Submillisievert CT using model-based iterative reconstruction with lung-specific setting: An initial phantom study.

OBJECTIVE: To assess image quality of filtered back-projection (FBP) and model-based iterative reconstruction (MBIR) with a conventional setting and a new lung-specific setting on submillisievert CT. METHODS: A lung phantom with artificial nodules was scanned with 10 mA at 120 kVp and 80 kVp (0.14 mSv and 0.05 mSv, respectively); images were reconstructed using FBP and MBIR with conventional setting (MBIRStnd) and lung-specific settings (MBIRRP20/Tx and MBIRRP20). Three observers subjectively scored overall image quality and image findings on a 5-point scale (1 = worst, 5 = best) compared with reference standard images (50 mA-FBP at 120, 100, 80 kVp). Image noise was measured objectively. RESULTS: MBIRRP20/Tx performed significantly better than MBIRStnd for overall image quality in 80-kVp images (p < 0.01), blurring of the border between lung and chest wall in 120p-kVp images (p < 0.05) and the ventral area of 80-kVp images (p < 0.001), and clarity of small vessels in the ventral area of 80-kVp images (p = 0.037). At 120 kVp, 10 mA-MBIRRP20 and 10 mA-MBIRRP20/Tx showed similar performance to 50 mA-FBP. MBIRStnd was better for noise reduction. Except for blurring in 120 kVp-MBIRStnd, MBIRs performed better than FBP. CONCLUSION: Although a conventional setting was advantageous in noise reduction, a lung-specific setting can provide more appropriate image quality, even on submillisievert CT. KEY POINTS: • Lung-specific submillisievert 10 mA-MBIR CT setting has similar performance to 50 mA-FBP • The new lung-specific settings improve vessel clarity and blurring of borders • The new settings may provide more appropriate images than conventional settings.

Prognostic importance of volumetric measurements in stage I lung adenocarcinoma.

PURPOSE: To perform volumetric analysis of stage I lung adenocarcinomas by using an automated computer program and to determine value of volumetric computed tomographic (CT) measurements associated with prognostic factors and outcome. MATERIALS AND METHODS: Consecutive patients (n = 145) with stage I lung adenocarcinoma who underwent surgery after preoperative chest CT were enrolled. By using volumetric automated computer-assisted analytic program, nodules were classified into three subgroups: pure ground glass, part solid, or solid. Total tumor volume, solid tumor volume, and percentage of solid volume of each cancer were calculated after eliminating vessel components. One radiologist measured the longest diameter of the solid tumor component and of total tumor with their ratio, which was defined as solid proportion. The value of these quantitative data by examining associations with pathologic prognostic factors and outcome measures (disease-free survival and overall survival) were analyzed with logistic regression and Cox proportional hazards regression models, respectively. Significant parameters identified at univariate analysis were included in the multiple analyses. RESULTS: All 22 recurrences occurred in patients with nodules classified as part solid or solid. Multiple logistic regression analysis revealed that percentage of solid volume of 63% or greater was an independent indicator associated with pleural invasion (P = .01). Multiple Cox proportional hazards regression analysis revealed that percentage of solid volume of 63% or greater was a significant indicator of lower disease-free survival (hazard ratio, 18.45 [95% confidence interval: 4.34, 78.49]; P < .001). Both solid tumor volume of 1.5 cm(3) or greater and percentage of solid volume of 63% or greater were significant indicators of decreased overall survival (hazard ratio, 5.92 and 9.60, respectively [95% confidence interval: 1.17, 30.33 and 1.17, 78.91, respectively]; P = .034 and .036, respectively). CONCLUSION: Two volumetric measurements (solid volume, ≥1.5 cm(3); percentage of solid volume, ≥63%) were found to be independent indicators associated with increased likelihood of recurrence and/or death in patients with stage I adenocarcinoma.

Pathologically proved nonspecific interstitial pneumonia: CT pattern analysis as compared with usual interstitial pneumonia CT pattern.

