Search

Algorithms that automatically identify nodular patterns in chest X-ray (CXR) images could benefit radiologists by reducing reading time and improving accuracy. A promising approach is to use deep learning, where a deep neural network (DNN) is trained to classify and localize nodular patterns (including mass) in CXR images. Such algorithms, however, require enough abnormal cases to learn representations of nodular patterns arising in practical clinical settings. Obtaining large amounts of high-quality data is impractical in medical imaging where (1) acquiring labeled images is extremely expensive, (2) annotations are subject to inaccuracies due to the inherent difficulty in interpreting images, and (3) normal cases occur far more frequently than abnormal cases. In this work, we devise a framework to generate realistic nodules and demonstrate how they can be used to train a DNN identify and localize nodular patterns in CXR images. While most previous research applying generative models to medical imaging are limited to generating visually plausible abnormalities and using these patterns for augmentation, we go a step further to show how the training algorithm can be adjusted accordingly to maximally benefit from synthetic abnormal patterns. A high-precision detection model was first developed and tested on internal and external datasets, and the proposed method was shown to enhance the model's recall while retaining the low level of false positives.

The validation of the accuracy of the quantification software in computed tomography (CT) images is very challenging. Therefore, we proposed a CT imaging phantom that accurately represents patient-specific anatomical structures and randomly integrates various lesions including disease-like patterns and lesions of various shapes and sizes using silicone casting and three-dimensional (3D) printing. Six nodules of various shapes and sizes were randomly added to the patient’s modeled lungs to evaluate the accuracy of the quantification software. By using silicone materials, CT intensities suitable for the lesions and lung parenchyma were realized, and their Hounsfield unit (HU) values were evaluated on a CT scan of the phantom. As a result, based on the CT scan of the imaging phantom model, the measured HU values for the normal lung parenchyma, each nodule, fibrosis, and emphysematous lesions were within the target value. The measurement error between the stereolithography model and 3D-printing phantoms was 0.2 ± 0.18 mm. In conclusion, the use of 3D printing and silicone casting allowed the application and evaluation of the proposed CT imaging phantom for the validation of the accuracy of the quantification software in CT images, which could be applied to CT-based quantification and development of imaging biomarkers.

The generative adversarial network (GAN) is a promising deep learning method for generating images. We evaluated the generation of highly realistic and high-resolution chest radiographs (CXRs) using progressive growing GAN (PGGAN). We trained two PGGAN models using normal and abnormal CXRs, solely relying on normal CXRs to demonstrate the quality of synthetic CXRs that were 1000 × 1000 pixels in size. Image Turing tests were evaluated by six radiologists in a binary fashion using two independent validation sets to judge the authenticity of each CXR, with a mean accuracy of 67.42% and 69.92% for the first and second trials, respectively. Inter-reader agreements were poor for the first (κ = 0.10) and second (κ = 0.14) Turing tests. Additionally, a convolutional neural network (CNN) was used to classify normal or abnormal CXR using only real images and/or synthetic images mixed datasets. The accuracy of the CNN model trained using a mixed dataset of synthetic and real data was 93.3%, compared to 91.0% for the model built using only the real data. PGGAN was able to generate CXRs that were identical to real CXRs, and this showed promise to overcome imbalances between classes in CNN training.

Training deep learning models on medical images heavily depends on experts’ expensive and laborious manual labels. In addition, these images, labels, and even models themselves are not widely publicly accessible and suffer from various kinds of bias and imbalances. In this paper, chest X-ray pre-trained model via self-supervised contrastive learning (CheSS) was proposed to learn models with various representations in chest radiographs (CXRs). Our contribution is a publicly accessible pretrained model trained with a 4.8-M CXR dataset using self-supervised learning with a contrastive learning and its validation with various kinds of downstream tasks including classification on the 6-class diseases in internal dataset, diseases classification in CheXpert, bone suppression, and nodule generation. When compared to a scratch model, on the 6-class classification test dataset, we achieved 28.5% increase in accuracy. On the CheXpert dataset, we achieved 1.3% increase in mean area under the receiver operating characteristic curve on the full dataset and 11.4% increase only using 1% data in stress test manner. On bone suppression with perceptual loss, we achieved improvement in peak signal to noise ratio from 34.99 to 37.77, structural similarity index measure from 0.976 to 0.977, and root-square-mean error from 4.410 to 3.301 when compared to ImageNet pretrained model. Finally, on nodule generation, we achieved improvement in Fréchet inception distance from 24.06 to 17.07. Our study showed the decent transferability of CheSS weights. CheSS weights can help researchers overcome data imbalance, data shortage, and inaccessibility of medical image datasets. CheSS weight is available at https://github.com/mi2rl/CheSS.

