Human Activity Recognition (HAR) refers to an emerging area of interest for medical, military, and security applications. However, the identification of the features to be used for activity ...classification and recognition is still an open point. The aim of this study was to compare two different feature sets for HAR. Particularly, we compared a set including time, frequency, and time-frequency domain features widely used in literature (
) with a set of time-domain features derived by considering the physical meaning of the acquired signals (
). The comparison of the two sets were based on the performances obtained using four machine learning classifiers. Sixty-one healthy subjects were asked to perform seven different daily activities wearing a MIMU-based device. Each signal was segmented using a 5-s window and for each window, 222 and 221 variables were extracted for the
and
respectively. Each set was reduced using a Genetic Algorithm (GA) simultaneously performing feature selection and classifier optimization. Our results showed that Support Vector Machine achieved the highest performances using both sets (97.1% and 96.7% for
and
respectively). However,
allows to better understand alterations of the biomechanical behavior in more complex situations, such as when applied to pathological subjects.
The home monitoring of patients affected by chronic heart failure (CHF) is of key importance in preventing acute episodes. Nevertheless, no wearable technological solution exists to date. A ...possibility could be offered by Cardiac Time Intervals extracted from simultaneous recordings of electrocardiographic (ECG) and phonocardiographic (PCG) signals. Nevertheless, the recording of a good-quality PCG signal requires accurate positioning of the stethoscope over the chest, which is unfeasible for a naïve user as the patient. In this work, we propose a solution based on multi-source PCG. We designed a flexible multi-sensor array to enable the recording of heart sounds by inexperienced users. The multi-sensor array is based on a flexible Printed Circuit Board mounting 48 microphones with a high spatial resolution, three electrodes to record an ECG and a Magneto-Inertial Measurement Unit. We validated the usability over a sample population of 42 inexperienced volunteers and found that all subjects could record signals of good to excellent quality. Moreover, we found that the multi-sensor array is suitable for use on a wide population of at-risk patients regardless of their body characteristics. Based on the promising findings of this study, we believe that the described device could enable the home monitoring of CHF patients soon.
Surface electromyography (sEMG) is the main non-invasive tool used to record the electrical activity of muscles during dynamic tasks. In clinical gait analysis, a number of techniques have been ...developed to obtain and interpret the muscle activation patterns of patients showing altered locomotion. However, the body of knowledge described in these studies is very seldom translated into routine clinical practice. The aim of this work is to analyze critically the key factors limiting the extensive use of these powerful techniques among clinicians. A thorough understanding of these limiting factors will provide an important opportunity to overcome limitations through specific actions, and advance toward an evidence-based approach to rehabilitation based on objective findings and measurements.
Gait analysis applications in clinics are still uncommon, for three main reasons: (1) the considerable time needed to prepare the subject for the examination; (2) the lack of user-independent tools; ...(3) the large variability of muscle activation patterns observed in healthy and pathological subjects. Numerical indices quantifying the muscle coordination of a subject could enable clinicians to identify patterns that deviate from those of a reference population and to follow the progress of the subject after surgery or completing a rehabilitation program. In this work, we present two user-independent indices. First, a muscle-specific index (MFI) that quantifies the similarity of the activation pattern of a muscle of a specific subject with that of a reference population. Second, a global index (GFI) that provides a score of the overall activation of a muscle set. These two indices were tested on two groups of healthy and pathological children with encouraging results. Hence, the two indices will allow clinicians to assess the muscle activation, identifying muscles showing an abnormal activation pattern, and associate a functional score to every single muscle as well as to the entire muscle set. These opportunities could contribute to facilitating the diffusion of surface EMG analysis in clinics.
Purpose
To assess the use of telemedicine with phone-call visits as a practical tool to follow-up with patients affected by urological benign diseases, whose clinic visits had been cancelled during ...the acute phase of the COVID-19 pandemic.
Methods
Patients were contacted via phone-call and a specific questionnaire was administered to evaluate the health status of these patients and to identify those who needed an “in-person” ambulatory visit due to the worsening of their condition. Secondarily, the patients’ perception of a potential shift towards a “telemedicine” approach to the management of their condition and to indirectly evaluate their desire to return to “in-person” clinic visits.
