Deep Learning Method for Precise Landmark Identification and Structural Assessment of Whole-Spine Radiographs.

This study measured parameters automatically by marking the point for measuring each parameter on whole-spine radiographs. Between January 2020 and December 2021, 1017 sequential lateral whole-spine radiographs were retrospectively obtained. Of these, 819 and 198 were used for training and testing the performance of the landmark detection model, respectively. To objectively evaluate the program's performance, 690 whole-spine radiographs from four other institutions were used for external validation. The combined dataset comprised radiographs from 857 female and 850 male patients (average age 42.2 ± 27.3 years; range 20-85 years). The landmark localizer showed the highest accuracy in identifying cervical landmarks (median error 1.5-2.4 mm), followed by lumbosacral landmarks (median error 2.1-3.0 mm). However, thoracic landmarks displayed larger localization errors (median 2.4-4.3 mm), indicating slightly reduced precision compared with the cervical and lumbosacral regions. The agreement between the deep learning model and two experts was good to excellent, with intraclass correlation coefficient values >0.88. The deep learning model also performed well on the external validation set. There were no statistical differences between datasets in all parameters, suggesting that the performance of the artificial intelligence model created was excellent. The proposed automatic alignment analysis system identified anatomical landmarks and positions of the spine with high precision and generated various radiograph imaging parameters that had a good correlation with manual measurements.

Image Turing test and its applications on synthetic chest radiographs by using the progressive growing generative adversarial network.

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.

Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations.

Realistic image generation is valuable in dental medicine, but still challenging for generative adversarial networks (GANs), which require large amounts of data to overcome the training instability. Thus, we generated lateral cephalogram X-ray images using a deep-learning-based progressive growing GAN (PGGAN). The quality of generated images was evaluated by three methods. First, signal-to-noise ratios of real/synthesized images, evaluated at the posterior arch region of the first cervical vertebra, showed no statistically significant difference (t-test, p = 0.211). Second, the results of an image Turing test, conducted by non-orthodontists and orthodontists for 100 randomly chosen images, indicated that they had difficulty in distinguishing whether the image was real or synthesized. Third, cephalometric tracing with 42 landmark points detection, performed on real and synthesized images by two expert orthodontists, showed consistency with mean difference of 2.08 ± 1.02 mm. Furthermore, convolutional neural network-based classification tasks were used to classify skeletal patterns using a real dataset with class imbalance and a dataset balanced with synthesized images. The classification accuracy for the latter case was increased by 1.5%/3.3% at internal/external test sets, respectively. Thus, the cephalometric images generated by PGGAN are sufficiently realistic and have potential to application in various fields of dental medicine.

Lgr6 marks epidermal stem cells with a nerve-dependent role in wound re-epithelialization.

Stem cells support lifelong maintenance of adult organs, but their specific roles during injury are poorly understood. Here we demonstrate that Lgr6 marks a regionally restricted population of epidermal stem cells that interact with nerves and specialize in wound re-epithelialization. Diphtheria toxin-mediated ablation of Lgr6 stem cells delays wound healing, and skin denervation phenocopies this effect. Using intravital imaging to capture stem cell dynamics after injury, we show that wound re-epithelialization by Lgr6 stem cells is diminished following loss of nerves. This induces recruitment of other stem cell populations, including hair follicle stem cells, which partially compensate to mediate wound closure. Single-cell lineage tracing and gene expression analysis reveal that the fate of Lgr6 stem cells is shifted toward differentiation following loss of their niche. We conclude that Lgr6 epidermal stem cells are primed for injury response and interact with nerves to regulate their fate.

Estimation of the Closest In-Path Vehicle by Low-Channel LiDAR and Camera Sensor Fusion for Autonomous Vehicles.

In autonomous driving, using a variety of sensors to recognize preceding vehicles at middle and long distances is helpful for improving driving performance and developing various functions. However, if only LiDAR or cameras are used in the recognition stage, it is difficult to obtain the necessary data due to the limitations of each sensor. In this paper, we proposed a method of converting the vision-tracked data into bird's eye-view (BEV) coordinates using an equation that projects LiDAR points onto an image and a method of fusion between LiDAR and vision-tracked data. Thus, the proposed method was effective through the results of detecting the closest in-path vehicle (CIPV) in various situations. In addition, even when experimenting with the EuroNCAP autonomous emergency braking (AEB) test protocol using the result of fusion, AEB performance was improved through improved cognitive performance than when using only LiDAR. In the experimental results, the performance of the proposed method was proven through actual vehicle tests in various scenarios. Consequently, it was convincing that the proposed sensor fusion method significantly improved the adaptive cruise control (ACC) function in autonomous maneuvering. We expect that this improvement in perception performance will contribute to improving the overall stability of ACC.

Two-photon live imaging of single corneal stem cells reveals compartmentalized organization of the limbal niche.

The functional heterogeneity of resident stem cells that support adult organs is incompletely understood. Here, we directly visualize the corneal limbus in the eyes of live mice and identify discrete stem cell niche compartments. By recording the life cycle of individual stem cells and their progeny, we directly analyze their fates and show that their location within the tissue can predict their differentiation status. Stem cells in the inner limbus undergo mostly symmetric divisions and are required to sustain the population of transient progenitors that support corneal homeostasis. Using in situ photolabeling, we captured their progeny exiting the niche before moving centripetally in unison. The long-implicated slow-cycling stem cells are functionally distinct and display local clonal dynamics during homeostasis but can contribute to corneal regeneration after injury. This study demonstrates how the compartmentalized organization of functionally diverse stem cell populations supports the maintenance and regeneration of an adult organ.

Prediction of Neurologically Intact Survival in Cardiac Arrest Patients without Pre-Hospital Return of Spontaneous Circulation: Machine Learning Approach.

Current multimodal approaches for the prognostication of out-of-hospital cardiac arrest (OHCA) are based mainly on the prediction of poor neurological outcomes; however, it is challenging to identify patients expected to have a favorable outcome, especially before the return of spontaneous circulation (ROSC). We developed and validated a machine learning-based system to predict good outcome in OHCA patients before ROSC. This prospective, multicenter, registry-based study analyzed non-traumatic OHCA data collected between October 2015 and June 2017. We used information available before ROSC as predictor variables, and the primary outcome was neurologically intact survival at discharge, defined as cerebral performance category 1 or 2. The developed models' robustness were evaluated and compared with various score metrics to confirm their performance. The model using a voting classifier had the best performance in predicting good neurological outcome (area under the curve = 0.926). We confirmed that the six top-weighted variables predicting neurological outcomes, such as several duration variables after the instant of OHCA and several electrocardiogram variables in the voting classifier model, showed significant differences between the two neurological outcome groups. These findings demonstrate the potential utility of a machine learning model to predict good neurological outcome of OHCA patients before ROSC.

Realistic High-Resolution Body Computed Tomography Image Synthesis by Using Progressive Growing Generative Adversarial Network: Visual Turing Test.

BACKGROUND: Generative adversarial network (GAN)-based synthetic images can be viable solutions to current supervised deep learning challenges. However, generating highly realistic images is a prerequisite for these approaches. OBJECTIVE: The aim of this study was to investigate and validate the unsupervised synthesis of highly realistic body computed tomography (CT) images by using a progressive growing GAN (PGGAN) trained to learn the probability distribution of normal data. METHODS: We trained the PGGAN by using 11,755 body CT scans. Ten radiologists (4 radiologists with <5 years of experience [Group I], 4 radiologists with 5-10 years of experience [Group II], and 2 radiologists with >10 years of experience [Group III]) evaluated the results in a binary approach by using an independent validation set of 300 images (150 real and 150 synthetic) to judge the authenticity of each image. RESULTS: The mean accuracy of the 10 readers in the entire image set was higher than random guessing (1781/3000, 59.4% vs 1500/3000, 50.0%, respectively; P<.001). However, in terms of identifying synthetic images as fake, there was no significant difference in the specificity between the visual Turing test and random guessing (779/1500, 51.9% vs 750/1500, 50.0%, respectively; P=.29). The accuracy between the 3 reader groups with different experience levels was not significantly different (Group I, 696/1200, 58.0%; Group II, 726/1200, 60.5%; and Group III, 359/600, 59.8%; P=.36). Interreader agreements were poor (κ=0.11) for the entire image set. In subgroup analysis, the discrepancies between real and synthetic CT images occurred mainly in the thoracoabdominal junction and in the anatomical details. CONCLUSIONS: The GAN can synthesize highly realistic high-resolution body CT images that are indistinguishable from real images; however, it has limitations in generating body images of the thoracoabdominal junction and lacks accuracy in the anatomical details.