Background Chest MRI is a useful diagnostic modality for the evaluation of anterior mediastinal lesions but the outcomes of anterior mediastinal cystic lesions diagnosed on chest MRI are unclear. Methods In this multicenter retrospective study, patients who underwent contrast-enhanced chest MRI in two tertiary centers to assess anterior mediastinal cystic lesions were included after excluding overt solid tumors and thymic hyperplasia. Anterior mediastinal cystic lesions were classified into two categories: probable (simple) cyst or indeterminate lesion (complex cyst). Size and imaging features of lesions during follow-up were evaluated and clinical outcomes were assessed. Results A total of 204 patients (mean age, 59 ± 11 years; M:F = 111:93) were studied; 186 (91.2%) were classified as probable cysts and 18 (8.8%) as indeterminate lesions on MRI. Among patients with probable cysts and more than 2 years of follow-up, lesion size was unchanged in 39.6% (36/91), decreased in 16.5% (15/91), and fluctuated in 8.8% (8/91). All patients who underwent surgery were confirmed cysts. None developed mural nodules or irregular wall thickening, suspicious for malignancy during follow-up. In patients with indeterminate lesions, 16.7% (3/18) had pathologically confirmed thymoma and 44.4% (8/18) had proven cysts. Follow-up numbers and intervals after MRI in patients with probable cysts were variable among physicians and institutions in clinical practice (p Conclusion Diagnosing anterior mediastinal cysts using MRI is reliable. MRI-based management of anterior mediastinal lesions may reduce the number of unnecessary follow-ups and surgeries.

To evaluate the effects of computer-aided diagnosis (CAD) on inter-reader agreement in Lung Imaging Reporting and Data System (Lung-RADS) categorization. Two hundred baseline CT scans covering all Lung-RADS categories were randomly selected from the National Lung Cancer Screening Trial. Five radiologists independently reviewed the CT scans and assigned Lung-RADS categories without CAD and with CAD. The CAD system presented up to five of the most risk-dominant nodules with measurements and predicted Lung-RADS category. Inter-reader agreement was analyzed using multirater Fleiss κ statistics. The five readers reported 139–151 negative screening results without CAD and 126–142 with CAD. With CAD, readers tended to upstage (average, 12.3%) rather than downstage Lung-RADS category (average, 4.4%). Inter-reader agreement of five readers for Lung-RADS categorization was moderate (Fleiss kappa, 0.60 [95% confidence interval, 0.57, 0.63]) without CAD, and slightly improved to substantial (Fleiss kappa, 0.65 [95% CI, 0.63, 0.68]) with CAD. The major cause for disagreement was assignment of different risk-dominant nodules in the reading sessions without and with CAD (54.2% [201/371] vs. 63.6% [232/365]). The proportion of disagreement in nodule size measurement was reduced from 5.1% (102/2000) to 3.1% (62/2000) with the use of CAD (p < 0.001). In 31 cancer-positive cases, substantial management discrepancies (category 1/2 vs. 4A/B) between reader pairs decreased with application of CAD (pooled sensitivity, 85.2% vs. 91.6%; p = 0.004). Application of CAD demonstrated a minor improvement in inter-reader agreement of Lung-RADS category, while showing the potential to reduce measurement variability and substantial management change in cancer-positive cases. • Inter-reader agreement of five readers for Lung-RADS categorization was minimally improved by application of CAD, with a Fleiss kappa value of 0.60 to 0.65. • The major cause for disagreement was assignment of different risk-dominant nodules in the reading sessions without and with CAD (54.2% vs. 63.6%). • In 31 cancer-positive cases, substantial management discrepancies between reader pairs, referring to a difference in follow-up interval of at least 9 months (category 1/2 vs. 4A/B), were reduced in half by application of CAD (32/310 to 16/310) (pooled sensitivity, 85.2% vs. 91.6%; p = 0.004).

