Average Kappa Research Articles

A parallel multi-scale time-frequency block convolutional neural network based on channel attention module for motor imagery classification

The motor imagery brain-computer interface (MI-BCI) based on electroencephalography (EEG) enables direct communication between the human brain and external devices. In this paper, the MTFB-CNN, a parallel multi-scale time-frequency block convolutional neural network based on the channel attention module, is proposed for EEG signals decoding, which can adaptively extract the time, frequency, and time-frequency domain features through parallel multi-scale time-frequency blocks, and then fuses and filters the features through attention mechanism and residual module. Experimental results based on the BCI Competition IV 2a and 2b datasets and the high gamma dataset show that the model achieves the highest average accuracy and kappa compared with existing baseline models. The MTFB-CNN is a novel and effective end-to-end model for decoding EEG signals without complex signals pre-processing operations, which has multi-scale feature extraction capability, making it successful in MI-BCI applications.

Time-Series Monitoring of Dust-Proof Nets Covering Urban Construction Waste by Multispectral Images in Zhengzhou, China

Rapid urbanization has produced a huge amount of construction waste. The operations and consequences of construction and demolition can lead to windblown dust problems, profoundly affecting the living environment of residents. Fortunately, dust-proof nets have been used in construction sites to reduce and prevent pollution by fine particles such as dust, so it is important to monitor and evaluate their efficacy. In this study, Earth observation techniques were used for the extraction and monitoring of solid waste and dust-proof nets. In order to fully perceive the validity and necessity of dust-proof nets for urban air health, we conducted a case study in Zhengzhou, China. We explored the potential of multispectral remote sensing available for monitoring urban construction waste and proposed a multi-layer classification method to identify construction waste and dust-proof nets based on Landsat-8 OLI and Sentinel-2 MSI data, with an average identification accuracy and Kappa coefficient of 96.27% and 0.93 for construction waste in the study area from 2015 to 2020, respectively. In addition, our study revealed the driving factors and impact of temporal variations in regional construction waste areas and dust-proof nets coverage. The results indicate the classification can track municipal solid waste management and changes in air pollutant concentrations and is useful for achieving SDG 11.6 (reduce the adverse per capita environmental impact of cities, including by paying special attention to air quality and municipal and other waste management). This study has the potential to monitor construction waste and dust-proof nets, paving the way for better urban environmental governance and surveillance actions in the future, especially involving big data.

AI provides congruent and prescriptive feedback for squat form: qualitative assessment of coaching provided by AI and physical therapist.

Objectives: To assess style and themes of feedback provided by artificial intelligence (AI) mobile application and physical therapist (PT) to participants during bodyweight squat exercise. Methods: Research population was age 20-35, without any pre-existing condition that precluded participation in bodyweight exercise. Qualitative methodology followed directed content analysis. Cohen's kappa coefficient verified consistency between coders. Results: Both AI and PT groups had sevenfemale and eightmale participants. Three themes emerged: affirmation schema, correction paradigms and physical assessments. Average kappa coefficient calculated for all codes was 0.96, a value that indicates almost perfect agreement. Conclusion: Themes generated highlight the AI focus on congruent, descriptiveand prescriptive feedback, while the PT demonstrated multipoint improvement capabilities. Further research should establish feedback comparisons with multiple PTs and correlate qualitative data with additional quantitative data on performance outcomes based on feedback.

Development and validation of standardized severity rating scale to assess the consistency of drug-drug interaction severity among various drug information resources.

The consistency in reporting the severity of drug interactions across the drug information resources is important in guiding the appropriate clinical use of drug-pairs, to minimize the associated adverse events. This necessitates the need of a standardized severity rating scale, that can accommodate the different severity ratings of the same interacting drug-pair into a reasonable severity category, that can ease the consistency assessment among different drug information resources. To develop and validate a standardized severity rating scale that can ease the consistency assessment among the various drug information resources. The definitions of various severity rating categories as documented in the eight drug information resources was consolidated to develop a standardized severity rating scale. Thus developed rating scale was validated using twenty commonly used drug-pairs. Fleiss' kappa score was used as an indicator for assessing overall consistency among various drug information resources, whereas, Cohen's kappa was used as an indicator of level of consistency between two drug information resources and between individual drug information resource and newly developed standardized severity rating scale. The newly developed standardized severity rating scale classifies the severity of drug-drug interactions into three categories namely mild, moderate and major. The Fleiss' kappa score was improved from 0.047 to 0.176, indicating improved strength of agreement [Average pairwise agreement: 16% Vs 36.7%] among various drug information resources. The average pairwise Cohen's kappa was 0.082 [Strength of agreement: poor] in original severity ratings whereas it was improved to 0.198 [Strength of agreement: almost equal to fair] in standardized severity rating scale. The newly developed standardized severity rating scale can be used as a tool to assess the consistency of severity rating categories among the various drug information resources.

An Approach for Retrieving Consistent Time Series “Urban Core–Suburban-Rural” (USR) Structure Using Nighttime Light Data from DMSP/OLS and NPP/VIIRS

The long time series and consistent “urban core-suburban-rural” (USR) structure in a city region is essential to understanding urban–suburban–rural interaction and urbanization pathways. It is always considered to be a single land use type (e.g., impervious area) in remote sensing research. The long-term (1992–present) nighttime light (NTL) data of the Defense Meteorological Satellite Program-Operational Linescan System (DMSP-OLS) and the Suomi National Polar-Orbiting Partnership Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) provide the potential for retrieving time series of USR structure. In this study, we propose an improved approach to mapping the USR structure of the three subcategories based on a heuristic algorithm of Mann–Kendall mutation detection on the NTL quantile curve. First, a minor adjustment of VIIRS NTL is applied for matching the value ranges of DMSP NTL data and keeping the advantage of VIIRS to generate a long-term NTL dataset. Second, the heuristic algorithm of Mann–Kendall mutation detection is processed to find two optimal thresholds in the NTL quantile curve, which is used for USR extraction. Finally, a temporal consistency check is used to post-process the initial USR area for obtaining a more consistent and reliable USR sequence. To evaluate the performance of the proposed method, we retrieved the USR structures of 19 typical cities in China from 1992 to 2020 based on NTL datasets. The evaluations of spatiotemporal consistency compared with the validation data indicate that the USR retrieval results show good agreement with the land use map derived from Landsat images and the time series product from MODIS. The average overall accuracy (OA) of overall urban extent is higher than 0.95 and the average kappa coefficient (KC) reaches 0.6. Moreover, we investigated the urban dynamics and USR interactions of 19 cities from 1992 to 2020. Overall, this study proposes an improved approach for long-term USR mapping from NTL images at a regional scale and it will provide a valuable method for urbanization dynamics analysis.

Object-Based Automatic Mapping of Winter Wheat Based on Temporal Phenology Patterns Derived from Multitemporal Sentinel-1 and Sentinel-2 Imagery

Although winter wheat has been mapped by remote sensing in several studies, such mapping efforts did not sufficiently utilize contextual information to reduce the noise and still depended heavily on optical imagery and exhausting classification approaches. Furthermore, the influence of similarity measures on winter wheat identification remains unclear. To overcome these limitations, this study developed an object-based automatic approach to map winter wheat using multitemporal Sentinel-1 (S1) and Sentinel-2 (S2) imagery. First, after S1 and S2 images were preprocessed, the Simple Non-Iterative Clustering (SNIC) algorithm was used to conduct image segmentation to obtain homogeneous spatial objects with a fusion of S1 and S2 bands. Second, the temporal phenology patterns (TPP) of winter wheat and other typical land covers were derived from object-level S1 and S2 imagery based on the collected ground truth samples, and two improved distance measures (i.e., a composite of Euclidean distance and Spectral Angle Distance, (ESD) and the difference–similarity factor distance (DSF)) were built to evaluate the similarity between two TPPs. Third, winter wheat objects were automatically identified from the segmented spatial objects by the maximum between-class variance method (OTSU) with distance measures based on the unique TPP of winter wheat. According to ground truth data, the DSF measure was superior to other distance measures in winter wheat mapping, since it achieved the best overall accuracy (OA), best kappa coefficient (Kappa) and more spatial details for each feasible band (i.e., NDVI, VV, and VH/VV), or it obtained results comparable to those for the best one (e.g., NDVI + VV). The resultant winter wheat maps derived from the NDVI band with the DSF measure achieved the best accuracy and more details, and had an average OA and Kappa of 92% and 84%, respectively. The VV polarization with the DSF measure produced the second best winter wheat maps with an average OA and Kappa of 91% and 80%, respectively. The results indicate the great potential of the proposed object-based approach for automatic winter wheat mapping for both optical and Synthetic Aperture Radar (SAR) imagery.

