Search

Brain segmentation from neonatal MRI images is a very challenging task due to large changes in the shape of cerebral structures and variations in signal intensities reflecting the gestational process. In this context, there is a clear need for segmentation techniques that are robust to variations in image contrast and to the spatial configuration of anatomical structures. In this work, we evaluate the potential of synthetic learning, a contrast‐independent model trained using synthetic images generated from the ground truth labels of very few subjects. We base our experiments on the dataset released by the developmental Human Connectome Project, for which high‐quality images are available for more than 700 babies aged between 26 and 45 weeks postconception. First, we confirm the impressive performance of a standard UNet trained on a few volumes, but also confirm that such models learn intensity‐related features specific to the training domain. We then confirm the robustness of the synthetic learning approach to variations in image contrast. However, we observe a clear influence of the age of the baby on the predictions. We improve the performance of this model by enriching the synthetic training set with realistic motion artifacts and over‐segmentation of the white matter. Based on extensive visual assessment, we argue that the better performance of the model trained on real T2w data may be due to systematic errors in the ground truth. We propose an original experiment allowing us to show that learning from real data will reproduce any systematic bias affecting the training set, while synthetic models can avoid this limitation. Overall, our experiments confirm that synthetic learning is an effective solution for segmenting neonatal brain MRI. Our adapted synthetic learning approach combines key features that will be instrumental for large multisite studies and clinical applications. [ABSTRACT FROM AUTHOR]

Although mouse‐tracking has been taken as a real‐time window on different aspects of human decision‐making processes, whether purely semantic information affects response conflict at the level of motor output as measured through mouse movements is still unknown. Here, across two experiments, we investigated the effects of semantic knowledge by predicting participants' performance in a standard keyboard task and in a mouse‐tracking task through distributional semantics, a usage‐based modeling approach to meaning. In Experiment 1, participants were shown word pairs and were required to perform a two‐alternative forced choice task selecting either the more abstract or the more concrete word, using standard keyboard presses. In Experiment 2, participants performed the same task, yet this time response selection was achieved by moving the computer mouse. Results showed that the involvement of semantic components in the task at hand is observable using both standard reaction times (Experiment 1) as well as using indexes extracted from mouse trajectories (Experiment 2). In particular, mouse trajectories reflected the response conflict and its temporal evolution, with a larger deviation for increasing word semantic relatedness. These findings support the validity of mouse‐tracking as a method to detect deep and implicit decision‐making features. Additionally, by demonstrating that a usage‐based model of meaning can account for the different degrees of cognitive conflict associated with task achievement, these findings testify the impact of the human semantic memory on decision‐making processes. [ABSTRACT FROM AUTHOR]

Temporal event localisation (TEL) has recently attracted increasing attention due to the rapid development of video platforms. Existing methods are based on either fully/weakly supervised or unsupervised learning, and thus they rely on expensive data annotation and time‐consuming training. Moreover, these models, which are trained on specific domain data, limit the model generalisation to data distribution shifts. To cope with these difficulties, the authors propose a zero‐shot TEL method that can operate without training data or annotations. Leveraging large‐scale vision and language pre‐trained models, for example, CLIP, we solve the two key problems: (1) how to find the relevant region where the event is likely to occur; (2) how to determine event duration after we find the relevant region. Query guided optimisation for local frame relevance relying on the query‐to‐frame relationship is proposed to find the most relevant frame region where the event is most likely to occur. Proposal generation method relying on the frame‐to‐frame relationship is proposed to determine the event duration. The authors also propose a greedy event sampling strategy to predict multiple durations with high reliability for the given event. The authors' methodology is unique, offering a label‐free, training‐free, and domain‐free approach. It enables the application of TEL purely at the testing stage. The practical results show it achieves competitive performance on the standard Charades‐STA and ActivityCaptions datasets. [ABSTRACT FROM AUTHOR]

Content‐based image retrieval (CBIR) is the problem of searching for items in an image database that are similar to the query image. Most of the existing image retrieval methods are trained based on metric learning loss functions (e.g. contrastive loss or triplet loss), however, which require the use of hard sample mining strategies (HMS) to better train the model. The HMS implies that picking out hard positive or negative samples increases the complexity of model training and requires a large amount of additional training time. To address this issue, lessons from recent work are leveraged on representation learning and a model called GS is proposed that combines the state‐of‐the‐art Generalized‐Mean (GeM) pooling and the smoothed average precision (AP). The entire network can be learned end‐to‐end by approximating the non‐differentiable AP function to a differentiable one‐without mining hard samples, only image‐level annotations. A model named GSA is also presented which achieves excellent retrieval performance jointly trained by two various loss functions. Experimental results validate the effectiveness of the proposed approach and demonstrate the competitive performance on a common standard image retrieval dataset (Revisited Oxford and Paris). [ABSTRACT FROM AUTHOR]