To apply radiomics analysis for overall survival prediction in chronic obstructive pulmonary disease (COPD), and evaluate the performance of the radiomics signature (RS). This study included 344 patients from the Korean Obstructive Lung Disease (KOLD) cohort. External validation was performed on a cohort of 112 patients. In total, 525 chest CT-based radiomics features were semi-automatically extracted. The five most useful features for survival prediction were selected by least absolute shrinkage and selection operation (LASSO) Cox regression analysis and used to generate a RS. The ability of the RS for classifying COPD patients into high or low mortality risk groups was evaluated with the Kaplan-Meier survival analysis and Cox proportional hazards regression analysis. The five features remaining after the LASSO analysis were %LAA−950, AWT_Pi10_6th, AWT_Pi10_heterogeneity, %WA_heterogeneity, and VA18mm. The RS demonstrated a C-index of 0.774 in the discovery group and 0.805 in the validation group. Patients with a RS greater than 1.053 were classified into the high-risk group and demonstrated worse overall survival than those in the low-risk group in both the discovery (log-rank test, < 0.001; hazard ratio [HR], 5.265) and validation groups (log-rank test, < 0.001; HR, 5.223). For both groups, RS was significantly associated with overall survival after adjustments for patient age and body mass index. A radiomics approach for survival prediction and risk stratification in COPD patients is feasible, and the constructed radiomics model demonstrated acceptable performance. The RS derived from chest CT data of COPD patients was able to effectively identify those at increased risk of mortality. • A total of 525 chest CT-based radiomics features were extracted and the five radiomics features of %LAA −950 , AWT_Pi10_6 th , AWT_Pi10_heterogeneity, %WA_heterogeneity, and VA 18mm were selected to generate a radiomics model. • A radiomics model for predicting survival of COPD patients demonstrated reliable performance with a C-index of 0.774 in the discovery group and 0.805 in the validation group. • Radiomics approach was able to effectively identify COPD patients with an increased risk of mortality, and patients assigned to the high-risk group demonstrated worse overall survival in both the discovery and validation groups.

Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust model requires large, high-quality data with annotations that are expensive to obtain. This situation poses a conundrum that annually-collected chest x-rays cannot be utilized due to the absence of labels, especially in deprived areas. In this study, we present a framework named distillation for self-supervision and self-train learning (DISTL) inspired by the learning process of the radiologists, which can improve the performance of vision transformer simultaneously with self-supervision and self-training through knowledge distillation. In external validation from three hospitals for diagnosis of tuberculosis, pneumothorax, and COVID-19, DISTL offers gradually improved performance as the amount of unlabeled data increase, even better than the fully supervised model with the same amount of labeled data. We additionally show that the model obtained with DISTL is robust to various real-world nuisances, offering better applicability in clinical setting.

Lung adenocarcinoma shows broad spectrum of prognosis and histologic heterogeneity. This study was to investigate the prognostic value of CT radiomics in resectable lung adenocarcinoma patients and assess its incremental value over clinical-pathologic risk factors. This retrospective analysis evaluated 1058 patients who underwent curative surgery for lung adenocarcinoma (training cohort: N = 754; temporal validation cohort: N = 304). Radiomics features were extracted from preoperative contrast-enhanced CT. Radiomics signature to predict disease-free survival (DFS) and overall survival (OS) was generated. Association between the radiomics signature and prognosis were evaluated using univariable and multivariable Cox proportional hazards regression analyses. Incremental value of the radiomics signature beyond clinical-pathologic risk factors was assessed using concordance index (C-index). The radiomics signatures were independently associated with DFS (hazard ratio [HR], 1.920; p

To investigate the optimal input matrix size for deep learning-based computer-aided detection (CAD) of nodules and masses on chest radiographs. We retrospectively collected 2088 abnormal (nodule/mass) and 352 normal chest radiographs from two institutions. Three thoracic radiologists drew 2758 abnormalities regions. A total of 1736 abnormal chest radiographs were used for training and tuning convolutional neural networks (CNNs). The remaining 352 abnormal and 352 normal chest radiographs were used as a test set. Two CNNs (Mask R-CNN and RetinaNet) were selected to validate the effects of the squared different matrix size of chest radiograph (256, 448, 896, 1344, and 1792). For comparison, figure of merit (FOM) of jackknife free-response receiver operating curve and sensitivity were obtained. In Mask R-CNN, matrix size 896 and 1344 achieved significantly higher FOM (0.869 and 0.856, respectively) for detecting abnormalities than 256, 448, and 1792 (0.667–0.820) (p

Lung lobe segmentation in chest CT has been used for the analysis of lung functions and surgical planning. However, accurate lobe segmentation is difficult as 80% of patients have incomplete and/or fake fissures. Furthermore, lung diseases such as chronic obstructive pulmonary disease (COPD) can increase the difficulty of differentiating the lobar fissures. Lobar fissures have similar intensities to those of the vessels and airway wall, which could lead to segmentation error in automated segmentation. In this study, a fully automated lung lobe segmentation method with 3D U-Net was developed and validated with internal and external datasets. The volumetric chest CT scans of 196 normal and mild-to-moderate COPD patients from three centers were obtained. Each scan was segmented using a conventional image processing method and manually corrected by an expert thoracic radiologist to create gold standards. The lobe regions in the CT images were then segmented using a 3D U-Net architecture with a deep convolutional neural network (CNN) using separate training, validation, and test datasets. In addition, 40 independent external CT images were used to evaluate the model. The segmentation results for both the conventional and deep learning methods were compared quantitatively to the gold standards using four accuracy metrics including the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). In internal validation, the segmentation method achieved high accuracy for the DSC, JSC, MSD, and HSD (0.97 ± 0.02, 0.94 ± 0.03, 0.69 ± 0.36, and 17.12 ± 11.07, respectively). In external validation, high accuracy was also obtained for the DSC, JSC, MSD, and HSD (0.96 ± 0.02, 0.92 ± 0.04, 1.31 ± 0.56, and 27.89 ± 7.50, respectively). This method took 6.49 ± 1.19 s and 8.61 ± 1.08 s for lobe segmentation of the left and right lungs, respectively. Although various automatic lung lobe segmentation methods have been developed, it is difficult to develop a robust segmentation method. However, the deep learning–based 3D U-Net method showed reasonable segmentation accuracy and computational time. In addition, this method could be adapted and applied to severe lung diseases in a clinical workflow.

Heterogeneous clinical manifestations and progression of chronic obstructive pulmonary disease (COPD) affect patient health risk assessment, stratification, and management. Pulmonary function tests are used to diagnose and classify the severity of COPD, but they cannot fully represent the type or range of pathophysiologic abnormalities of the disease. To evaluate whether deep radiomics from chest computed tomography (CT) images can predict mortality in patients with COPD, we designed a convolutional neural network (CNN) model for extracting representative features from CT images and then performed random survival forest to predict survival in COPD patients. We trained CNN-based binary classifier based on six-minute walk distance results (> 440 m or not) and extracted high-throughput image features (i.e., deep radiomics) directly from the last fully connected layer of it. The various sizes of fully connected layers and combinations of deep features were experimented using a discovery cohort with 344 patients from the Korean Obstructive Lung Disease cohort and an external validation cohort with 102 patients from Penang General Hospital in Malaysia. In the integrative analysis of discovery and external validation cohorts, with combining 256 deep features from the coronal slice of the vertebral body and two sagittal slices of the left/right lung, deep radiomics for survival prediction achieved concordance indices of 0.8008 (95% CI, 0.7642–0.8373) and 0.7156 (95% CI, 0.7024–0.7288), respectively. Deep radiomics from CT images could be used to predict mortality in COPD patients.

