Effect of smoking on the diagnostic results and complication rates of percutaneous transthoracic needle biopsy.

OBJECTIVE: To investigate the association of smoking with the outcomes of percutaneous transthoracic needle biopsy (PTNB). METHODS: In total, 4668 PTNBs for pulmonary lesions were retrospectively identified. The associations of smoking status (never, former, current smokers) and smoking intensity (≤ 20, 21-40, > 40 pack-years) with diagnostic results (malignancy, non-diagnostic pathologies, and false-negative results in non-diagnostic pathologies) and complications (pneumothorax and hemoptysis) were assessed using multivariable logistic regression analysis. RESULTS: Among the 4668 PTNBs (median age of the patients, 66 years [interquartile range, 58-74]; 2715 men), malignancies, non-diagnostic pathologies, and specific benign pathologies were identified in 3054 (65.4%), 1282 (27.5%), and 332 PTNBs (7.1%), respectively. False-negative results for malignancy occurred in 20.5% (236/1153) of non-diagnostic pathologies with decidable reference standards. Current smoking was associated with malignancy (adjusted odds ratio [OR], 1.31; 95% confidence interval [CI]: 1.02-1.69; p = 0.03) and false-negative results (OR, 2.64; 95% CI: 1.32-5.28; p = 0.006), while heavy smoking (> 40 pack-years) was associated with non-diagnostic pathologies (OR, 1.69; 95% CI: 1.19-2.40; p = 0.003) and false-negative results (OR, 2.12; 95% CI: 1.17-3.92; p = 0.02). Pneumothorax and hemoptysis occurred in 21.8% (1018/4668) and 10.6% (495/4668) of PTNBs, respectively. Heavy smoking was associated with pneumothorax (OR, 1.33; 95% CI: 1.01-1.74; p = 0.04), while heavy smoking (OR, 0.64; 95% CI: 0.40-0.99; p = 0.048) and current smoking (OR, 0.64; 95% CI: 0.42-0.96; p = 0.04) were inversely associated with hemoptysis. CONCLUSION: Smoking history was associated with the outcomes of PTNBs. Current and heavy smoking increased false-negative results and changed the complication rates of PTNBs. CLINICAL RELEVANCE STATEMENT: Smoking status and intensity were independently associated with the outcomes of PTNBs. Non-diagnostic pathologies should be interpreted cautiously in current or heavy smokers. A patient's smoking history should be ascertained before PTNB to predict and manage complications. KEY POINTS: • Smoking status and intensity might independently contribute to the diagnostic results and complications of PTNBs. • Current and heavy smoking (> 40 pack-years) were independently associated with the outcomes of PTNBs. • Operators need to recognize the association between smoking history and the outcomes of PTNBs.

Diagnostic performance and prognostic value of CT-defined visceral pleural invasion in early-stage lung adenocarcinomas.

OBJECTIVES: To analyze the diagnostic performance and prognostic value of CT-defined visceral pleural invasion (CT-VPI) in early-stage lung adenocarcinomas. METHODS: Among patients with clinical stage I lung adenocarcinomas, half of patients were randomly selected for a diagnostic study, in which five thoracic radiologists determined the presence of CT-VPI. Probabilities for CT-VPI were obtained using deep learning (DL). Areas under the receiver operating characteristic curve (AUCs) and binary diagnostic measures were calculated and compared. Inter-rater agreement was assessed. For all patients, the prognostic value of CT-VPI by two radiologists and DL (using high-sensitivity and high-specificity cutoffs) was investigated using Cox regression. RESULTS: In 681 patients (median age, 65 years [interquartile range, 58-71]; 382 women), pathologic VPI was positive in 130 patients. For the diagnostic study (n = 339), the pooled AUC of five radiologists was similar to that of DL (0.78 vs. 0.79; p = 0.76). The binary diagnostic performance of radiologists was variable (sensitivity, 45.3-71.9%; specificity, 71.6-88.7%). Inter-rater agreement was moderate (weighted Fleiss κ, 0.51; 95%CI: 0.43-0.55). For overall survival (n = 680), CT-VPI by radiologists (adjusted hazard ratio [HR], 1.27 and 0.99; 95%CI: 0.84-1.92 and 0.63-1.56; p = 0.26 and 0.97) or DL (HR, 1.44 and 1.06; 95%CI: 0.86-2.42 and 0.67-1.68; p = 0.17 and 0.80) was not prognostic. CT-VPI by an attending radiologist was prognostic only in radiologically solid tumors (HR, 1.82; 95%CI: 1.07-3.07; p = 0.03). CONCLUSION: The diagnostic performance and prognostic value of CT-VPI are limited in clinical stage I lung adenocarcinomas. This feature may be applied for radiologically solid tumors, but substantial reader variability should be overcome. CLINICAL RELEVANCE STATEMENT: Although the diagnostic performance and prognostic value of CT-VPI are limited in clinical stage I lung adenocarcinomas, this parameter may be applied for radiologically solid tumors with appropriate caution regarding inter-reader variability. KEY POINTS: • Use of CT-defined visceral pleural invasion in clinical staging should be cautious, because prognostic value of CT-defined visceral pleural invasion remains unexplored. • Diagnostic performance and prognostic value of CT-defined visceral pleural invasion varied among radiologists and deep learning. • Role of CT-defined visceral pleural invasion in clinical staging may be limited to radiologically solid tumors.

Cigarette smoking and disproportionate changes of thoracic skeletal muscles in low-dose chest computed tomography.

Association between smoking intensity and the quantity and quality of thoracic skeletal muscles (TSMs) remains unexplored. Skeletal muscle index (SMI; skeletal muscle area/height2) and percentage of normal attenuation muscle area (NAMA%) were measured to represent the quantity and quality of the skeletal muscles, respectively, and quantification was performed in pectoralis muscle at aortic arch (AA-PM), TSM at carina (C-TSM), erector spinae muscle at T12 (T12-ESM), and skeletal muscle at L1 (L1-SM). Among the 258 men (median age, 62 years [IQR: 58-69]), 183 were current smokers (median smoking intensity, 40 pack-years [IQR: 30-46]). SMI and NAMA% of AA-PM significantly decreased with pack-year (ß = - 0.028 and - 0.076; P < 0.001 and P = 0.021, respectively). Smoking intensity was inversely associated with NAMA% of C-TSM (ß = - 0.063; P = 0.001), whereas smoking intensity showed a borderline association with SMI of C-TSM (ß = - 0.023; P = 0.057). Smoking intensity was associated with the change in NAMA% of L1-SM (ß = - 0.040; P = 0.027), but was not associated with SMI of L1-SM (P > 0.05). Neither NAMA% nor SMI of T12-ESM was affected by smoking intensity (P > 0.05). In conclusion, smoking intensity was associated with the change of TSMs. Its association varied according to the location of TSMs, with the most associated parts being the upper (AA-PM) and middle TSMs (C-TSM).

Identification of Active Pulmonary Tuberculosis Among Patients With Positive Interferon-Gamma Release Assay Results: Value of a Deep Learning-based Computer-aided Detection System in Different Scenarios of Implementation.

PURPOSE: To evaluate the accuracy of a deep learning-based computer-aided detection (CAD) system in identifying active pulmonary tuberculosis on chest radiographs (CRs) of patients with positive interferon-gamma release assay (IGRA) results in different scenarios of clinical implementation. MATERIALS AND METHODS: We collected the CRs of consecutive patients with positive IGRA results. Findings of active pulmonary tuberculosis on CRs were independently evaluated by the CAD and a thoracic radiologist, followed by interpretation using the CAD. Sensitivity and specificity were evaluated in different scenarios: (a) radiologists' interpretation, (b) radiologists' CAD-assisted interpretation, and (c) CAD-based prescreening (radiologists' interpretation for positive CAD results only). We conducted a reader test to compare the accuracy of the CAD with those of 5 radiologists. RESULTS: Among 1780 patients (men, 53.8%; median age, 56 y), 44 (2.5%) were diagnosed with active pulmonary tuberculosis. The CAD-assisted interpretation exhibited a higher sensitivity (81.8% vs. 72.7%; P =0.046) but lower specificity than the radiologists' interpretation (84.1% vs. 85.7%; P <0.001). The CAD-based prescreening exhibited a higher specificity than the radiologists' interpretation (88.8% vs. 85.7%; P <0.001) at the same sensitivity, with a workload reduction of 85.2% (1780 to 263). In the reader test, the CAD exhibited a higher sensitivity than radiologists (72.7% vs. 59.5%; P =0.005) at the same specificity (88.0%), and CAD-assisted interpretation significantly improved the sensitivity of radiologists' interpretation (72.3%; P <0.001). CONCLUSIONS: For identifying active pulmonary tuberculosis among patients with positive IGRA results, deep learning-based CAD can enhance the sensitivity of interpretation. CAD-based prescreening may reduce the radiologists' workload at an improved specificity.

Determination of the optimum definition of growth evaluation for indeterminate pulmonary nodules detected in lung cancer screening.

OBJECTIVE: To determine the optimum definition of growth for indeterminate pulmonary nodules detected in lung cancer screening. MATERIALS AND METHODS: Individuals with indeterminate nodules as defined by volume of 50-500 mm3 (solid nodules) and solid component volume of 50-500 mm3 or average diameter of non-solid component ≥8 mm (part-solid nodules) on baseline lung cancer screening low-dose chest CT (LDCT) were included. The average diameters and volumes of the nodules were measured on baseline and follow-up LDCTs with semi-automated segmentation. Sensitivities and specificities for lung cancer diagnosis of nodule growth defined by a) percentage volume growth ≥25% (defined in the NELSON study); b) absolute diameter growth >1.5 mm (defined in the Lung-RADS version 1.1); and c) subjective decision by a radiologist were evaluated. Sensitivities and specificities of diagnostic referral based on various thresholds of volume doubling time (VDT) were also evaluated. RESULTS: Altogether, 115 nodules (one nodule per individual; 93 solid and 22 part-solid nodules; 105 men; median age, 68 years) were evaluated (median follow-up interval: 201 days; interquartile range: 127-371 days). Percentage volume growth ≥25% exhibited higher sensitivity but lower specificity than those of diametrical measurement compared to absolute diameter growth >1.5 mm (sensitivity, 69.2% vs. 42.3%, p = 0.023; specificity, 82.0% vs. 96.6%, p = 0.002). The radiologist had an equivalent sensitivity (53.9%; p = 0.289) but higher specificity (98.9%; p = 0.002) compared to those of volume growth, but did not differ from those of diameter growth (p>0.05 both in sensitivity and specificity). Compared to the VDT threshold of 600 days (sensitivity, 61.5%; specificity, 87.6%), VDT thresholds ≤200 and ≤300 days exhibited significantly lower sensitivity (30.8%, p = 0.013) and higher specificity (94.4%, p = 0.041), respectively. CONCLUSION: Growth evaluation of screening-detected indeterminate nodules with volumetric measurement exhibited higher sensitivity but lower specificity compared to diametric measurements.

Validation for measurements of skeletal muscle areas using low-dose chest computed tomography.

Various methods were suggested to measure skeletal muscle areas (SMAs) using chest low-dose computed tomography (chest LDCT) as a substitute for SMA at 3rd lumbar vertebra level (L3-SMA). In this study, four SMAs (L1-SMA, T12-erector spinae muscle areas, chest wall muscle area at carina level, pectoralis muscle area at aortic arch level) were segmented semi-automatically in 780 individuals taking concurrent chest and abdomen LDCT for healthcare screening. Four SMAs were compared to L3-SMA and annual changes were calculated from individuals with multiple examinations (n = 101). Skeletal muscle index (SMI; SMA/height2) cut-off for sarcopenia was determined by lower 5th percentile of young individuals (age ≤ 40 years). L1-SMA showed the greatest correlation to L3-SMA (men, R2 = 0.7920; women, R2 = 0.7396), and the smallest annual changes (0.3300 ± 4.7365%) among four SMAs. L1-SMI cut-offs for determining sarcopenia were 39.2cm2/m2 in men, and 27.5cm2/m2 in women. Forty-six men (9.5%) and ten women (3.4%) were found to have sarcopenia using L1-SMI cut-offs. In conclusion, L1-SMA could be a reasonable substitute for L3-SMA in chest LDCT. Suggested L1-SMI cut-offs for sarcopenia were 39.2cm2/m2 for men and 27.5cm2/m2 for women in Asian.

Percutaneous transthoracic needle biopsies in immunocompromised hosts with suspicious pulmonary infection: diagnostic yields and complications.

BACKGROUND: Pulmonary infection is a major cause of morbidity and mortality in immunocompromised patients, in whom diagnostic yields of cone-beam computed tomography (CBCT)-guided percutaneous transthoracic needle biopsies (PTNBs) have not been evaluated so far. PURPOSE: To evaluate diagnostic yields and complications of CBCT-guided PTNBs in immunocompromised patients. MATERIAL AND METHODS: From January 2015 to January 2018, 43 patients (25 men, 18 women; mean age 54.1 ± 16.4 years) who were suspected of having pulmonary infections were included in this retrospective study. Electronic medical records and radiologic studies were reviewed, including the underlying medical status, information on target lesions, PTNB procedural factors, and pathologic results. Logistic regression was performed to explore factors related with post-PTNB complications. RESULTS: Among 43 patients, specific causative organisms or family of organisms were identified by PTNBs in 16 patients (37.2%). The most common causative organism was fungus (10/16, 62.5%), while bacterial infection was pathologically proven only in one patient (6.3%). Clinically significant change in management occurred in 12 of 43 patients (27.9%). Post-PTNB complications developed in 12 patients (27.9%; pneumothorax [n = 6] and hemoptysis [n = 6]) without PTNB-related mortality. Lower lobar location (odds ratio [OR] = 0.07, P = 0.006) was related with post-PTNB pneumothorax, while lower platelet counts (≤127 × 103/µL) were associated with post-PTNB hemoptysis (OR = 9.82, P = 0.025). CONCLUSION: CBCT-guided PTNBs revealed microbiological pathogens in 37.2% of immunocompromised patients and led to subsequent clinical actions in 27.9% of patients. Post-PTNB complications occurred in 27.9% of patients, and it might be necessary to perform PTNBs more carefully in immunocompromised patients with lower platelet counts.

Assessing the reproducibility of high temporal and spatial resolution dynamic contrast-enhanced magnetic resonance imaging in patients with gliomas.

Temporal and spatial resolution of dynamic contrast-enhanced MR imaging (DCE-MRI) is critical to reproducibility, and the reproducibility of high-resolution (HR) DCE-MRI was evaluated. Thirty consecutive patients suspected to have brain tumors were prospectively enrolled with written informed consent. All patients underwent both HR-DCE (voxel size, 1.1 × 1.1 × 1.1 mm3; scan interval, 1.6 s) and conventional DCE (C-DCE; voxel size, 1.25 × 1.25 × 3.0 mm3; scan interval, 4.0 s) MRI. Regions of interests (ROIs) for enhancing lesions were segmented twice in each patient with glioblastoma (n = 7) to calculate DCE parameters (Ktrans, Vp, and Ve). Intraclass correlation coefficients (ICCs) of DCE parameters were obtained. In patients with gliomas (n = 25), arterial input functions (AIFs) and DCE parameters derived from T2 hyperintense lesions were obtained, and DCE parameters were compared according to WHO grades. ICCs of HR-DCE parameters were good to excellent (0.84-0.95), and ICCs of C-DCE parameters were moderate to excellent (0.66-0.96). Maximal signal intensity and wash-in slope of AIFs from HR-DCE MRI were significantly greater than those from C-DCE MRI (31.85 vs. 7.09 and 2.14 vs. 0.63; p < 0.001). Both 95th percentile Ktrans and Ve from HR-DCE and C-DCE MRI could differentiate grade 4 from grade 2 and 3 gliomas (p < 0.05). In conclusion, HR-DCE parameters generally showed better reproducibility than C-DCE parameters, and HR-DCE MRI provided better quality of AIFs.

Deep learning computer-aided detection system for pneumonia in febrile neutropenia patients: a diagnostic cohort study.

BACKGROUND: Diagnosis of pneumonia is critical in managing patients with febrile neutropenia (FN), however, chest X-ray (CXR) has limited performance in the detection of pneumonia. We aimed to evaluate the performance of a deep learning-based computer-aided detection (CAD) system in pneumonia detection in the CXRs of consecutive FN patients and investigated whether CAD could improve radiologists' diagnostic performance when used as a second reader. METHODS: CXRs of patients with FN (a body temperature ≥ 38.3 °C, or a sustained body temperature ≥ 38.0 °C for an hour; absolute neutrophil count < 500/mm3) obtained between January and December 2017 were consecutively included, from a single tertiary referral hospital. Reference standards for the diagnosis of pneumonia were defined by consensus of two thoracic radiologists after reviewing medical records and CXRs. A commercialized, deep learning-based CAD system was retrospectively applied to detect pulmonary infiltrates on CXRs. For comparing performance, five radiologists independently interpreted CXRs initially without the CAD results (radiologist-alone interpretation), followed by the interpretation with CAD. The sensitivities and specificities for detection of pneumonia were compared between radiologist-alone interpretation and interpretation with CAD. The standalone performance of the CAD was also evaluated, using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Moreover, sensitivity and specificity of standalone CAD were compared with those of radiologist-alone interpretation. RESULTS: Among 525 CXRs from 413 patients (52.3% men; median age 59 years), pneumonia was diagnosed in 128 (24.4%) CXRs. In the interpretation with CAD, average sensitivity of radiologists was significantly improved (75.4% to 79.4%, P = 0.003) while their specificity remained similar (75.4% to 76.8%, P = 0.101), compared to radiologist-alone interpretation. The CAD exhibited AUC, sensitivity, and specificity of 0.895, 88.3%, and 68.3%, respectively. The standalone CAD exhibited higher sensitivity (86.6% vs. 75.2%, P < 0.001) and lower specificity (64.8% vs. 75.4%, P < 0.001) compared to radiologist-alone interpretation. CONCLUSIONS: In patients with FN, the deep learning-based CAD system exhibited radiologist-level performance in detecting pneumonia on CXRs and enhanced radiologists' performance.

Deep Learning for Detection of Pulmonary Metastasis on Chest Radiographs.

Background A computer-aided detection (CAD) system may help surveillance for pulmonary metastasis at chest radiography in situations where there is limited access to CT. Purpose To evaluate whether a deep learning (DL)-based CAD system can improve diagnostic yield for newly visible lung metastasis on chest radiographs in patients with cancer. Materials and Methods A regulatory-approved CAD system for lung nodules was implemented to interpret chest radiographs from patients referred by the medical oncology department in clinical practice. In this retrospective diagnostic cohort study, chest radiographs interpreted with assistance from a CAD system after the implementation (January to April 2019, CAD-assisted interpretation group) and those interpreted before the implementation (September to December 2018, conventional interpretation group) of the CAD system were consecutively included. The diagnostic yield (frequency of true-positive detections) and false-referral rate (frequency of false-positive detections) of formal reports of chest radiographs for newly visible lung metastasis were compared between the two groups using generalized estimating equations. Propensity score matching was performed between the two groups for age, sex, and primary cancer. Results A total of 2916 chest radiographs from 1521 patients (1546 men, 1370 women; mean age, 62 years) and 5681 chest radiographs from 3456 patients (2941 men, 2740 women; mean age, 62 years) were analyzed in the CAD-assisted interpretation and conventional interpretation groups, respectively. The diagnostic yield for newly visible metastasis was higher in the CAD-assisted interpretation group (0.86%, 25 of 2916 [95% CI: 0.58, 1.3] vs 0.32%, 18 of 568 [95% CI: 0.20, 0.50%]; P = .004). The false-referral rate in the CAD-assisted interpretation group (0.34%, 10 of 2916 [95% CI: 0.19, 0.64]) was not inferior to that in the conventional interpretation group (0.25%, 14 of 5681 [95% CI: 0.15, 0.42]) at the noninferiority margin of 0.5% (95% CI of difference: -0.15, 0.35). Conclusion A deep learning-based computer-aided detection system improved the diagnostic yield for newly visible metastasis on chest radiographs in patients with cancer with a similar false-referral rate. © RSNA, 2021 Online supplemental material is available for this article.

Effectiveness of radiologist training in improving reader agreement for Lung-RADS 4X categorization.

OBJECTIVES: To identify the agreement on Lung CT Screening Reporting and Data System 4X categorization between radiologists and an expert-adjudicated reference standard and to investigate whether training led to improvement of the agreement measures and diagnostic potential for lung cancer. METHODS: Category 4 nodules in the Korean Lung Cancer Screening Project were identified retrospectively, and each 4X nodule was matched with one 4A or 4B nodule. An expert panel re-evaluated the categories and determined the reference standard. Nineteen radiologists were asked to determine the presence of CT features of malignancy and 4X categorization for each nodule. A review was performed in two sessions, and training material was given after session 1. Agreement on 4X categorization between radiologists and the expert-adjudicated reference standard and agreement between radiologist-assessed 4X categorization and lung cancer diagnosis were evaluated. RESULTS: The 48 expert-adjudicated 4X nodules and 64 non-4X nodules were evenly distributed in each session. The proportion of category 4X decreased after training (56.4% ± 16.9% vs. 33.4% ± 8.0%; p < 0.001). Cohen's κ indicated poor agreement (0.39 ± 0.16) in session 1, but agreement improved in session 2 (0.47 ± 0.09; p = 0.03). The increase in agreement in session 2 was observed among inexperienced radiologists (p < 0.05), and experienced and inexperienced reviewers exhibited comparable agreement performance in session 2 (p > 0.05). All agreement measures between radiologist-assessed 4X categorization and lung cancer diagnosis increased in session 2 (p < 0.05). CONCLUSION: Radiologist training can improve reader agreement on 4X categorization, leading to enhanced diagnostic performance for lung cancer. KEY POINTS: • Agreement on 4X categorization between radiologists and an expert-adjudicated reference standard was initially poor, but improved significantly after training. • The mean proportion of 4X categorization by 19 radiologists decreased from 56.4% ± 16.9% in session 1 to 33.4% ± 8.0% in session 2. • All agreement measures between the 4X categorization and lung cancer diagnosis increased significantly in session 2, implying that appropriate training and guidance increased the diagnostic potential of category 4X.

Tumor Stiffness Measurements on MR Elastography for Single Nodular Hepatocellular Carcinomas Can Predict Tumor Recurrence After Hepatic Resection.

BACKGROUND: Tumor stiffness (TS), measured by magnetic resonance elastography (MRE), could be associated with tumor mechanical properties and tumor grade. PURPOSE: To determine whether TS obtained using MRE is associated with survival in patients with single nodular hepatocellular carcinoma (HCC) after hepatic resection (HR). STUDY TYPE: Retrospective. POPULATION: In all, 95 patients with pathologically confirmed HCCs. FIELD STRENGTH/SEQUENCE: 1.5T/3D spin-echo echo-planar imaging MRE. ASSESSMENT: TS values of the whole tumor (TS-WT) and of a solid portion of the tumor (TS-SP) after excluding the necrotic area were measured on stiffness maps. Known imaging prognostic factors of HCC were also analyzed. After surgery, pathologic findings were evaluated from resected pathology specimens. STATISTICAL TESTS: Fisher's exact test and the Mann-Whitney U-test were performed to determine the significance of differences according to the tumor grade. Overall survival (OS) / recurrence-free survival (RFS) analyses were performed using Kaplan-Meier analyses and Cox multivariable models. RESULTS: The average TS-WT was 2.14 ± 0.74 kPa, and the average TS-SP was 2.51 ± 1.07 kPa. The cumulative incidence of RFS was 73.1%, 63.1%, and 57.3% at 1, 3, and 5 years, respectively. The TS-WT, TS-SP, and tumor size (≥5 cm) were significant prognostic factors for RFS (P < 0.001; P < 0.001; P = 0.017, respectively). The estimated overall 1-, 3-, and 5-year survival rates were 95.7%, 86.9%, and 80.8%, respectively. The alpha-fetoprotein changes, platelets, tumor size (≥5 cm), and vascular invasion in pathology were significant predictive factors for overall survival (all P < 0.05). Tumor necrosis, TS-WT, TS-SP, and vascular invasion in pathology were significantly correlated with poorly differentiated HCC (all P < 0.05). DATA CONCLUSION: The TS-WT, TW-SP, and tumor size (≥5 cm) were significant predictive factors of RFS after HR in patients with HCC. Level of Evidence Technical Efficacy Stage 5 J. MAGN. RESON. IMAGING 2021;53:587-596.

Growth and Clinical Impact of 6-mm or Larger Subsolid Nodules after 5 Years of Stability at Chest CT.

Background It remains unclear whether 5 years of stability is sufficient to establish the benign behavior of subsolid nodules (SSNs) of the lung. There are no guidelines for the length of follow-up needed for these SSNs. Purpose To investigate the incidence of interval growth of pulmonary SSNs 6 mm or greater in diameter after 5 years of stability and their clinical outcome. Materials and Methods This retrospective study assessed SSNs 6 mm or greater that were stable for 5 years after detection (January 2002 to December 2018). The incidence of interval growth after 5 years of stability and the clinical and radiologic features of these SSNs were investigated. Clinical stage shifts of growing SSNs, presence of metastasis, and overall survival were assessed during the follow-up period. Subgroup analysis was performed in patients with nonenhanced thin-section (section thickness ≤1.5 mm) CT for interval growth after 5 years of stability. Results A total of 235 SSNs in 235 patients (mean age, 64 years ± 10 [standard deviation]; 132 women) were evaluated. There were 212 pure ground-glass nodules and 24 part-solid nodules. During follow-up (median, 112 months; range, 84-208 months), five of the 235 SSNs (2%; three primary ground-glass nodules and two part-solid nodules) showed interval growth. Three of these five growing SSNs were 10 mm or greater. Three of the five SSNs with interval growth had clinical stage shifts after growth (from Tis [in situ] to T1mi [minimally invasive] in one lesion; from T1mi to T1a in two lesions). There were no deaths or metastases from lung cancer during follow-up. Of 160 SSNs imaged with section thickness of 1.5 mm or less, two (1%) grew; both lesions were 10 mm or greater. Conclusion Only 2% of subsolid pulmonary nodules greater than or equal to 6 mm that had been stable for 5 years showed subsequent growth. At median follow-up of 9 years (after the initial 5-year period of stability), growth of those lung nodules had no clinical effect. © RSNA, 2020 See also the editorial by Naidich and Azour in this issue.

Deep Learning for Chest Radiograph Diagnosis in the Emergency Department.

BackgroundThe performance of a deep learning (DL) algorithm should be validated in actual clinical situations, before its clinical implementation.PurposeTo evaluate the performance of a DL algorithm for identifying chest radiographs with clinically relevant abnormalities in the emergency department (ED) setting.Materials and MethodsThis single-center retrospective study included consecutive patients who visited the ED and underwent initial chest radiography between January 1 and March 31, 2017. Chest radiographs were analyzed with a commercially available DL algorithm. The performance of the algorithm was evaluated by determining the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity at predefined operating cutoffs (high-sensitivity and high-specificity cutoffs). The sensitivities and specificities of the algorithm were compared with those of the on-call radiology residents who interpreted the chest radiographs in the actual practice by using McNemar tests. If there were discordant findings between the algorithm and resident, the residents reinterpreted the chest radiographs by using the algorithm's output.ResultsA total of 1135 patients (mean age, 53 years ± 18; 582 men) were evaluated. In the identification of abnormal chest radiographs, the algorithm showed an AUC of 0.95 (95% confidence interval [CI]: 0.93, 0.96), a sensitivity of 88.7% (227 of 256 radiographs; 95% CI: 84.1%, 92.3%), and a specificity of 69.6% (612 of 879 radiographs; 95% CI: 66.5%, 72.7%) at the high-sensitivity cutoff and a sensitivity of 81.6% (209 of 256 radiographs; 95% CI: 76.3%, 86.2%) and specificity of 90.3% (794 of 879 radiographs; 95% CI: 88.2%, 92.2%) at the high-specificity cutoff. Radiology residents showed lower sensitivity (65.6% [168 of 256 radiographs; 95% CI: 59.5%, 71.4%], P < .001) and higher specificity (98.1% [862 of 879 radiographs; 95% CI: 96.9%, 98.9%], P < .001) compared with the algorithm. After reinterpretation of chest radiographs with use of the algorithm's outputs, the sensitivity of the residents improved (73.4% [188 of 256 radiographs; 95% CI: 68.0%, 78.8%], P = .003), whereas specificity was reduced (94.3% [829 of 879 radiographs; 95% CI: 92.8%, 95.8%], P < .001).ConclusionA deep learning algorithm used with emergency department chest radiographs showed diagnostic performance for identifying clinically relevant abnormalities and helped improve the sensitivity of radiology residents' evaluation.Published under a CC BY 4.0 license.Online supplemental material is available for this article.See also the editorial by Munera and Infante in this issue.

Application of Vendor-Neutral Iterative Reconstruction Technique to Pediatric Abdominal Computed Tomography.

