logo
ResearchBunny Logo
A deep learning approach for morphological feature extraction based on variational auto-encoder: an application to mandible shape

Biology

A deep learning approach for morphological feature extraction based on variational auto-encoder: an application to mandible shape

M. Tsutsumi, N. Saito, et al.

Explore the groundbreaking Morpho-VAE, a unique framework that employs deep learning for shape analysis in image data. This innovative tool, developed by Masato Tsutsumi, Nen Saito, Daisuke Koyabu, and Chikara Furusawa, excels at distinguishing morphological features among different classes, particularly in primate mandible images, showcasing its potential for biological discoveries.

00:00
00:00
Playback language: English
Abstract
This paper introduces Morpho-VAE, a landmark-free deep learning framework for shape analysis using image data. Morpho-VAE, a modified variational autoencoder (VAE), combines unsupervised and supervised learning to extract morphological features distinguishing different labeled classes. Applied to primate mandible images, it effectively clustered samples by family, even without correlation to phylogenetic distance. It also demonstrated reconstruction of missing segments in incomplete images, making it a versatile tool for biological shape analysis.
Publisher
npj Systems Biology and Applications
Published On
Jul 06, 2023
Authors
Masato Tsutsumi, Nen Saito, Daisuke Koyabu, Chikara Furusawa
Tags
Morpho-VAE
deep learning
shape analysis
primate mandible
morphological features
unsupervised learning
image data

Related Publications

Explore these studies to deepen your understanding of the subject.

Interpretable early warning recommendations in interactive learning environments: a deep-neural network approach based on learning behavior knowledge graph
Education

Interpretable early warning recommendations in interactive learning environments: a deep-neural network approach based on learning behavior knowledge graph

X. Xia and W. Qi

A multi-model architecture based on deep learning for aircraft load prediction
Engineering and Technology

A multi-model architecture based on deep learning for aircraft load prediction

C. Sun, H. Li, et al.

A digital solution framework for enabling electric vehicle battery circularity based on an ecosystem value optimization approach
Engineering and Technology

A digital solution framework for enabling electric vehicle battery circularity based on an ecosystem value optimization approach

A. Kumar, P. Huyn, et al.

A high-efficiency programmable modulator for extreme ultraviolet light with nanometre feature size based on an electronic phase transition
Physics

A high-efficiency programmable modulator for extreme ultraviolet light with nanometre feature size based on an electronic phase transition

I. Vaskivskyi, A. Mraz, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny