As biological wide-field visual neurons in locusts, lobula giant motion detectors (LGMDs) can effectively predict collisions and trigger avoidance before the collision occurs. This capability has extensive potential applications in the field of autonomous driving, unmanned aerial vehicles, and more. Currently, describing the LGMD characteristics is divided into two viewpoints, one emphasizing the presynaptic visual pathway and the other emphasizing the postsynaptic LGMDs neuron. Indeed, both have their research support leading to the emergence of two computational models, but both lack a biophysical description of the behavior in the individual LGMD neuron. This paper aims to mimic and explain LGMD's individual behavior based on fractional spiking neurons and construct a biomimetic visual model for the LGMD compatible with these two characteristics. Methods: We implement the visual model in the form of spikes by choosing an event camera rather than a conventional CMOS camera to simulate the photoreceptors and follow the topology of the ON/OFF visual pathway, enabling it to incorporate the lateral inhibition to mimic the LGMD's system from the bottom up. Second, most computational models of motion perception use only the dendrites within the LGMD neurons as the ideal pathway for linear summation, ignoring dendritic effects inducing neuronal properties. Thus, we introduced fractional spiking neuron (FSN) circuits into the model by altering dendritic morphological parameters to simulate multiscale spike frequency adaptation (SFA) observed in LGMDs. In addition, we have attempted to add one more circuit of dendritic trees into fractional spiking neurons to be compatible with the postsynaptic FFI in LGMDs and provide a novel explanatory approach and a predictive model for studying LGMD neurons. Results: Finally, we test that the event-driven biomimetic visual model can achieve collision detection and looming selection in different complex scenes, especially fast-moving objects.
In the field of physiological signals monitoring and its applications, non-contact technology is often proposed as a possible alternative to traditional contact devices. The ability to extract information about a patient’s health status in an unobtrusive way, without stressing the subject and without the need of qualified personnel, fuels research in this growing field. Among the various methodologies, RADAR-based non-contact technology is gaining great interest. This scoping review aims to summarize the main research lines concerning RADAR-based physiological sensing and machine learning applications reporting recent trends, issues and gaps with the scientific literature, best methodological practices, employed standards to be followed, challenges, and future directions. After a systematic search and screening, one hundred and ninety two papers were collected following the guidelines of PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses). The included records covered two macro-areas being regression of physiological signals or physiological features (n = 68 papers) and the other a cluster of papers regarding the processing of RADAR-based physiological signals and features applied to four fields of interest, being RADAR-based diagnosis (n = 73), RADAR-based human behaviour monitoring (n = 21), RADAR-based biometrics authentication (n = 18) and RADAR-based affective computing (n = 9). Papers collected under the diagnosis category were further divided, on the basis of their aims: in breath pattern classification (n = 39), infection detection (n = 10), sleep stage classification (n = 9), heart disease detection (n = 8) and quality detection (n = 7). Papers collected under the human behaviour monitoring were further divided based on their aims: fatigue detection (n = 8), human detection (n = 7), human localisation (n = 4), human orientation (n = 2), and activities classification (n = 3).
The Kanta Patient Data Repository contains healthcare data from the population of Finland for more than a decade. The repository is a continuously expanding real world dataset produced by many information systems and healthcare service providers. Kanta data has been accessible for secondary uses such as scientific research since 2019. The data can be requested from the Finnish authority Findata. However, before a request has been accepted, it is difficult to assess if the accumulated data allows answering a specific research question. Publicly available descriptions of data structures in Kanta do not tell how much they are used in practice. This publication enables future data use cases by providing a view on the overall availability of types of structured health data in the Kanta patient data repository based on a sample of 96 200 medical histories of over 18-year-old patients. We conclude that Kanta PDR is a promising source of real world data for development and evaluation of medical risk calculators within the Finnish population. The wide coverage of the Finnish population and timeliness of the data are its strengths as a source of research data also outside of Finnish context. However, the limitations on data availability in variable level need to be considered on a case-by-case basis. Main challenges in the use of Kanta data are multiple code systems for laboratory results, short durations of recorded data for specific data types, and missing or very rarely used structured format e.g., in cases of tobacco and alcohol use.
