Adapting Action Recognition Neural Networks for Automated Infantile Spasm Detection.

Infantile spasms are a severe epileptic syndrome characterized by short muscular contractions lasting from 0.5 to 2 seconds. They are often misdiagnosed due to their atypical presentation, and treatment is frequently delayed, leading to stagnation or regression in psychomotor development and significant cognitive and motor sequelae. One promising approach to addressing this issue is the use of markerless computer vision techniques. In this paper, we introduce a novel approach for recognizing infantile spasms based exclusively on video data. We utilize an expanded 3D neural network pre-trained on an extensive human action recognition dataset called Kinetics. By employing this model, we extract features from short segments of varying sizes sampled from seizure videos, which allows us to effectively capture the spatio-temporal characteristics of infantile spasms. We then apply multiple classifiers to perform binary classification on these extracted features. The best system achieved an average area under the ROC curve of 0.813±0.058 for a 3-second window.

Distinct subsets of multi-lymphoid progenitors support ontogeny-related changes in human lymphopoiesis.

Changes in lymphocyte production patterns occurring across human ontogeny remain poorly defined. In this study, we demonstrate that human lymphopoiesis is supported by three waves of embryonic, fetal, and postnatal multi-lymphoid progenitors (MLPs) differing in CD7 and CD10 expression and their output of CD127-/+ early lymphoid progenitors (ELPs). In addition, our results reveal that, like the fetal-to-adult switch in erythropoiesis, transition to postnatal life coincides with a shift from multilineage to B lineage-biased lymphopoiesis and an increase in production of CD127+ ELPs, which persists until puberty. A further developmental transition is observed in elderly individuals whereby B cell differentiation bypasses the CD127+ compartment and branches directly from CD10+ MLPs. Functional analyses indicate that these changes are determined at the level of hematopoietic stem cells. These findings provide insights for understanding identity and function of human MLPs and the establishment and maintenance of adaptative immunity.

Multimodal cartography of human lymphopoiesis reveals B and T/NK/ILC lineages are subjected to differential regulation.

The developmental cartography of human lymphopoiesis remains incompletely understood. Here, we establish a multimodal map demonstrating that lymphoid specification follows independent direct or stepwise hierarchic routes converging toward the emergence of newly characterized CD117lo multi-lymphoid progenitors (MLPs) that undergo a proliferation arrest before entering the CD127- (NK/ILC/T) or CD127+ (B) lymphoid pathways. While the differentiation of CD127- early lymphoid progenitors is mainly driven by Flt3 signaling, emergence of their CD127+ counterparts is regulated cell-intrinsically and depends exclusively on the divisional history of their upstream precursors, including hematopoietic stem cells. Further, transcriptional mapping of differentiation trajectories reveals that whereas myeloid granulomonocytic lineages follow continuous differentiation pathways, lymphoid trajectories are intrinsically discontinuous and characterized by sequential waves of cell proliferation allowing pre-commitment amplification of lymphoid progenitor pools. Besides identifying new lymphoid specification pathways and regulatory checkpoints, our results demonstrate that NK/ILC/T and B lineages are under fundamentally distinct modes of regulation. (149 words).

Spinal Muscular Atrophy Hypotonia Detection Using Computer Vision and Artificial Intelligence.

This case-control study uses computer vision and artificial intelligence to develop a screening tool for detecting spinal muscular atrophy in infants.