Publication
Point-Based Weakly Supervised 2.5D Cell Segmentation
Fabian Schmeisser; Andreas Dengel; Sheraz Ahmed
In: Michael Wand; Kristina Malinovska; Jürgen Schmidhuber; Igor V. Tetko (Hrsg.). 33rd International Conference on Artificial Neural Networks Lugano, Switzerland, September 17–20, 2024 Proceedings, Part VIII. International Conference on Artificial Neural Networks (ICANN-2024), