-
Frontiers in Medical Technology 2023The healthcare sector has to face changes happening fast and often in an unpredictable way, such as epidemiological trends, the advancements of medical technology and...
The healthcare sector has to face changes happening fast and often in an unpredictable way, such as epidemiological trends, the advancements of medical technology and processes or evolving social and economic needs. This results in a frequent need for infrastructures' retrofitting, with an increasing focus on the environmental impact of buildings, which have one of the highest embodied carbon footprints per square meter in the construction sector. As result, interest in healthcare buildings' adaptability is growing among researchers and practitioners. After an introduction on the research topic, a focus on the definition of adaptability and the existing assessment models is provided to address the following research question: to what extent are adaptability models effective to evaluate and orient the design of healthcare buildings? A quite varied use of the term adaptability has been found in the literature, as well as a new research trend aiming to establish a link with circularity. Moreover, most of the assessment models do not have a focus and have never been tested on the healthcare sector. An approach to circular and adaptable design is presented through the case study of the Joseph Bracops Hospital (Belgium), which has been submitted for evaluation by the Reversible Building Design protocol developed by Dr. Durmisevic. The evaluation highlights some of the current barriers in the design of adaptable healthcare facilities. Insights for future research are provided to encourage data-collection about the service life of healthcare buildings, so to understand if the adaptability of these infrastructures should be mainly monofuntional or transfunctional.
PubMed: 37492599
DOI: 10.3389/fmedt.2023.1199581 -
Stimulus-guided adaptive transformer network for retinal blood vessel segmentation in fundus images.Medical Image Analysis Oct 2023Automated retinal blood vessel segmentation in fundus images provides important evidence to ophthalmologists in coping with prevalent ocular diseases in an efficient and...
Automated retinal blood vessel segmentation in fundus images provides important evidence to ophthalmologists in coping with prevalent ocular diseases in an efficient and non-invasive way. However, segmenting blood vessels in fundus images is a challenging task, due to the high variety in scale and appearance of blood vessels and the high similarity in visual features between the lesions and retinal vascular. Inspired by the way that the visual cortex adaptively responds to the type of stimulus, we propose a Stimulus-Guided Adaptive Transformer Network (SGAT-Net) for accurate retinal blood vessel segmentation. It entails a Stimulus-Guided Adaptive Module (SGA-Module) that can extract local-global compound features based on inductive bias and self-attention mechanism. Alongside a light-weight residual encoder (ResEncoder) structure capturing the relevant details of appearance, a Stimulus-Guided Adaptive Pooling Transformer (SGAP-Former) is introduced to reweight the maximum and average pooling to enrich the contextual embedding representation while suppressing the redundant information. Moreover, a Stimulus-Guided Adaptive Feature Fusion (SGAFF) module is designed to adaptively emphasize the local details and global context and fuse them in the latent space to adjust the receptive field (RF) based on the task. The evaluation is implemented on the largest fundus image dataset (FIVES) and three popular retinal image datasets (DRIVE, STARE, CHASEDB1). Experimental results show that the proposed method achieves a competitive performance over the other existing method, with a clear advantage in avoiding errors that commonly happen in areas with highly similar visual features. The sourcecode is publicly available at: https://github.com/Gins-07/SGAT.
Topics: Humans; Retinal Vessels; Face; Fundus Oculi
PubMed: 37598606
DOI: 10.1016/j.media.2023.102929 -
Scientific Reports Oct 2023Autism spectrum disorder (ASD) are neurodevelopmental conditions characterised by deficits in social communication and interaction and repetitive behaviours. Maternal...
Autism spectrum disorder (ASD) are neurodevelopmental conditions characterised by deficits in social communication and interaction and repetitive behaviours. Maternal immune activation (MIA) during the mid-pregnancy is a known risk factor for ASD. Although reported in 15% of affected individuals, little is known about the specificity of their clinical profiles. Adaptive skills represent a holistic approach to a person's competencies and reflect specifically in ASD, their strengths and difficulties. In this study, we hypothesised that ASD individual with a history of MIA (MIA) could be more severely socio-adaptively impaired than those without MIA during pregnancy (MIA). To answer this question, we considered two independent cohorts of individuals with ASD (PARIS study and FACE ASD) screened for pregnancy history, and used supervised and unsupervised machine learning algorithms. We included 295 mother-child dyads with 14% of them with MIA. We found that ASD-MIA individuals displayed more severe maladaptive behaviors, specifically in their socialization abilities. MIA directly influenced individual's socio-adaptive skills, independent of other covariates, including ASD severity. Interestingly, MIA affect persistently the socio-adaptive behavioral trajectories of individuals with ASD. The current study has a retrospective design with possible recall bias regarding the MIA event and, even if pooled from two cohorts, has a relatively small population. In addition, we were limited by the number of covariables available potentially impacted socio-adaptive behaviors. Larger prospective study with additional dimensions related to ASD is needed to confirm our results. Specific pathophysiological pathways may explain these clinical peculiarities of ASD- MIA individuals, and may open the way to new perspectives in deciphering the phenotypic complexity of ASD and for the development of specific immunomodulatory strategies.
Topics: Pregnancy; Female; Humans; Autism Spectrum Disorder; Retrospective Studies; Prospective Studies; Prenatal Exposure Delayed Effects; Adaptation, Psychological
PubMed: 37848536
DOI: 10.1038/s41598-023-45060-z -
Methods in Molecular Biology (Clifton,... 2024Establishing a mapping between (from and to) the functionality of interest and the underlying network structure (design principles) remains a crucial step toward...
Establishing a mapping between (from and to) the functionality of interest and the underlying network structure (design principles) remains a crucial step toward understanding and design of bio-systems. Perfect adaptation is one such crucial functionality that enables every living organism to regulate its essential activities in the presence of external disturbances. Previous approaches to deducing the design principles for adaptation have either relied on computationally burdensome brute-force methods or rule-based design strategies detecting only a subset of all possible adaptive network structures. This chapter outlines a scalable and generalizable method inspired by systems theory that unravels an exhaustive set of adaptation-capable structures. We first use the well-known performance parameters to characterize perfect adaptation. These performance parameters are then mapped back to a few parameters (poles, zeros, gain) characteristic of the underlying dynamical system constituted by the rate equations. Therefore, the performance parameters evaluated for the scenario of perfect adaptation can be expressed as a set of precise mathematical conditions involving the system parameters. Finally, we use algebraic graph theory to translate these abstract mathematical conditions to certain structural requirements for adaptation. The proposed algorithm does not assume any particular dynamics and is applicable to networks of any size. Moreover, the results offer a significant advancement in the realm of understanding and designing complex biochemical networks.
Topics: Adaptation, Biological; Algorithms; Models, Biological
PubMed: 38468081
DOI: 10.1007/978-1-0716-3658-9_3 -
HardwareX Mar 2024Cardiovascular pressure sensors require dedicated, reliable, and customisable performance testing equipment. Devices available on the market, such as pulsatile pumps and...
Cardiovascular pressure sensors require dedicated, reliable, and customisable performance testing equipment. Devices available on the market, such as pulsatile pumps and pulse multipliers, offer limited adaptability to the needs of pressure sensor testing or are highly complex tools designed for other purposes. Therefore, there is a strong need to provide an adaptable and versatile device for characterisation during prototype development, prior to animal model testing. Early development requires detailed characterisation of a sensor performance in a realistic environmental scenario. To address this need, we adapted an off-the-shelf pressure chamber with a custom Arduino-based controller to achieve a rapid change in pressure that simulates the pulsatile profile of human blood pressure. The system is a highly customisable tool, and we have experimentally shown that it works successfully in a wide range of pressures from 30 mmHg to 400 mmHg with a resolution of 2 mmHg. By adjusting the chamber volume using a water balloon, we achieved a cycle rate of up to 120 beats per minute. The device can be operated directly from the Arduino IDE or with a customised graphical user interface developed by our research group. The proposed system is intended to assist other researchers in the development of industrial and biomedical pressure sensors.
PubMed: 38188700
DOI: 10.1016/j.ohx.2023.e00500 -
Philosophical Transactions of the Royal... Nov 2023Worldwide, marginalized and low-income communities will disproportionately suffer climate change impacts while also retaining the least political power to mitigate their...