Assessment of Forest Cover Changes in Vavuniya District, Sri Lanka: Implications for the Establishment of Subnational Forest Reference Emission Level

Assessment of forest cover changes is required to establish the forest reference emission level (FREL) at any scale. Due to civil conflict, such assessments have not yet been undertaken in Sri Lanka, especially in the conflict zone. Here, we assessed the forest cover changes in Vavuniya District, Sri Lanka, from 2001 to 2020, using a combination of the Google Earth Engine (GEE) platform and the phenology-based threshold classification (PBTC) method. Landsat 5 TM data for 2001, 2006, and 2010, and Landsat 8 OLI data for 2016 and 2020 were used to classify forest cover by categories, and their related changes could be assessed by four categories, namely dry monsoon forest, open forest, other lands, and water bodies. With an overall average accuracy of 87% and an average kappa coefficient of 0.83, forest cover was estimated at 57.6% of the total land area in 2020. There was an increase of 0.46% per annum for the entire district between 2001 and 2010, but a drastic loss of 0.60% per year was observed between 2010 and 2020. Specifically, the dry monsoon forest lost 0.30%, but open forest gained 3.62% annually over the same period. Loss and gain of forest cover resulted in carbon emissions and removals of 165,306.6 MgCO2 and 24,064.5 MgCO2 annually, respectively, over the same period. Our findings could be used to set the baseline trend of deforestation, based on which, a subnational forest reference emission level can be established as an emission benchmark, against which comparisons of carbon emissions following the implementation of REDD+ activities can be made, and result-based payment can be claimed under the Paris Agreement.

Hyperspectral Image Classification with Optimized Compressed Synergic Deep Convolution Neural Network with Aquila Optimization.

The classification technology of hyperspectral images (HSI) consists of many contiguous spectral bands that are often utilized for a various Earth observation activities, such as surveillance, detection, and identification. The incorporation of both spectral and spatial characteristics is necessary for improved classification accuracy. In the classification of hyperspectral images, deep learning has gained significant traction. This research analyzes how to accurately classify new HSI from limited samples with labels. A novel deep-learning-based categorization based on feature extraction and classification is designed for this purpose. Initial extraction of spectral and spatial information is followed by spectral and spatial information integration to generate fused features. The classification challenge is completed using a compressed synergic deep convolution neural network with Aquila optimization (CSDCNN-AO) model constructed by utilising a novel optimization technique known as the Aquila Optimizer (AO). The HSI, the Kennedy Space Center (KSC), the Indian Pines (IP) dataset, the Houston U (HU) dataset, and the Salinas Scene (SS) dataset are used for experiment assessment. The sequence testing on these four HSI-classified datasets demonstrate that our innovative framework outperforms the conventional technique on common evaluation measures such as average accuracy (AA), overall accuracy (OA), and Kappa coefficient (k). In addition, it significantly reduces training time and computational cost, resulting in enhanced training stability, maximum performance, and remarkable training accuracy.

Bone defect classifications in revision total knee arthroplasty, their reliability and utility: a systematic review.

