Search

Abstract Goblet cells (GCs) in the conjunctiva are specialized epithelial cells secreting mucins for the mucus layer of protective tear film and playing immune tolerance functions for ocular surface health. Because GC loss is observed in various ocular surface diseases, GC examination is important for precision diagnosis. Moxifloxacin-based fluorescence microscopy (MBFM) was recently developed for non-invasive high-contrast GC visualization. MBFM showed promise for GC examination by high-speed large-area imaging and a robust analysis method is needed to provide GC information. In this study, we developed a deep learning framework for GC image analysis, named dual-channel attention U-Net (DCAU-Net). Dual-channel convolution was used both to extract the overall image texture and to acquire the GC morphological characteristics. A global channel attention module was adopted by combining attention algorithms and channel-wise pooling. DCAU-Net showed 93.1% GC segmentation accuracy and 94.3% GC density estimation accuracy. Further application to both normal and ocular surface damage rabbit models revealed the spatial variations of both GC density and size in normal rabbits and the decreases of both GC density and size in damage rabbit models during recovery after acute damage. The GC analysis results were consistent with histology. Together with the non-invasive high-contrast imaging method, DCAU-Net would provide GC information for the diagnosis of ocular surface diseases.

Abstract Benign paroxysmal positional vertigo (BPPV), the most common vestibular disorder, is diagnosed by an examiner changing the posture of the examinee and inducing nystagmus. Among the diagnostic methods used to observe nystagmus, video-nystagmography has been widely used recently because it is non-invasive. A specialist with professional knowledge and training in vertigo diagnosis is needed to diagnose BPPV accurately, but the ratio of vertigo patients to specialists is too high, thus necessitating the need for automated diagnosis of BPPV. In this paper, a convolutional neural network-based nystagmus extraction system, ANyEye, optimized for video-nystagmography data is proposed. A pupil was segmented to track the exact pupil trajectory from real-world data obtained during field inspection. A deep convolutional neural network model was trained with the new video-nystagmography dataset for the pupil segmentation task, and a compensation algorithm was designed to correct pupil position. In addition, a slippage detection algorithm based on moving averages was designed to eliminate the motion artifacts induced by goggle slippage. ANyEye outperformed other eye-tracking methods including learning and non-learning-based algorithms with five-pixel error detection rate of 91.26%.

Abstract Direct visualization of the atomic structure in scanning transmission electron microscopy has led to a comprehensive understanding of the structure-property relationship. However, a reliable characterization of the structural transition on a picometric scale is still challenging because of the limited spatial resolution and noise. Here, we demonstrate that the primary segmentation of atomic signals from background, succeeded by a denoising process, enables structural analysis in a sub-pixel accuracy. Poisson noise is eliminated using the block matching and three-dimensional filtering with Anscombe transformation, and remnant noise is removed via morphological filtering, which results in an increase of peak signal-to-noise ratio from 7 to 11 dB. Extracting the centroids of atomic columns segmented via K-means clustering, an unsupervised method for robust thresholding, achieves an average error of less than 0.7 pixel, which corresponds to 4.6 pm. This study will contribute to a profound understanding of the local structural dynamics in crystal structures.

Left ventricular hypertrophy is a significant independent risk factor for all-cause mortality and morbidity, and an accurate diagnosis at an early stage of heart change is clinically significant. Electrocardiography is the most convenient, economical, and non-invasive method for screening in primary care. However, the coincidence rate of the actual left ventricular hypertrophy and diagnostic findings was low, consequently increasing the interest in algorithms using big data and deep learning. We attempted to diagnose left ventricular hypertrophy using big data and deep learning algorithms, and aimed to confirm its diagnostic power according to the differences between males and females. This retrospective study used electrocardiographs obtained at Yonsei University Wonju Severance Christian Hospital, Wonju, Korea, from October 2010 to February 2020. Binary classification was performed for primary screening for left ventricular hypertrophy. Three datasets were used for the experiment: the male, female, and entire dataset. A cutoff for binary classification was defined as the meaningful as a screening test (

PurposeThere has been little progress in research on the best anatomical position for effective chest compressions and cardiac function during cardiopulmonary resuscitation (CPR). This study aimed to divide the left ventricle (LV) into segments to determine the best position for effective chest compressions using the LV systolic function seen during CPR.MethodsWe used transesophageal echocardiography images acquired during CPR. A deep neural network with an attention mechanism and a residual feature aggregation module were applied to the images to segment the LV. The results were compared between the proposed model and U-Net.ResultsThe results of the proposed model showed higher performance in most metrics when compared to U-Net: dice coefficient (0.899±0.017 vs. 0.792±0.027, p0.05). There was a significant difference between the proposed model and U-Net.ConclusionCompared to U-Net, the proposed model showed better performance for all metrics. This model would allow us to evaluate the systolic function of the heart during CPR in greater detail by segmenting the LV more accurately.