Association between long-term exposure to air pollutants and cardiopulmonary mortality rates in South Korea.

BACKGROUND: The association between long-term exposure to air pollutants, including nitrogen dioxide (NO2), carbon monoxide (CO), sulfur dioxide (SO2), ozone (O3), and particulate matter 10 µm or less in diameter (PM10), and mortality by ischemic heart disease (IHD), cerebrovascular disease (CVD), pneumonia (PN), and chronic lower respiratory disease (CLRD) is unclear. We investigated whether living in an administrative district with heavy air pollution is associated with an increased risk of mortality by the diseases through an ecological study using South Korean administrative data over 19 years. METHODS: A total of 249 Si-Gun-Gus, unit of administrative districts in South Korea were studied. In each district, the daily concentrations of CO, SO2, NO2, O3, and PM10 were averaged over 19 years (2001-2018). Age-adjusted mortality rates by IHD, CVD, PN and CLRD for each district were averaged for the same study period. Multivariate beta-regression analysis was performed to estimate the associations between air pollutant concentrations and mortality rates, after adjusting for confounding factors including altitude, population density, higher education rate, smoking rate, obesity rate, and gross regional domestic product per capita. Associations were also estimated for two subgrouping schema: Capital and non-Capital areas (77:172 districts) and urban and rural areas (168:81 districts). RESULTS: For IHD, higher SO2 concentrations were significantly associated with a higher mortality rate, whereas other air pollutants had null associations. For CVD, SO2 and PM10 concentrations were significantly associated with a higher mortality rate. For PN, O3 concentrations had significant positive associations with a higher mortality rate, while SO2, NO2, and PM10 concentrations had significant negative associations. For CLRD, O3 concentrations were associated with an increased mortality rate, while CO, NO2, and PM10 concentrations had negative associations. In the subgroup analysis, positive associations between SO2 concentrations and IHD mortality were consistently observed in all subgroups, while other pollutant-disease pairs showed null, or mixed associations. CONCLUSION: Long-term exposure to high SO2 concentration was significantly and consistently associated with a high mortality rate nationwide and in Capital and non-Capital areas, and in urban and rural areas. Associations between other air pollutants and disease-related mortalities need to be investigated in further studies.

Correction to: Maximum emergency department overcrowding is correlated with occurrence of unexpected cardiac arrest.

An amendment to this paper has been published and can be accessed via the original article.

Maximum emergency department overcrowding is correlated with occurrence of unexpected cardiac arrest.

