Validation of a Deep Learning-based Automatic Detection Algorithm for Measurement of Endotracheal Tube-to-Carina Distance on Chest Radiographs.

BACKGROUND: Improper endotracheal tube (ETT) positioning is frequently observed and potentially hazardous in the intensive care unit. The authors developed a deep learning-based automatic detection algorithm detecting the ETT tip and carina on portable supine chest radiographs to measure the ETT-carina distance. This study investigated the hypothesis that the algorithm might be more accurate than frontline critical care clinicians in ETT tip detection, carina detection, and ETT-carina distance measurement. METHODS: A deep learning-based automatic detection algorithm was developed using 1,842 portable supine chest radiographs of 1,842 adult intubated patients, where two board-certified intensivists worked together to annotate the distal ETT end and tracheal bifurcation. The performance of the deep learning-based algorithm was assessed in 4-fold cross-validation (1,842 radiographs), external validation (216 radiographs), and an observer performance test (462 radiographs) involving 11 critical care clinicians. The performance metrics included the errors from the ground truth in ETT tip detection, carina detection, and ETT-carina distance measurement. RESULTS: During 4-fold cross-validation and external validation, the median errors (interquartile range) of the algorithm in ETT-carina distance measurement were 3.9 (1.8 to 7.1) mm and 4.2 (1.7 to 7.8) mm, respectively. During the observer performance test, the median errors (interquartile range) of the algorithm were 2.6 (1.6 to 4.8) mm, 3.6 (2.1 to 5.9) mm, and 4.0 (1.7 to 7.2) mm in ETT tip detection, carina detection, and ETT-carina distance measurement, significantly superior to that of 6, 10, and 7 clinicians (all P < 0.05), respectively. The algorithm outperformed 7, 3, and 0, 9, 6, and 4, and 5, 5, and 3 clinicians (all P < 0.005) regarding the proportions of chest radiographs within 5 mm, 10 mm, and 15 mm error in ETT tip detection, carina detection, and ETT-carina distance measurement, respectively. No clinician was significantly more accurate than the algorithm in any comparison. CONCLUSIONS: A deep learning-based algorithm can match or even outperform frontline critical care clinicians in ETT tip detection, carina detection, and ETT-carina distance measurement.

Segmentation of finger tendon and synovial sheath in ultrasound image using deep convolutional neural network.

BACKGROUND: Trigger finger is a common hand disease, which is caused by a mismatch in diameter between the tendon and the pulley. Ultrasound images are typically used to diagnose this disease, which are also used to guide surgical treatment. However, background noise and unclear tissue boundaries in the images increase the difficulty of the process. To overcome these problems, a computer-aided tool for the identification of finger tissue is needed. RESULTS: Two datasets were used for evaluation: one comprised different cases of individual images and another consisting of eight groups of continuous images. Regarding result similarity and contour smoothness, our proposed deeply supervised dilated fully convolutional DenseNet (D2FC-DN) is better than ATASM (the state-of-art segmentation method) and representative CNN methods. As a practical application, our proposed method can be used to build a tendon and synovial sheath model that can be used in a training system for ultrasound-guided trigger finger surgery. CONCLUSION: We proposed a D2FC-DN for finger tendon and synovial sheath segmentation in ultrasound images. The segmentation results were remarkably accurate for two datasets. It can be applied to assist the diagnosis of trigger finger by highlighting the tissues and generate models for surgical training systems in the future. METHODS: We propose a novel finger tendon segmentation method for use with ultrasound images that can also be used for synovial sheath segmentation that yields a more complete description for analysis. In this study, a hybrid of effective convolutional neural network techniques are applied, resulting in a deeply supervised dilated fully convolutional DenseNet (D2FC-DN), which displayed excellent segmentation performance on the tendon and synovial sheath.

Dielectrophoresis System for Testing Antimicrobial Susceptibility of Gram-Negative Bacteria to ß-Lactam Antibiotics.

