MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible and Diverse Neuronal Morphology Generation

Nianzu Yang, Kaipeng Zeng, Haotian Lu, Yexin Wu, Zexin Yuan, Shengdian Jiang, Jiaxiang Wu, Yimin Wang, Junchi Yan

Primary Area: applications to neuroscience & cognitive science

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Neuroscience, Neural Morphology, Computational Neuroscience

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a method for plausible and diverse neuronal morphology generation.

Abstract: Neuronal morphology is essential for studying brain functioning and understanding neurodegenerative disorders, e.g. Alzheimer. As the acquiring of real-world morphology data is expensive, computational approaches especially learning-based ones e.g. MorphVAE for morphology generation were recently studied, which are often conducted in a way of randomly augmenting a given authentic morphology to achieve both plausibility and diversity. Under such a setting, this paper proposes \textbf{MorphGrower} which aims to generate more plausible morphology samples by mimicking the natural growth mechanism instead of a one-shot treatment as done in MorphVAE. In particular, MorphGrower generates morphologies layer by layer synchronously and chooses a pair of sibling branches as the basic generation block, and the generation of each layer is conditioned on the morphological structure of previous layers and then generate morphologies via a conditional variational autoencoder with spherical latent space. Extensive experimental results on four real-world datasets demonstrate that MorphGrower outperforms MorphVAE by a notable margin. Our code will be publicly available to facilitate future research.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5669