Worldwide, marginalized and low-income communities will disproportionately suffer climate change impacts while also retaining the least political power to mitigate their consequences. To adapt to environmental shocks, communities must balance intensifying natural resource consumption with the need to ensure the sustainability of ecosystem provisioning services. Thus, scientists have long been providing policy recommendations that seek to balance humanitarian needs with the best outcomes for the conservation of ecosystems and wildlife. However, many conservation and development practitioners from biological backgrounds receive minimal training in either social research methods or participatory project design. Without a clear understanding of the sociocultural factors shaping decision-making, their initiatives may fail to meet their goals, even when communities support proposed initiatives. This paper explores the underlying assumptions of a community's agency, or its ability to develop and enact preferred resilience-enhancing adaptations. We present a context-adaptable toolkit to assess community agency, identify barriers to adaptation, and survey perceptions of behaviour change around natural resource conservation and alternative food acquisition strategies. This tool draws on public health and ecology methods to facilitate conversations between community members, practitioners and scientists. We then provide insights from the toolkit's collaborative development and pilot testing with Vezo fishing communities in southwestern Madagascar. This article is part of the theme issue 'Climate change adaptation needs a science of culture'.
Topics: Humans; Climate Change; Environment; Madagascar; Resilience, Psychological; Self Efficacy; Community Participation; Adaptation, Psychological
PubMed: 37718606
DOI: 10.1098/rstb.2022.0391 -
Journal of Applied Clinical Medical... Nov 2023Defining dosimetric rules to automatically detect patients requiring adaptive radiotherapy (ART) is not straightforward, and most centres perform ad-hoc ART with no...
PURPOSE
Defining dosimetric rules to automatically detect patients requiring adaptive radiotherapy (ART) is not straightforward, and most centres perform ad-hoc ART with no specific protocol. This study aims to propose and analyse different steps to design a protocol for dosimetrically triggered ART of head and neck (H&N) cancer. As a proof-of-concept, the designed protocol was applied to patients treated in TomoTherapy units, using their available software for daily MVCT image and dose accumulation.
METHODS
An initial protocol was designed by a multidisciplinary team, with a set of flagging criteria based only on dose-volume metrics, including two action levels: (1) surveillance (orange flag), and (2) immediate verification (red flag). This protocol was adapted to the clinical needs following an iterative process. First, the protocol was applied to 38 H&N patients with daily imaging. Automatic software generated the daily contours, recomputed the daily dose and flagged the dosimetric differences with respect to the planning dose. Second, these results were compared, by a sensitivity/specificity test, to the answers of a physician. Third, the physician, supported by the multidisciplinary team, performed a self-analysis of the provided answers and translated them into mathematical rules in order to upgrade the protocol. The upgraded protocol was applied to different definitions of the target volume (i.e. deformed CTV + 0, 2 and 4 mm), in order to quantify how the number of flags decreases when reducing the CTV-to-PTV margin.
RESULTS
The sensitivity of the initial protocol was very low, specifically for the orange flags. The best values were 0.84 for red and 0.15 for orange flags. After the review and upgrade process, the sensitivity of the upgraded protocol increased to 0.96 for red and 0.84 for orange flags. The number of patients flagged per week with the final (upgraded) protocol decreased in median by 26% and 18% for red and orange flags, respectively, when reducing the CTV-to-PTV margin from 4 to 2 mm. This resulted in only one patient flagged at the last fraction for both red and orange flags.
CONCLUSION
Our results demonstrate the value of iterative protocol design with retrospective data, and shows the feasibility of automatically-triggered ART using simple dosimetric rules to mimic the physician's decisions. Using a proper target volume definition is important and influences the flagging rate, particularly when decreasing the CTV-to-PTV margin.
Topics: Humans; Radiotherapy Dosage; Radiotherapy Planning, Computer-Assisted; Retrospective Studies; Radiotherapy, Intensity-Modulated; Head and Neck Neoplasms; Clinical Protocols
PubMed: 37448193
DOI: 10.1002/acm2.14095 -
IEEE Transactions on Cybernetics Nov 2023This work aims at presenting a new sampled-data model-free adaptive control (SDMFAC) for continuous-time systems with the explicit use of sampling period and past input...
