Explore the vast range of titles available.

This study investigates a 3D and fully convolutional neural network (CNN) for subcortical brain structure segmentation in MRI. 3D CNN architectures have been generally avoided due to their computational and memory requirements during inference. We address the problem via small kernels, allowing deeper architectures. We further model both local and global context by embedding intermediate-layer outputs in the final prediction, which encourages consistency between features extracted at different scales and embeds fine-grained information directly in the segmentation process. Our model is efficiently trained end-to-end on a graphics processing unit (GPU), in a single stage, exploiting the dense inference capabilities of fully CNNs. We performed comprehensive experiments over two publicly available datasets. First, we demonstrate a state-of-the-art performance on the ISBR dataset. Then, we report a large-scale multi-site evaluation over 1112 unregistered subject datasets acquired from 17 different sites (ABIDE dataset), with ages ranging from 7 to 64 years, showing that our method is robust to various acquisition protocols, demographics and clinical factors. Our method yielded segmentations that are highly consistent with a standard atlas-based approach, while running in a fraction of the time needed by atlas-based methods and avoiding registration/normalization steps. This makes it convenient for massive multi-site neuroanatomical imaging studies. To the best of our knowledge, our work is the first to study subcortical structure segmentation on such large-scale and heterogeneous data.

The segmentation of retinal vasculature from eye fundus images is a fundamental task in retinal image analysis. Over recent years, increasingly complex approaches based on sophisticated Convolutional Neural Network architectures have been pushing performance on well-established benchmark datasets. In this paper, we take a step back and analyze the real need of such complexity. We first compile and review the performance of 20 different techniques on some popular databases, and we demonstrate that a minimalistic version of a standard U-Net with several orders of magnitude less parameters, carefully trained and rigorously evaluated, closely approximates the performance of current best techniques. We then show that a cascaded extension (W-Net) reaches outstanding performance on several popular datasets, still using orders of magnitude less learnable weights than any previously published work. Furthermore, we provide the most comprehensive cross-dataset performance analysis to date, involving up to 10 different databases. Our analysis demonstrates that the retinal vessel segmentation is far from solved when considering test images that differ substantially from the training data, and that this task represents an ideal scenario for the exploration of domain adaptation techniques. In this context, we experiment with a simple self-labeling strategy that enables moderate enhancement of cross-dataset performance, indicating that there is still much room for improvement in this area. Finally, we test our approach on Artery/Vein and vessel segmentation from OCTA imaging problems, where we again achieve results well-aligned with the state-of-the-art, at a fraction of the model complexity available in recent literature. Code to reproduce the results in this paper is released.

Neonatal MRIs are used increasingly in preterm infants. However, it is not always feasible to analyze this data. Having a tool that assesses brain maturation during this period of extraordinary changes would be immensely helpful. Approaches based on deep learning approaches could solve this task since, once properly trained and validated, they can be used in practically any system and provide holistic quantitative information in a matter of minutes. However, one major deterrent for radiologists is that these tools are not easily interpretable. Indeed, it is important that structures driving the results be detailed and survive comparison to the available literature. To solve these challenges, we propose an interpretable pipeline based on deep learning to predict postmenstrual age at scan, a key measure for assessing neonatal brain development. For this purpose, we train a state-of-the-art deep neural network to segment the brain into 87 different regions using normal preterm and term infants from the dHCP study. We then extract informative features for brain age estimation using the segmented MRIs and predict the brain age at scan with a regression model. The proposed framework achieves a mean absolute error of 0.46 weeks to predict postmenstrual age at scan. While our model is based solely on structural T2-weighted images, the results are superior to recent, arguably more complex approaches. Furthermore, based on the extracted knowledge from the trained models, we found that frontal and parietal lobes are among the most important structures for neonatal brain age estimation.

The human cerebellum plays an essential role in motor control, is involved in cognitive function (i.e., attention, working memory, and language), and helps to regulate emotional responses. Quantitative in-vivo assessment of the cerebellum is important in the study of several neurological diseases including cerebellar ataxia, autism, and schizophrenia. Different structural subdivisions of the cerebellum have been shown to correlate with differing pathologies. To further understand these pathologies, it is helpful to automatically parcellate the cerebellum at the highest fidelity possible. In this paper, we coordinated with colleagues around the world to evaluate automated cerebellum parcellation algorithms on two clinical cohorts showing that the cerebellum can be parcellated to a high accuracy by newer methods. We characterize these various methods at four hierarchical levels: coarse (i.e., whole cerebellum and gross structures), lobe, subdivisions of the vermis, and the lobules. Due to the number of labels, the hierarchy of labels, the number of algorithms, and the two cohorts, we have restricted our analyses to the Dice measure of overlap. Under these conditions, machine learning based methods provide a collection of strategies that are efficient and deliver parcellations of a high standard across both cohorts, surpassing previous work in the area. In conjunction with the rank-sum computation, we identified an overall winning method. •First paper to evaluate the state-of-the-art in cerebellum parcellation.•Presenting results on both Adult and Pediatric Cohorts.•Adult Cohort contains healthy controls, and patients with either symptoms of cerebellar dysfunction or SCA 6.•Pediatric Cohort contains healthy controls, and patients with ADHD or Autism.