PURPOSE: To assess the variability of computed tomography (CT) patterns in patients with pathologic nonspecific interstitial pneumonia (NSIP) and to evaluate correlation of CT patterns with new idiopathic pulmonary fibrosis (IPF) classification guidelines, including pathologic diagnosis and predicted mortality. MATERIALS AND METHODS: The ethical review boards of the five institutions that contributed cases waived the need for informed consent for retrospective review of patient records and images. The study included 114 patients with (a) a pathologic diagnosis of idiopathic NSIP (n = 39) or (b) a pathologic diagnosis of usual interstitial pneumonia (UIP) and a clinical diagnosis of IPF (n = 75). Two groups of independent observers evaluated the extent and distribution of various CT findings and identified the following five patterns: UIP, possible UIP, indeterminate (either UIP or NSIP), NSIP, and suggestive of an alternative diagnosis. CT findings were compared with pathologic diagnoses and outcome from clinical findings by using the log-rank test and Kaplan-Meier curves. RESULTS: Radiologists classified 17 cases as UIP, 24 as possible UIP, 13 as indeterminate (either UIP or NSIP), and 56 as NSIP. In 35 of 39 patients with pathologic NSIP, a diagnosis of NSIP was made with CT. On the basis of CT interpretations, the mean overall survival time of patients with UIP, possible UIP, indeterminate findings, or NSIP was 33.5, 73.0, 101.0, and 140.2 months, respectively. Outcome of patients with a CT diagnosis of UIP was significantly worse than that of patients with a pattern of possible UIP, indeterminate findings, or NSIP (log-rank test: P = .013, P = .018, and P < .001, respectively). CONCLUSION: CT pattern in patients with pathologic NSIP is more uniform than that in patients with pathologic UIP, and CT NSIP pattern is associated with better patient outcome than is CT UIP pattern.

"KAIZEN" method realizing implementation of deep-learning models for COVID-19 CT diagnosis in real world hospitals.

Numerous COVID-19 diagnostic imaging Artificial Intelligence (AI) studies exist. However, none of their models were of potential clinical use, primarily owing to methodological defects and the lack of implementation considerations for inference. In this study, all development processes of the deep-learning models are performed based on strict criteria of the "KAIZEN checklist", which is proposed based on previous AI development guidelines to overcome the deficiencies mentioned above. We develop and evaluate two binary-classification deep-learning models to triage COVID-19: a slice model examining a Computed Tomography (CT) slice to find COVID-19 lesions; a series model examining a series of CT images to find an infected patient. We collected 2,400,200 CT slices from twelve emergency centers in Japan. Area Under Curve (AUC) and accuracy were calculated for classification performance. The inference time of the system that includes these two models were measured. For validation data, the slice and series models recognized COVID-19 with AUCs and accuracies of 0.989 and 0.982, 95.9% and 93.0% respectively. For test data, the models' AUCs and accuracies were 0.958 and 0.953, 90.0% and 91.4% respectively. The average inference time per case was 2.83 s. Our deep-learning system realizes accuracy and inference speed high enough for practical use. The systems have already been implemented in four hospitals and eight are under progression. We released an application software and implementation code for free in a highly usable state to allow its use in Japan and globally.

The effect of the virtual monochromatic spectral imaging for the metallic artifact and the pulmonary nodule detection.

OBJECTIVES: This study aimed to evaluate whether dual-energy computed tomography can reduce metal artifacts and improve detection of pulmonary nodules. METHODS: Twelve simulated nodules were randomly placed inside a chest phantom with a pacemaker. Then, dual-energy computed tomography was performed, and 5 virtual monochromatic images at 40, 50, 65, 100, and 140 keV were reconstructed with 5- and 0.625-mm slice thicknesses. Two independent observers assessed the metal artifact (3-point scale from 1, none, to 3, severe) and detection of the nodule (5-point scale from 1, definitely absent, to 5, definitely present). Statistical analysis was performed with a P value of less than 0.01 (0.05/5). RESULTS: With both slice thicknesses, the metallic artifact increased at 40 or 50 keV and decreased at 100 or 140 keV relative to that at 65 keV (P < 0.01). The nodule detection score was not significantly different between each kiloelectron volt level with the 0.625-mm slice thickness; however, the score was significantly worse at 40 keV compared to 65 keV (P < 0.01) with the 5-mm slice thickness. CONCLUSIONS: High monochromatic energy images can reduce metal artifacts without a change in nodule detection score. Low monochromatic energy images increase metal artifacts and worsen nodule detection in thick slices.

Pulmonary Textures Classification via a Multi-Scale Attention Network.

Precise classification of pulmonary textures is crucial to develop a computer aided diagnosis (CAD) system of diffuse lung diseases (DLDs). Although deep learning techniques have been applied to this task, the classification performance is not satisfied for clinical requirements, since commonly-used deep networks built by stacking convolutional blocks are not able to learn discriminative feature representation to distinguish complex pulmonary textures. For addressing this problem, we design a multi-scale attention network (MSAN) architecture comprised by several stacked residual attention modules followed by a multi-scale fusion module. Our deep network can not only exploit powerful information on different scales but also automatically select optimal features for more discriminative feature representation. Besides, we develop visualization techniques to make the proposed deep model transparent for humans. The proposed method is evaluated by using a large dataset. Experimental results show that our method has achieved the average classification accuracy of 94.78% and the average f-value of 0.9475 in the classification of 7 categories of pulmonary textures. Besides, visualization results intuitively explain the working behavior of the deep network. The proposed method has achieved the state-of-the-art performance to classify pulmonary textures on high resolution CT images.