Gram-negative bacteria (GNBs) are common pathogens causing severe sepsis. Rapid evaluation of drug susceptibility would guide effective antibiotic treatment and promote life-saving. A total of 78 clinical isolates of 13 Gram-negative species collected between April 2013 and November 2013 from two medical centers in Tainan were tested. Bacterial morphology changes in different concentrations of antibiotics were observed under the electric field of a quadruple electrode array using light microscopy. The minimal inhibitory concentrations (MICs) of four antimicrobial agents, namely, cefazolin, ceftazidime, cefepime, and doripenem, were determined by the dielectrophoretic antimicrobial susceptibility testing (dAST) and by the conventional broth dilution testing (BDT). The antibiotics at the concentration of 1× MIC induced obvious morphological changes in susceptible GNBs, including cell elongation, cell swelling, or lysis, at 90 min. In contrast, resistant strains remained unchanged. The MIC results measured by dAST were in good agreement with those of BDT (essential agreement 95.6%). The category agreement rate was 89.2%, and the very major errors rate for dAST was 2.9%. In conclusion, dAST could accurately determine drug susceptibility within 90 min. Comprehensive tests by dAST for more drugs against more GNB species are possible in the future.

Tendon-motion tracking in an ultrasound image sequence using optical-flow-based block matching.

BACKGROUND: Tendon motion, which is commonly observed using ultrasound imaging, is one of the most important features used in tendinopathy diagnosis. However, speckle noise and out-of-plane issues make the tracking process difficult. Manual tracking is usually time consuming and often yields inconsistent results between users. METHODS: To automatically track tendon motion in ultrasound images, we developed a new method that combines the advantages of optical flow and multi-kernel block matching. For every pair of adjacent image frames, the optical flow is computed and used to estimate the accumulated displacement. The proposed method selects the frame interval adaptively based on this displacement. Multi-kernel block matching is then computed on the two selected frames, and, to reduce tracking errors, the detailed displacements of the frames in between are interpolated based on the optical flow results. RESULTS: In the experiments, cadaver data were used to evaluate the tracking results. The mean absolute error was less than 0.05 mm. The proposed method also tracked the motion of tendons in vivo, which provides useful information for clinical diagnosis. CONCLUSION: The proposed method provides a new index for adaptively determining the frame interval. Compared with other methods, the proposed method yields tracking results that are significantly more accurate.

Finger movement function after ultrasound-guided percutaneous pulley release for trigger finger: effects of postoperative rehabilitation.

OBJECTIVE: To develop and test a postoperative rehabilitation protocol for use by individuals with trigger finger undergoing ultrasound-guided percutaneous pulley release. DESIGN: Nonrandomized controlled trial. SETTING: Hospital and local community. PARTICIPANTS: Individuals suffering from trigger finger with joint contracture (N=21) were recruited and grouped into an intervention group (n=9) or a control group (n=12). INTERVENTIONS: All the participants underwent the same surgical procedure performed by the same surgeon. A 4-week postoperative rehabilitation program was designed based on the wound healing process. The intervention group received postoperative rehabilitation after the surgery, whereas the control group received no treatment after the surgery. MAIN OUTCOME MEASURES: The finger movement functions were quantitatively evaluated before and 1 month after the surgery using a 3-dimensional motion capture system. The fingertip workspace and joint range of motion (ROM) were evaluated while the participant was performing a sequential 5-posture movement, including finger extension, intrinsic plus, straight fist, full fist, and hook fist. RESULTS: The intervention group demonstrated significantly more improvements than the control group in the fingertip workspace (49% vs 17%), ROM of the distal interphalangeal (DIP) joint (16% vs 4%), ROM of the proximal interphalangeal (PIP) joint (21% vs 5%), and total active ROM (17% vs 5%). CONCLUSIONS: This pilot study evaluated a postoperative rehabilitation protocol for trigger finger and demonstrated its effects on various finger functions. Participants who underwent the rehabilitation program had significantly more improvements in the fingertip workspace, ROM of the DIP and PIP joints, and total active ROM.