BACKGROUND: Emergency department overcrowding negatively impacts critically ill patients and could lead to the occurrence of cardiac arrest. However, the association between emergency department crowding and the occurrence of in-hospital cardiac arrest has not been thoroughly investigated. This study aimed to evaluate the correlation between emergency department occupancy rates and the incidence of in-hospital cardiac arrest. METHODS: A single-center, observational, registry-based cohort study was performed including all consecutive adult, non-traumatic in-hospital cardiac arrest patients between January 2014 and June 2017. We used emergency department occupancy rates as a crowding index at the time of presentation of cardiac arrest and at the time of maximum crowding, and the average crowding rate for the duration of emergency department stay for each patient. To calculate incidence rate, we divided the number of arrest cases for each emergency department occupancy period by accumulated time. The primary outcome is the association between the incidence of in-hospital cardiac arrest and emergency department occupancy rates. RESULTS: During the study period, 629 adult, non-traumatic cardiac arrest patients were enrolled in our registry. Among these, 187 patients experienced in-hospital cardiac arrest. Overall survival discharge rate was 24.6%, and 20.3% of patients showed favorable neurologic outcomes at discharge. Emergency department occupancy rates were positively correlated with in-hospital cardiac arrest occurrence. Moreover, maximum emergency department occupancy in the critical zone had the strongest positive correlation with in-hospital cardiac arrest occurrence (Spearman rank correlation ρ = 1.0, P < .01). Meanwhile, occupancy rates were not associated with the ED mortality. CONCLUSION: Maximum emergency department occupancy was strongly associated with in-hospital cardiac arrest occurrence. Adequate monitoring and managing the maximum occupancy rate would be important to reduce unexpected cardiac arrest.

Convolutional Neural Network Technology in Endoscopic Imaging: Artificial Intelligence for Endoscopy.

Recently, significant improvements have been made in artificial intelligence. The artificial neural network was introduced in the 1950s. However, because of the low computing power and insufficient datasets available at that time, artificial neural networks suffered from overfitting and vanishing gradient problems for training deep networks. This concept has become more promising owing to the enhanced big data processing capability, improvement in computing power with parallel processing units, and new algorithms for deep neural networks, which are becoming increasingly successful and attracting interest in many domains, including computer vision, speech recognition, and natural language processing. Recent studies in this technology augur well for medical and healthcare applications, especially in endoscopic imaging. This paper provides perspectives on the history, development, applications, and challenges of deep-learning technology.

Impact of air pollution on breast cancer incidence and mortality: a nationwide analysis in South Korea.

Breast cancer is one of the major female health problems worldwide. Although there is growing evidence indicating that air pollution increases the risk of breast cancer, there is still inconsistency among previous studies. Unlike the previous studies those had case-control or cohort study designs, we performed a nationwide, whole-population census study. In all 252 administrative districts in South Korea, the associations between ambient NO2 and particulate matter 10 (PM10) concentration, and age-adjusted breast cancer mortality rate in females (from 2005 to 2016, Nmortality = 23,565), and incidence rate (from 2004 to 2013, Nincidence = 133,373) were investigated via multivariable beta regression. Population density, altitude, rate of higher education, smoking rate, obesity rate, parity, unemployment rate, breastfeeding rate, oral contraceptive usage rate, and Gross Regional Domestic Product per capita were considered as potential confounders. Ambient air pollutant concentrations were positively and significantly associated with the breast cancer incidence rate: per 100 ppb CO increase, Odds Ratio OR = 1.08 (95% Confidence Interval CI = 1.06-1.10), per 10 ppb NO2, OR = 1.14 (95% CI = 1.12-1.16), per 1 ppb SO2, OR = 1.04 (95% CI = 1.02-1.05), per 10 µg/m3 PM10, OR = 1.13 (95% CI = 1.09-1.17). However, no significant association between the air pollutants and the breast cancer mortality rate was observed except for PM10: per 10 µg/m3 PM10, OR = 1.05 (95% CI = 1.01-1.09).

[Data Augmentation Techniques for Deep Learning-Based Medical Image Analyses]. / 딥러닝 기반 의료영상 분석을 위한 데이터 증강 기법.

Medical image analyses have been widely used to differentiate normal and abnormal cases, detect lesions, segment organs, etc. Recently, owing to many breakthroughs in artificial intelligence techniques, medical image analyses based on deep learning have been actively studied. However, sufficient medical data are difficult to obtain, and data imbalance between classes hinder the improvement of deep learning performance. To resolve these issues, various studies have been performed, and data augmentation has been found to be a solution. In this review, we introduce data augmentation techniques, including image processing, such as rotation, shift, and intensity variation methods, generative adversarial network-based method, and image property mixing methods. Subsequently, we examine various deep learning studies based on data augmentation techniques. Finally, we discuss the necessity and future directions of data augmentation.