In this study, a combined convolutional neural network for the diagnosis of three benign skin tumors was designed, and its effectiveness was verified through quantitative and statistical analysis. To this end, 698 sonographic images were taken and diagnosed at the Department of Dermatology at Severance Hospital in Seoul, Korea, between 10 November 2017 and 17 January 2020. Through an empirical process, a convolutional neural network combining two structures, which consist of a residual structure and an attention-gated structure, was designed. Five-fold cross-validation was applied, and the train set for each fold was augmented by the Fast AutoAugment technique. As a result of training, for three benign skin tumors, an average accuracy of 95.87%, an average sensitivity of 90.10%, and an average specificity of 96.23% were derived. Also, through statistical analysis using a class activation map and physicians’ findings, it was found that the judgment criteria of physicians and the trained combined convolutional neural network were similar. This study suggests that the model designed and trained in this study can be a diagnostic aid to assist physicians and enable more efficient and accurate diagnoses.

Two-dimensional (2D) materials are attracting increasing research interest owing to their distinct tunable physical properties. Moreover, the ubiquitous defects in 2D materials offer an opportunity to tailor their electronic properties. Recently, atomic-level structural modification methods for 2D materials have been developed, further triggering the need for the precise control of defects. Following the ground-breaking advancements in the atomic-scale characterization of defects in 2D materials, valuable information on defect-driven electronic properties has been published. It is therefore important to present a review work on the recent research developments on atomic-level defect control and characterization of 2D materials. This Perspective highlights the type and role of atomic defects in 2D materials, as well as some current technologies for engineering such defects. In addition, we emphasize on atomic-level characterization methods with a focus on aberration-corrected transmission electron microscopy and deep learning as a powerful method for characterizing defects in 2D materials. Based on the two characterization techniques, we present the experimental results of laser-induced structurally modified MoTe2 and transition metal decorated h-BN. We believe that this work will provide fundamental knowledge for engineering and characterizing defects in 2D materials for the design of application-specific electronic devices.

Skin cancer, previously known to be a common disease in Western countries, is becoming more common in Asian countries. Skin cancer differs from other carcinomas in that it is visible to our eyes. Although skin biopsy is essential for the diagnosis of skin cancer, decisions regarding whether or not to conduct a biopsy are made by an experienced dermatologist. From this perspective, it is easy to obtain and store photos using a smartphone, and artificial intelligence technologies developed to analyze these photos can represent a useful tool to complement the dermatologist's knowledge. In addition, the universal use of dermoscopy, which allows for non-invasive inspection of the upper dermal level of skin lesions with a usual 10-fold magnification, adds to the image storage and analysis techniques, foreshadowing breakthroughs in skin cancer diagnosis. Current problems include the inaccuracy of the available technology and resulting legal liabilities. This paper presents a comprehensive review of the clinical applications of artificial intelligence and a discussion on how it can be implemented in the field of cutaneous oncology.

The non-invasive examination of conjunctival goblet cells using a microscope is a novel procedure for the diagnosis of ocular surface diseases. However, it is difficult to generate an all-in-focus image due to the curvature of the eyes and the limited focal depth of the microscope. The microscope acquires multiple images with the axial translation of focus, and the image stack must be processed. Thus, we propose a multi-focus image fusion method to generate an all-in-focus image from multiple microscopic images. First, a bandpass filter is applied to the source images and the focus areas are extracted using Laplacian transformation and thresholding with a morphological operation. Next, a self-adjusting guided filter is applied for the natural connections between local focus images. A window-size-updating method is adopted in the guided filter to reduce the number of parameters. This paper presents a novel algorithm that can operate for a large quantity of images (10 or more) and obtain an all-in-focus image. To quantitatively evaluate the proposed method, two different types of evaluation metrics are used: “full-reference” and “no-reference”. The experimental results demonstrate that this algorithm is robust to noise and capable of preserving local focus information through focal area extraction. Additionally, the proposed method outperforms state-of-the-art approaches in terms of both visual effects and image quality assessments.