To investigate whether radiomics on iodine overlay maps from dual-energy computed tomography (DECT) can predict survival outcomes in patients with resectable lung cancer. Ninety-three lung cancer patients eligible for curative surgery were examined with DECT at the time of diagnosis. The median follow-up was 60.4 months. Radiomic features of the entire primary tumour were extracted from iodine overlay maps generated by DECT. A Cox proportional hazards regression model was used to determine independent predictors of overall survival (OS) and disease-free survival (DFS), respectively. Forty-two patients (45.2%) had disease recurrence and 39 patients (41.9%) died during the follow-up period. The mean DFS was 49.8 months and OS was 55.2 months. Univariate analysis revealed that significant predictors of both OS and DFS were stage and radiomic parameters, including histogram energy, histogram entropy, grey-level co-occurrence matrix (GLCM) angular second moment, GLCM entropy and homogeneity. The multivariate analysis identified stage and entropy as independent risk factors predicting both OS (stage, hazard ratio (HR) = 2.020 [95% CI 1.014–4.026], p = 0.046; entropy, HR = 1.543 [95% CI 1.069–2.228], p = 0.021) and DFS (stage, HR = 2.132 [95% CI 1.060–4.287], p = 0.034; entropy, HR = 1.497 [95% CI 1.031–2.173], p = 0.034). The C-index showed that adding entropy improved prediction of OS compared to stage only (0.720 and 0.667, respectively; p = 0.048). Radiomic features extracted from iodine overlay map reflecting heterogeneity of tumour perfusion can add prognostic information for patients with resectable lung cancer. • Radiomic feature (histogram entropy) from DECT iodine overlay maps was an independent risk factor predicting both overall survival and disease-free survival. • Adding histogram entropy to clinical stage improved prediction of overall survival compared to stage only (0.720 and 0.667, respectively; p = 0.048). • DECT can be a good option for comprehensive pre-operative evaluation in cases of resectable lung cancer.

This study aimed to compare shallow and deep learning of classifying the patterns of interstitial lung diseases (ILDs). Using high-resolution computed tomography images, two experienced radiologists marked 1200 regions of interest (ROIs), in which 600 ROIs were each acquired using a GE or Siemens scanner and each group of 600 ROIs consisted of 100 ROIs for subregions that included normal and five regional pulmonary disease patterns (ground-glass opacity, consolidation, reticular opacity, emphysema, and honeycombing). We employed the convolution neural network (CNN) with six learnable layers that consisted of four convolution layers and two fully connected layers. The classification results were compared with the results classified by a shallow learning of a support vector machine (SVM). The CNN classifier showed significantly better performance for accuracy compared with that of the SVM classifier by 6–9%. As the convolution layer increases, the classification accuracy of the CNN showed better performance from 81.27 to 95.12%. Especially in the cases showing pathological ambiguity such as between normal and emphysema cases or between honeycombing and reticular opacity cases, the increment of the convolution layer greatly drops the misclassification rate between each case. Conclusively, the CNN classifier showed significantly greater accuracy than the SVM classifier, and the results implied structural characteristics that are inherent to the specific ILD patterns.

To assess the volume doubling time (VDT) of lung cancers in IIP compared with COPD. A total of 61 patients (32 with IIP and 29 with COPD) were identified. A radiologist performed three-dimensional manual segmentation for lung cancers. VDTs were calculated and compared between two groups. Logistic regression was performed to identify factors associated with rapid tumour growth (VDT < 90 days). The median VDT of lung cancers in IIP (78.2 days) was significantly shorter than that in COPD (126.1 days; p=0.004). Squamous cell carcinoma (SqCC) was the most frequent subtype, followed by small cell lung cancer (SCLC) in IIP. In COPD, SqCC was the most frequent subtype, followed by adenocarcinoma. Rapid tumour growth was observed in 20 cancers from IIP, and in nine cancers from COPD (p=0.021). SCLC was significantly correlated with rapid tumour growth (p=0.038). Multivariate analysis revealed that the presence of IIP was the single independent predictor of rapid tumour growth (p = 0.016; odds ratio, 3.7). Lung cancers in IIP showed more rapid growth, with median VDT < 90 days. Therefore, a shorter follow-up interval (

To retrospectively investigate whether the baseline extent and 1-year change in regional disease patterns on CT can predict survival of patients with idiopathic pulmonary fibrosis (IPF). A total of 144 IPF patients with CT scans at the time of diagnosis and 1 year later were included. The extents of five regional disease patterns were quantified using an in-house texture-based automated system. The fibrosis score was defined as the sum of the extent of honeycombing and reticular opacity. The Cox proportional hazard model was used to determine the independent predictors of survival. A total of 106 patients (73.6%) died during the follow-up period. Univariate analysis revealed that age, baseline forced vital capacity, total lung capacity, diffusing capacity of the lung for carbon monoxide, six-minute walk distance, desaturation, honeycombing, reticular opacity, fibrosis score, and interval changes in honeycombing and fibrosis score were significantly associated with survival. Multivariate analysis revealed that age, desaturation, fibrosis score and interval change in fibrosis score were significant independent predictors of survival (p = 0.003

