Unsupervised classification of plethysmography signals with advanced visual representations.
Ontology highlight
ABSTRACT:
SUBMITTER: Germain T
PROVIDER: S-EPMC10242092 | biostudies-literature | 2023
REPOSITORIES: biostudies-literature
Publications
Unsupervised classification of plethysmography signals with advanced visual representations.
Germain Thibaut T Truong Charles C Oudre Laurent L Krejci Eric E
Frontiers in physiology 20230523
Ventilation is a simple physiological function that ensures the vital supply of oxygen and the elimination of CO<sub>2</sub>. The recording of the airflow through the nostrils of a mouse over time makes it possible to calculate the position of critical points, based on the shape of the signals, to compute the respiratory frequency and the volume of air exchanged. These descriptors only account for a part of the dynamics of respiratory exchanges. In this work we present a new algorithm that direc ...[more]
Similar Datasets
Project description:Infants are at risk for potentially life-threatening postoperative apnea (POA). We developed an Automated Unsupervised Respiratory Event Analysis (AUREA) to classify breathing patterns obtained with dual belt respiratory inductance plethysmography and a reference using Expectation Maximization (EM). This work describes AUREA and evaluates its performance. AUREA computes six metrics and inputs them into a series of four binary k-means classifiers. Breathing patterns were characterized by normalized variance, nonperiodic power, instantaneous frequency and phase. Signals were classified sample by sample into one of 5 patterns: pause (PAU), movement (MVT), synchronous (SYB) and asynchronous (ASB) breathing, and unknown (UNK). MVT and UNK were combined as UNKNOWN. Twenty-one preprocessed records obtained from infants at risk for POA were analyzed. Performance was evaluated with a confusion matrix, overall accuracy, and pattern specific precision, recall, and F-score. Segments of identical patterns were evaluated for fragmentation and pattern matching with the EM reference. PAU exhibited very low normalized variance. MVT had high normalized nonperiodic power and low frequency. SYB and ASB had a median frequency of respectively, 0.76Hz and 0.71Hz, and a mode for phase of 4o and 100o. Overall accuracy was 0.80. AUREA confused patterns most often with UNKNOWN (25.5%). The pattern specific F-score was highest for SYB (0.88) and lowest for PAU (0.60). PAU had high precision (0.78) and low recall (0.49). Fragmentation was evident in pattern events <2s. In 75% of the EM pattern events >2s, 50% of the samples classified by AUREA had identical patterns. Frequency and phase for SYB and ASB were consistent with published values for synchronous and asynchronous breathing in infants. The low normalized variance in PAU, was consistent with published scoring rules for pediatric apnea. These findings support the use of AUREA to classify breathing patterns and warrant a future evaluation of clinically relevant respiratory events.
| S-EPMC7485851 | biostudies-literature
Project description:Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.
| S-EPMC4041723 | biostudies-literature
Project description:IntroductionThis study evaluated the accuracy of motion signals extracted from video monitoring data to differentiate epileptic motor seizures in patients with drug-resistant epilepsy. 3D near-infrared video was recorded by the Nelli® seizure monitoring system (Tampere, Finland).Methods10 patients with 130 seizures were included in the training dataset, and 17 different patients with 98 seizures formed the testing dataset. Only seizures with unequivocal hyperkinetic, tonic, and tonic-clonic semiology were included. Motion features from the catch22 feature collection extracted from video were explored to transform the patients' videos into numerical time series for clustering and visualization.ResultsChanges in feature generation provided incremental discrimination power to differentiate between hyperkinetic, tonic, and tonic-clonic seizures. Temporal motion features showed the best results in the unsupervised clustering analysis. Using these features, the system differentiated hyperkinetic, tonic and tonic-clonic seizures with 91, 88, and 45% accuracy after 100 cross-validation runs, respectively. F1-scores were 93, 90, and 37%, respectively. Overall accuracy and f1-score were 74%.ConclusionThe selected features of motion distinguished semiological differences within epileptic seizure types, enabling seizure classification to distinct motor seizure types. Further studies are needed with a larger dataset and additional seizure types. These results indicate the potential of video-based hybrid seizure monitoring systems to facilitate seizure classification improving the algorithmic processing and thus streamlining the clinical workflow for human annotators in hybrid (algorithmic-human) seizure monitoring systems.
| S-EPMC10652877 | biostudies-literature
Project description:96 scATAC-seq samples generated for the retinoic acid-induced mESC differentiation at day 4.
