lung attenuation area on expiration scan showed significant correlations with decreased 3D and apico-basal displacements (r = - 0.546, P < 0.0001; r = - 0.521, P < 0.0001) in emphysema patients. Dorsal-ventral displacement was smaller in IPF than normal subjects (P < 0.0001). The standard deviation of the displacement angle was greater in both emphysema and IPF patients than normal subjects (P < 0.0001). In conclusion, apico-basal movement of the diaphragm is reduced in emphysema while dorsal-ventral movement is reduced in IPF. Image registration technique to multi-volume CT scans provides insight into the pathophysiology of limited diaphragmatic motion in emphysema and IPF.

Assessing the speed-accuracy trade-offs of popular convolutional neural networks for single-crop rib fracture classification

Rib fractures are injuries commonly assessed in trauma wards. Deep learning has demonstrated state-of-the-art accuracy for a variety of tasks, including image classification. This paper assesses the speed-accuracy trade-offs and general suitability of four popular convolutional neural networks to classify rib fractures from axial computed tomography imagery. We transfer learned InceptionV3, ResNet50, MobileNetV2, and VGG16 models, additionally training "decomposed" models comprised of taking only the first n blocks for each block for each architecture. Given that acute (new) fractures are generally most important to detect, we trained two types of models: a classful model with classes acute, old (healed), and normal (non-fractured); and a binary model with acute vs. the other classes. We found that the first 7 blocks of InceptionV3 achieved the best results and general speed-accuracy trade-off. The classful model achieved a 5-fold cross-validation average accuracy and macro recall of 96.00% and 94.0%, respectively. The binary model achieved a 5-fold cross-validation average accuracy, macro recall, and area under receiver operator characteristic curve of 97.76%, 94.6%, and 94.7%, respectively. On a Windows 10 PC with 32GB RAM and an Nvidia 1080ti GPU, the model's average CPU and GPU per-crop inference times were 13.6 and 12.2 ms, respectively. Compared to the InceptionV3 Block 7 classful model, a radiologist with 9 years of experience was less accurate but more sensitive to acute fractures; meanwhile, the deep learning model had fewer false positive diagnoses and better sensitivity to old fractures and normal ribs. The Cohen's Kappa between the two was 0.813.

Generation-based study of airway remodeling in smokers with normal-looking CT with normalization to control inter-subject variability

PURPOSE

With the help of quantitative computed tomography (QCT), it is possible to identify smoking-associated airway remodeling. However, there is currently little information on whether QCT-based airway metrics are sensitive to early airway wall remodeling in subclinical phases of smoking-associated airway disease. This study aimed to evaluate a predictive model that normalized airway parameters and investigate structural airway alterations in smokers with normal-looking CT using the normalization scheme.

METHODS

In this retrospective analysis, 222 non-smokers (male 97, female 125) and 69 smokers (male 66, female 3) from January 2014 to December 2016 were included, and airway parameters were quantitatively analyzed. To control inter-subject variability, multiple linear regressions of tracheal wall thickness (WT), diameter (D), and luminal area (LA) were performed, adjusted for age, sex, and height. Using this normalization scheme, airway parameters with matched generation were compared between smokers and non-smokers.

RESULTS

Using the normalization scheme, it was possible to assess generation-based structural alterations of the airways in subclinical smokers. Smokers showed diffuse luminal narrowing of airways for most generations (P < 0.05, except 3rd generation), no change in wall thickness of the proximal bronchi (1st-3rd generation), and a thinning of distal airways (P <0.05, ≥4th generation).

CONCLUSION

QCT assessment for subclinical smokers can help identify minimal structural changes in airways induced by smoking.

Establishment of a Nationwide Korean Imaging Cohort of Coronavirus Disease 2019

BACKGROUND

The Korean Society of Thoracic Radiology (KSTR) recently constructed a nation-wide coronavirus disease 2019 (COVID-19) database and imaging repository, referred to the Korean imaging cohort of COVID-19 (KICC-19) based on the collaborative efforts of its members. The purpose of this study was to provide a summary of the clinico-epidemiological data and imaging data of the KICC-19.

METHODS

The KSTR members at 17 COVID-19 referral centers retrospectively collected imaging data and clinical information of consecutive patients with reverse transcription polymerase chain reaction-proven COVID-19 in respiratory specimens from February 2020 through May 2020 who underwent diagnostic chest computed tomography (CT) or radiograph in each participating hospital.

RESULTS

The cohort consisted of 239 men and 283 women (mean age, 52.3 years; age range, 11-97 years). Of the 522 subjects, 201 (38.5%) had an underlying disease. The most common symptoms were fever (n = 292) and cough (n = 245). The 151 patients (28.9%) had lymphocytopenia, 86 had (16.5%) thrombocytopenia, and 227 patients (43.5%) had an elevated CRP at admission. The 121 (23.4%) needed nasal oxygen therapy or mechanical ventilation (n = 38; 7.3%), and 49 patients (9.4%) were admitted to an intensive care unit. Although most patients had cured, 21 patients (4.0%) died. The 465 (89.1%) subjects underwent a low to standard-dose chest CT scan at least once during hospitalization, resulting in a total of 658 CT scans. The 497 subjects (95.2%) underwent chest radiography at least once during hospitalization, which resulted in a total of 1,475 chest radiographs.

CONCLUSION

The KICC-19 was successfully established and comprised of 658 CT scans and 1,475 chest radiographs of 522 hospitalized Korean COVID-19 patients. The KICC-19 will provide a more comprehensive understanding of the clinical, epidemiological, and radiologic characteristics of patients with COVID-19.

2020 Clinical Practice Guideline for Percutaneous Transthoracic Needle Biopsy of Pulmonary Lesions: A Consensus Statement and Recommendations of the Korean Society of Thoracic Radiology

Percutaneous transthoracic needle biopsy (PTNB) is one of the essential diagnostic procedures for pulmonary lesions. Its role is increasing in the era of CT screening for lung cancer and precision medicine. The Korean Society of Thoracic Radiology developed the first evidence-based clinical guideline for PTNB in Korea by adapting pre-existing guidelines. The guideline provides 39 recommendations for the following four main domains of 12 key questions: the indications for PTNB, pre-procedural evaluation, procedural technique of PTNB and its accuracy, and management of post-biopsy complications. We hope that these recommendations can improve the diagnostic accuracy and safety of PTNB in clinical practice and promote standardization of the procedure nationwide.

Relative Regional Air Volume Change Maps at the Acinar Scale Reflect Variable Ventilation in Low Lung Attenuation of COPD patients

OBJECTIVES

The purpose of this study was to investigate regional air volume changes at the acinar scale of the lung in chronic obstructive pulmonary disease (COPD) patients using an image registration technique.

MATERIALS AND METHODS

Thirty-four emphysema patients and 24 subjects with normal chest CT and pulmonary function test (PFT) results were included in this retrospective study for which informed consent was waived by the institutional review board. After lung segmentation, a mass-preserving image registration technique was used to compute relative regional air volume changes (RRAVCs) between inspiration and expiration CT scans. After determining the appropriate thresholds of RRAVCs for low ventilation areas (LVAs), they were displayed and analyzed using color maps on the background inspiration CT image, and compared with the low attenuation area (LAA) map. Correlations between quantitative CT parameters and PFTs were assessed using Pearson's correlation test, and parameters were compared between emphysema and normal-CT patients using the Student's t-test.

RESULTS

LVA percentage with an RRAVC threshold of 0.5 (%LVA_0.5) showed the strongest correlations with FEV₁/FVC (r = -0.566), FEV₁ (r = -0.534), %LAA_-950insp (r = 0.712), and %LAA_-856exp (r = 0.775). %LVA_0.5 was significantly higher (P < 0.001) in COPD patients than normal subjects. Despite the identical appearance of emphysematous lesions on the LAA_-950insp map, the RRAVC map depicted a wide range of ventilation differences between these LAA clusters.

CONCLUSION

RRAVC-based %LVA_0.5 correlated well with FEV₁/FVC, FEV₁, %LAA_-950insp and %LAA_-856exp. RRAVC holds the potential for providing additional acinar scale functional information for emphysematous LAAs in inspiratory CT images, providing the basis for a novel set for emphysematous phenotypes.

Interstitial Lung Abnormalities: What Radiologists Should Know

Interstitial lung abnormalities (ILAs) are radiologic abnormalities found incidentally on chest CT that are potentially related to interstitial lung diseases. Several articles have reported that ILAs are associated with increased mortality, and they can show radiologic progression. With the increased recognition of ILAs on CT, the role of radiologists in reporting them is critical. This review aims to discuss the clinical significance and radiologic characteristics of ILAs to facilitate and enhance their management.

Quantitative CT-based image registration metrics provide different ventilation and lung motion patterns in prone and supine positions in healthy subjects

Background

Previous studies suggested that the prone position (PP) improves oxygenation and reduces mortality among patients with acute respiratory distress syndrome (ARDS). However, the mechanism of this clinical benefit of PP is not completely understood. The aim of the present study was to quantitatively compare regional characteristics of lung functions in the PP with those in the supine position (SP) using inspiratory and expiratory computed tomography (CT) scans.

Methods

Ninety subjects with normal pulmonary function and inspiration and expiration CT images were included in the study. Thirty-four subjects were scanned in PP, and 56 subjects were scanned in SP. Non-rigid image registration-based inspiratory-expiratory image matching assessment was used for regional lung function analysis. Tissue fractions (TF) were computed based on the CT density and compared on a lobar basis. Three registration-derived functional variables, relative regional air volume change (RRAVC), volumetric expansion ratio (J), and three-dimensional relative regional displacement (s*) were used to evaluate regional ventilation and deformation characteristics.

Results

J was greater in PP than in SP in the right middle lobe (P = 0 .025), and RRAVC was increased in the upper and right middle lobes (P < 0.001). The ratio of the TF on inspiratory and expiratory scans, J, and RRAVC at the upper lobes to those at the middle and lower lobes and that ratio at the upper and middle lobes to those at the lower lobes of were all near unity in PP, and significantly higher than those in SP (0.98–1.06 vs 0.61–0.94, P < 0.001).

Conclusion

We visually and quantitatively observed that PP not only induced more uniform contributions of regional lung ventilation along the ventral-dorsal axis but also minimized the lobar differences of lung functions in comparison with SP. This may help in the clinician’s search for an understanding of the benefits of the application of PP to the patients with ARDS or other gravitationally dependent pathologic lung diseases.

Trial registration

Retrospectively registered.

Quantitative CT-based structural alterations of segmental airways in cement dust-exposed subjects

Background

Dust exposure has been reported as a risk factor of pulmonary disease, leading to alterations of segmental airways and parenchymal lungs. This study aims to investigate alterations of quantitative computed tomography (QCT)-based airway structural and functional metrics due to cement-dust exposure.

Methods

To reduce confounding factors, subjects with normal spirometry without fibrosis, asthma and pneumonia histories were only selected, and a propensity score matching was applied to match age, sex, height, smoking status, and pack-years. Thus, from a larger data set (N = 609), only 41 cement dust-exposed subjects were compared with 164 non-cement dust-exposed subjects. QCT imaging metrics of airway hydraulic diameter (D_h), wall thickness (WT), and bifurcation angle (θ) were extracted at total lung capacity (TLC) and functional residual capacity (FRC), along with their deformation ratios between TLC and FRC.

Results

In TLC scan, dust-exposed subjects showed a decrease of D_h (airway narrowing) especially at lower-lobes (p < 0.05), an increase of WT (wall thickening) at all segmental airways (p < 0.05), and an alteration of θ at most of the central airways (p < 0.001) compared with non-dust-exposed subjects. Furthermore, dust-exposed subjects had smaller deformation ratios of WT at the segmental airways (p < 0.05) and θ at the right main bronchi and left main bronchi (p < 0.01), indicating airway stiffness.

Conclusions

Dust-exposed subjects with normal spirometry demonstrated airway narrowing at lower-lobes, wall thickening at all segmental airways, a different bifurcation angle at central airways, and a loss of airway wall elasticity at lower-lobes. The airway structural alterations may indicate different airway pathophysiology due to cement dusts.