Results
607 were contacted by phone-call. 87.5% (531/607) of the cases showed stability of the symptoms so no clinic in-person or emergency visits were needed. 81.5% (495/607) of patients were more concerned about the risk of contagion than their urological condition. The median score for phone visit comprehensibility and ease of communication of exams was 5/5; whilst patients’ perception of phone visits’ usefulness was scored 4/5. 53% (322/607) of the interviewees didn’t own the basic supports required to be able to perform a real telemedicine consult according to the required standards.
Conclusion
Telemedicine approach limits the number of unnecessary accesses to medical facilities and represents an important tool for the limitation of the risk of transmission of infectious diseases, such as COVID-19. However, infrastructures, health workers and patients should reach out to a computerization process to allow a wider diffusion of more advanced forms of telemedicine, such as televisit.
Timely and reliable fetal monitoring is crucial to prevent adverse events during pregnancy and delivery. Fetal phonocardiography, i.e., the recording of fetal heart sounds, is emerging as a novel ...possibility to monitor fetal health status. Indeed, due to its passive nature and its noninvasiveness, the technique is suitable for long-term monitoring and for telemonitoring applications. Despite the high share of literature focusing on signal processing, no previous work has reviewed the technological hardware solutions devoted to the recording of fetal heart sounds. Thus, the aim of this scoping review is to collect information regarding the acquisition devices for fetal phonocardiography (FPCG), focusing on technical specifications and clinical use. Overall, PRISMA-guidelines-based analysis selected 57 studies that described 26 research prototypes and eight commercial devices for FPCG acquisition. Results of our review study reveal that no commercial devices were designed for fetal-specific purposes, that the latest advances involve the use of multiple microphones and sensors, and that no quantitative validation was usually performed. By highlighting the past and future trends and the most relevant innovations from both a technical and clinical perspective, this review will represent a useful reference for the evaluation of different acquisition devices and for the development of new FPCG-based systems for fetal monitoring.
Segmentation and Classification of Gait Cycles Agostini, Valentina; Balestra, Gabriella; Knaflitz, Marco
IEEE transactions on neural systems and rehabilitation engineering,
2014-Sept., 2014-Sep, Letnik:
22, Številka:
5
Journal Article
Recenzirano
Odprti dostop
Gait abnormalities can be studied by means of instrumented gait analysis. Foot-switches are useful to study the foot-floor contact and for timing the gait phases in many gait disorders, provided that ...a reliable foot-switch signal may be collected. Considering long walks allows reducing the intra-subject variability, but requires automatic and user-independent methods to analyze a large number of gait cycles. The aim of this work is to describe and validate an algorithm for the segmentation of the foot-switch signal and the classification of the gait cycles. The performance of the algorithm was assessed comparing its results against the manual segmentation and classification performed by a gait analysis expert on the same signal. The performance was found to be equal to 100% for healthy subjects and over 98% for pathological subjects. The algorithm allows determining the atypical cycles (cycles that do not match the standard sequence of gait phases) for many different kinds of pathological gait, since it is not based on pathology-specific templates.
The aim of this study is to present a personalized predictive model (PPM) with a machine learning (ML) system that is able to identify and classify patients with suspected prostate cancer (PCa) ...following mpMRI. We extracted all the patients who underwent fusion biopsy (FB) from March 2014 to December 2019, while patients from August 2020 to April 2021 were included as a validation set. The proposed system was based on the following four ML methods: a fuzzy inference system (FIS), the support vector machine (SVM), k-nearest neighbors (KNN), and self-organizing maps (SOMs). Then, a system based on fuzzy logic (FL) + SVM was compared with logistic regression (LR) and standard diagnostic tools. A total of 1448 patients were included in the training set, while 181 patients were included in the validation set. The area under the curve (AUC) of the proposed FIS + SVM model was comparable with the LR model but outperformed the other diagnostic tools. The FIS + SVM model demonstrated the best performance, in terms of negative predictive value (NPV), on the training set (78.5%); moreover, it outperformed the LR in terms of specificity (92.1% vs. 83%). Considering the validation set, our model outperformed the other methods in terms of NPV (60.7%), sensitivity (90.8%), and accuracy (69.1%). In conclusion, we successfully developed and validated a PPM tool using the FIS + SVM model to calculate the probability of PCa prior to a prostate FB, avoiding useless ones in 15% of the cases.