There are various classification systems described in the literature for managing bone defects in revision knee arthroplasty (RTKA). We analysed the reliability and usefulness of these classification systems. (1) To review and critique the various classification systems proposed for bone loss in RTKA. (2) Among all the proposed classifications which one is the most commonly used by surgeons to report their results. (3) What is the reliability of various bone defect classification systems for RTKA. In this review, we have assessed the studies validating those classifications with a detailed description of the limitations and the proposed modifications. This systematic review was conducted following PRISMA guidelines. Pubmed/Medline, CINAHL, EMBASE, Scopus, Cochrane databases and Web of Science databases were searched using multiple search terms and MeSH terms where possible. Studies meeting inclusion criteria were assessed for statistical parameters of reliability of a classification system. We found 16 classification systems for bone defects in RTKA. Six studies were found evaluating a classification system with reporting their reliability parameters. Fifty-four studies were found which classified bone loss using AORI classification in their series. AORI classification is most commonly reported for classifying bone defects. Type T2B and F2B are the most common bone defects in RTKA. The average kappa value for AORI classification for femoral bone loss was 0.38 (0.27-0.50) and 0.76 (0.63-1) for tibial bone loss assessment. None of the available classification systems is reliably established in determining the bone loss and treatment plans in RTKA. Among all, AORI classification is the most widely used system in clinical practice. The reliability of AORI Classification is fair for femoral bone loss and substantial for tibial bone loss.

Sand Dunes Spectral Index Determination Using Machine Learning Model: Case study of Baiji Sand Dunes Field Northern Iraq

Monitoring the propagation of dunes is essential for natural hazard management. Accurate dunes mapping is critical in this situation. Landscape elements such as vegetation, water, dunes, and built-up are commonly separated using spectral indices. The discovery of dune features using a spectral index is one of the most significant achievements in earth observation. In this research, it was suggested Drifting Sand Index (DSI) is a newly created index that can be used to extract the land of dunes. The DSI is calculated using the normalized difference between six Landsat-8 bands (B, R, G, NIR, SWIR-1, SWIR-2). The linear SVM algorithm was implemented using library (LibLINEAR) in the R software to calculate a new linear equation. Two versions of the index have been proposed, the first is the complete version (DSI-C), and the second is the reduced version (DSI-R). The suggested indices results were compared to four previously proposed spectral indices (NDSI-1, NDSI-2, CI, and NDSLI). The acquired results demonstrated that the DSI-C and DSI-R had a high ability to distinguish between sand and different land covers, such as vegetation, water bodies, and various soil types. The average overall accuracy for all levels of the DSI-R, DSI-C, NDSI-1, NDSI-2, CI, and NDSLI was 88.59%, 83.43%, 78.030%, 68.52%, 65.98%, and 56.490%, respectively. The average Kappa Coefficient for DSI-R, DSI-C NDSI-1, NDSI-2, CI, and NDSLI was 77.20%, 66.87%, 56.076%, 37.073%, 31.978%, and 13.011%, respectively.

Citrus orchard mapping in Juybar, Iran: Analysis of NDVI time series and feature fusion of multi-source satellite imageries

Nowadays crop mapping as an interdisciplinary hot topic attracted both agriculture and remote sensing researchers' interests. This study proposed an automatic method to map citrus orchards in Juybar, Iran, where planting citrus trees is booming there. In this regard, 148 Sentinel-1, Sentinel-2, and ALOS Digital Surface Model (DSM) tiles are processed in Google Earth Engine to provide a hybrid feature set including initial satellite images, Gray Level Co-occurrence Matrix (GLCM) textural features, and spectral features such as vegetation, built-up, bare-soil indices, and the proposed Vegetation Dynamic Index (VDI). A semi-automatic sample selection paradigm is also developed based on a time-series analysis of 12 monthly Normalized Difference Vegetation Indices (NDVIs), Otsu thresholding, multi-level thresholding (MLT), and using two proposed indices called Evergreenness Index (EGI) and Water-covered or No-vegetation (WCNV) index, and finally human post-revision. The output of the Support Vector Machine (SVM) classification using 60,000 samples and the post-classification operation showed that the classified map has an average overall accuracy (OA) and an average kappa coefficient (KC) equal to 99.7% and 0.992, respectively. The results show that multispectral bands lonely extracted orchards with high accuracy (OA: 99.55%, KC: 0.986), and the rest of the features only made a slight improvement to that. For the year 2019, an area of about 4351 ha is estimated as citrus orchards, which is in accordance with the agriculture department's reports (~4700 ha). The results indicate that from 2016 to 2019, despite a “citrus to non-citrus” land-use conversion of about 754 ha, the citrus orchards area was totally expanded by about 17%. Comparing the results with the Google Earth images indicates the precise extraction of orchards with a 10 m spatial resolution. To use the proposed method for extensive cases or areas with other types of evergreen trees, it is recommended to use high-resolution normalized DSMs (nDSMs) and textural features.

Unsupervised change detection in SAR images based on generalized likelihood ratio test and a two-stage morphological filter

ABSTRACT Generalized likelihood ratio test (GLRT) is an efficient method to generate difference image (DI) for change detection (CD) using synthetic aperture radar (SAR) images. GLRT is usually applied with a fixed-size moving window to the neighbourhood regions in multitemporal SAR images. The fixed window may be however not optimal for all the pixels under test. To solve disadvantages of the GLRT method, an adaptive circular window is proposed in this work. While the adaptive square window and the best fixed square window achieve an average Kappa coefficient of 83.55% and 82.12%, respectively, the adaptive circular window improves the average Kappa coefficient by 83.65% in six datasets. As another difficulty, speckle noise reduces quality of DI in SAR change detection. Three steps are considered to minimize effects of the speckle noise: (1) a two-stage morphological filter is suggested to reduce the speckle noise; (2) to generate DI, the adaptive circular window for generalized likelihood ratio test (ACWGLRT) is proposed that reduces influence of the speckle noise while preserves the edge details of multitemporal images; and (3) spatial fuzzy c-means (SFCM) is used to reduce effects of the residual speckle-noise during DI classification. The experimental results show superior performance of the proposed change detection method with respect to several competitors. The proposed method has the best Kappa coefficient and percentage correct classification (PCC) in four datasets of Ottawa, San Francisco, Farmland C, and Inland water.

Long-Term and Bimonthly Estimation of Lake Water Extent Using Google Earth Engine and Landsat Data

Lakes are one of the most important parts of the terrestrial hydrosphere. The long-term series of lake area dynamic data with high spatial-temporal resolution is of great significance to the study of global change of the water environment. Satellite observations (such as Landsat) have provided images since the 1970s, but there were challenges for the construction of long-term sequences of lake area on a monthly temporal scale. We proposed a temporal-spatial interpolation and rule-based (TSIRB) approach on the Google Earth Engine, which aims to achieve automatic water extraction and bimonthly sequence construction of lake area. There are three main steps of this method which include bimonthly image sequence construction, automatic water extraction, and anomaly rectification. We applied the TSIRB method to five typical lakes (covering salt lakes, river lagoons, and plateau alpine lakes), and constructed the bimonthly surface water dataset (BSWD) from 1987 to 2020. The accuracy assessment that was based on a confusion matrix and random sampling showed that the average overall accuracy (OA) of water extraction was 96.6%, and the average Kappa was 0.90. The BSWD sequence was compared with the lake water level observation data, and the results show that the BSWD data is closely correlated with the water level observation sequence, with correlation coefficient greater than 0.87. The BSWD improves the hollows in the global surface water (GSW) monthly data and has advantages in the temporal continuity of surface water data. The BSWD can provide a 30-m-scale and bimonthly series of surface water for more than 30 years, which shows good value for the long-term dynamic monitoring of lakes, especially in areas that are lacking in situ surveying data.

Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm.

Background and Objectives: Polysomnography is manually scored by sleep experts. However, manual scoring is a time-consuming and labor-intensive task. The goal of this study was to verify the accuracy of automated sleep-stage scoring based on a deep learning algorithm compared to manual sleep-stage scoring. Materials and Methods: A total of 602 polysomnography datasets from subjects (Male:Female = 397:205) aged 19 to 65 years (mean age, 43.8, standard deviation = 12.2) were included in the study. The performance of the proposed model was evaluated based on kappa value and bootstrapped point-estimate of median percent agreement with a 95% bootstrap confidence interval and R = 1000. The proposed model was trained using 482 datasets and validated using 48 datasets. For testing, 72 datasets were selected randomly. Results: The proposed model exhibited good concordance rates with manual scoring for stages W (94%), N1 (83.9%), N2 (89%), N3 (92%), and R (93%). The average kappa value was 0.84. For the bootstrap method, high overall agreement between the automated deep learning algorithm and manual scoring was observed in stages W (98%), N1 (94%), N2 (92%), N3 (99%), and R (98%) and total (96%). Conclusions: Automated sleep-stage scoring using the proposed model may be a reliable method for sleep-stage classification.

Motor Imagery Classification via Kernel-Based Domain Adaptation on an SPD Manifold.

Background: Recording the calibration data of a brain–computer interface is a laborious process and is an unpleasant experience for the subjects. Domain adaptation is an effective technology to remedy the shortage of target data by leveraging rich labeled data from the sources. However, most prior methods have needed to extract the features of the EEG signal first, which triggers another challenge in BCI classification, due to small sample sets or a lack of labels for the target. Methods: In this paper, we propose a novel domain adaptation framework, referred to as kernel-based Riemannian manifold domain adaptation (KMDA). KMDA circumvents the tedious feature extraction process by analyzing the covariance matrices of electroencephalogram (EEG) signals. Covariance matrices define a symmetric positive definite space (SPD) that can be described by Riemannian metrics. In KMDA, the covariance matrices are aligned in the Riemannian manifold, and then are mapped to a high dimensional space by a log-Euclidean metric Gaussian kernel, where subspace learning is performed by minimizing the conditional distribution distance between the sources and the target while preserving the target discriminative information. We also present an approach to convert the EEG trials into 2D frames (E-frames) to further lower the dimension of covariance descriptors. Results: Experiments on three EEG datasets demonstrated that KMDA outperforms several state-of-the-art domain adaptation methods in classification accuracy, with an average Kappa of 0.56 for BCI competition IV dataset IIa, 0.75 for BCI competition IV dataset IIIa, and an average accuracy of 81.56% for BCI competition III dataset IVa. Additionally, the overall accuracy was further improved by 5.28% with the E-frames. KMDA showed potential in addressing subject dependence and shortening the calibration time of motor imagery-based brain–computer interfaces.

Large-Scale Surface Water Mapping Based on Landsat and Sentinel-1 Images

Surface water is a highly dynamical object on the earth’s surface. At present, satellite remote sensing is the most effective way to accurately depict the temporal and spatial variation characteristics of surface water on a large scale. In this study, a region-adaptive random forest algorithm is designed on the Google Earth Engine (GEE) for automatic surface water mapping by using data from multi-sensors such as Landsat 7 ETM+, Landsat 8 OLI, and Sentinel-1 SAR images as source data, and China as a case study region. The visual comparison of the mapping results with the original images under different landform areas shows that the extracted water body boundary is consistent with the water range in the image. The cross-validation with the JRC GSW validation samples shows a very high precision that the average producer’s accuracy and average user’s accuracy of water is 0.933 and 0.998, respectively. The average overall accuracy and average kappa is 0.966 and 0.931, respectively. The independent verification results of lakes with different areas also prove the high accuracy for our method, with a maximum average error of 3.299%. These results show that the method is an ideal way for large-scale surface water mapping with a high spatial–temporal resolution.

Sleep Monitoring Using Ear-Centered Setups: Investigating the Influence From Electrode Configurations.

Among candidate positions, those in the facial area and around the ears have the benefit of being relatively hairless, and in our view deserve extra attention. In this paper, we seek to determine the limits to sleep monitoring quality within this spatial constraint. We compare 13 different, realistic sensor setups derived from the same data set and analysed with the same pipeline. All setups which include both a lateral and an EOG derivation show similar, state-of-the-art performance, with average Cohen's kappa values of at least 0.80. If large electrode distances are used, positioning is not critical for achieving large sleep-related signal-to-noise-ratio, and hence accurate sleep scoring. We argue that with the current competitive performance of automated staging approaches, there is a need for establishing an improved benchmark beyond current single human rater scoring.