This work aims at presenting a new sampled-data model-free adaptive control (SDMFAC) for continuous-time systems with the explicit use of sampling period and past input and output (I/O) data to enhance control performance. A sampled-data-based dynamical linearization model (SDDLM) is established to address the unknown nonlinearities and nonaffine structure of the continuous-time system, which all the complex uncertainties are compressed into a parameter gradient vector that is further estimated by designing a parameter updating law. By virtue of the SDDLM, we propose a new SDMFAC that not only can use both additional control information and sampling period information to improve control performance but also can restrain uncertainties by including a parameter adaptation mechanism. The proposed SDMFAC is data-driven and thus overcomes the problems caused by model-dependence as in the traditional control design methods. The simulation study is performed to demonstrate the validity of the results.
PubMed: 37988209
DOI: 10.1109/TCYB.2023.3324060 -
Plant Signaling & Behavior Dec 2024Plants, as sessile organisms, are subjected to diverse abiotic stresses, including salinity, desiccation, metal toxicity, thermal fluctuations, and hypoxia at different... (Review)
Review
Plants, as sessile organisms, are subjected to diverse abiotic stresses, including salinity, desiccation, metal toxicity, thermal fluctuations, and hypoxia at different phases of plant growth. Plants can activate messenger molecules to initiate a signaling cascade of response toward environmental stresses that results in either cell death or plant acclimation. Nitric oxide (NO) is a small gaseous redox-active molecule that exhibits a plethora of physiological functions in growth, development, flowering, senescence, stomata closure and responses to environmental stresses. It can also facilitate alteration in protein function and reprogram the gene profiling by direct or indirect interaction with different target molecules. The bioactivity of NO can be manifested through different redox-based protein modifications including -nitrosylation, protein nitration, and metal nitrosylation in plants. Although there has been considerable progress in the role of NO in regulating stress signaling, still the physiological mechanisms regarding the abiotic stress tolerance in plants remain unclear. This review summarizes recent advances in understanding the emerging knowledge regarding NO function in plant tolerance against abiotic stresses. The manuscript also highlighted the importance of NO as an abiotic stress modulator and developed a rational design for crop cultivation under a stress environment.
Topics: Nitric Oxide; Signal Transduction; Acclimatization; Cell Death; Stress, Physiological
PubMed: 38190763
DOI: 10.1080/15592324.2023.2298053 -
Neural Networks : the Official Journal... Aug 2023Lifelong learning represents an emerging machine learning paradigm that aims at designing new methods providing accurate analyses in complex and dynamic real-world...
Lifelong learning represents an emerging machine learning paradigm that aims at designing new methods providing accurate analyses in complex and dynamic real-world environments. Although a significant amount of research has been conducted in image classification and reinforcement learning, very limited work has been done to solve lifelong anomaly detection problems. In this context, a successful method has to detect anomalies while adapting to changing environments and preserving knowledge to avoid catastrophic forgetting. While state-of-the-art online anomaly detection methods are able to detect anomalies and adapt to a changing environment, they are not designed to preserve past knowledge. On the other hand, while lifelong learning methods are focused on adapting to changing environments and preserving knowledge, they are not tailored for detecting anomalies, and often require task labels or task boundaries which are not available in task-agnostic lifelong anomaly detection scenarios. This paper proposes VLAD, a novel VAE-based Lifelong Anomaly Detection method addressing all these challenges simultaneously in complex task-agnostic scenarios. VLAD leverages the combination of lifelong change point detection and an effective model update strategy supported by experience replay with a hierarchical memory maintained by means of consolidation and summarization. An extensive quantitative evaluation showcases the merit of the proposed method in a variety of applied settings. VLAD outperforms state-of-the-art methods for anomaly detection, presenting increased robustness and performance in complex lifelong settings.
Topics: Knowledge; Machine Learning; Reinforcement, Psychology; Upper Extremity
PubMed: 37307668
DOI: 10.1016/j.neunet.2023.05.032