We propose the use of ensemble classifiers to overcome inter-scanner variations in the differentiation of regional disease patterns in high-resolution computed tomography (HRCT) images of diffuse interstitial lung disease patients obtained from different scanners. A total of 600 rectangular 20 × 20-pixel regions of interest (ROIs) on HRCT images obtained from two different scanners (GE and Siemens) and the whole lung area of 92 HRCT images were classified as one of six regional pulmonary disease patterns by two expert radiologists. Textual and shape features were extracted from each ROI and the whole lung parenchyma. For automatic classification, individual and ensemble classifiers were trained and tested with the ROI dataset. We designed the following three experimental sets: an intra-scanner study in which the training and test sets were from the same scanner, an integrated scanner study in which the data from the two scanners were merged, and an inter-scanner study in which the training and test sets were acquired from different scanners. In the ROI-based classification, the ensemble classifiers showed better (p

To investigate the reproducibility of computer-aided detection (CAD) for detection of pulmonary nodules and masses for consecutive chest radiographies (CXRs) of the same patient within a short-term period. A total of 944 CXRs (Chest PA) with nodules and masses, recorded between January 2010 and November 2016 at the Asan Medical Center, were obtained. In all, 1092 regions of interest for the nodules and mass were delineated using an in-house software. All CXRs were randomly split into 6:2:2 sets for training, development, and validation. Furthermore, paired follow-up CXRs (n = 121) acquired within one week in the validation set, in which expert thoracic radiologists confirmed no changes, were used to evaluate the reproducibility of CAD by two radiologists (R1 and R2). The reproducibility comparison of four different convolutional neural net algorithms and two chest radiologists (with 13- and 14-years’ experience) was conducted. Model performances were evaluated by figure-of-merit (FOM) analysis of the jackknife free-response receiver operating curve and reproducibility rates were evaluated in terms of percent positive agreement (PPA) and Chamberlain’s percent positive agreement (CPPA). Reproducibility analysis of the four CADs and R1 and R2 showed variations in the PPA and CPPA. Model performance of YOLO (You Only Look Once) v2 based eDenseYOLO showed a higher FOM (0.89; 0.85–0.93) than RetinaNet (0.89; 0.85–0.93) and atrous spatial pyramid pooling U-Net (0.85; 0.80–0.89). eDenseYOLO showed higher PPAs (97.87%) and CPPAs (95.80%) than Mask R-CNN, RetinaNet, ASSP U-Net, R1, and R2 (PPA: 96.52%, 94.23%, 95.04%, 96.55%, and 94.98%; CPPA: 93.18%, 89.09%, 90.57%, 93.33%, and 90.43%). There were moderate variations in the reproducibility of CAD with different algorithms, which likely indicates that measurement of reproducibility is necessary for evaluating CAD performance in actual clinical environments.

Magnetic resonance imaging (MRI) is the most accurate technique for evaluating residual tumor after neoadjuvant chemotherapy. However, precise determination of the extent of dispersed residual tumor in the breast following treatment remains a difficult task. We hereby introduce three-dimensional (3D)-printed surgical guides for use in breast cancer patients undergoing breast-conserving surgery after receiving neoadjuvant chemotherapy. We prospectively applied the 3D-printed surgical guides on breast cancer patients who underwent partial breast resection after receiving neoadjuvant chemotherapy. Breasts and tumors were modeled in 3D by using pretreatment magnetic resonance images, and surgical guides were created by using a 3D printer to mark the primary tumor. Out of the five patients who participated in the study, all patients had clear resection margins, and two patients experienced complete pathological remission. There were no recurrences during the median follow-up period of 21.9 months. Thus, our newly-developed 3D-printed surgical guides were useful for accurately marking the extent of breast tumor based on pretreatment magnetic resonance images, which is important for designating the extent of surgery needed in patients who have received neoadjuvant chemotherapy.