ASTERI: image-based representation of EEG signals for motor imagery classification

PurposeElectroencephalography (EEG) signals are valuable in the monitoring and investigation of neurological diseases and in the control of brain-machine interfaces (BCI). However, these signals are noisy and are non-linear and non-stationary in nature. Signal analysis is an expensive task and can lead to misdiagnosis. Deep learning can be used to overcome these challenges. The most used deep architectures are based on convolutional neural networks (CNNs). Representing EEG signals as images can be useful to use deep architectures based on CNNs in solutions based on intelligent EEG-based systems.MethodsIn this work, we propose the ASTERI method, for representing EEG signals in two dimensions using the backprojection reconstruction method. To validate the proposal, experiments were performed with motor imagery EEG signals from the BCI Competition IV 2b motor imagery database. To extract attributes from the EEG signal windows, we used the ASTERI representation and investigated the pre-trained networks VGG16 and LeNet. To classify the final classification of imagined movements to the right and to the left, we used Random Forests.ResultsFor the original database, the validation with 100 trees achieved an average accuracy and kappa index of 88.97% and 0.78, respectively. In the case of augmented databases with synthetic instances, the average accuracies were 89.10% and 89.13% for increases of 50% and 150% for each class, respectively.ConclusionThe experimental results showed that the ASTERI method, together with hybrid deep architectures based on CNN and Random Forests, can generate competitive results in solving motor imagery problems. The representation of signals as images can also contribute to the exploration of new solutions of applied neuroscience problems based on deep architectures.

Using artificial intelligence reading label system in diabetic retinopathy grading training of junior ophthalmology residents and medical students

PurposeEvaluate the efficiency of using an artificial intelligence reading label system in the diabetic retinopathy grading training of junior ophthalmology resident doctors and medical students.MethodsLoading 520 diabetic retinopathy patients’ colour fundus images into the artificial intelligence reading label system. Thirteen participants, including six junior ophthalmology residents and seven medical students, read the images randomly for eight rounds. They evaluated the grading of images and labeled the typical lesions. The sensitivity, specificity, and kappa scores were determined by comparison with the participants’ results and diagnosis gold standards.ResultsThrough eight rounds of reading, the average kappa score was elevated from 0.67 to 0.81. The average kappa score for rounds 1 to 4 was 0.77, and the average kappa score for rounds 5 to 8 was 0.81. The participants were divided into two groups. The participants in Group 1 were junior ophthalmology resident doctors, and the participants in Group 2 were medical students. The average kappa score of Group 1 was elevated from 0.71 to 0.76. The average kappa score of Group 2 was elevated from 0.63 to 0.84.ConclusionThe artificial intelligence reading label system is a valuable tool for training resident doctors and medical students in performing diabetic retinopathy grading.

Reliability and Repeatability of the China-Japan Friendship Hospital Typing Classification for Nontraumatic Osteonecrosis of the Femoral Head.

The purpose of this study was to analyze the interobserver reliability and intraobserver repeatability of the China-Japan Friendship Hospital (CJFH) typing classification system for nontraumatic osteonecrosis of the femoral head (ONFH). Image data of 50 hips were randomly selected in 289 patients (433 hips) with ONFH who underwent treatment in the China-Japan Friendship Hospital from 2012 to 2016. Bilateral hip plain radiography, magnetic resonance imaging (MRI), or computerized tomography (CT) were performed in all hips. The assessments were performed by 8 new residents independently, and the repeatability was assessed at 4-week intervals. Evaluation indicators included the size, location, and extent of necrotic lesions. Kappa values were used to determine the reliability and repeatability. According to the CJFH classification system, 2,800 evaluations were performed with an average interobserver Kappa value of 0.711, and 400 assessments were performed with an average intraobserver Kappa value of 0.748. Reliability analysis indicated a higher reliability and repeatability of this classification system. Critical factors affecting the consistency included the accurate selection of the median coronal plane and definitive tri-pillar division of the femoral head. The CJFH classification system is a simple and direct evaluation model for ONFH with substantial inter- and intraobserver reliability.