OBJECTIVE: To compare image qualities between vendor-neutral and vendor-specific hybrid iterative reconstruction (IR) techniques for abdominopelvic computed tomography (CT) in young patients. MATERIALS AND METHODS: In phantom study, we used an anthropomorphic pediatric phantom, age-equivalent to 5-year-old, and reconstructed CT data using traditional filtered back projection (FBP), vendor-specific and vendor-neutral IR techniques (ClariCT; ClariPI) in various radiation doses. Noise, low-contrast detectability and subjective spatial resolution were compared between FBP, vendor-specific (i.e., iDose1 to 5; Philips Healthcare), and vendor-neutral (i.e., ClariCT1 to 5) IR techniques in phantom. In 43 patients (median, 14 years; age range 1-19 years), noise, contrast-to-noise ratio (CNR), and qualitative image quality scores of abdominopelvic CT were compared between FBP, iDose level 4 (iDose4), and ClariCT level 2 (ClariCT2), which showed most similar image quality to clinically used vendor-specific IR images (i.e., iDose4) in phantom study. Noise, CNR, and qualitative imaging scores were compared using one-way repeated measure analysis of variance. RESULTS: In phantom study, ClariCT2 showed noise level similar to iDose4 (14.68-7.66 Hounsfield unit [HU] vs. 14.78-6.99 HU at CT dose index volume range of 0.8-3.8 mGy). Subjective low-contrast detectability and spatial resolution were similar between ClariCT2 and iDose4. In clinical study, ClariCT2 was equivalent to iDose4 for noise (14.26-17.33 vs. 16.01-18.90) and CNR (3.55-5.24 vs. 3.20-4.60) (p > 0.05). For qualitative imaging scores, the overall image quality ([reader 1, reader 2]; 2.74 vs. 2.07, 3.02 vs. 2.28) and noise (2.88 vs. 2.23, 2.93 vs. 2.33) of ClariCT2 were superior to those of FBP (p < 0.05), and not different from those of iDose4 (2.74 vs. 2.72, 3.02 vs. 2.98; 2.88 vs. 2.77, 2.93 vs. 2.86) (p > 0.05). CONCLUSION: Vendor-neutral IR technique shows image quality similar to that of clinically used vendor-specific hybrid IR technique for abdominopelvic CT in young patients.

Validation of prediction models for risk stratification of incidentally detected pulmonary subsolid nodules: a retrospective cohort study in a Korean tertiary medical centre.

OBJECTIVES: To validate the performances of two prediction models (Brock and Lee models) for the differentiation of minimally invasive adenocarcinoma (MIA) and invasive pulmonary adenocarcinoma (IPA) from preinvasive lesions among subsolid nodules (SSNs). DESIGN: A retrospective cohort study. SETTING: A tertiary university hospital in South Korea. PARTICIPANTS: 410 patients with 410 incidentally detected SSNs who underwent surgical resection for the pulmonary adenocarcinoma spectrum between 2011 and 2015. PRIMARY AND SECONDARY OUTCOME MEASURES: Using clinical and radiological variables, the predicted probability of MIA/IPA was calculated from pre-existing logistic models (Brock and Lee models). Areas under the receiver operating characteristic curve (AUCs) were calculated and compared between models. Performance metrics including sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) were also obtained. RESULTS: For pure ground-glass nodules (n=101), the AUC of the Brock model in differentiating MIA/IPA (59/101) from preinvasive lesions (42/101) was 0.671. Sensitivity, specificity, accuracy, PPV and NPV based on the optimal cut-off value were 64.4%, 64.3%, 64.4%, 71.7% and 56.3%, respectively. Sensitivity, specificity, accuracy, PPV and NPV according to the Lee criteria were 76.3%, 42.9%, 62.4%, 65.2% and 56.3%, respectively. AUC was not obtained for the Lee model as a single cut-off of nodule size (≥10 mm) was suggested by this model for the assessment of pure ground-glass nodules. For part-solid nodules (n=309; 26 preinvasive lesions and 283 MIA/IPAs), the AUC was 0.746 for the Brock model and 0.771 for the Lee model (p=0.574). Sensitivity, specificity, accuracy, PPV and NPV were 82.3%, 53.8%, 79.9%, 95.1% and 21.9%, respectively, for the Brock model and 77.0%, 69.2%, 76.4%, 96.5% and 21.7%, respectively, for the Lee model. CONCLUSIONS: The performance of prediction models for the incidentally detected SSNs in differentiating MIA/IPA from preinvasive lesions might be suboptimal. Thus, an alternative risk calculation model is required for the incidentally detected SSNs.

Critical Test Result Notification via Mobile Phone-Based Automated Text Message System in the Radiologic Field: Single Institutional Experience.

