RESUMO
Vocal communication depends on distinguishing self-generated vocalizations from other sounds. Vocal motor corollary discharge (CD) signals are thought to support this ability by adaptively suppressing auditory cortical responses to auditory feedback. One challenge is that vocalizations, especially those produced during courtship and other social interactions, are accompanied by other movements and are emitted during a state of heightened arousal, factors that could potentially modulate auditory cortical activity. Here, we monitor auditory cortical activity, ultrasonic vocalizations (USVs), and other non-vocal courtship behaviors in a head-fixed male mouse while he interacts with a female mouse. This approach reveals a vocalization-specific signature in the auditory cortex that suppresses the activity of USV playback-excited neurons, emerges before vocal onset, and scales with USV band power. Notably, this vocal modulatory signature is also present in the auditory cortex of congenitally deaf mice, revealing an adaptive vocal CD signal that manifests independently of auditory feedback or auditory experience.
RESUMO
This review examines the recent advancements in transparent electrodes and their crucial role in multimodal sensing technologies. Transparent electrodes, notable for their optical transparency and electrical conductivity, are revolutionizing sensors by enabling the simultaneous detection of diverse physical, chemical, and biological signals. Materials like graphene, carbon nanotubes, and conductive polymers, which offer a balance between optical transparency, electrical conductivity, and mechanical flexibility, are at the forefront of this development. These electrodes are integral in various applications, from healthcare to solar cell technologies, enhancing sensor performance in complex environments. The paper addresses challenges in applying these electrodes, such as the need for mechanical flexibility, high optoelectronic performance, and biocompatibility. It explores new materials and innovative techniques to overcome these hurdles, aiming to broaden the capabilities of multimodal sensing devices. The review provides a comparative analysis of different transparent electrode materials, discussing their applications and the ongoing development of novel electrode systems for multimodal sensing. This exploration offers insights into future advancements in transparent electrodes, highlighting their transformative potential in bioelectronics and multimodal sensing technologies.
RESUMO
Synthetic data generation has emerged as a promising solution to overcome the challenges which are posed by data scarcity and privacy concerns, as well as, to address the need for training artificial intelligence (AI) algorithms on unbiased data with sufficient sample size and statistical power. Our review explores the application and efficacy of synthetic data methods in healthcare considering the diversity of medical data. To this end, we systematically searched the PubMed and Scopus databases with a great focus on tabular, imaging, radiomics, time-series, and omics data. Studies involving multi-modal synthetic data generation were also explored. The type of method used for the synthetic data generation process was identified in each study and was categorized into statistical, probabilistic, machine learning, and deep learning. Emphasis was given to the programming languages used for the implementation of each method. Our evaluation revealed that the majority of the studies utilize synthetic data generators to: (i) reduce the cost and time required for clinical trials for rare diseases and conditions, (ii) enhance the predictive power of AI models in personalized medicine, (iii) ensure the delivery of fair treatment recommendations across diverse patient populations, and (iv) enable researchers to access high-quality, representative multimodal datasets without exposing sensitive patient information, among others. We underline the wide use of deep learning based synthetic data generators in 72.6 % of the included studies, with 75.3 % of the generators being implemented in Python. A thorough documentation of open-source repositories is finally provided to accelerate research in the field.
RESUMO
Cancer research encompasses data across various scales, modalities, and resolutions, from screening and diagnostic imaging to digitized histopathology slides to various types of molecular data and clinical records. The integration of these diverse data types for personalized cancer care and predictive modeling holds the promise of enhancing the accuracy and reliability of cancer screening, diagnosis, and treatment. Traditional analytical methods, which often focus on isolated or unimodal information, fall short of capturing the complex and heterogeneous nature of cancer data. The advent of deep neural networks has spurred the development of sophisticated multimodal data fusion techniques capable of extracting and synthesizing information from disparate sources. Among these, Graph Neural Networks (GNNs) and Transformers have emerged as powerful tools for multimodal learning, demonstrating significant success. This review presents the foundational principles of multimodal learning including oncology data modalities, taxonomy of multimodal learning, and fusion strategies. We delve into the recent advancements in GNNs and Transformers for the fusion of multimodal data in oncology, spotlighting key studies and their pivotal findings. We discuss the unique challenges of multimodal learning, such as data heterogeneity and integration complexities, alongside the opportunities it presents for a more nuanced and comprehensive understanding of cancer. Finally, we present some of the latest comprehensive multimodal pan-cancer data sources. By surveying the landscape of multimodal data integration in oncology, our goal is to underline the transformative potential of multimodal GNNs and Transformers. Through technological advancements and the methodological innovations presented in this review, we aim to chart a course for future research in this promising field. This review may be the first that highlights the current state of multimodal modeling applications in cancer using GNNs and transformers, presents comprehensive multimodal oncology data sources, and sets the stage for multimodal evolution, encouraging further exploration and development in personalized cancer care.