Functional near-infrared spectroscopy (fNIRS) is a valuable non-invasive tool for monitoring brain activity. The classification of fNIRS data in relation to conscious activity holds significance for advancing our understanding of the brain and facilitating the development of brain-computer interfaces (BCI). Many researchers have turned to deep learning to tackle the classification challenges inherent in fNIRS data due to its strong generalization and robustness. In the application of fNIRS, reliability is really important, and one mathematical formulation of the reliability of confidence is calibration. However, many researchers overlook the important issue of calibration. To address this gap, we propose integrating calibration into fNIRS field and assess the reliability of existing models. Surprisingly, our results indicate poor calibration performance in many proposed models. To advance calibration development in the fNIRS field, we summarize three practical tips. Through this letter, we hope to emphasize the critical role of calibration in fNIRS research and argue for enhancing the reliability of deep learning-based predictions in fNIRS classification tasks. All data from our experimental process are openly available on GitHub.
This paper is a continuation on my revolutionary theory of solving the pointwise fluid flow approximation model for time-varying queues. Thus, the long-standing simulative approach has now been replaced by an exact solution by using a constant ratio 𝛽 (Ismail's ratio) , offering an exact analytical solution. The stability dynamics of the time-varying 𝑀/𝐸 𝑘 /1 queueing system are then examined numerically in relation to time, 𝛽, and the queueing parameters.
Objective: In this paper we propose a novel use of the wavelet transform in analyzing spectral impedance to discriminate cancerous and non-cancerous lung tissue. Methods: Cancerous and Non Cancerous ex-vivo tissue samples were obtained during a human clinical trial of patients undergoing a lobectomy. Spectral Impedance measurements of the tissues samples were performed using a custom impedance bridge and measurement system. Three methods are described using the wavelet transform of the spectral impedances and comparing results to pathological assessments of the lesion. Results: In a cohort of n=46 patients, for which both tumor and away-from-tumor samples have been collected, we report sensitivity of 87% and specificity of 84%. Conclusion: Three techniques have been proposed as an algorithm basis to improve the sensitivity and specificity of discriminating between cancerous and non-cancerous tissue. Significance: Lung Cancer is the cause of 20% of all cancer related death globally and is the most diagnosed cancer worldwide. Utilizing the proposed methods of analyzing tissue samples and reporting on cancer state at the surgical suite offers clinicians an additional tool to better diagnose and subsequently treat the deadly disease.
Individuals with transtibial amputation can activate residual limb muscles to volitionally control robotic ankle prostheses for walking and postural control. Most continuous myoelectric ankle prostheses have used a tethered, pneumatic device. The Open Source Leg allows for myoelectric control on an untethered electromechanically actuated ankle. To evaluate continuous proportional myoelectric control on the Open Source Ankle, we recruited five individuals with transtibial amputation. Participants walked over ground with an experimental powered prosthesis and their prescribed passive prosthesis before and after multiple powered device practice sessions. Participants averaged five hours of total walking time, and received no visual feedback during practice. After the final testing session, participants indicated their prosthesis preference via questionnaire. Participants increased peak ankle power after practice (powered 1.02 ± 1.09 W/kg and passive 0.3 ± 0.13 W/kg). Additionally, participants generated greater ankle work with the powered prosthesis compared to their passive device (p=0.009, 148% increase). Although peak power generation was not different, participants preferred walking with a prosthesis under myoelectric control compared to their passive device. These results indicate individuals with transtibial amputation can walk with an untethered powered prosthesis under continuous myoelectric control and generate similar magnitudes in peak power to their passive prosthesis after minimal training.
