Vision-language models for decoding provider attention during neonatal resuscitation

Neonatal resuscitations demand an exceptional level of attentiveness from providers, who must process multiple streams of information simultaneously. Gaze strongly influences decision making; thus, understanding where a provider is looking during neonatal resuscitations could inform provider training, enhance real-time decision support, and improve the design of delivery rooms and neonatal intensive care units (NICUs). Current approaches to quantifying neonatal providers' gaze rely on manual coding or simulations, which limit scalability and utility. Here, we introduce an automated, real-time, deep learning approach capable of decoding provider gaze into semantic classes directly from first-person point-of-view videos recorded during live resuscitations. Combining state-of-the-art, real-time segmentation with vision-language models (CLIP), our low-shot pipeline attains 91\% classification accuracy in identifying gaze targets without training. Upon fine-tuning, the performance of our gaze-guided vision transformer exceeds 98\% accuracy in gaze classification, approaching human-level precision. This system, capable of real-time inference, enables objective quantification of provider attention dynamics during live neonatal resuscitation. Our approach offers a scalable solution that seamlessly integrates with existing infrastructure for data-scarce gaze analysis, thereby offering new opportunities for understanding and refining clinical decision making.

Neural Networks as Paths through the Space of Representations

Deep neural networks implement a sequence of layer-by-layer operations that are each relatively easy to understand, but the resulting overall computation is generally difficult to understand. We develop a simple idea for interpreting the layer-by-layer construction of useful representations: the role of each layer is to reformat information to reduce the "distance" to the target outputs. We formalize this intuitive idea of "distance" by leveraging recent work on metric representational similarity, and show how it leads to a rich space of geometric concepts. With this framework, the layer-wise computation implemented by a deep neural network can be viewed as a path in a high-dimensional representation space. We develop tools to characterize the geometry of these in terms of distances, angles, and geodesics. We then ask three sets of questions of residual networks trained on CIFAR-10: (1) how straight are paths, and how does each layer contribute towards the target? (2) how do these properties emerge over training? and (3) how similar are the paths taken by wider versus deeper networks? We conclude by sketching additional ways that this kind of representational geometry can be used to understand and interpret network training, or to prescriptively improve network architectures to suit a task.

A Large Deformation Diffeomorphic Approach to Registration of CLARITY Images via Mutual Information

CLARITY is a method for converting biological tissues into translucent and porous hydrogel-tissue hybrids. This facilitates interrogation with light sheet microscopy and penetration of molecular probes while avoiding physical slicing. In this work, we develop a pipeline for registering CLARIfied mouse brains to an annotated brain atlas. Due to the novelty of this microscopy technique it is impractical to use absolute intensity values to align these images to existing standard atlases. Thus we adopt a large deformation diffeomorphic approach for registering images via mutual information matching. Furthermore we show how a cascaded multi-resolution approach can improve registration quality while reducing algorithm run time. As acquired image volumes were over a terabyte in size, they were far too large for work on personal computers. Therefore the NeuroData computational infrastructure was deployed for multi-resolution storage and visualization of these images and aligned annotations on the web.