Clinical and pathological correlates of severity classifications in trigger fingers based on computer-aided image analysis.

BACKGROUND: The treatment of trigger finger so far has heavily relied on clinicians' evaluations for the severity of patients' symptoms and the functionality of affected fingers. However, there is still a lack of pathological evidence supporting the criteria of clinical evaluations. This study's aim was to correlate clinical classification and pathological changes for trigger finger based on the tissue abnormality observed from microscopic images. METHODS: Tissue samples were acquired, and microscopic images were randomly selected and then graded by three pathologists and two physicians, respectively. Moreover, the acquired images were automatically analyzed to derive two quantitative parameters, the size ratio of the abnormal tissue region and the number ratio of the abnormal nuclei, which can reflect tissue abnormality caused by trigger finger. A self-developed image analysis system was used to avoid human subjectivity during the quantification process. Finally, correlations between the quantitative image parameters, pathological grading, and clinical severity classification were assessed. RESULTS: One-way ANOVA tests revealed significant correlations between the image quantification and pathological grading as well as between the image quantification and clinical severity classification. The Cohen's kappa coefficient test also depicted good consistency between pathological grading and clinical severity classification. CONCLUSIONS: The criteria of clinical classification were found to be highly associated with the pathological changes of affected tissues. The correlations serve as explicit evidence supporting clinicians in making a treatment strategy of trigger finger. In addition, our proposed computer-aided image analysis system was considered to be a promising and objective approach to determining trigger finger severity at the microscopic level.

Assessments of polymerization shrinkage by optical coherence tomography-based digital image correlation analysis-Part I: Parameter identification.

OBJECTIVE: To investigate the feasibility of optical coherence tomography (OCT)-based digital image correlation (DIC) analysis and to identify the experimental parameters for measurements of polymerization shrinkage. METHODS: Class I cavities were prepared on bovine incisors and filled with Filtek Z350XT Flowable (Z350F). One OCT image of the polymerized restoration was processed to generate virtually displaced images. In addition, the tooth specimen was physically moved under OCT scanning. A DIC software analyzed these virtual and physical transformation sets and assessed the effects of subset sizes on accuracy. The refractive index of unpolymerized and polymerized Z350F was measured via OCT images. Finally, different particles (70-80 µm glass beads, 150-212 µm glass beads, and 75-150 µm zirconia powder) were added to Z350F to inspect the analyzing quality. RESULTS: The analyses revealed a high correlation (>99.99%) for virtual movements within 131 pixels (639 µm) and low errors (<5.21%) within a 10-µm physical movement. A subset size of 51 × 51 pixels demonstrated the convergence of correlation coefficients and calculation time. The refractive index of Z350F did not change significantly after polymerization. Adding glass beads or zirconia particles caused light reflection or shielding in OCT images, whereas blank Z350F produced the best DIC analysis results. SIGNIFICANCE: The OCT-based DIC analysis with the experimental conditions is feasible in measuring polymerization shrinkage of RBC restorations. The subset size in the DIC analysis should be identified to optimize the analysis conditions and results. Uses of hyper- or hypo-reflective particles is not recommended in this method.

Model-based spike detection of epileptic EEG data.

Accurate automatic spike detection is highly beneficial to clinical assessment of epileptic electroencephalogram (EEG) data. In this paper, a new two-stage approach is proposed for epileptic spike detection. First, the k-point nonlinear energy operator (k-NEO) is adopted to detect all possible spike candidates, then a newly proposed spike model with slow wave features is applied to these candidates for spike classification. Experimental results show that the proposed system, using the AdaBoost classifier, outperforms the conventional method in both two- and three-class EEG pattern classification problems. The proposed system not only achieves better accuracy for spike detection, but also provides new ability to differentiate between spikes and spikes with slow waves. Though spikes with slow waves occur frequently in epileptic EEGs, they are not used in conventional spike detection. Identifying spikes with slow waves allows the proposed system to have better capability for assisting clinical neurologists in routine EEG examinations and epileptic diagnosis.