Prostheses are becoming more advanced and biomimetic with time, providing additional capabilities to their users. However, prosthetic sensation lags far behind its natural limb counterpart, limiting the use of sensory feedback in prosthetic motion planning and execution. Without actionable sensation, prostheses may never meet the functional requirements to match biological performance. We propose an approach for upper-limb prosthetic object slip prediction and notification, delivered to the wearer through direct nerve stimulation. The method is based on sensory synthesis, training a linear regression of the sensors embedded in a prosthetic hand to predict slip before it occurs. Four participants with transhumeral amputation performed block pulling tasks against increasing resistance, attempting to pull the block as far as possible without slip. These trials were performed with two different prediction notification paradigms. At lower grasp forces, spike notification stimulation reduced the incidence of object slip by 32%, and at higher grasp forces, the maximum achieved pull forces increased by 19% across participants when provided with stimulation proportional to the likelihood of a predicted slip. These results suggest that this approach may be effective in recreating a lost sense of grip stability in the missing limb and may reduce unanticipated slips.
This review article delves deeply into the various machine learning (ML) methods and algorithms employed in discerning protein functions. Each method discussed is assessed for its efficacy, limitations, potential improvements, and future prospects. We present an innovative hierarchical classification system that arranges algorithms into intricate categories and unique techniques. This taxonomy is based on a tri-level hierarchy, starting with the methodology category and narrowing down to specific techniques. Such a framework allows for a structured and comprehensive classification of algorithms, assisting researchers in understanding the interrelationships among diverse algorithms and techniques. The study incorporates both empirical and experimental evaluations to differentiate between the techniques. The empirical evaluation ranks the techniques based on four criteria. The experimental assessments rank: (1) individual techniques under the same methodology subcategory, (2) different sub-categories within a same category, and (3) the broad categories themselves. Integrating the innovative methodological classification, empirical findings, and experimental assessments, the article offers a well-rounded understanding of ML strategies in protein function identification. The paper also explores techniques for multi-task and multi-label detection of protein functions, in addition to focusing on single-task methods. Moreover, the paper sheds light on the future avenues of ML in protein function determination.
Despite the emergence of numerous Deep Learning (DL) models for breast cancer detection via mammograms, there is a lack of evidence about their robustness to perform well on new unseen mammograms. To fill this gap, we introduce StethoNet, a DL-based framework that consists of multiple Convolutional Neural Network (CNN) trained models for classifying benign and malignant tumors. StethoNet was trained on the Chinese Mammography Database (CMMD), and tested on unseen images from CMMD, as well as on images from two independent datasets, i.e., the Vindr-Mammo and the INbreast datasets. To mitigate domain-shift effects, we applied an effective entropy-based domain adaptation technique at the preprocessing stage. Furthermore, a Bayesian hyperparameters optimization scheme was implemented for StethoNet optimization. To ensure interpretable results that corroborate with prior clinical knowledge, attention maps generated using Gradientweighted Class Activation Mapping (GRAD-CAM) were compared with Regions of Interest (ROIs) identified by radiologists. StethoNet achieved impressive Area Under the receiver operating characteristics Curve (AUC) scores: 90.7% (88.6%-92.8%), 83.9% (76.0%-91.8%), and 85.7% (82.1%-89.4%) for the CMMD, INbreast, and Vindr-Mammo datasets, respectively. These results surpass the current state of the art and highlight the robustness and generalizability of StethoNet, scaffolding the integration of DL models into breast cancer mammography screening workflows. Our code is available at https://github.com/CharLamp10/breast cancer detection.git.
