Related Experiment Video
Updated: Jan 1, 2026
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
2.4K
An automated 3D modeling pipeline for constructing 3D models of MONOGENEAN HARDPART using machine learning techniques
Bee Guan Teo1,2, Sarinder Kaur Dhillon3
1School of Engineering, Monash University Malaysia, Kuala Lumpur, Malaysia.
BMC Bioinformatics
|December 25, 2019
Summary
Researchers developed an automated 3D modeling pipeline using Artificial Neural Networks (ANN) to create 3D models of monogenean anchors. This approach streamlines the process, avoiding repetitive manual work for new species.
Area of Science:
- Computational Biology
- Parasitology
- 3D Modeling
Background:
- 3D visualization of small organisms like monogeneans is challenging.
- Traditional 3D model development is labor-intensive and repetitive.
- A novel approach is needed to efficiently create 3D models of monogenean anchors.
Purpose of the Study:
- To develop an automated 3D modeling pipeline for monogenean anchors.
- To avoid the tedious process of creating each 3D model from scratch.
- To facilitate the study of monogenean morphology and function in three dimensions.
Main Methods:
- Development of an automated 3D modeling pipeline.
- Integration of an Artificial Neural Network (ANN) for model deformation.
- Utilizing 2D illustrations as input for generating target 3D models.
Main Results:
- An automated pipeline successfully generated 8 target 3D monogenean anchor models.
- The pipeline deformed a generic 3D model into species-specific anchors.
- The process was automated, eliminating repetitive manual modeling.
Conclusions:
- The automated pipeline demonstrates a viable machine learning application in 3D modeling.
- This study showcases a cross-disciplinary integration of machine learning and biological structure modeling.
- The developed pipeline offers an efficient method for creating 3D biological models.