A knowledge-based approach for carpal tunnel segmentation from magnetic resonance images.

Carpal tunnel syndrome (CTS) has been reported as one of the most common peripheral neuropathies. Carpal tunnel segmentation from magnetic resonance (MR) images is important for the evaluation of CTS. To date, manual segmentation, which is time-consuming and operator dependent, remains the most common approach for the analysis of the carpal tunnel structure. Therefore, we propose a new knowledge-based method for automatic segmentation of the carpal tunnel from MR images. The proposed method first requires the segmentation of the carpal tunnel from the most proximally cross-sectional image. Three anatomical features of the carpal tunnel are detected by watershed and polygonal curve fitting algorithms to automatically initialize a deformable model as close to the carpal tunnel in the given image as possible. The model subsequently deforms toward the tunnel boundary based on image intensity information, shape bending degree, and the geometry constraints of the carpal tunnel. After the deformation process, the carpal tunnel in the most proximal image is segmented and subsequently applied to a contour propagation step to extract the tunnel contours sequentially from the remaining cross-sectional images. MR volumes from 15 subjects were included in the validation experiments. Compared with the ground truth of two experts, our method showed good agreement on tunnel segmentations by an average margin of error within 1 mm and dice similarity coefficient above 0.9.

Scaphoid Fracture Detection by Using Convolutional Neural Network.

Scaphoid fractures frequently appear in injury radiograph, but approximately 20% are occult. While there are few studies in the fracture detection of X-ray scaphoid images, their effectiveness is insignificant in detecting the scaphoid fractures. Traditional image processing technology had been applied to segment interesting areas of X-ray images, but it always suffered from the requirements of manual intervention and a large amount of computational time. To date, the models of convolutional neural networks have been widely applied to medical image recognition; thus, this study proposed a two-stage convolutional neural network to detect scaphoid fractures. In the first stage, the scaphoid bone is separated from the X-ray image using the Faster R-CNN network. The second stage uses the ResNet model as the backbone for feature extraction, and uses the feature pyramid network and the convolutional block attention module to develop the detection and classification models for scaphoid fractures. Various metrics such as recall, precision, sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC) are used to evaluate our proposed method's performance. The scaphoid bone detection achieved an accuracy of 99.70%. The results of scaphoid fracture detection with the rotational bounding box revealed a recall of 0.789, precision of 0.894, accuracy of 0.853, sensitivity of 0.789, specificity of 0.90, and AUC of 0.920. The resulting scaphoid fracture classification had the following performances: recall of 0.735, precision of 0.898, accuracy of 0.829, sensitivity of 0.735, specificity of 0.920, and AUC of 0.917. According to the experimental results, we found that the proposed method can provide effective references for measuring scaphoid fractures. It has a high potential to consider the solution of detection of scaphoid fractures. In the future, the integration of images of the anterior-posterior and lateral views of each participant to develop more powerful convolutional neural networks for fracture detection by X-ray radiograph is probably important to research.

Detecting Endotracheal Tube and Carina on Portable Supine Chest Radiographs Using One-Stage Detector with a Coarse-to-Fine Attention.

In intensive care units (ICUs), after endotracheal intubation, the position of the endotracheal tube (ETT) should be checked to avoid complications. The malposition can be detected by the distance between the ETT tip and the Carina (ETT-Carina distance). However, it struggles with a limited performance for two major problems, i.e., occlusion by external machine, and the posture and machine of taking chest radiographs. While previous studies addressed these problems, they always suffered from the requirements of manual intervention. Therefore, the purpose of this paper is to locate the ETT tip and the Carina more accurately for detecting the malposition without manual intervention. The proposed architecture is composed of FCOS: Fully Convolutional One-Stage Object Detection, an attention mechanism named Coarse-to-Fine Attention (CTFA), and a segmentation branch. Moreover, a post-process algorithm is adopted to select the final location of the ETT tip and the Carina. Three metrics were used to evaluate the performance of the proposed method. With the dataset provided by National Cheng Kung University Hospital, the accuracy of the malposition detected by the proposed method achieves 88.82% and the ETT-Carina distance errors are less than 5.333±6.240 mm.