Dual-energy dynamic CT of lung adenocarcinoma: correlation of iodine uptake with tumor gene expression.

OBJECTIVES: To compare iodine content (IC) of solitary lung cancer using dynamic measurements of CT attenuation (Hounsfield Units, HU) and to correlate their quantitative CT data with expressions of vascular endothelial growth factor (VEGF), epidermal growth factor receptor (EGFR) and hypoxia-inducible factor-1α (HIF-1α) using immunostaining methods. METHODS: This study included 18 patients with adenocarcinoma, who undergone dual energy dynamic multiphase CT to examine solitary lung nodules (6 part-solid and 12 solid nodules). Tumor size was 21.1 mm±8.1 (9-39mm) [Mean±SD (range)]. Contrast volume was determined by weight (2ml/kg). Contrast volume and injection rate were 110.5 ml±17.2 (80-144ml) and 1.84ml/s±0.30 (1.3-2.4ml/s), respectively. Enhancement values ([CT value at each delayed scan-CT value at unenhanced scan]) and net enhancement values ([peak CT value-CT value at unenhanced scan]) were calculated in HU from 65keV monochromatic image. IC at each delayed scan was measured in mg/cm(3) from the iodine-water material decomposition pair on the advantage workstation VolumeShare4. Immunostaining using VEGF, EGFR, and HIF-1α was performed by two pathologists, who evaluated the expression level of them subjectively. Statistical analyses were performed with rank correlation tests and regression analysis. RESULTS: IC at 2- and 3-minute delayed scan (x) and immunostaining score of HIF-1α (y) showed a significantly positive correlation (r=0.64 and 0.52, p=0.004 and 0.03): regression equation, y=1.34+0.58x and y=1.51+0.55x, respectively. CONCLUSIONS: Dual-energy dynamic multiphase CT can measure iodine content in lung adenocarcinoma. Iodine content at 2- and 3-minute delayed scan might correlate with the expression level of HIF-1α.

Computed tomography (CT) findings in 88 neurofibromatosis 1 (NF1) patients: Prevalence rates and correlations of thoracic findings.

PURPOSE: To evaluate the prevalence rates and the correlations of thoracic computed tomography (CT) findings of neurofibromatosis 1 (NF1) in 88 patients. MATERIALS AND METHODS: Chest CT images of 88 NF1 patients were independently reviewed by three observers, and the CT findings were evaluated. If abnormal findings were present, their number, size, and distribution were recorded. The prevalence rate of each CT finding was calculated, and the correlations between CT findings were analyzed. RESULTS: Of the 88 cases, 13 were positive for cysts, 16 for emphysema, 8 for nodules, 8 for GGNs (ground glass nodules), 13 for mediastinal masses, 20 for scoliosis, 44 for subcutaneous nodules, and 34 for skin nodules. Cysts showed upper and peripheral dominant distributions. Regarding 13 mediastinal masses, 2 were diagnosed as malignant peripheral nerve sheath tumors (MPNSTs), 1 was diagnosed as primary lung cancer, 2 were diagnosed as lateral meningocele, 3 were diagnosed as neurofibromas, and the remaining 7 were considered neurofibromas. There was a significant correlation between the prevalence of subcutaneous nodules and that of skin nodules. Significant positive correlations were also seen between size and number, size and rate of central distribution, and number and rate of central distribution of cysts. CONCLUSION: Various CT findings were found in NF-1 patients, and the prevalence rates of subcutaneous and skin nodules were higher than other findings. Though the prevalence rates of subcutaneous nodules and skin nodules were significantly correlated, the other CT findings in NF-1 occurred independently. The number, size, and distribution of the cysts showed significant positive correlations with each other.

Ultra-low-dose CT of the lung: effect of iterative reconstruction techniques on image quality.

RATIONALE AND OBJECTIVES: To compare quality of ultra-low-dose thin-section computed tomography (CT) images of the lung reconstructed using model-based iterative reconstruction (MBIR) and adaptive statistical iterative reconstruction (ASIR) to filtered back projection (FBP) and to determine the minimum tube current-time product on MBIR images by comparing to standard-dose FBP images. MATERIALS AND METHODS: Ten cadaveric lungs were scanned using 120 kVp and four different tube current-time products (8, 16, 32, and 80 mAs). Thin-section images were reconstructed using MBIR, three ASIR blends (30%, 60%, and 90%), and FBP. Using the 8-mAs data, side-to-side comparison of the four iterative reconstruction image sets to FBP was performed by two independent observers who evaluated normal and abnormal findings, subjective image noise, streak artifact, and overall image quality. Image noise was also measured quantitatively. Subsequently, 8-, 16-, and 32-mAs MBIR images were compared to standard-dose FBP images. Comparisons of image sets were analyzed using the Wilcoxon signed rank test with Bonferroni correction. RESULTS: At 8 mAs, MBIR images were significantly better (P < .005) than other reconstruction techniques except in evaluation of interlobular septal thickening. Each set of low-dose MBIR images had significantly lower (P < .001) subjective and objective noise and streak artifacts than standard-dose FBP images. Conspicuity and visibility of normal and abnormal findings were not significantly different between 16-mAs MBIR and 80-mAs FBP images except in identification of intralobular reticular opacities. CONCLUSIONS: MBIR imaging shows higher overall quality with lower noise and streak artifacts than ASIR or FBP imaging, resulting in nearly 80% dose reduction without any degradations of overall image quality.