Deep learning is now widely used as an efficient tool for medical image classification and segmentation. However, conventional machine learning techniques are still more accurate than deep learning when only a small dataset is available. In this study, we present a general data augmentation strategy using Perlin noise, applying it to pixel-by-pixel image classification and quantification of various kinds of image patterns of diffuse interstitial lung disease (DILD). Using retrospectively obtained high-resolution computed tomography (HRCT) images from 106 patients, 100 regions-of-interest (ROIs) for each of six classes of image patterns (normal, ground-glass opacity, reticular opacity, honeycombing, emphysema, and consolidation) were selected for deep learning classification by experienced thoracic radiologists. For extra-validation, the deep learning quantification of the six classification patterns was evaluated for 92 HRCT whole lung images for which hand-labeled segmentation masks created by two experienced radiologists were available. FusionNet, a convolutional neural network (CNN), was used for training, test, and extra-validation on classifications of DILD image patterns. The accuracy of FusionNet with data augmentation using Perlin noise (89.5%, 49.8%, and 55.0% for ROI-based classification and whole lung quantifications by two radiologists, respectively) was significantly higher than that with conventional data augmentation (82.1%, 45.7%, and 49.9%, respectively). This data augmentation strategy using Perlin noise could be widely applied to deep learning studies for image classification and segmentation, especially in cases with relatively small datasets.

Chronic obstructive pulmonary disease (COPD) is a spectrum of various syndromes that share airflow limitation but differ in many respects. Although airflow limitation is a defining element of COPD, forced expiratory volume in 1 s (FEV1) alone is not sufficient to explain the heterogeneity of COPD. Phenotypic characterization of clinically relevant subgroups of COPD will increase our understanding of COPD. Furthermore, a greater understanding of the complex interrelationships between the phenotypes and their environmental, genetic, molecular, and cellular basis may be achieved with comprehensive and integrated method (systems biology and network medicine). Incorporation of information obtained from these analyses into our clinical practice would allow clinicians to treat individual patients with so-called Personalized, Predictive, Preventive, and Participatory (P4) medicine. By understanding COPD heterogeneity, it may be possible in the future to detect the disease earlier and to target treatment to reduce mortality and modify the course of the disease.

Interpolation artifact is known to occur when the heart rate is decreased lower than the critical value for the specific pitch. The purpose of our study is to determine the minimum heart rate (minHR) for the specific pitch that provides images without interpolation artifact when using dual-source computed tomography (DSCT). We scanned the 'thin slice thickness block' of the CT performance phantom provided by the American Association of Physicists in Medicine using DSCT for variable pitches. Change in heart rate was simulated through ECG editing by changing R-R interval. Axial, sagittal, and coronal image sets were reconstructed and assessed for the presence and extent of interpolation artifact. MinHR at which no interpolation artifact was detected for each pitch value was determined. Length of interpolation artifact (LOA) on sagittal view was also measured when the heart rate was simulated at 10 bpm lower than the minHR on each pitch setting. MinHRs for each pitch value were 9-10 bpm from the estimated heart rate. However, minHR for the lowest pitch value 0.2, estimated heart value 40 bpm was 37 bpm. LOA was larger in the low heart rate condition. Measured values of minHR were correlated exactly with the calculated values. MinHRs that provide images without interpolation artifact for each pitch value when using DSCT were determined. The concept of minHR is important for obtaining high quality images of cardiac CT angiography when using DSCT.

The motivation is to introduce new shape features and optimize the classifier to improve performance of differentiating obstructive lung diseases, based on high-resolution computerized tomography (HRCT) images. Two hundred sixty-five HRCT images from 82 subjects were selected. On each image, two experienced radiologists selected regions of interest (ROIs) representing area of severe centrilobular emphysema, mild centrilobular emphysema, bronchiolitis obliterans, or normal lung. Besides 13 textural features, additional 11 shape features were employed to evaluate the contribution of shape features. To optimize the system, various ROI size (16 × 16, 32 × 32, and 64 × 64 pixels) and other classifier parameters were tested. For automated classification, the Bayesian classifier and support vector machine (SVM) were implemented. To assess cross-validation of the system, a five-folding method was used. In the comparison of methods employing only the textural features, adding shape features yielded the significant improvement of overall sensitivity (7.3%, 6.1%, and 4.1% in the Bayesian and 9.1%, 7.5%, and 6.4% in the SVM, in the ROI size 16 × 16, 32 × 32, 64 × 64 pixels, respectively; t test, P

Xenon ventilation CT using a dual-source dual-energy technique is a promising functional imaging method for the lung. We report the typical ventilation abnormalities, collateral ventilation and air trapping in the affected lung segment demonstrated on xenon ventilation CT in a child with bronchial atresia.