In pathology, various tissue and cell components play diverse biological roles. The morphology of each component can vary markedly with differentiation status or pathological conditions, making it critical for understanding diseases. Traditional computational pathology methods typically employ patch-based feature extraction, which aggregates visual features across entire images. However, this approach does not differentiate between tissue types, limiting component analysis. To address this limitation, we introduce a novel concept in pathology image analysis, namely segment representation learning, and present an algorithm, SegRep, for this purpose. SegRep uses a unique dual-masking strategy that combines input masking and feature map masking. This approach effectively removes external influences for the targeted segment, identified via a segmentation model or manual annotation, allowing for the extraction of segment-specific feature representations. In addition, SegRep utilizes a selfsupervised learning algorithm to achieve optimized segment representation. We evaluated SegRep's efficacy in clustering and classification tasks using a dataset of human gastric cancer samples. The results demonstrate SegRep's superior capability in extracting feature vectors that are highly specific to different pathology image segments. Compared with traditional methods, SegRep shows significant improvements in accuracy and specificity in both clustering and classification tasks. Segment representations obtained via SegRep can offer a more detailed and insightful perspective on computational pathology, paving the way for advanced applications in the field.
Objective: Digital subtraction angiography (DSA) is significantly important for cerebrovascular disease diagnosis and treatment. However, artifacts and noise are inevitable and reduce image quality. These problems could make clinical diagnosis difficult. In this paper, we introduce a novel deep learning architecture, exploiting the information decoupling training strategy to generate highquality DSA images. Methods: We propose the generative decoupling network, a feature decoupling convolutional network, which maximizes the difference between different structures throughout a decoupling training strategy. In this network, an axial residual block and a learnable sampling method are proposed to enhance the strength of feature extraction. Results: The results showed that our proposed method significantly outperforms the existing methods in the DSA generation task. Furthermore, we quantified the method using the metrics of SSIM, PSNR, VSI, FID and FSIM, with the results of 93.57%, 24.18dB, 98.04%, 351.59, and 89.95%, respectively. Conclusion: Our method can produce high-quality DSA images with little or even no artifact and noise. Significance: The proposed method can effectively reduce artifacts and noise, and generate high quality DSA images with complete and clear vascular structures.
To date, the dynamic mechanisms by which the corticospinal tract (CST) and its alternative tract (i.e. the reticulospinal tract (RST)) interact and evolve after the CST has been damaged by stroke has not been fully explored. To gain insight into the mechanisms, we construct a computational model to reproduce several critical features of subscore distributions of the Fugl-Meyer assessment (FMA) for the upper extremity following stroke. Subscores of the FMA present clues about the working neural substrates affected by stroke, potentially distinguishing preferential uses of the CST and RST. A stochastic gradient descent method is employed to emulate biologically plausible phenomena, including activity- or use-dependent plasticity and the preferred use of more strongly connected neural circuits. The model replicates several segments of empirical evidence presented by imaging and neurophysiological studies. One of the main predictions is that substantial CST recovery is achievable unless the initial degree of residual corticospinal neurons following stroke falls below a certain level. Another prediction is that while the functional capabilities of the CST and RST increase in a harmonic way post-stroke, the degrees of functional capability those tracts reach are in a competitive relationship. We confirm that the neural system prioritizes optimizing a more strongly connected motor tract and uses the other tract in a supplementary manner to enhance overall motor capability. This model presents insights into efficient therapy designs.
_Goal:_ Vascular surgical procedures are challenging and require proficient suturing skills. To develop these skills, medical training simulators with objective feedback for formative assessment are gaining popularity. As hardware advancements offer more complex, unique sensors, determining effective task performance measures becomes imperative for efficient suturing training. _Methods:_ 97 subjects of varying clinical expertise completed four trials on a suturing skills measurement and feedback platform (SutureCoach). Instrument handling metrics were calculated from electromagnetic motion trackers affixed to the needle driver. _Results:_ The results of the study showed that all metrics significantly differentiated between novices (no medical experience) from both experts (attending surgeons/fellows) and intermediates (residents). Rotational motion metrics were more consistent in differentiating experts and intermediates over traditionally used tooltip motion metrics. _Conclusions:_ Our work emphasizes the importance of tool motion metrics for open suturing skills assessment and establishes groundwork to explore rotational motion for quantifying a critical facet of surgical performance. _Impact Statement_–This study aims to determine the effectiveness of metrics derived from needle driver rotational and tooltip motion tracking to determine differences in clinical expertise in open needle driving.
