loading page

Automated Segmentation of Insect Anatomy from Micro-CT Images Using Deep Learning
  • +2
  • Evropi Toulkeridou,
  • Carlos Gutierrez,
  • Daniel Baum,
  • Kenji Doya,
  • Evan Economo
Evropi Toulkeridou
Okinawa Institute of Science and Technology Graduate University

Corresponding Author:[email protected]

Author Profile
Carlos Gutierrez
Okinawa Institute of Science and Technology Graduate University
Author Profile
Daniel Baum
Zuse-Institut Berlin
Author Profile
Kenji Doya
Okinawa Institute of Science and Technology Graduate University
Author Profile
Evan Economo
Okinawa Institute of Science and Technology Graduate University
Author Profile

Abstract

Three-dimensional (3D) imaging, such as micro-computed tomography (micro-CT), is increasingly being used by organismal biologists for precise and comprehensive anatomical characterization. However, the segmentation of anatomical structures remains a bottleneck in research, often requiring tedious manual work. Here, we propose a pipeline for the fully-automated segmentation of anatomical structures in micro-CT images utilizing state-of-the-art deep learning methods, selecting the ant brain as a test case. We implemented the U-Net architecture for 2D image segmentation for our convolutional neural network (CNN), combined with pixel-island detection. For training and validation of the network, we assembled a dataset of semi-manually segmented brain images of 76 ant species. The trained network predicted the brain area in ant images fast and accurately; its performance tested on validation sets showed good agreement between the prediction and the target, scoring 80% Intersection over Union (IoU) and 90% Dice Coefficient (F1) accuracy. While manual segmentation usually takes many hours for each brain, the trained network takes only a few minutes. Furthermore, our network is generalizable for segmenting the whole neural system in full-body scans, and works in tests on distantly related and morphologically divergent insects (e.g., fruit flies). The latter suggests that methods like the one presented here generally apply across diverse taxa. Our method makes the construction of segmented maps and the morphological quantification of different species more efficient and scalable to large datasets, a step toward a big data approach to organismal anatomy.
01 May 2023Submitted to Natural Sciences
02 May 2023Submission Checks Completed
02 May 2023Assigned to Editor
07 May 2023Reviewer(s) Assigned
14 Jul 2023Review(s) Completed, Editorial Evaluation Pending
24 Jul 2023Editorial Decision: Revise Major
21 Aug 20231st Revision Received
23 Aug 2023Submission Checks Completed
23 Aug 2023Assigned to Editor
23 Aug 2023Review(s) Completed, Editorial Evaluation Pending
28 Aug 2023Editorial Decision: Accept