Irbm最新文献

Objective

In ophthalmology, there is a need to explore the relationships between clinical parameters of the cornea and the corneal shape. This study explores the paradigm of machine learning with nonlinear regression methods to verify whether corneal shapes can effectively be predicted from clinical data only, in an attempt to better assess and visualize their effects on the corneal shape.

Methods

The dimensionality of a database of normal anterior corneal surfaces was first reduced by Zernike modeling into short vectors of 12 to 20 coefficients used as targets. The associated structural, refractive and demographic corneal parameters were used as predictors. The nonlinear regression methods were borrowed from the scikit-learn library. All possible regression models (method + predictors + targets) were pre-tested in an exploratory step and those that performed better than linear regression were fully tested with 10-fold validation. The best model was selected based on mean RMSE scores measuring the distance between the predicted corneal surfaces of a model and the raw (non-modeled) true surfaces. The quality of the best model's predictions was visually assessed thanks to atlases of average elevation maps that displayed the centroids of the predicted and true surfaces on a number of clinical variables.

Results

The best model identified was gradient boosting regression using all available clinical parameters to predict 16 Zernike coefficients. The predicted and true corneal surfaces represented in average elevation maps were remarkably similar. The most explicative predictor was the radius of the best-fit sphere, and departures from that sphere were mostly explained by the eye side and by refractive parameters (axis and cylinder).

Conclusion

It is possible to make a reasonably good prediction of the normal corneal shape solely from a set of clinical parameters. In so doing, one can visualize their effects on the corneal shape and identify its most important contributors.

Background

The global prevalence of autism spectrum disorder (ASD) is around 1%. Yet the current diagnosis of ASD mainly depends on clinicians' experience and caregivers' report, which are subjective, time consuming, and labor demanding. An objective and efficient way to diagnose ASD is urgently needed. The objective of this study was to quantify an omnipresent yet least studied behavioral characteristic in children with ASD – interpersonal motor coordination (IMC), and to investigate the feasibility of using IMC related features to identify ASD by implementing machine learning algorithms.

Methods

Twenty children with ASD and twenty-three children with typical development (TD) were filmed in a conversation with an interviewer. Motion energy analysis was implemented to obtain the movement time series, and cross wavelet analysis (CWA) quantified the level of IMC at different movement frequencies. Machine learning algorithms were utilized to examine whether these two groups of children could be accurately classified using features of IMC.

Results

Statistical analysis revealed reduced IMC in the ASD group at relatively high movement frequencies. The establishment of machine learning (ML) models showed that the maximum classification accuracy was 85.37% (specificity = 95.24%, sensitivity = 75.00%) using five original coherence values computed with CWA. In addition, the classification accuracy could be improved to 92.68% (specificity = 95.24%, sensitivity = 90.00%) with three novel features created by taking the sum of statistically significant features.

Conclusions

Children with ASD demonstrated an atypical profile of IMC, and IMC could be used to objectively classify children with ASD and TD. In addition, our analyses showed that creating novel features based on statistically significant features could help improve classification performance. It is proposed that such economic, contactless, and calibration-free approach to data collection might well serve both ASD research and practice, particularly early objective identification. However, this study could be improved with respect to larger sample size with balanced gender ratio and different severity.

Objectives

Segmentation of cranial bones in magnetic resonance images (MRIs) is a challenging and indispensable task to study neonatal brain development and injury. This paper presents a new approach for creating subject-specific probability maps of the scalp, skull and cerebrospinal fluid (CSF) from retrospective bimodal (MR and CT) images acquired from neonates in the gestational age range of 39 to 42 weeks. These maps are subsequently employed for the segmentation of cranial bones in cerebral MRIs from neonates in the same age range.

Material and methods

Retrospective MR and CT of neonates with normal head in the gestational age range of 39-42 weeks were preprocessed, segmented semi-automatically and employed as atlas data. For an input MR image acquired from a subject under study, a preprocessing stage and three main processing blocks were performed: First, subject-specific head and intracranial templates and CSF probability map were created using retrospective MR atlas data. Second, the CT atlas data were coregistered to MR templates and the resulted deformation matrices were fed to the next block to create subject-specific scalp and skull probability maps. Finally, some novel performance measures were presented to evaluate the performance of subject-specific CSF, scalp and skull probability maps for skull and intracranial segmentation in neonatal MRIs.

Results

The subject-specific probability maps were employed for brain tissue extraction and compared with two public methods such as Brain Extraction Tool (BET) and Brain Surface Extractor (BSE). They were also applied for cranial bone extraction. Then, the similarity in shape between the frontal and occipital sutures (which had been reconstructed from segmented cranial bones) and the ground truth landmarks was evaluated. For this purpose, modified versions of the Dice similarity coefficient (DSC) were used. Finally, a retrospective bimodal (MR-CT) data acquired from a neonate within a short time interval was used for evaluation. After co-alignment of the two images, the DSC and modified Hausdorff distance (MHD) were used to compare the similarity of cranial bones in the MR and CT images.