Computer-Assisted System in Stress Radiography for Anterior Cruciate Ligament Injury with Correspondent Evaluation of Relevant Diagnostic Factors.

We sought to design a computer-assisted system measuring the anterior tibial translation in stress radiography, evaluate its diagnostic performance for an anterior cruciate ligament (ACL) tear, and assess factors affecting the diagnostic accuracy. Retrospective research for patients with both knee stress radiography and magnetic resonance imaging (MRI) at our institution was performed. A complete ACL rupture was confirmed on an MRI. The anterior tibial translations with four different methods were measured in 249 patients by the designed algorithm. The diagnostic accuracy of each method in patients with all successful measurements was evaluated. Univariate logistic regression analysis for factors affecting diagnostic accuracy of method four was performed. In the inclusive 249 patients, 177 patients (129 with completely torn ACLs) were available for analysis. Mean anterior tibial translations were significantly increased in the patients with a completely torn ACL by all four methods, with diagnostic accuracies ranging from 66.7% to 75.1%. The diagnostic accuracy of method four was negatively associated with the time interval between stress radiography and MRI as well as force-joint distance on stress view, and not significantly associated with age, gender, flexion angle, intercondylar distance, and force-joint angle. A computer-assisted system measuring the anterior tibial translation in stress radiography showed acceptable diagnostic performance of complete ACL injury. A shorter time interval between stress radiography and MRI as well as shorter force-joint distance were associated with higher diagnostic accuracy.

Cortical activation by tactile stimulation to face and anterior neck areas: an fMRI study with three analytic methods.

The main purpose of this study was to investigate the sensory cortical activation of the anterior neck region and the relationship between the neck and face representation areas. Functional MRI by blood oxygenation level dependent measurements was performed while tactile stimulation was applied to the face or neck area. Nonpainful tactile stimuli were manually delivered by an experimenter at a frequency of ∼1 Hz. Block (epoch) design was adopted with a block duration of 30 s and a whole run duration of 6 min. For each location, two runs were performed. After the image data were preprocessed, both parameteric and nonparametric methods were performed to test the group results. The results showed that (1) unilateral face or neck stimulation could elicit bilateral cortical activation, (2) mainly the face representation and face-hand junction areas, but not the conventional neck representation area, were activated by face or neck stimulation, and (3) the activation areas were larger when right face or neck was stimulated. In conclusion, the sensory cortical representation area of the anterior neck region was mainly at the junction of hand and face representation area and the activated area was larger when the right face or neck was stimulated.

Registration-based segmentation with articulated model from multipostural magnetic resonance images for hand bone motion animation.

PURPOSE: The quantitative measurements of hand bones, including volume, surface, orientation, and position are essential in investigating hand kinematics. Moreover, within the measurement stage, bone segmentation is the most important step due to its certain influences on measuring accuracy. Since hand bones are small and tubular in shape, magnetic resonance (MR) imaging is prone to artifacts such as nonuniform intensity and fuzzy boundaries. Thus, greater detail is required for improving segmentation accuracy. The authors then propose using a novel registration-based method on an articulated hand model to segment hand bones from multipostural MR images. METHODS: The proposed method consists of the model construction and registration-based segmentation stages. Given a reference postural image, the first stage requires construction of a drivable reference model characterized by hand bone shapes, intensity patterns, and articulated joint mechanism. By applying the reference model to the second stage, the authors initially design a model-based registration pursuant to intensity distribution similarity, MR bone intensity properties, and constraints of model geometry to align the reference model to target bone regions of the given postural image. The authors then refine the resulting surface to improve the superimposition between the registered reference model and target bone boundaries. RESULTS: For each subject, given a reference postural image, the proposed method can automatically segment all hand bones from all other postural images. Compared to the ground truth from two experts, the resulting surface image had an average margin of error within 1 mm (mm) only. In addition, the proposed method showed good agreement on the overlap of bone segmentations by dice similarity coefficient and also demonstrated better segmentation results than conventional methods. CONCLUSIONS: The proposed registration-based segmentation method can successfully overcome drawbacks caused by inherent artifacts in MR images and obtain more accurate segmentation results automatically. Moreover, realistic hand motion animations can be generated based on the bone segmentation results. The proposed method is found helpful for understanding hand bone geometries in dynamic postures that can be used in simulating 3D hand motion through multipostural MR images.