The severity of chronic obstructive pulmonary disease (COPD) is evaluated not only by airflow limitation but also by factors such as exercise capacity and body mass index. Recent advances in CT technology suggest that it might be a useful tool for evaluating the severity of the disease components of COPD. The aim of this study is to evaluate the correlation between the parameters measured on volumetric CT, including the extent of emphysema, air trapping, and airway thickening, and clinical parameters. CT scans were performed in 34 patients with COPD at full inspiration and expiration. We used in-house software to measure CT parameters, including volume fraction of emphysema (V950), mean lung density (MLD), CT air trapping index (CT ATI), segmental bronchial wall area (WA), lumen area (LA), and wall area percent (WA%). We found that the CT parameters were correlated with the pulmonary function test (PFT) results, body mass index (BMI), the modified Medical Research Council Dyspnea scale (MMRC scale), the six-minute-walk distance (6MWD), and the BODE index. V950 insp correlated to the BMI, FEV1, 6MWD, and the BODE index. The CT ATI correlated with the physiologic ATI (VC – FVC) (R = 0.345, p = 0.045) and the MMRC scale (R = 0.532, p = 0.001). There was a positive correlation between the WA% and the BMI (R = 0.563, p

Background: The diagnosis of squalene aspiration pneumonia in children is often difficult because of minimal non-specific symptoms. Objective: To investigate the radiological findings of squalene aspiration pneumonia in children. Materials and methods: We reviewed the chest radiographs (n = 8) and CT scans (n = 7), including high-resolution CT (n = 3), of eight patients (four boys, four girls; age 3 months to 6 years) with squalene aspiration pneumonia. All patients presented minimal symptoms. Results: Chest radiographs showed right-sided predominantly parahilar infiltrations. The extent and the opacity of the lesions decreased slowly during the follow-up period (mean 5.4 months) after halting the exposure. On CT, affected areas appeared as dense consolidations surrounded by ground-glass opacities showing a crazy-paving pattern in a geographic lobular distribution in all patients. The lesions were predominantly in the right lung and dependent areas in all patients and extensively involved all pulmonary lobes in five patients. Conclusions: These radiological findings, although non-specific, can lead to an appropriate diagnosis, particularly when patients present few symptoms.

To evaluate the usefulness of a texture-based automated quantification system (AQS) for evaluating the extent and interval change of regional disease patterns on initial and follow-up high-resolution computed tomographies (HRCTs) of fibrotic interstitial pneumonia (FIP).Eighty-nine patients with clinically and/or biopsy confirmed usual interstitial pneumonia (UIP) (n = 71) and non-specific interstitial pneumonia (NSIP) (n = 18) were included. An AQS to quantify five disease patterns (ground-glass opacity [GGO], reticular opacity [RO], honeycombing [HC], emphysema [EMPH], consolidation [CONS]) and normal lung was developed. The extent and interval changes of each disease pattern, FS (fibrosis score), TA (total abnormal lung fraction) of entire lung on initial and 1-year follow-up HRCTs were quantified. The agreement between the results of AQS and two readers was assessed. Results of AQS were correlated with forced vital capacity (FVC) and carbon monoxide diffusing capacity (DLco).The Intraclass correlation coefficient (ICC) study revealed acceptable agreement between visual assessment and AQS (r = 0.78, 0.66 for HC; 0.76, 0.61 for FS; 0.64, 0.68 for TA, initial and follow-up HRCTs, respectively). Linear regression analysis revealed the extent of HC, TA on initial CT, interval changes of FS contributed negatively to DLco, and interval changes of FS, TA contributed negatively to FVC.Our AQS is comparable with visual assessment for evaluating the disease extent and the interval changes of FIP on HRCT.