Related Experiment Video
Updated: Aug 13, 2025
08:59
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
Published on: October 28, 2018
7.1K
Automated morphological phenotyping using learned shape descriptors and functional maps: A novel approach to
Oshane O Thomas1, Hongyu Shen2, Ryan L Raaum3,4,5
1Department of Anthropology, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States of America.
Plos Computational Biology
|January 19, 2023
Summary
Morphological Variation Quantifier (morphVQ) automates shape analysis using functional maps, offering a computationally efficient alternative to manual landmarking in geometric morphometrics. This method captures detailed shape variation and aids in classifying biological groups.
Area of Science:
- Geometric morphometrics
- Computational biology
- Evolutionary biology
Background:
- Geometric morphometrics is crucial for quantifying biological shape variation across diverse scientific fields.
- Manual landmark placement in traditional methods limits dataset size and introduces observer bias, hindering comprehensive morphological analysis.
Purpose of the Study:
- To develop an automated pipeline, Morphological Variation Quantifier (morphVQ), for quantifying and analyzing shape variation.
- To overcome limitations of manual landmarking by using descriptor learning on whole triangular meshes for functional correspondence.
- To create a novel representation of shape variation using latent shape space differences (LSSDs).
Main Methods:
- morphVQ utilizes descriptor learning to establish functional maps between whole triangular meshes, bypassing landmark configurations.
- Consistent ZoomOut refinement enhances functional maps, generating area-based and conformal latent shape space differences (LSSDs).
- LSSDs are compared against manual digitization and auto3DGM (an automated phenotyping approach) for validation.
Main Results:
- LSSDs demonstrate comparable or superior performance to existing 3D geometric morphometrics (3DGM) and auto3DGM methods.
- morphVQ is more computationally efficient and incorporates greater morphological detail by analyzing entire surfaces.
- The method accurately classifies biological groupings, such as genus affiliation, and generates shape spaces similar to established techniques.
Conclusions:
- morphVQ provides an automated, computationally efficient, and detailed approach to shape analysis in geometric morphometrics.
- The pipeline effectively captures morphological variation, overcomes manual landmarking limitations, and aids in comparative biological studies.
- morphVQ represents a significant advancement for researchers needing to analyze large-scale morphological datasets with reduced bias.