A motion compounding technique for speckle reduction in ultrasound images.

The quality of ultrasound images is usually influenced by speckle noise and the temporal decorrelation of the speckle patterns. To reduce the speckle noise, compounding techniques have been widely applied. Partially correlated images scanned on the same subject cross-section are combined to generate a compound image with improved image quality. However, the compounding technique might introduce image blurring if the transducer or the target moves too fast. This blurring effect becomes especially critical when assessing tissue deformation in clinical motion examinations. In this paper, an ultrasound motion compounding system is proposed to improve the quality of ultrasound motion sequences. The proposed motion compounding technique uses a hierarchical adaptive feature weighted motion estimation method to realign the frames before compounding. Each frame is first registered and warped to the reference frame before being compounded to reduce the speckle noise. Experimental results showed that the motion could be assessed accurately and better visualization could be achieved for the compound images, with improved signal-to-noise and contrast-to-noise ratios.

DeepNerve: A New Convolutional Neural Network for the Localization and Segmentation of the Median Nerve in Ultrasound Image Sequences.

Carpal tunnel syndrome commonly occurs in individuals working in occupations that involve use of vibrating manual tools or tasks with highly repetitive and forceful manual exertion. In recent years, carpal tunnel syndrome has been evaluated by ultrasound imaging that monitors median nerve movement. Conventional image analysis methods, such as the active contour model, are typically used to expedite automatic segmentation of the median nerve, but these usually suffer from an arduous manual intervention. We propose a new convolutional neural network framework for localization and segmentation of the median nerve, called DeepNerve, that is based on the U-Net model. DeepNerve integrates the characteristics of MaskTrack and convolutional long short-term memory to effectively locate and segment the median nerve. On the basis of experimental results, the proposed model achieved high performance and generated average Dice measurement, precision, recall and F-score values of 0.8975, 0.8912, 0.9119 and 0.9015, respectively. The segmentation results of DeepNerve were significantly improved in comparison with those of conventional active contour models. Additionally, the results of Student's t-test revealed significant differences in four deformation measurements of the median nerve, including area, perimeter, aspect ratio and circularity. We conclude that the proposed DeepNerve not only generates satisfactory results for localization and segmentation of the median nerve, but also creates more promising measurements for applications in clinical carpal tunnel syndrome diagnosis.

Automatic Fetal Middle Sagittal Plane Detection in Ultrasound Using Generative Adversarial Network.

BACKGROUND AND OBJECTIVE: In the first trimester of pregnancy, fetal growth, and abnormalities can be assessed using the exact middle sagittal plane (MSP) of the fetus. However, the ultrasound (US) image quality and operator experience affect the accuracy. We present an automatic system that enables precise fetal MSP detection from three-dimensional (3D) US and provides an evaluation of its performance using a generative adversarial network (GAN) framework. METHOD: The neural network is designed as a filter and generates masks to obtain the MSP, learning the features and MSP location in 3D space. Using the proposed image analysis system, a seed point was obtained from 218 first-trimester fetal 3D US volumes using deep learning and the MSP was automatically extracted. RESULTS: The experimental results reveal the feasibility and excellent performance of the proposed approach between the automatically and manually detected MSPs. There was no significant difference between the semi-automatic and automatic systems. Further, the inference time in the automatic system was up to two times faster than the semi-automatic approach. CONCLUSION: The proposed system offers precise fetal MSP measurements. Therefore, this automatic fetal MSP detection and measurement approach is anticipated to be useful clinically. The proposed system can also be applied to other relevant clinical fields in the future.