Power‐Flow (PF) solution in isolated microgrids has attracted notable attention recently, because these systems present various particularities compared with the traditional PF solution in large meshed transmission networks. In this sense, this paper develops a novel Newton‐like PF solver for isolated microgrids. The new proposal is based on the Modified Midpoint method and shows high convergence order with relatively low computational burden. These characteristics bring superior theoretical performance compared with the standard Newton–Raphson (NR) method and other high order techniques, which has been conventionally used. Extensive simulations are performed on various small‐, and large‐scale benchmark Microgrids under different loading conditions and R/X ratios. Results provided serve to confirm the theoretical features of the developed solver, outperforming the NR technique as well as other recently developed solvers in all the studied systems with acceptable reliability even under high stressed conditions. [ABSTRACT FROM AUTHOR]

Animals regulate their nutrient consumption to maximize the expression of fitness traits with competing nutritional needs ("nutritional trade‐offs"). Nutritional trade‐offs have been studied using a response surface modeling approach known as the Geometric Framework for nutrition (GF). Current experimental design in GF studies does not explore the entire area of the nutritional space resulting in performance landscapes that may be incomplete. This hampers our ability to understand the properties of the performance landscape (e.g., peak shape) from which meaningful biological insights can be obtained. Here, I tested alternative experimental designs to explore the full range of the performance landscape in GF studies. I compared the performance of the standard GF design strategy with three alternatives: hexagonal, square, and random points grid strategies with respect to their accuracy in reconstructing baseline performance landscapes from a landmark GF dataset. I showed that standard GF design did not reconstruct the properties of baseline performance landscape appropriately particularly for traits that respond strongly to the interaction between nutrients. Moreover, the peak estimates in the reconstructed performance landscape using standard GF design were accurate in terms of the nutrient ratio but incomplete in terms of peak shape. All other grid designs provided more accurate reconstructions of the baseline performance landscape while also providing accurate estimates of nutrient ratio and peak shape. Thus, alternative experimental designs can maximize information from performance landscapes in GF studies, enabling reliable biological insights into nutritional trade‐offs and physiological limits within and across species. [ABSTRACT FROM AUTHOR]

Humans have the ability to learn surprisingly complicated statistical information in a variety of modalities and situations, often based on relatively little input. These statistical learning (SL) skills appear to underlie many kinds of learning, but despite their ubiquity, we still do not fully understand precisely what SL is and what individual differences on SL tasks reflect. Here, we present experimental work suggesting that at least some individual differences arise from stimulus‐specific variation in perceptual fluency: the ability to rapidly or efficiently code and remember the stimuli that SL occurs over. Experiment 1 demonstrates that participants show improved SL when the stimuli are simple and familiar; Experiment 2 shows that this improvement is not evident for simple but unfamiliar stimuli; and Experiment 3 shows that for the same stimuli (Chinese characters), SL is higher for people who are familiar with them (Chinese speakers) than those who are not (English speakers matched on age and education level). Overall, our findings indicate that performance on a standard SL task varies substantially within the same (visual) modality as a function of whether the stimuli involved are familiar or not, independent of stimulus complexity. Moreover, test–retest correlations of performance in an SL task using stimuli of the same level of familiarity (but distinct items) are stronger than correlations across the same task with stimuli of different levels of familiarity. Finally, we demonstrate that SL performance is predicted by an independent measure of stimulus‐specific perceptual fluency that contains no SL component at all. Our results suggest that a key component of SL performance may be related to stimulus‐specific processing and familiarity. [ABSTRACT FROM AUTHOR]

Spatial transcriptomics is considered as an important part of spatiotemporal molecular images to bridge molecular information with clinical images. Of those potentials and opportunities, the excellent quality of human sample preparation and handling will ensure the precise and reliable information generated from clinical spatial transcriptome. The present study aims at defining potential factors that might influence the quality of spatial transcriptomics in lung cancer, para‐cancer, or normal tissues, pathological images of sections and the RNA integrity before spatial transcriptome sequencing. We categorised potential influencing factors from clinical aspects, including patient selection, pathological definition, surgical types, sample harvest, temporary preservation conditions and solutions, frozen approaches, transport and storage conditions and duration. We emphasis on the relationship between the combination of histological scores with RNA integrity number (RIN) and the unique molecular identifier (UMI), which is determines the quality of of spatial transcriptomics; however, we did not find significantly relevance between them. Our results showed that isolated times and dry conditions of sample are critical for the UMI and the quality of spatial transcriptomic samples. Thus, clinical procedures of sample preparation should be furthermore optimised and standardised as new standards of operation performance for clinical spatial transcriptome. Our data suggested that the temporary preservation time and condition of samples at operation room should be within 30 min and in 'dry' status. The direct cryo‐preservation within OCT media for human lung sample is recommended. Thus, we believe that clinical spatial transcriptome will be a decisive approach and bridge in the development of spatiotemporal molecular images and provide new insights for understanding molecular mechanisms of diseases at multi‐orientations. [ABSTRACT FROM AUTHOR]