Conclusion

Significant improvements were achieved compared to conventional methods which rely solely on MR image intensities. These advancements hold promise for enhancing neurodevelopmental studies in neonates. The algorithm for creating subject-specific atlases is publicly accessible through a graphical user interface at medvispy.ee.kntu.ac.ir.

Introduction

Neonatal seizure is a common neurologic disorder in neonates. The diagnosis of a neonatal seizure can be made clinically or with an EEG. However, the clinical diagnosis of neonatal seizures is difficult, particularly in critically ill infants, because of the multitude of epileptic and nonepileptic clinical manifestations. On the other hand neonatal seizure can be effectively detected using EEG recordings. Hence, there is a need for an electroencephalograph (EEG) based automatic diagnosis framework for neonatal seizure.

Methods

This work proposed a wavelet scattering transform (WST) and histogram-based nearest component analysis (HBNCA) based framework for classifying seizures and non-seizure neonate's EEG signals. The WST converts EEG signals into its translation invariant and deformation stable representation. The HBNCA method is deployed to find the effective wavelet scattering coefficients (WSC) for classifying seizures and non-seizures EEG signals. Then, various classifiers are used to identify the effectiveness of the features.

Results

The proposed framework is managed to get an average accuracy of 98.59% and 97.83% for a 1-second duration of EEG signal for repeated random subsampling validation (RRSV) and leave one out cross-validation (LOOCV), respectively.

Conclusions

The results are compared with the other state of art methods. The accurate classification from the 1-second duration of the EEG signal shows the potential of the proposed framework for reliable neonatal seizure classification.

1) Introduction: Preterm labor (PL) has globally become the leading cause of death in children under the age of 5 years. One of the most significant keys to preventing preterm labor is its early detection. 2) Objectives: The primary objectives of this study are to address the problem of PL by providing a new approach by analyzing the electrohysterographic (EHG) signals, which are recorded on the mother's abdomen during labor and pregnancy. 3) Methods: The EHG signal reflects the electrical activity that induces the mechanical contraction of the myometrium. Because EHGs are known to be non-stationary signals, and because we anticipate connectivity to alter during contraction (due to electrical diffusion and the mechanotransduction process), we applied the windowing approach on real signals to identify the best windows and the best nodes with the most significant data to be used for classification. The suggested pipeline includes: i) dividing the 16 EHG signals that are recorded from the abdomen of pregnant women in N windows; ii) apply the connectivity matrices on each window; iii) apply the Graph theory-based measures on the connectivity matrices on each window; iv) apply the consensus Matrix on each window in order to retrieve the best windows and the best nodes. Following that, several neural network and machine learning methods are applied to the best windows and best nodes to categorize pregnancy and labor contractions, based on the different input parameters (connectivity method alone, connectivity method plus graph parameters, best nodes, all nodes, best windows, all windows). 4) Results: Results showed that the best nodes are nodes 8, 9, 10, 11, and 12; while the best windows are 2, 4, and 5. The classification results obtained by using only these best nodes are better than when using the whole nodes. The results are always better when using the full burst, whatever the chosen nodes. 5) Conclusion: The windowing approach proved to be an innovative technique that can improve the differentiation between labor and pregnancy EHG signals.

Context

Deep learning algorithms have been widely used for cardiac image segmentation. However, most of these architectures rely on convolutions that hardly model long-range dependencies, limiting their ability to extract contextual information. Moreover, the traditional U-net architecture suffers from the difference of semantic information between feature maps of the encoder and decoder (also known as the semantic gap).

Material and method

To address this issue, a new network architecture relying on attention mechanism was introduced. Swin Filtering Blocks (SFB), that use Swin Transformer blocks in a cross-attention manner, were added between the encoder and the decoder to filter information coming from the encoder based on the feature map from the decoder. Attention was also employed at the lowest resolution in the form of a transformer layer to increase the receptive field of the network.

We conducted experiments to assess both generalization capability and to evaluate how training on all frames of the cardiac cycle rather than only the end-diastole and end-systole impacts strain and segmentation performances.

Results and conclusion

Visual inspection of feature maps suggested that Swin Filtering Blocks contribute to the reduction of the semantic gap. Performing attention between all patches using a transformer layer brought higher performance than convolutions. Training the model with all phases of the cardiac cycle resulted in slightly more accurate segmentations while leading to a more noticeable improvement for strain estimation. A limited decrease in performance was observed when testing on out-of-distribution data, but the gap widens for the most apical slices.