RESUMO
In both plant breeding and crop management, interpretability plays a crucial role in instilling trust in AI-driven approaches and enabling the provision of actionable insights. The primary objective of this research is to explore and evaluate the potential contributions of deep learning network architectures that employ stacked LSTM for end-of-season maize grain yield prediction. A secondary aim is to expand the capabilities of these networks by adapting them to better accommodate and leverage the multi-modality properties of remote sensing data. In this study, a multi-modal deep learning architecture that assimilates inputs from heterogeneous data streams, including high-resolution hyperspectral imagery, LiDAR point clouds, and environmental data, is proposed to forecast maize crop yields. The architecture includes attention mechanisms that assign varying levels of importance to different modalities and temporal features that, reflect the dynamics of plant growth and environmental interactions. The interpretability of the attention weights is investigated in multi-modal networks that seek to both improve predictions and attribute crop yield outcomes to genetic and environmental variables. This approach also contributes to increased interpretability of the model's predictions. The temporal attention weight distributions highlighted relevant factors and critical growth stages that contribute to the predictions. The results of this study affirm that the attention weights are consistent with recognized biological growth stages, thereby substantiating the network's capability to learn biologically interpretable features. Accuracies of the model's predictions of yield ranged from 0.82-0.93 R2 ref in this genetics-focused study, further highlighting the potential of attention-based models. Further, this research facilitates understanding of how multi-modality remote sensing aligns with the physiological stages of maize. The proposed architecture shows promise in improving predictions and offering interpretable insights into the factors affecting maize crop yields, while demonstrating the impact of data collection by different modalities through the growing season. By identifying relevant factors and critical growth stages, the model's attention weights provide valuable information that can be used in both plant breeding and crop management. The consistency of attention weights with biological growth stages reinforces the potential of deep learning networks in agricultural applications, particularly in leveraging remote sensing data for yield prediction. To the best of our knowledge, this is the first study that investigates the use of hyperspectral and LiDAR UAV time series data for explaining/interpreting plant growth stages within deep learning networks and forecasting plot-level maize grain yield using late fusion modalities with attention mechanisms.
RESUMO
Systemic lupus erythematosus (SLE) is an autoimmune disease that affects multiple organs and systems. Ocular involvement is estimated to manifest in one-third of individuals with SLE, of which lupus retinopathy and choroidopathy represent the severe subtype accompanied by vision impairment. Advancements in multimodal ophthalmic imaging have allowed ophthalmologists to reveal subclinical microvascular and structural changes in fundus of patients with SLE without ocular manifestations. Both ocular manifestations and subclinical fundus damage have been shown to correlate with SLE disease activity and, in some patients, even precede other systemic injuries as the first presentation of SLE. Moreover, ocular fundus might serve as a window into the state of systemic vasculitis in patients with SLE. Given the similarities of the anatomy, physiological and pathological processes shared among ocular fundus, and other vital organ damage in SLE, such as kidney and brain, it is assumed that ocular fundus involvement has implications in the diagnosis and evaluation of other systemic impairments. Therefore, evaluating the fundus characteristics of patients with SLE not only contributes to the early diagnosis and intervention of potential vision damage, but also holds considerate significance for the evaluation of SLE vasculitis state and prediction of other systemic injuries.