Paradoxical signal pattern of mediastinal cysts on T2-weighted MR imaging: phantom and clinical study.

PURPOSE: To evaluate the intracystic MRI (magnetic resonance imaging) signal intensity of mediastinal cystic masses on T2-weighted images. MATERIALS AND METHODS: A phantom study was performed to evaluate the signal intensity of a mediastinal cystic mass phantom (rubber balloon containing water) adjacent to a cardiac phantom pulsing at the rate of 60/min. T2-weighted images (sequence, fast spin echo [FSE] and single shot fast spin echo [SSFSE]) were acquired for the mediastinal cystic mass phantom. Further, a clinical study was performed in 33 patients (16 men, 17 women; age range, 19-85 years; mean, 65 years) with thymic cysts or pericardial cysts. In all patients, T2-weighted images (FSE and SSFSE) were acquired. The signal intensity of cystic lesion was evaluated and was compared with that of muscle. A region of interest (ROI) was positioned on the standard MR console, and signal intensity of the cystic mass (cSI), that of the muscle (mSI), and the rate of absolute value of cSI-mSI to standard deviation (SD) of background noise (|cSI-mSI|/SD=CNR [contrast-to-noise ratio]) were measured. RESULTS: The phantom study demonstrated that the rate phantom-ROI/saline-ROI was higher in SSFSE (0.36) than in FSE (0.19). In clinical cases, the degree of the signal intensity was higher in SSFSE than in FSE. The CNR was significantly higher in SSFSE (mean ± standard deviation, 111.0 ± 47.6) than in FSE (72.8 ± 36.6) (p<0.001, Wilcoxon signed-rank test). CONCLUSIONS: Anterior mediastinal cysts often show lower signal intensity than the original signal intensity of water on T2-weighted images. SSFSE sequence reduces this paradoxical signal pattern on T2-weighted images, which may otherwise cause misinterpretation when assessing cystic lesions.

Pulmonary nodules: effect of adaptive statistical iterative reconstruction (ASIR) technique on performance of a computer-aided detection (CAD) system-comparison of performance between different-dose CT scans.

PURPOSE: To evaluate the effects of ASIR on CAD system of pulmonary nodules using clinical routine-dose CT and lower-dose CT. MATERIALS AND METHODS: Thirty-five patients (body mass index, 22.17 ± 4.37 kg/m(2)) were scanned by multidetector-row CT with tube currents (clinical routine-dose CT, automatically adjusted mA; lower-dose CT, 10 mA) and X-ray voltage (120 kVp). Each 0.625-mm-thick image was reconstructed at 0%-, 50%-, and 100%-ASIR: 0%-ASIR is reconstructed using only the filtered back-projection algorithm (FBP), while 100%-ASIR is reconstructed using the maximum ASIR and 50%-ASIR implies a blending of 50% FBP and ASIR. CAD output was compared retrospectively with the results of the reference standard which was established using a consensus panel of three radiologists. Data were analyzed using Bonferroni/Dunn's method. Radiation dose was calculated by multiplying dose-length product by conversion coefficient of 0.021. RESULTS: The consensus panel found 265 non-calcified nodules ≤ 30 mm (ground-glass opacity [GGO], 103; part-solid, 34; and solid, 128). CAD sensitivity was significantly higher at 100%-ASIR [clinical routine-dose CT, 71% (overall), 49% (GGO); lower-dose CT, 52% (overall), 67% (solid)] than at 0%-ASIR [clinical routine-dose CT, 54% (overall), 25% (GGO); lower-dose CT, 36% (overall), 50% (solid)] (p<0.001). Mean number of false-positive findings per examination was significantly higher at 100%-ASIR (clinical routine-dose CT, 8.5; lower-dose CT, 6.2) than at 0%-ASIR (clinical routine-dose CT, 4.6; lower-dose CT, 3.5; p<0.001). Effective doses were 10.77 ± 3.41 mSv in clinical routine-dose CT and 2.67 ± 0.17 mSv in lower-dose CT. CONCLUSION: CAD sensitivity at 100%-ASIR on lower-dose CT is almost equal to that at 0%-ASIR on clinical routine-dose CT. ASIR can increase CAD sensitivity despite increased false-positive findings.