Transformer, which is notable for its ability of global context modeling, has been used to remedy the shortcomings of Convolutional neural networks (CNN) and break its dominance in medical image ...segmentation. However, the self-attention module is both memory and computational inefficient, so many methods have to build their Transformer branch upon largely downsampled feature maps or adopt the tokenized image patches to fit their model into accessible GPUs. This patch-wise operation restricts the network in extracting pixel-level intrinsic structural or dependencies inside each patch, hurting the performance of pixel-level classification tasks.
To tackle these issues, we propose a memory- and computation-efficient self-attention module to enable reasoning on relatively high-resolution features, promoting the efficiency of learning global information while effective grasping fine spatial details. Furthermore, we design a novel Multi-Branch Transformer (MultiTrans) architecture to provide hierarchical features for handling objects with variable shapes and sizes in medical images. By building four parallel Transformer branches on different levels of CNN, our hybrid network aggregates both multi-scale global contexts and multi-scale local features.
MultiTrans achieves the highest segmentation accuracy on three medical image datasets with different modalities: Synapse, ACDC and M&Ms. Compared to the Standard Self-Attention (SSA), the proposed Efficient Self-Attention (ESA) can largely reduce the training memory and computational complexity while even slightly improve the accuracy. Specifically, the training memory cost, FLOPs and Params of our ESA are 18.77%, 20.68% and 74.07% of the SSA.
Experiments on three medical image datasets demonstrate the generality and robustness of the designed network. The ablation study shows the efficiency and effectiveness of our proposed ESA. Code is available at: https://github.com/Yanhua-Zhang/MultiTrans-extension.
•We design a memory- and computation-efficient self-attention module through which our Transformer branch can directly inference on relatively high-resolution feature maps, maintaining a grasp of fine spatial details and enabling a more flexible design space for Transformer-based architectures.•We propose a novel Multi-Branch Transformer decoder architecture to aggregate hierarchical features from both CNN and Transformer to provide rich clues for segmentation, enabling effective handling of objects with diverse shapes and sizes.•MultiTrans achieves the highest accuracy on three medical image datasets with different modalities. Compared to the Standard Self-Attention, the proposed hybrid Efficient Self-Attention can largely reduce the computation and training memory while maintaining comparable performance.
Display omitted
•Muscle onset-offset timings during gait show a high stride-to-stride variability.•Different strides may show different timings even in the same activation modality.•A dendrogram ...algorithm was presented to cluster strides with similar timings.•The algorithm was validated on 5 lower limb muscles.•The concept of principal and secondary activations was introduced.
Human gait is characterized by a large stride-to-stride variability of the muscle activation patterns (onset-offset timings). For this reason prolonged walking sessions lasting several minutes are analyzed. To interpret correctly the electromyographic (EMG) data collected during gait, it is important to group strides sharing similar EMG activation patterns. The aim of this work is to present and validate a method, based on hierarchical clustering, able to group strides showing homogeneous onset-offset activation intervals. Results show that the variability of the onset-offset timing is significantly reduced after clustering, for all of the five lower limb muscles considered to test this method. A by-product of the clustering procedure is the possibility to define and extract the principal activations of a muscle during gait. We define principal activations those activations that are necessary for the specific muscle contribution to the biomechanical function of walking. This concept may be useful whenever the dynamic performance of the muscle has to be compared in subsequent times, such as in patient’s follow-up or when the performance of a specific subject is to be compared to that of a group of selected subjects. The contribution presented in this work could be beneficial in implementing a personalized medicine approach to rehabilitation. Clinical gait analysis, enriched by hierarchical clustering of EMG patterns as well as by the quantitative assessment of muscles principal activations, could greatly contribute to the design of therapeutic treatments tailored on the patient’s needs.