Assuntos
Fundo de Olho , Lúpus Eritematoso Sistêmico , Humanos , Lúpus Eritematoso Sistêmico/complicações , Lúpus Eritematoso Sistêmico/diagnóstico , Doenças Retinianas/etiologia , Doenças Retinianas/diagnóstico , Doenças Retinianas/patologia , Doenças da Coroide/etiologia , Doenças da Coroide/diagnósticoRESUMO
Introduction: The prevailing theories of consciousness consider the integration of different sensory stimuli as a key component for this phenomenon to rise on the brain level. Despite many theories and models have been proposed for multisensory integration between supraliminal stimuli (e.g., the optimal integration model), we do not know if multisensory integration occurs also for subliminal stimuli and what psychophysical mechanisms it follows. Methods: To investigate this, subjects were exposed to visual (Virtual Reality) and/or haptic stimuli (Electro-Cutaneous Stimulation) above or below their perceptual threshold. They had to discriminate, in a two-Alternative Forced Choice Task, the intensity of unimodal and/or bimodal stimuli. They were then asked to discriminate the sensory modality while recording their EEG responses. Results: We found evidence of multisensory integration for supraliminal condition, following the classical optimal model. Importantly, even for subliminal trials participant's performances in the bimodal condition were significantly more accurate when discriminating the intensity of the stimulation. Moreover, significant differences emerged between unimodal and bimodal activity templates in parieto-temporal areas known for their integrative role. Discussion: These converging evidences - even if preliminary and needing confirmation from the collection of further data - suggest that subliminal multimodal stimuli can be integrated, thus filling a meaningful gap in the debate about the relationship between consciousness and multisensory integration.
RESUMO
We present a 56-year-old female with a macular vortex vein in her right eye and a varix of vortex vein ampulla in the inferior nasal fundus of her left eye. The choroidal lesions were evaluated by multimodal imaging including fundoscopy with contact lens, ultra-widefield fundus photography, swept-souse optical coherence tomography (SS-OCT), enface image of widefield optical coherence tomography (widefield enface-OCT), and ultra-widefield fundus angiography. Widefield enface-OCT revealed submacular large choroidal vessels in the right eye. Ultra-widefield indocyanine green fluorescence angiography (UWICGA) of the right eye showed the dye of those submacular choroidal vessels drained from the ampullae beneath the macula. Fundoscopy revealed an elevated lesion with crescent shadows in the inferior nasal fundus of the left eye. Dynamic fundoscopy with compression of the left eye resulted in a diminishing of the elevation and release of the compression resulted in an enlargement of the elevation. Ultra-widefield fundus photography of the left eye in the right inferior gaze revealed an elevated lesion with a crescent shadow in the inferior nasal fundus, while it is not prominent in the primary gaze. The B-scan of SS-OCT revealed a hyporeflective lesion in the choroid beneath the elevated lesion of the left eye. The elevated lesion was consistent with the vortex vein ampulla on UWICGA. This is the first case where two different choroidal vascular anomalies, macular vortex vein and varix of vortex ampulla, coexist in a single patient. Multimodal imaging is useful to visualize and diagnose choroidal vascular anomalies.
RESUMO
Cloning by somatic cell nuclear transfer (SCNT) remained challenging for Rhesus monkeys, mostly due to its low efficiency and neonatal death. Genome-scale analyses revealed that monkey SCNT embryos displayed widespread DNA methylation and transcriptional alterations, thus including loss of genomic imprinting that correlated with placental dysfunction. The transfer of inner cell masses (ICM) from cloned blastocysts into ICM-depleted fertilized embryos rescued placental insufficiency and gave rise to a cloned Rhesus monkey that reached adulthood without noticeable abnormalities.
RESUMO
BACKGROUND: Globally, the demographic shift towards an aging population leads to significant challenges in healthcare systems, specifically due to an increasing incidence of multimorbidity resulting in polypharmacy among the elderly. Simultaneously, sleep disorders are a common complaint for elderly people. A treatment with pharmacological therapies often leads to side effects causing a high potential for dependency. Within this context, there is a high need to explore non-pharmacological therapeutic approaches. The purpose of this study is to evaluate the effectiveness of acupuncture and music therapy, both individually and combined as a multimodal therapy, in the treatment of sleep disorders in individuals aged 70 years and older. METHODS: We conduct a confirmatory randomized controlled trial using a two-factorial study design. A total of n = 100 elderly people receive evidence-based standard care information for age-related sleep disorders. Beyond that, patients are randomly assigned into four groups of n = 25 each to receive acupuncture, receptive music therapy with a monochord, multimodal therapy with both acupuncture and music therapy, or no further therapy. The study's primary outcome measurement is the improvement in sleep quality as assessed by the Pittsburgh Sleep Quality Index (PSQI) (global score), at the end of intervention. Additionally, depression scores (Geriatric Depression Scale), health-related quality of life (Short-Form-Health Survey-12), neurovegetative activity measured via heart rate variability, and safety data are collected as secondary outcomes. Using a mixed-methods approach, a qualitative process evaluation will be conducted to complement the quantitative data. DISCUSSION: The study is ongoing and the last patient in is expected to be enrolled in April 2024. The results can provide valuable insights into the effectiveness of non-pharmacological interventions for sleep disorders among the elderly, contributing to a more personalized and holistic approach in geriatric healthcare. TRIAL REGISTRATION: German Clinical Trials Register (DRKS00031886).