Objective: Deep Brain Stimulation (DBS) is effective for movement disorders, particularly Parkinson's disease (PD). However, a closed-loop DBS system using reinforcement learning (RL) for automatic parameter tuning, offering enhanced energy efficiency and the effect of thalamus restoration, is yet to be developed for clinical and commercial applications. Methods: In this research, we instantiate a basal ganglia-thalamic (BGT) model and design it as an interactive environment suitable for RL models. Four finely tuned RL agents based on different frameworks, namely Soft Actor-Critic (SAC), Twin Delayed Deep Deterministic Policy Gradient (TD3), Proximal Policy Optimization (PPO), and Advantage Actor-Critic (A2C), are established for further comparison. Results: Within the implemented RL architectures, the optimized TD3 demonstrates a significant 67% reduction in average power dissipation when compared to the open-loop system while preserving the normal response of the simulated BGT circuitry. As a result, our method mitigates thalamic error responses under pathological conditions and prevents overstimulation. Significance: In summary, this study introduces a novel approach to implementing an adaptive parameter-tuning closed-loop DBS system. Leveraging the advantages of TD3, our proposed approach holds significant promise for advancing the integration of RL applications into DBS systems, ultimately optimizing therapeutic effects in future clinical trials.
The gold standard methods for real-time core temperature (CT) monitoring are invasive and cost-inefficient. The application of Kalman filters for an indirect estimation of CT has been explored in the literature since 2010. This paper presents a comparative study between different state of the art Extended Kalman Filter (EKF) estimation algorithms and a new approach based on a biomimetic human body response pre-emptive mapping concept. In this new method, a mapping model of the physiological response of the heart rate (HR) change to CT increase is pre-applied to the input of the EKF estimation CT procedure in a near real-time manner. The algorithm was trained and tested using two datasets (total participants = 18). The best performing algorithm with this novel pre-emptive mapping achieved in an average Root Mean Squared Error (RMSE) of 0.34°C while the best state of the art EKF model (without pre-emptive mapping) resulted in a RMSE of 0.41°C, leading to a 17% improvement performance of our novel method. Given these favorable outcomes, it is compelling to assess its efficacy on a larger dataset in the near future.
Cervical cancer poses a major health threat to women globally. Optical coherence tomography (OCT) imaging has recently shown promise for non-invasive cervical lesion diagnosis. However, a shortage of high-quality labeled cervical OCT images hampers the practical training of deep learning models. Inspired by the idea of self-supervised pre-training, we propose MCSwin, a novel framework combining masked image modeling (MIM) with contrastive learning based on the Swin-Transformer architecture for high-resolution cervical OCT images. In this contrastive-MIM framework, mixed image encoding is combined with a latent contextual regressor to solve the inconsistency problem between pre-training and fine-tuning and separate the encoder's feature extraction task from the decoder's reconstruction task, allowing the encoder to extract better image representations. Besides, contrastive losses at the patch and image levels are elaborately designed to leverage massive unlabelled data. We validated the superiority of MCSwin over the state-of-the-art self-supervised learning approaches with five-fold cross-validation on an OCT image dataset containing 1,452 patients from a multicenter clinical study in China, plus two external validation sets from top-ranked Chinese hospitals: West China (Huaxi) and Xiangya. A human-machine comparison experiment on the Huaxi and Xiangya datasets for volume-level binary classification also indicates that MCSwin can match or exceed the average level of four skilled medical experts, especially in identifying high-risk cervical lesions. Additionally, the integrated GradCAM module of MCSwin enables cervical lesion visualization and interpretation, providing good interpretability for gynecologists to diagnose cervical diseases efficiently. Therefore, our work has great potential to assist gynecologists in intelligently interpreting cervical OCT images in clinical settings.