In this study, we aimed to develop a new automated method for kidney volume measurement in children using ultrasonography (US) with image pre-processing and hybrid learning and to formulate an equation to calculate the expected kidney volume. The volumes of 282 kidneys (141 subjects,

Cell migration plays an important role in the identification of various diseases and physiological phenomena in living organisms, such as cancer metastasis, nerve development, immune function, wound healing, and embryo formulation and development. The study of cell migration with a real-time microscope generally takes several hours and involves analysis of the movement characteristics by tracking the positions of cells at each time interval in the images of the observed cells. Morphological analysis considers the shapes of the cells, and a phase contrast microscope is used to observe the shape clearly. Therefore, we developed a segmentation and tracking method to perform a kinetic analysis by considering the morphological transformation of cells. The main features of the algorithm are noise reduction using a block-matching 3D filtering method, k-means clustering to mitigate the halo signal that interferes with cell segmentation, and the detection of cell boundaries via active contours, which is an excellent way to detect boundaries. The reliability of the algorithm developed in this study was verified using a comparison with the manual tracking results. In addition, the segmentation results were compared to our method with unsupervised state-of-the-art methods to verify the proposed segmentation process. As a result of the study, the proposed method had a lower error of less than 40% compared to the conventional active contour method.

To understand the dynamics of a living system, the analysis of particular and/or cellular dynamics has been performed based on shape-based center point detection. After collecting sequential time-lapse images of cellular dynamics, the trajectory of a moving object is determined from the set of center points of the cell analyzed from each image. The accuracy of trajectory is significant in understanding the stochastic nature of the dynamics of biological objects. In this study, to localize a cellular object in time-lapse images, three different localization methods, namely radial symmetry, circular Hough transform, and modified active contour, were considered. To analyze the accuracy of cellular dynamics, several statistical parameters such as mean square displacement and velocity autocorrelation function were employed, and localization error derived from these was reported for each localization method. In particular, through denoising using a Poisson noise filter, improved localization characteristics could be achieved. The modified active contour with denoising reduced localization error significantly, and thus allowed for accurate estimation of the statistical parameters of cellular dynamics.

In animal models of Parkinson's disease (PD), 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP) is one of the most widely used agents that damages the nigrostriatal dopaminergic pathway. However, brain structural changes in response to MPTP remain unclear. This study aimed to investigate in vivo longitudinal changes in gray matter (GM) volume and white matter (WM) microstructure in primate models administered with MPTP. In six cynomolgus monkeys, high-resolution magnetic resonance imaging (MRI) and diffusion tensor imaging (DTI) scans were acquired 7 times over 32 weeks, and assessments of motor symptoms were conducted over 15 months, before and after the MPTP injection. Changes in GM volume and WM microstructure were estimated on a voxel-by-voxel basis. Mixed-effects regression models were used to examine the trajectories of these structural changes. GM volume initially increased after the MPTP injection and gradually decreased in the striatum, midbrain, and other dopaminergic areas. The cerebellar volume temporarily decreased and returned to its baseline level. The rate of midbrain volume increase was positively correlated with the increase rate of motor symptom severity (Spearman rho = 0.93, p = 0.008). Mean, axial, and radial diffusivity in the striatum and frontal areas demonstrated initial increases and subsequent decreases. The current multi-modal imaging study of MPTP-administered monkeys revealed widespread and dynamic structural changes not only in the nigrostriatal pathway but also in other cortical, subcortical, and cerebellar areas. Our findings may suggest the need to further investigate the roles of inflammatory reactions and glial activation as potential underlying mechanisms of these structural changes.

[This corrects the article DOI: 10.1371/journal.pone.0193321.].

Acral melanoma is the most common type of melanoma in Asians, and usually results in a poor prognosis due to late diagnosis. We applied a convolutional neural network to dermoscopy images of acral melanoma and benign nevi on the hands and feet and evaluated its usefulness for the early diagnosis of these conditions.A total of 724 dermoscopy images comprising acral melanoma (350 images from 81 patients) and benign nevi (374 images from 194 patients), and confirmed by histopathological examination, were analyzed in this study. To perform the 2-fold cross validation, we split them into two mutually exclusive subsets: half of the total image dataset was selected for training and the rest for testing, and we calculated the accuracy of diagnosis comparing it with the dermatologist's and non-expert's evaluation.The accuracy (percentage of true positive and true negative from all images) of the convolutional neural network was 83.51% and 80.23%, which was higher than the non-expert's evaluation (67.84%, 62.71%) and close to that of the expert (81.08%, 81.64%). Moreover, the convolutional neural network showed area-under-the-curve values like 0.8, 0.84 and Youden's index like 0.6795, 0.6073, which were similar score with the expert.Although further data analysis is necessary to improve their accuracy, convolutional neural networks would be helpful to detect acral melanoma from dermoscopy images of the hands and feet.

