Year: 2024
Type: conference-paper
Abstract: Star-convex shapes arise across bio-microscopy and radiology in the form of nuclei, nodules, metastases, and other units. Existing instance segmentation networks for such structures train on densely labeled instances for each dataset, which requires substantial and often impractical manual annotation effort. Further, significant reengineering or finetuning is needed when presented with new datasets and imaging modalities due to changes in contrast, shape, orientation, resolution, and density. We present AnyStar, a domain-randomized generative model that simulates synthetic training data of blob-like objects with randomized appearance, environments, and imaging physics to train general-purpose star-convex instance segmentation networks. As a result, networks trained using our generative model do not require annotated images from un-seen datasets. A single network trained on our synthesized data accurately 3D segments C. elegans and P. dumerilii nuclei in fluorescence microscopy, mouse cortical nuclei in μCT, zebrafish brain nuclei in EM, and placental cotyledons in human fetal MRI, all without any retraining, finetuning, transfer learning, or domain adaptation. Code is available at https://github.com/neel-dey/AnyStar.
Language: English
Subfield: Biophysics
Domain: Life Sciences
Open Access status: green
Awards: G2058387751, Neuroimaging Analysis Center (NAC), Characterizing the Relationship between Uterine Activity and Placental Function Across Pregnancy with MRI, Novel MRI Assessment of Placental Structure and Function Throughout Pregnancy, G5238647092, Deep Learning Algorithms for FreeSurfer, Fetal MRI: robust self-driving brain acquisition and body movement quantification, Diagnosing the undiagnosable: studies of Alzheimer disease mimics and confounders via "neuropathometry" of dissection photos with 3D scanning
OpenAlex ID: W4394593075