Deep learning neural networks are especially potent at dealing with structured data, such as images and volumes. Both modified LiviaNET and HyperDense-Net performed well at a prior competition segmenting 6-month-old infant magnetic resonance images, but neonatal cerebral tissue type identification is challenging given its uniquely inverted tissue contrasts. The current study aims to evaluate the two architectures to segment neonatal brain tissue types at term equivalent age. Both networks were retrained over 24 pairs of neonatal T1 and T2 data from the Developing Human Connectome Project public data set and validated on another eight pairs against ground truth. We then reported the best-performing model from training and its performance by computing the Dice similarity coefficient (DSC) for each tissue type against eight test subjects. During the testing phase, among the segmentation approaches tested, the dual-modality HyperDense-Net achieved the best statistically significantly test mean DSC values, obtaining 0.94/0.95/0.92 for the tissue types and took 80 h to train and 10 min to segment, including preprocessing. The single-modality LiviaNET was better at processing T2-weighted images than processing T1-weighted images across all tissue types, achieving mean DSC values of 0.90/0.90/0.88 for gray matter, white matter, and cerebrospinal fluid, respectively, while requiring 30 h to train and 8 min to segment each brain, including preprocessing. Our evaluation demonstrates that both neural networks can segment neonatal brains, achieving previously reported performance. Both networks will be continuously retrained over an increasingly larger repertoire of neonatal brain data and be made available through the Canadian Neonatal Brain Platform to better serve the neonatal brain imaging research community.

Laparoscopic technique has demonstrated numerous advantages compared to open conventional surgery. Nevertheless, this procedure increases the surgeons fatigue and thus, the potential to commit errors that may harm the patient during the operation. The post-surgery pain is also augmented because the surgeons are forced to adopt non-neutral postures during the practice. This study reveals how a postural freedom element could help surgeons to improve the postural hygiene. During this study, thirteen participants with and without previous experience in laparoscopic surgery performed a test with two instruments: a prototype that implement this postural freedom concept and a conventional fixed instrument. The results obtained indicate that the postural freedom element allows the participants to maintain neutral positions during greatest part of the experiment and suggest that the implementation of an articulated element could increases the neutral positions adopted during a real laparoscopic procedure. The use of the postural freedom concept allowed to the participants to reduce the awkward positions during upper limb motions and to reduce displacements, avoiding extreme abductions that are common with the conventional fixed instruments.

Wild chimpanzees live in large and complex social communities, but their complexity is determined by the number of potential social partners as well as the frequent changes in group composition due to fission–fusion dynamics. Alternatively, captive housed chimpanzee groups are usually much smaller and less complex. However, studies have shown that groups can be housed in adjacent habitats, potentially increasing the number of social partners, i.e., granting additional relationship opportunities and enhanced social complexity. While most social network studies analyze social groups as closed systems, this study assessed the impact of social interactions between two neighboring groups of chimpanzees, based on two social network indices (Vertex strength centrality and Deviation from edge weight disparity). Furthermore, Linear Mixed Models (LMMs) were employed to assess whether gender, age, and intra-/intergroup directionality influenced these indices. We recorded occurrences of social behaviors, social proximity and whether chimpanzees observed individuals in the other group as a measure of interest. Most social behaviors were directed towards group members; however, 13% were directed towards the neighboring group. Although enclosure barriers constrained the chimpanzee’s capacity to physically interact, it does not necessarily impede social interactions with the outside world. Hence, the presence of neighboring chimpanzees potentially provides additional relationship opportunities, increasing social stimulation and complexity leading to an enriching social environment.

Housing different animal groups in close-by facilities is common in wildlife centers. However, the impact on animal welfare is insufficiently studied in the literature. In this study, we analyzed the behavior of two adjacently housed chimpanzee groups to investigate how intergroup interactions may affect their behavior and, thus, their welfare. We recorded occurrences of abnormal and self-directed behaviors, two well-known indicators of stress in chimpanzees. Furthermore, we explored the social responses to said intergroup interactions by recording all inter- and intragroup affiliative and agonistic behaviors. Finally, we measured the number of vigilance occurrences that individuals directed towards other chimpanzees as an indicator of interest. Generalized Linear Mixed Models (GLMMs) were used to assess whether and how social interactions between neighboring groups might influence their behaviors, taking gender, age, group, and intergroup participation into account. Our results suggest that intergroup interactions promoted the occurrence of affiliative behaviors between group members. However, intergroup interactions caused the chimpanzees to exhibit a higher number of abnormal and self-directed behaviors and increased vigilance towards their group members when agonistic intergroup interactions occurred. Thus, adjacent housing does impact the chimpanzees’ behavior and welfare and should be continuously monitored and assessed to promote and maximize welfare.

Environmental enrichment is a valuable tool for promoting primate welfare in captivity. In this context, research on personality can help clarify how individual differences influence engagement with environmental enrichment at the individual level. Numerous studies suggest that specific personality traits may be associated with heightened motivation to explore or solve environmental enrichments tasks. Nevertheless, this relationship remains unexplored within the genus Gorilla . Likewise, few studies report the effect of sex on engagement with environmental enrichment in this taxon. Addressing this gap may contribute to the development of enrichment programs tailored to individual needs. We examined the relationships between personality and sex and interest and success in completing a cognitive feeding enrichment task in 17 zoo-housed western gorillas ( Gorilla gorilla ). The enrichment task involved retrieving food from a tube presented in a social context. Each session consisted of a 30-min recording of a gorilla performing the enrichment task, with three sessions per individual. We conducted personality assessments using the Gorilla Behavior Index questionnaire. Exploratory factor analysis revealed three factors that accounted for 74% of the variance (Extraversion-Introversion, Protectiveness–Indifference, and Fearfulness–Boldness). We found a negative association between Protectiveness and success rate in the enrichment task. In contrast, we found no evidence that personality factors influenced interest in the enrichment. Additionally, success increased across sessions, and females extracted food more efficiently than males. Overall, our findings suggest that personality traits and sex play an important role in explaining individual differences in engagement with and outcomes of enrichment tasks in captive gorillas.