The use of automatic electrical stimulation in response to early seizure detection has been introduced as a new treatment for intractable epilepsy. For the effective application of this method as a successful treatment, improving the accuracy of the early seizure detection is crucial. In this paper, we proposed the application of a frequency-based algorithm derived from principal component analysis (PCA), and demonstrated improved efficacy for early seizure detection in a pilocarpine-induced epilepsy rat model. A total of 100 ictal electroencephalographs (EEG) during spontaneous recurrent seizures from 11 epileptic rats were finally included for the analysis. PCA was applied to the covariance matrix of a conventional EEG frequency band signal. Two PCA results were compared: one from the initial segment of seizures (5 sec of seizure onset) and the other from the whole segment of seizures. In order to compare the accuracy, we obtained the specific threshold satisfying the target performance from the training set, and compared the False Positive (FP), False Negative (FN), and Latency (Lat) of the PCA based feature derived from the initial segment of seizures to the other six features in the testing set. The PCA based feature derived from the initial segment of seizures performed significantly better than other features with a 1.40% FP, zero FN, and 0.14 s Lat. These results demonstrated that the proposed frequency-based feature from PCA that captures the characteristics of the initial phase of seizure was effective for early detection of seizures. Experiments with rat ictal EEGs showed an improved early seizure detection rate with PCA applied to the covariance of the initial 5 s segment of visual seizure onset instead of using the whole seizure segment or other conventional frequency bands.

Photographs of skin wounds have the most important information during the secondary intention healing (SIH). However, there is no standard method for handling those images and analyzing them efficiently and conveniently.To investigate the sequential changes of SIH depending on the body sites using a color patch method.We performed retrospective reviews of 30 patients (11 facial and 19 non-facial areas) who underwent SIH for the restoration of skin defects and captured sequential photographs with a color patch which is specially designed for automatically calculating defect and scar sizes.Using a novel image analysis method with a color patch, skin defects were calculated more accurately (range of error rate: -3.39% ~ + 3.05%). All patients had smaller scar size than the original defect size after SIH treatment (rates of decrease: 18.8% ~ 86.1%), and facial area showed significantly higher decrease rate compared with the non-facial area such as scalp and extremities (67.05 ± 12.48 vs. 53.29 ± 18.11, P < 0.05). From the result of estimating the date corresponding to the half of the final decrement, all of the facial area showed improvements within two weeks (8.45 ± 3.91), and non-facial area needed 14.33 ± 9.78 days.From the results of sequential changes of skin defects, SIH can be recommended as an alternative treatment method for restoration with more careful dressing for initial two weeks.

In certain image acquisitions processes, like in fluorescence microscopy or astronomy, only a limited number of photons can be collected due to various physical constraints. The resulting images suffer from signal dependent noise, which can be modeled as a Poisson distribution, and a low signal-to-noise ratio. However, the majority of research on noise reduction algorithms focuses on signal independent Gaussian noise. In this paper, we model noise as a combination of Poisson and Gaussian probability distributions to construct a more accurate model and adopt the contourlet transform which provides a sparse representation of the directional components in images. We also apply hidden Markov models with a framework that neatly describes the spatial and interscale dependencies which are the properties of transformation coefficients of natural images. In this paper, an effective denoising algorithm for Poisson-Gaussian noise is proposed using the contourlet transform, hidden Markov models and noise estimation in the transform domain. We supplement the algorithm by cycle spinning and Wiener filtering for further improvements. We finally show experimental results with simulations and fluorescence microscopy images which demonstrate the improved performance of the proposed approach.

Testing is increasingly recognized as a vital part of language revitalization. I demonstrate here that assessment of linguistic knowledge should also be part of the planning process that precedes the creation of a revitalization program. I take as an example Jejueo, the language of Korea's Jeju Island. Whereas previously published work contradicted UNESCO's conclusion that the language is critically endangered, a test that I designed to elicit basic vocabulary and verbal patterns from 224 participants (from elementary school students to senior citizens) revealed otherwise. Alarming deficits in basic knowledge of the language were uncovered that both confirmed UNESCO's classification of the language and identified the particular areas in which remediation is required.