Large-scale capture of hidden fluorescent labels for training generalizable markerless motion capture models.

Deep learning-based markerless tracking has revolutionized studies of animal behavior. Yet the generalizability of trained models tends to be limited, as new training data typically needs to be generated manually for each setup or visual environment. With each model trained from scratch, researchers track distinct landmarks and analyze the resulting kinematic data in idiosyncratic ways. Moreover, due to inherent limitations in manual annotation, only a sparse set of landmarks are typically labeled. To address these issues, we developed an approach, which we term GlowTrack, for generating orders of magnitude more training data, enabling models that generalize across experimental contexts. We describe: a) a high-throughput approach for producing hidden labels using fluorescent markers; b) a multi-camera, multi-light setup for simulating diverse visual conditions; and c) a technique for labeling many landmarks in parallel, enabling dense tracking. These advances lay a foundation for standardized behavioral pipelines and more complete scrutiny of movement.

Increased hyaluronan expression at distinct time points in acute lymphedema.

Lymphatic dysfunction in lymphedema results in chronic accumulation of interstitial fluid and life-long tissue swelling. In the absence of restored lymphatic drainage via adequate lymphangiogenesis, the interstitial environment can remodel in ways that decrease the elevated interstitial stress. Presently, relatively little is known about the glycosaminoglycans (GAGs) that become upregulated in the interstitium during lymphedema. We employed a mouse tail model of acute lymphedema that reproduces important features of the chronic human condition to establish a relationship between hyaluronan (HA) and sulfated GAG concentration with tissue swelling. We found that HA was upregulated by tissue injury at day 5 and became upregulated again by skin swelling (HA content increasing by 27% relative to controls at days 15 and 20). Surprisingly, the second phase of HA expression was associated with the declining phase of the tail skin swelling (tail diameter significantly decreasing by 17% from day 10 peak to day 20), demonstrating that HA is upregulated by tissue swelling and may help to counteract the edema in the mouse tail. This finding was confirmed by intradermal injection of an HA degrading enzyme (hyaluronidase) to the swollen tail, which was found to worsen the tail swelling. Sulfated GAGs, including chondroitin sulfate (CS), were not regulated by tissue swelling. The results demonstrate that HA, but not sulfated GAGs, is upregulated in the interstitium by acute tissue swelling. We speculate that HA expression during lymphedema may be part of a natural adaptive mechanism of the interstitial environment to reduce capillary filtration and increase interstitial fluid outflow following lymphatic obstruction and fluid accumulation.