Background

Emotion assessment plays a vital role in understanding and enhancing various aspects of human life, from mental well-being and social interactions to decision-making processes. Electrodermal Activity (EDA) is widely used for emotion assessment, as it is highly sensitive to sympathetic nervous system activity. While numerous existing approaches are available for EDA-based emotion assessment, they often fall short in capturing the dynamic non-linear variations and time-varying characteristics of EDA. These limitations hinder their effectiveness in accurately classifying emotional states along the Arousal and Valence dimensions. This study aims to address these shortcomings by introducing Transition Network Analysis (TNA) as a novel approach to EDA-based emotion assessment.

Methods

To explore the dynamic non-linear variations in EDA and their impact on the classification of Arousal and Valence dimensions, we decomposed EDA data into its phasic and tonic components. The phasic information is represented over a transition network. From the transition network, we extracted seven features. These features were subsequently used for classification purposes employing four different machine learning classifiers: logistic regression, multi-layer perceptron, random forest, and support vector machine (SVM). The performance of each classifier was evaluated using Leave-One-Subject-Out cross-validation. The study evaluated the performance of these classifiers in characterizing emotional dimensions.

Results

The results of this research reveal significant variations in Degree Centrality and Closeness Centrality within the transition network features, enabling effective characterization of Arousal and Valence dimensions. Among the classifiers, the SVM achieved F1 scores of 71% and 72% for Arousal and Valence classification, respectively.

Significance

This study holds significant implications as it not only enhances our understanding of EDA's non-linear dynamics but also demonstrates the potential of TNA in addressing the limitations of existing techniques for EDA-based emotion assessment. The findings open exciting opportunities for the advancement of wearable EDA monitoring devices in naturalistic settings, bridging a critical gap in the field of affective computing. Furthermore, this research underlines the importance of recognizing the limitations in current EDA-based emotion assessment methods and suggests an innovative path forward in the pursuit of more accurate and comprehensive emotional state classification.

Objective

This study aims to evaluate the impact of image factors on the performance of deep learning models used for ophthalmic ultrasound image diagnosis.

Methods

A total of 3,373 ophthalmic ultrasound images are used to deeply evaluate the influence of image factors on the performance of deep learning classification models. Inceptionv3, Xception, and the fusion model Inceptionv3-Xception are used to explore how brightness, contrast, gain, noise, size, format, pseudo-color seven image-related factors affect the classification performance of the model.

Results

Inceptionv3-Xception has advantages in the recognition accuracy of various image factors. When the image brightness changes, the model's performance shows a downward trend (0.5 vs. 1 vs. 1.8, ACC 95.73 vs. 97.06 vs. 93.54, P < 0.05). When the image contrast changes, the model's performance is comparable (0.5 vs. 1 vs. 1.2, ACC 96.23 vs. 96.95 vs. 97.45, P > 0.05). When the image gain drops to 50 dB, the model's accuracy decreases significantly (50 dB vs. 105 dB, ACC 96.49 vs. 97.57, P < 0.05). When Gaussian noise is added to the image, the model's performance gradually decreases (0.02 vs. 0, ACC 89.48vs97.06, P < 0.05). When the image size drops to 25% of the original image, the model's performance decreases significantly (25% vs. 100%, ACC 93.18 vs. 97.06, P < 0.01). When the image format changes, the model's recognition accuracy is similar (JPG vs. BMP vs. PNG, ACC 96.98 vs. 97.06 vs. 97.06, P > 0.05). The accuracy of the model in recognizing pseudo-color images decreases significantly compared to grayscale images (grayscale vs. pseudo-color, ACC 35.96 vs. 97.06).

Conclusion

These results indicate that image quality greatly influences the model training process, and acquiring high-quality images is an important prerequisite for high recognition performance of the model. This study offers valuable insights for the improvement of other robust deep learning models for ophthalmic ultrasound image recognition.

Objectives

This paper is proposed to identify both promising technologies and potential products in the domain of biosensor using patent-based Technology-Driven Technology Roadmaps (TRM).

Materials and methods

The technology-driven TRM with timelines in this study is developed in three layers: technology, function and product. Patent applications are collected and identified to interpret technologies and functions for biosensors in healthcare, and product manuals or releases can be used as product introductions.

Results

Most biosensors in healthcare patents are concentrated in biochemical (T2) and electroencephalography (T5). Glycated hemoglobin (F1), measuring of glucose (F3), and biological process and molecular systems (F6) have a relatively larger patent count. Biochemical (T2) can combine with biological process and molecular systems (F6), and then brain's real-time electrical activity monitoring can be handled. Biochemical (T2) can also devote to glycated hemoglobin (F1), and glucose monitoring (F3), and thus create QCM sensor, CGM and GlucoWatch etc. applications.

Conclusion

Biochemical (T2) has a wide application among different functions for wearable biosensors in healthcare. This paper identifies and explores new developments biochemical (T2), and electroencephalography (T5) in wearable biosensors are expected to play a significant role over the coming decade in improving the current healthcare infrastructure, and enhancing the democratization of information and allocation of medical resources.