Fully automated 3D segmentation and separation of multiple cervical vertebrae in CT images using a 2D convolutional neural network.

BACKGROUND AND OBJECTIVE: We investigated a novel method using a 2D convolutional neural network (CNN) to identify superior and inferior vertebrae in a single slice of CT images, and a post-processing for 3D segmentation and separation of cervical vertebrae. METHODS: The cervical spines of patients (N == 17, 1684 slices) from Severance and Gangnam Severance Hospitals (S/GSH) and healthy controls (N == 24, 3490 slices) from Seoul National University Bundang Hospital (SNUBH) were scanned by using various volumetric CT protocols. To prepare gold standard masks of cervical spine in CT images, each spine was segmented by using conventional image-processing methods and manually corrected by an expert. The gold standard masks were preprocessed and labeled into superior and inferior cervical vertebrae separately in the axial slices. The 2D U-Net model was trained by using the disease dataset (S/GSH) and additional validation was performed by using the healthy control dataset (SNUBH), and then the training and validation were repeated by switching the two datasets. RESULTS: In case of the model was trained with the disease dataset (S/GSH) and validated with the healthy control (SNUBH), the mean and standard deviation (SD) of the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD) were 94.37%% ± 1.45%, 89.47%% ± 2.55%, 0.33 ± 0.12 mm and 20.89 ± 3.98 mm, and 88.67%% ± 5.82%, 80.83%% ± 8.09%, 1.05 ± 0.63 mm and 29.17 ± 19.74 mm, respectively. In case of the model was trained with the healthy control (SNUBH) and validated with the disease dataset (S/GSH), the mean and SD of DSC, JSC, MSD, and HSD were 96.23%% ± 1.55%, 92.95%% ± 2.58%, 0.39 ± 0.20 mm and 16.23 ± 6.72 mm, and 93.15%% ± 3.09%, 87.54%% ± 5.11%, 0.38 ± 0.17 mm and 20.85 ± 7.11 mm, respectively. CONCLUSIONS: The results demonstrated that our fully automated method achieved comparable accuracies with inter- and intra-observer variabilities of manual segmentation by human experts, which is time consuming.

Age and sex subgroups vulnerable to copycat suicide: evaluation of nationwide data in South Korea.

Media reports of a celebrity's suicide may be followed by copycat suicides, and the impact may vary in different age and sex subgroups. We proposed a quantitative framework to assess the vulnerability of age and sex subgroups to copycat suicide and used this method to investigate copycat suicides in relation to the suicides of 10 celebrities in South Korea from 1993 to 2013. By applying a detrending model to control for annual and seasonal fluctuations, we estimated the expected number of suicides within a copycat suicide period. The copycat effect was assessed in two ways: the magnitude of copycat suicide by dividing the observed by the expected number of suicides, and the mortality rate by subtracting the expected from the observed number of suicides. Females aged 20-29 years were the most vulnerable subgroup according to both the magnitude of the copycat effect (2.31-fold increase over baseline) and the mortality rate from copycat suicide (22.7-increase). Males aged 50-59 years were the second most vulnerable subgroup according to the copycat suicide mortality rate (20.5- increase). We hope that the proposed quantitative framework will be used to identify vulnerable subgroups to copycat effect, thereby helping devise strategies for prevention.

Deep Learning in Medical Imaging.

The artificial neural network (ANN), one of the machine learning (ML) algorithms, inspired by the human brain system, was developed by connecting layers with artificial neurons. However, due to the low computing power and insufficient learnable data, ANN has suffered from overfitting and vanishing gradient problems for training deep networks. The advancement of computing power with graphics processing units and the availability of large data acquisition, deep neural network outperforms human or other ML capabilities in computer vision and speech recognition tasks. These potentials are recently applied to healthcare problems, including computer-aided detection/diagnosis, disease prediction, image segmentation, image generation, etc. In this review article, we will explain the history, development, and applications in medical imaging.

A Perlin Noise-Based Augmentation Strategy for Deep Learning with Small Data Samples of HRCT Images.

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.