Assuntos
Terapia por Acupuntura , Musicoterapia , Transtornos do Sono-Vigília , Humanos , Terapia por Acupuntura/métodos , Idoso , Transtornos do Sono-Vigília/terapia , Masculino , Feminino , Ensaios Clínicos Controlados Aleatórios como Assunto , Idoso de 80 Anos ou maisRESUMO
INTRODUCTION: Prep-4-RT is a co-designed stepped-care multimodal prehabilitation program for people scheduled to receive radiotherapy for head and neck cancer (HNC). Prehabilitation, which occurs between diagnosis and treatment commencement, aims to improve a patient's health to reduce the incidence and severity of current and future impairments. HNC treatment can be distressing and has detrimental impacts on function and quality of life. HNC patients have increased social vulnerabilities including higher rates of socio-economic disadvantage and engagement in lifestyle habits which increase cancer risk. High levels of physical and psychological impacts of HNC treatment and increased social vulnerabilities of this population warrant investigation of optimal pathways of care, such as prehabilitation. This paper describes a research protocol to evaluate the feasibility of Prep-4-RT, which was designed to prepare HNC patients for the physical and psychological impacts of radiotherapy. METHODS AND ANALYSIS: At least sixty adult HNC patients, scheduled to receive radiotherapy (with or without chemotherapy), will be recruited over a five-month period. All participants will receive access to Prep-4-RT self-management resources. Participants identified through screening as high-risk will also be offered individualised interventions with relevant allied health professionals prior to the commencement of radiotherapy (psychologists, dietitians, speech pathologists and physiotherapists). Participants will complete evaluation surveys assessing their experiences with Prep-4-RT resources and interventions. Clinicians will also complete program evaluation surveys. Primary feasibility outcomes include adoption (uptake and intention to try) and fidelity (adherence to the specialist prehabilitation pathway). Secondary feasibility outcomes include acceptability (patient and clinician) of and satisfaction (patient) with Prep-4-RT as well as operational costs. Feasibility outcome data will be analysed using exact binomial and one-sample t tests, as appropriate. ETHICS AND DISSEMINATION: Ethics approval has been obtained at the Peter MacCallum Cancer Centre in Melbourne, Australia. Results will be presented at national conferences and published in peer-reviewed journal(s) so that it can be accessed by clinicians involved in the care of HNC patients receiving radiotherapy. If the model of care is found to be feasible and acceptable, the transferability and scalability to other cancer centres, or for other cancer types, may be investigated. REGISTRATION DETAILS: ANZCTA (Australian New Zealand Clinical Trials Registry) ACTRN12623000770662.
RESUMO
This paper employs a high-throughput parallel batch (microtiter plate) adsorption screen with sequential salt step increases to rapidly generate protein elution profiles for multiple resins at different pHs using a protein library. The chromatographic set used in this work includes single mode, multimodal anion-exchange (MMA), and multimodal cation-exchange (MMC) resins. The protein library consists of proteins with isoelectric points ranging from 5.1 to 11.4 with varying hydrophobicities as determined by their retention on hydrophobic interaction chromatography. The batch sequential experiments are carried out using one protein at a time with a wide set of resins at multiple pH conditions, thus enabling simple microtiter plate detection. A mathematical formulation is then used to determine the first moment of the distributions from each chromatogram (sequential step elution) generated in the parallel batch experiments. Batch data first moments (expressed in salt concentration) are then compared to results obtained from column linear salt gradient elution, and the techniques are shown to be consistent. In addition, first moment data are used to calculate one-resin separability scores, which are a measure of a resin's ability, at a specified pH, to separate the entire set of proteins in the library from one another. Again, the results from the batch and column experiments are shown to be comparable. The first moment data sets were then employed to calculate the two-resin separability scores, which are a measure of the ability of two resins to synergistically separate the entire set of proteins in the library. Importantly, these results based on the two-resin separability performances derived from the batch and column experiments were again shown to be consistent. This approach for rapidly screening large numbers of chromatographic resins and mobile phase conditions for their elution behavior may prove useful for enabling the rapid discovery of new chromatographic ligands and resins.