Adenocarcinoma-Papillary Cystic Pattern Arising in a Mixed Squamous and Glandular Papilloma of the Lung

Mixed squamous and glandular papilloma (mixed papilloma) of the lung has been reported in fewer than 25 cases in the English literature. Although it is known as a benign tumor, malignant transformation has been reported. Papillary cystic carcinoma is characterized by papillary and cystic growth patterns and has been reported as a subtype of adenocarcinoma, mainly in the salivary glands, breast, and pancreas. In this article, we report a case of adenocarcinoma-papillary cystic pattern arising from mixed papilloma of the lung in a 76-year-old male patient. Chest computed tomography scan revealed an endobronchial mass growing at the right medial segmental bronchus. Middle lobe lobectomy was performed, revealing a 4.9 × 1.9 cm-sized mass that protruded into the bronchus. Microscopically, the tumor showed numerous cysts lined by micropapillary projections. The tumor cells had round and vesicular nuclei with prominent nucleoli, and mitosis was frequent. A limited portion of the tumor consisted of benign mixed papilloma. The tumor showed diffuse immunoreactivity for thyroid transcription factor-1 and strong expression of p16. We investigated the mutational status of cancer-related genes using targeted next-generation sequencing and identified a genetic alteration in the BRAF gene. This is the first case report of papillary cystic carcinoma arising in mixed papilloma of the lung.

Non-diagnostic Results of Percutaneous Transthoracic Needle Biopsy: A Meta-analysis

Non-diagnostic results can affect the diagnostic performance of percutaneous transthoracic needle biopsy (PTNB) but have not been critically meta-analyzed yet. To meta-analyze the incidence and malignancy rate of non-diagnostic results, 3-by-2 table approaches rather than the conventional 2-by-2 approaches are needed to know its impact on the diagnostic performance of PTNB. A systematic literature search identified studies evaluating the diagnostic performance of PTNB with extractable outcomes. A total of 143 studies with 35,059 biopsies were included. The pooled incidence of non-diagnostic results was 6.8% (95% CI, 6.0-7.6%; I² = 0.91). The pooled malignancy rate of non-diagnostic results was 59.3% (95% CI, 51.7-66.8%; I² = 0.80), and was correlated with the prevalence of malignancy (correlation coefficient, 0.66; 95% CI, 0.42-0.91). Pooled percentage decrease of sensitivity and specificity due to non-diagnostic results were 4.5% (95% CI, 3.2-5.7%; I² = 0.64) and 10.7% (95% CI, 7.7-13.7%; I² = 0.70), respectively, and the pooled incidence of non-diagnostic results was 4.4% (95% CI, 3.2-5.8%; I² = 0.83) in lesions ultimately diagnosed as malignancies and 10.4% (95% CI, 7.5-13.8%; I² = 0.74) in benign disease. In conclusion, non-diagnostic results averagely occurred in 6.8% of PTNB and more than half of the results were malignancies. The non-diagnostic results decreased specificity and sensitivity by 10.7% and 4.5%, respectively, demanding efforts to minimize the non-diagnostic results in PTNB.

Structural and Functional Features on Quantitative Chest Computed Tomography in the Korean Asian versus the White American Healthy Non-Smokers

OBJECTIVE

Considering the different prevalence rates of diseases such as asthma and chronic obstructive pulmonary disease in Asians relative to other races, Koreans may have unique airway structure and lung function. This study aimed to investigate unique features of airway structure and lung function based on quantitative computed tomography (QCT)-imaging metrics in the Korean Asian population (Koreans) as compared with the White American population (Whites).

MATERIALS AND METHODS

QCT data of healthy non-smokers (223 Koreans vs. 70 Whites) were collected, including QCT structural variables of wall thickness (WT) and hydraulic diameter (Dh) and functional variables of air volume, total air volume change in the lung (ΔVair), percent emphysema-like lung (Emph%), and percent functional small airway disease-like lung (fSAD%). Mann-Whitney U tests were performed to compare the two groups.

RESULTS

As compared with Whites, Koreans had smaller volume at inspiration, ΔVair between inspiration and expiration (p < 0.001), and Emph% at inspiration (p < 0.001). Especially, Korean females had a decrease of ΔVair in the lower lobes (p < 0.001), associated with fSAD% at the lower lobes (p < 0.05). In addition, Koreans had smaller Dh and WT of the trachea (both, p < 0.05), correlated with the forced expiratory volume in 1 second (R = 0.49, 0.39; all p < 0.001) and forced vital capacity (R = 0.55, 0.45; all p < 0.001).

CONCLUSION

Koreans had unique features of airway structure and lung function as compared with Whites, and the difference was clearer in female individuals. Discriminating structural and functional features between Koreans and Whites enables exploration of inter-racial differences of pulmonary disease in terms of severity, distribution, and phenotype.