PURPOSE: To investigate the feasibility of sharing critical test result (CTR) notifications (CTRNs) via automated text messaging. MATERIALS AND METHODS: CTRNs via automated text messaging was used to notify physicians of CTRs in a tertiary hospital with 1,786 beds. From June 2016 to September 2016, notifications for 545 CTRs were given via a CTRN system. Among them, 490 CTRs (292 male and 198 female patients; mean age, 53.6 years old [range, 1-88]) were included in analysis. CTR levels (CTRLs) were assigned to four categories (CTRL1 to CTRL3 and unclassified) when reported, and reclassified into three CTRLs according to their clinical relevance and urgency. Response time was defined as time lapse between CTR reporting and documentation by physicians. Analysis of variance was performed to compare response times according to CTRLs and patients' location. RESULTS: Corresponding actions were taken in 404 of 490 cases (82.4%) without any delayed CTRN-related morbidity. There were 15 CTRL1 (3.1%), 50 CTRL2 (10.2%), 112 CTRL3 (22.9%) cases, and the remaining 313 CTRL cases were unclassified. After reclassification, CTRL1, CTRL2, and CTRL3 were 81 (16.5%), 177 (36.1%), and 232 cases (47.3%), respectively. Response time of reclassified CTRL3 was significantly longer than that of reclassified CTRL1 (median 23.0, [interquartile range 2.0-133.5] hours versus 4.0 [0.0-22.0] hours; P < .001). Response time of outpatient cases (80.0 [6.0 to 157.0] hours) was significantly longer (P < .001) than those of inpatient (3.0 [0.0-16.0]) and emergency department cases (5.0 [1.0-21.0]). CONCLUSION: Automated text messaging could be a feasible option for CTRNs in the radiologic field. Further large-scale investigations regarding efficiency of this system are warranted.

Does radiation therapy increase gadolinium accumulation in the brain?: Quantitative analysis of T1 shortening using R1 relaxometry in glioblastoma multiforme patients.

OBJECTIVE: This study evaluated the possibility of accelerated gadolinium accumulation in irradiated brain parenchyma where the blood-brain barrier was weakened. METHODS: From January 2010 to June 2015, 44 patients with supratentorial glioblastoma were retrospectively identified who underwent pre- and post-radiation brain MR imaging, including R1 mapping. The mean dose of administered gadobutrol (Gadovist, Bayer, Germany) was 5.1 vials. Regions of interest (ROIs) were drawn around tumors that were located within 50-100% iso-dose lines of maximum radiation dose. ROIs were also drawn at globus pallidus, thalamus, and cerebral white matter. Averages of R1 values (unit: s-1) before and after radiation and those of R1 ratio (post-radiation R1 / pre-radiation R1) were compared by t-test or rank sum test as appropriate. Multiple linear regression analysis was performed to evaluate independent association factors for R1 value increase at irradiated parenchyma. RESULTS: The mean R1 values in peri-tumoral areas were significantly increased after radiotherapy (0.7901±0.0977 [mean±SD] vs. 0.8146±0.1064; P <.01). The mean R1 ratio of high radiation dose areas was significantly higher than that of low dose areas (1.0055±0.0654 vs. 0.9882±0.0642; P <.01). The mean R1 ratio was lower in those who underwent hypofractionated radiotherapy (mean dose, 45.0 Gy) than those who underwent routine radiotherapy (mean dose, 61.1 Gy) (0.9913±0.0740 vs. 1.0463±0.0633; P = .08). Multiple linear regression analysis revealed that only radiotherapy type was significantly associated with increased R1 (P = .02) around tumors. CONCLUSIONS: Radiotherapy can induce R1 value increase in the brain parenchyma, which might suggest accelerated gadolinium accumulation due to damage to the blood-brain barrier.

Time-dependent analysis of incidence, risk factors and clinical significance of pneumothorax after percutaneous lung biopsy.

OBJECTIVES: To evaluate the time-dependent incidence, risk factors and clinical significance of percutaneous lung biopsy (PLB)-related pneumothorax. METHODS: From January 2012-November 2015, 3,251 patients underwent 3,354 cone-beam CT-guided PLBs for lung lesions. Cox, logistic and linear regression analyses were performed to identify time-dependent risk factors of PLB-related pneumothorax, risk factors of drainage catheter insertion and those of prolonged catheter placement, respectively. RESULTS: Pneumothorax occurred in 915/3,354 PLBs (27.3 %), with 230/915 (25.1 %) occurring during follow-ups. Risk factors for earlier occurrence of PLB-related pneumothorax include emphysema (HR=1.624), smaller target (HR=0.922), deeper location (HR=1.175) and longer puncture time (HR=1.036), while haemoptysis (HR=0.503) showed a protective effect against earlier development of pneumothorax. Seventy-five cases (8.2 %) underwent chest catheter placement. Mean duration of catheter placement was 3.2±2.0 days. Emphysema (odds ratio [OR]=2.400) and longer puncture time (OR=1.053) were assessed as significant risk factors for catheter insertion, and older age (parameter estimate=1.014) was a predictive factor for prolonged catheter placement. CONCLUSION: PLB-related pneumothorax occurred in 27.3 %, of which 25.1 % developed during follow-ups. Smaller target size, emphysema, deeply-located lesions were significant risk factors of PLB-related pneumothorax. Emphysema and older age were related to drainage catheter insertion and prolonged catheter placement, respectively. KEY POINTS: • One-fourth of percutaneous lung biopsy (PLB)-related pneumothorax occurs during follow-up. • Smaller, deeply-located target and emphysema lead to early occurrence of pneumothorax. • Emphysema is related to drainage catheter insertion for PLB-related pneumothorax. • Older age may lead to prolonged catheter placement for PLB-related pneumothorax. • Tailored management can be possible with time-dependent information of PLB-related pneumothorax.