RESUMO
In Alzheimer's disease (AD) assessment, traditional deep learning approaches have often employed separate methodologies to handle the diverse modalities of input data. Recognizing the critical need for a cohesive and interconnected analytical framework, we propose the AD-Transformer, a novel transformer-based unified deep learning model. This innovative framework seamlessly integrates structural magnetic resonance imaging (sMRI), clinical, and genetic data from the extensive Alzheimer's Disease Neuroimaging Initiative (ADNI) database, encompassing 1651 subjects. By employing a Patch-CNN block, the AD-Transformer efficiently transforms image data into image tokens, while a linear projection layer adeptly converts non-image data into corresponding tokens. As the core, a transformer block learns comprehensive representations of the input data, capturing the intricate interplay between modalities. The AD-Transformer sets a new benchmark in AD diagnosis and Mild Cognitive Impairment (MCI) conversion prediction, achieving remarkable average area under curve (AUC) values of 0.993 and 0.845, respectively, surpassing those of traditional image-only models and non-unified multimodal models. Our experimental results confirmed the potential of the AD-Transformer as a potent tool in AD diagnosis and MCI conversion prediction. By providing a unified framework that jointly learns holistic representations of both image and non-image data, the AD-Transformer paves the way for more effective and precise clinical assessments, offering a clinically adaptable strategy for leveraging diverse data modalities in the battle against AD.
RESUMO
BACKGROUND: Omphalocele is a congenital midline abdominal wall defect resulting in herniation of viscera into a membrane-covered sac. Pulmonary complications, including pulmonary hypoplasia, pulmonary hypertension, and prolonged respiratory support are a leading cause of neonatal morbidity and mortality. OBJECTIVE(S): This study aimed to assess the role of fetal MRI-derived lung volumes and omphalocele defect size as clinical tools to prognosticate postnatal pulmonary morbidity and neonatal mortality in those with a prenatally diagnosed omphalocele (PDO). STUDY DESIGN: This was a retrospective cohort study of all pregnancies with PDO at our fetal center from 2007-2023. Pregnancies with aneuploidy or concurrent life-limiting fetal anomalies were excluded. Using fetal MRI, observed-to-expected total fetal lung volume (O/E TLV) ratios were determined by a previously published method. The transverse diameter of the abdominal defect was also measured. The O/E TLV ratios and abdominal defect measurements were compared with postnatal outcomes. The primary outcome was death at any time. Secondary outcomes included death in the first 30 days of life or before discharge from birth hospitalization, the requirement of respiratory support with intubation and mechanical ventilation, or development of pulmonary hypertension. RESULTS: Of 101 pregnancies with a PDO, 54 pregnancies (53.5%) with prenatally diagnosed omphalocele met inclusion criteria. There was a significant increase in the rate of death when compared between the three O/E TLV classifications: 1/36 (2.8%) in the O/E ≥ 50% group, 3/14 (21.4%) in the O/E 25 - 49.9% group, and 4/4 (100%) in the O/E < 25% group (p < 0.001). The rate of intubation increased with the severity of O/E TLV classification, with 27.8% in the O/E ≥ 50% group, 64.3% in the O/E 25 - 49.9% group, and 100% in the O/E < 25% group (pâ¯=â¯0.003). The rate of pulmonary hypertension was also higher in the O/E 25 - 49.9% (50.0%) and the O/E < 25% (50.0%) groups compared to the O/E ≥ 50% group (8.3%, pâ¯=â¯0.002). There was no association between the transverse diameter of the abdominal wall defect and the primary outcome of death (ORâ¯=â¯1.08 95% CIâ¯=â¯[0.65-1.78], p=0.77). CONCLUSIONS: In our cohort of patients with PDO, O/E TLV <50% is associated with death, need for intubation, prolonged intubation, and pulmonary hypertension. In contrast, omphalocele size demonstrated no prognostic value for these outcomes. The strong association between low fetal lung volume on MRI and poor neonatal outcomes highlights the utility of fetal MRI for estimating postnatal prognosis. Clinicians can utilize fetal lung volumes to direct perinatal counseling and optimize the plan of care.
RESUMO
The interplay between the tumor cells and their microenvironments is as inseparable as the relationship between "seeds" and "soil." The tumor microenvironments (TMEs) exacerbate malignancy by enriching malignant cell subclones, generating extracellular matrices, and recruiting immunosuppressive cells, thereby diminishing the efficacy of clinical therapies. Modulating TMEs has emerged as a promising strategy to enhance cancer therapy. However, the existing drugs used in clinical settings do not target the TMEs specifically, underscoring the urgent need for advanced strategies. Bioactive materials present unique opportunities for modulating TMEs. Poly(amino acid)s with precisely controllable structures and properties offer exceptional characteristics, such as diverse structural units, excellent biosafety, ease of modification, sensitive biological responsiveness, and unique secondary structures. These attributes hold significant potential for the modulation of TMEs and clinical applications further. Consequently, developing bioactive poly(amino acid)s capable of modulating the TMEs by elucidating structure-activity relationships and mechanisms is a promising approach for innovative clinical oncology therapy. This review summarizes the recent progress of our research team in developing bioactive poly(amino acid)s for multi-modal tumor therapy. First, a brief overview of poly(amino acid) synthesis and their advantages as nanocarriers is provided. Subsequently, the pioneering research of our research group on synthesizing the biologically responsive, dynamically allosteric, and immunologically effective poly(amino acid)s are highlighted. These poly(amino acid)s are designed to enhance tumor therapy by modulating the intracellular, extracellular matrix, and stromal cell microenvironments. Finally, the future development of poly(amino acid)s is discussed. This review will guide and inspire the construction of bioactive poly(amino acid)s with promising clinical applications in cancer therapy. This article is categorized under: Therapeutic Approaches and Drug Discovery > Nanomedicine for Oncologic Disease Biology-Inspired Nanomaterials > Peptide-Based Structures.
Assuntos
Aminoácidos , Neoplasias , Microambiente Tumoral , Humanos , Neoplasias/tratamento farmacológico , Aminoácidos/química , Aminoácidos/uso terapêutico , Animais , Microambiente Tumoral/efeitos dos fármacos , Camundongos , Polímeros/química , Antineoplásicos/química , Antineoplásicos/farmacologia , Antineoplásicos/uso terapêuticoRESUMO
OBJECTIVES: The objective of this study is to assess accuracy, time-efficiency and consistency of a novel artificial intelligence (AI)-driven automated tool for cone-beam computed tomography (CBCT) and intraoral scan (IOS) registration compared with manual and semi-automated approaches. MATERIALS AND METHODS: A dataset of 31 intraoral scans (IOSs) and CBCT scans was used to validate automated IOS-CBCT registration (AR) when compared with manual (MR) and semi-automated registration (SR). CBCT scans were conducted by placing cotton rolls between the cheeks and teeth to facilitate gingival delineation. The time taken to perform multimodal registration was recorded in seconds. A qualitative analysis was carried out to assess the correspondence between hard and soft tissue anatomy on IOS and CBCT. In addition, a quantitative analysis was conducted by measuring median surface deviation (MSD) and root mean square (RMS) differences between registered IOSs. RESULTS: AR was the most time-efficient, taking 51.4 ± 17.2 s, compared with MR (840 ± 168.9 s) and SR approaches (274.7 ± 100.7 s). Both AR and SR resulted in significantly higher qualitative scores, favoring perfect IOS-CBCT registration, compared with MR (p = .001). Additionally, AR demonstrated significantly superior quantitative performance compared with SR, as indicated by low MSD (0.04 ± 0.07 mm) and RMS (0.19 ± 0.31 mm). In contrast, MR exhibited a significantly higher discrepancy compared with both AR (MSD = 0.13 ± 0.20 mm; RMS = 0.32 ± 0.14 mm) and SR (MSD = 0.11 ± 0.15 mm; RMS = 0.40 ± 0.30 mm). CONCLUSIONS: The novel AI-driven method provided an accurate, time-efficient, and consistent multimodal IOS-CBCT registration, encompassing both soft and hard tissues. This approach stands as a valuable alternative to manual and semi-automated registration approaches in the presurgical implant planning workflow.
RESUMO
Ischemic lesion segmentation and the time since stroke (TSS) onset classification from paired multi-modal MRI imaging of unwitnessed acute ischemic stroke (AIS) patients is crucial, which supports tissue plasminogen activator (tPA) thrombolysis decision-making. Deep learning methods demonstrate superiority in TSS classification. However, they often overfit task-irrelevant features due to insufficient paired labeled data, resulting in poor generalization. We observed that unpaired data are readily available and inherently carry task-relevant cues, but are less often considered and explored. Based on this, in this paper, we propose to fully excavate the potential of unpaired unlabeled data and use them to facilitate the downstream AIS analysis task. We first analyze the utility of features at the varied grain and propose a multi-grained contrastive learning (MGCL) framework to learn task-related prior representations from both coarse-grained and fine-grained levels. The former can learn global prior representations to enhance the location ability for the ischemic lesions and perceive the healthy surroundings, while the latter can learn local prior representations to enhance the perception ability for semantic relation between the ischemic lesion and other health regions. To better transfer and utilize the learned task-related representation, we designed a novel multi-task framework to simultaneously achieve ischemic lesion segmentation and TSS classification with limited labeled data. In addition, a multi-modal region-related feature fusion module is proposed to enable the feature correlation and synergy between multi-modal deep image features for more accurate TSS decision-making. Extensive experiments on the large-scale multi-center MRI dataset demonstrate the superiority of the proposed framework. Therefore, it is promising that it helps better stroke evaluation and treatment decision-making.
RESUMO
PURPOSE: To identify risk factors associated with increased postoperative opioid consumption and inferior pain outcomes following knee and shoulder arthroscopy. METHODS: Using the data set from the NonOpioid Prescriptions after Arthroscopic Surgery in Canada (NO PAin) trial, eight prognostic factors were chosen a priori to evaluate their effect on opioid consumption and patient-reported pain following arthroscopic knee and shoulder surgery. The primary outcome was the number of oral morphine equivalents (OMEs) consumed at 2 and 6 weeks postoperatively. The secondary outcome was patient-reported postoperative pain using the Visual Analogue Scale (VAS) at 2 and 6 weeks postoperatively. A multivariable linear regression was used to analyse these outcomes with eight prognostic factors as independent variables. RESULTS: Tobacco usage was significantly associated with higher opioid usage at 2 (p < 0.001) and 6 weeks (p = 0.02) postoperatively. Former tobacco users had a higher 2-week (p = 0.002) and cumulative OME (p = 0.002) consumption compared to current and nonsmokers. Patients with a higher number of comorbidities (p = 0.006) and those who were employed (p = 0.006) reported higher pain scores at 6 weeks. Patients in the 'not employed/other' category had significantly lower pain scores at 6 weeks postoperatively (p = 0.046). CONCLUSION: Former smoking status was significantly associated with increased post-operative opioid consumption following knee and shoulder arthroscopy at 2 and 6 weeks postoperatively. Increased pain was found to be significantly associated with employment status and an increasing number of comorbidities at 6 weeks postoperatively. These findings can aid clinicians in identifying and mitigating increased opioid utilization as well as worse pain outcomes in high-risk patient populations. LEVEL OF EVIDENCE: Level III, cohort study.
RESUMO
We investigated the contribution of multisensory predictions to body ownership, and beyond, to the integration of body-related signals. Contrary to the prevailing idea, according to which, to be integrated, cues necessarily have to be perceived simultaneously, we instead proposed the prediction-confirmation account. According to this account, a perceived cue can be integrated with a predicted cue as long as both signals are relatively simultaneous. To test this hypothesis, a standard rubber hand illusion (RHI) paradigm was used. In the first part of each trial, the illusion was induced while participants observed the rubber hand being touched with a paintbrush. In the subsequent part of the trial, (i) both rubber hand and the participant's real hand were stroked as before (i.e., visible/synchronous condition), (ii) the rubber hand was not stroke anymore (i.e., visible/tactile-only condition), or (iii) both rubber hand and the participant's real hand were synchronously stroked while the location where the rubber hand was touched was occulted (i.e., occulted/synchronous condition). However, in this latter condition, participants still perceived the approaching movement of the paintbrush. Thus, based on this visual cue, the participants can properly predict the timepoint at which the tactile cue should occur (i.e., visuotactile predictions). Our major finding was that compared with the visible/tactile-only condition, the occulted/synchronous condition did not exhibit a decrease of the RHI as in the visible/synchronous condition. This finding supports the prediction-confirmation account and suggests that this mechanism operates even in the standard version of the RHI.