Convolutional Neural Network-Based Humerus Segmentation and Application to Bone Mineral Density Estimation from Chest X-ray Images of Critical Infants.

Measuring bone mineral density (BMD) is important for surveying osteopenia in premature infants. However, the clinical availability of dual-energy X-ray absorptiometry (DEXA) for standard BMD measurement is very limited, and it is not a practical technique for critically premature infants. Developing alternative approaches for DEXA might improve clinical care for bone health. This study aimed to measure the BMD of premature infants via routine chest X-rays in the intensive care unit. A convolutional neural network (CNN) for humeral segmentation and quantification of BMD with calibration phantoms (QRM-DEXA) and soft tissue correction were developed. There were 210 X-rays of premature infants evaluated by this system, with an average Dice similarity coefficient value of 97.81% for humeral segmentation. The estimated humerus BMDs (g/cm3; mean ± standard) were 0.32 ± 0.06, 0.37 ± 0.06, and 0.32 ± 0.09, respectively, for the upper, middle, and bottom parts of the left humerus for the enrolled infants. To our knowledge, this is the first pilot study to apply a CNN model to humerus segmentation and to measure BMD in preterm infants. These preliminary results may accelerate the progress of BMD research in critical medicine and assist with nutritional care in premature infants.

EEG-based motor imagery analysis using weighted wavelet transform features.

In this study, an electroencephalogram (EEG) analysis system for single-trial classification of motor imagery (MI) data is proposed. Feature extraction in brain-computer interface (BCI) work is an important task that significantly affects the success of brain signal classification. The continuous wavelet transform (CWT) is applied together with Student's two-sample t-statistics for 2D time-scale feature extraction, where features are extracted from EEG signals recorded from subjects performing left and right MI. First, we utilize the CWT to construct a 2D time-scale feature, which yields a highly redundant representation of EEG signals in the time-frequency domain, from which we can obtain precise localization of event-related brain desynchronization and synchronization (ERD and ERS) components. We then weight the 2D time-scale feature with Student's two-sample t-statistics, representing a time-scale plot of discriminant information between left and right MI. These important characteristics, including precise localization and significant discriminative ability, substantially enhance the classification of mental tasks. Finally, a correlation coefficient is used to classify the MI data. Due to its simplicity, it will enable the performance of our proposed method to be clearly demonstrated. Compared to a conventional 2D time-frequency feature and three well-known time-frequency approaches, the experimental results show that the proposed method provides reliable 2D time-scale features for BCI classification.

Cerebral control of winking before and after learning: An event-related fMRI study.

INTRODUCTION: The main purpose of this study was to investigate the cerebral areas responsible for winking by observing the activation pattern and learning effects on cerebral cortices by comparing differences in activation pattern during winking before and after learning. METHODS: Sixty-three subjects were recruited, including 22 (11 males; 11 females) who could wink bilaterally and 41 (14 males; 27 females) who could wink unilaterally. Event-related functional magnetic resonance was performed. The subjects were asked to blink and wink according to projected instructions as the events for image analysis. The activation pattern was obtained by contrasting with the baseline images without eyelid movements. Those who could only wink unilaterally were asked to train themselves to wink the other eye. For those who succeeded (n = 24), another imaging study was performed and the results were compared with those before training. RESULTS AND CONCLUSION: Left winking resulted in activation in the left frontal lobe, while right winking resulted in activation in bilateral frontal lobes with predominance on the right side. For the subjects capable of only winking unilaterally, learning to wink on the other side activated similar cortical areas to those in the subjects capable of bilateral winking without training.