2018-04-20 | GSE107651 | GEO
Project description:A low-cost quantitative continuous measurement of movements utilizes accelerometers to generate signal outputs to precisely record the positions of extremities during the performance of movements. This procedure can readily be accomplished with inexpensive materials constructed indivisuals throughout the world. The proposed protocol provides the framework for trained raters to assess the signal outputs by visual observation to generate objective measurements like the measurements of the actual movements. Expert raters can then remotely give quantitative suggestions for providers in underserved regions to utilize precision medicine to develop optimal treatment plans tailored to the specific needs of each individual. The proposed protocol lays the foundations for experts located in tertiary centers to provide optimal assessments of signal outputs generated remotely in underserved regions. This protocol provides the means to address gaps in current research including the dearth of objective measurements of movements utilizing automatic intelligence and machine learning to accurately and precisely analyze movement assessments. Future research will include the development of robotic tools to perform assessments and analyses of the movements of human beings to enhance the conduct of movement evaluations of people with Parkinson's disease and related conditions to apply precision medicine for optimal diagnostic and therapeutic interventions.
| S-EPMC9168139 | biostudies-literature
Project description:Infants recovering from anesthesia are at risk of life threatening Postoperative Apnea (POA). POA events are rare, and so the study of POA requires the analysis of long cardiorespiratory records. Manual scoring is the preferred method of analysis for these data, but it is limited by low intra- and inter-scorer repeatability. Furthermore, recommended scoring rules do not provide a comprehensive description of the respiratory patterns. This work describes a set of manual scoring tools that address these limitations. These tools include: (i) a set of definitions and scoring rules for 6 mutually exclusive, unique patterns that fully characterize infant respiratory inductive plethysmography (RIP) signals; (ii) RIPScore, a graphical, manual scoring software to apply these rules to infant data; (iii) a library of data segments representing each of the 6 patterns; (iv) a fully automated, interactive formal training protocol to standardize the analysis and establish intra- and inter-scorer repeatability; and (v) a quality control method to monitor scorer ongoing performance over time. To evaluate these tools, three scorers from varied backgrounds were recruited and trained to reach a performance level similar to that of an expert. These scorers used RIPScore to analyze data from infants at risk of POA in two separate, independent instances. Scorers performed with high accuracy and consistency, analyzed data efficiently, had very good intra- and inter-scorer repeatability, and exhibited only minor confusion between patterns. These results indicate that our tools represent an excellent method for the analysis of respiratory patterns in long data records. Although the tools were developed for the study of POA, their use extends to any study of respiratory patterns using RIP (e.g., sleep apnea, extubation readiness). Moreover, by establishing and monitoring scorer repeatability, our tools enable the analysis of large data sets by multiple scorers, which is essential for longitudinal and multicenter studies.
| S-EPMC4517879 | biostudies-literature
Project description:The success of supervised learning techniques for automatic speech processing does not always extend to problems with limited annotated speech. Unsupervised representation learning aims at utilizing unlabelled data to learn a transformation that makes speech easily distinguishable for classification tasks, whereby deep auto-encoder variants have been most successful in finding such representations. This paper proposes a novel mechanism to incorporate geometric position of speech samples within the global structure of an unlabelled feature set. Regression to the geometric position is also added as an additional constraint for the representation learning auto-encoder. The representation learnt by the proposed model has been evaluated over a supervised classification task for limited vocabulary keyword spotting, with the proposed representation outperforming the commonly used cepstral features by about 9% in terms of classification accuracy, despite using a limited amount of labels during supervision. Furthermore, a small keyword dataset has been collected for Kadazan, an indigenous, low-resourced Southeast Asian language. Analysis for the Kadazan dataset also confirms the superiority of the proposed representation for limited annotation. The results are significant as they confirm that the proposed method can learn unsupervised speech representations effectively for classification tasks with scarce labelled data.
| S-EPMC8323719 | biostudies-literature
Project description:Humans constantly assess the appearance of materials to plan actions, such as stepping on icy roads without slipping. Visual inference of materials is important but challenging because a given material can appear dramatically different in various scenes. This problem especially stands out for translucent materials, whose appearance strongly depends on lighting, geometry, and viewpoint. Despite this, humans can still distinguish between different materials, and it remains unsolved how to systematically discover visual features pertinent to material inference from natural images. Here, we develop an unsupervised style-based image generation model to identify perceptually relevant dimensions for translucent material appearances from photographs. We find our model, with its layer-wise latent representation, can synthesize images of diverse and realistic materials. Importantly, without supervision, human-understandable scene attributes, including the object's shape, material, and body color, spontaneously emerge in the model's layer-wise latent space in a scale-specific manner. By embedding an image into the learned latent space, we can manipulate specific layers' latent code to modify the appearance of the object in the image. Specifically, we find that manipulation on the early-layers (coarse spatial scale) transforms the object's shape, while manipulation on the later-layers (fine spatial scale) modifies its body color. The middle-layers of the latent space selectively encode translucency features and manipulation of such layers coherently modifies the translucency appearance, without changing the object's shape or body color. Moreover, we find the middle-layers of the latent space can successfully predict human translucency ratings, suggesting that translucent impressions are established in mid-to-low spatial scale features. This layer-wise latent representation allows us to systematically discover perceptually relevant image features for human translucency perception. Together, our findings reveal that learning the scale-specific statistical structure of natural images might be crucial for humans to efficiently represent material properties across contexts.
| S-EPMC9942964 | biostudies-literature
Project description:Representation learning models have become a mainstay of modern genomics. These models are trained to yield vector representations, or embeddings, of various biological entities, such as cells, genes, individuals, or genomic regions. Recent applications of unsupervised embedding approaches have been shown to learn relationships among genomic regions that define functional elements in a genome. Unsupervised representation learning of genomic regions is free of the supervision from curated metadata and can condense rich biological knowledge from publicly available data to region embeddings. However, there exists no method for evaluating the quality of these embeddings in the absence of metadata, making it difficult to assess the reliability of analyses based on the embeddings, and to tune model training to yield optimal results. To bridge this gap, we propose four evaluation metrics: the cluster tendency score (CTS), the reconstruction score (RCS), the genome distance scaling score (GDSS), and the neighborhood preserving score (NPS). The CTS and RCS statistically quantify how well region embeddings can be clustered and how well the embeddings preserve information in training data. The GDSS and NPS exploit the biological tendency of regions close in genomic space to have similar biological functions; they measure how much such information is captured by individual region embeddings in a set. We demonstrate the utility of these statistical and biological scores for evaluating unsupervised genomic region embeddings and provide guidelines for learning reliable embeddings.
| S-EPMC11316252 | biostudies-literature
Project description:Whole body plethysmography (WBP) monitors respiratory rate and depth but conventional analysis fails to capture the diversity of waveforms. Our first purpose was to develop a waveform cluster analysis method for quantifying dynamic changes in respiratory waveforms. WBP data, from adult Sprague-Dawley rats, were sorted into time domains and principle component analysis was used for hierarchical clustering. The clustering method effectively sorted waveforms into categories including sniffing, tidal breaths of varying duration, and augmented breaths (sighs). We next used this clustering method to quantify breathing after opioid (fentanyl) overdose and treatment with ampakine CX1942, an allosteric modulator of AMPA receptors. Fentanyl caused the expected decrease in breathing, but our cluster analysis revealed changes in the temporal appearance of inspiratory efforts. Ampakine CX1942 treatment shifted respiratory waveforms toward baseline values. We conclude that this method allows for rapid assessment of breathing patterns across extended data recordings. Expanding analyses to include larger portions of recorded WBP data may provide insight on how breathing is affected by disease or therapy.
| S-EPMC8417563 | biostudies-literature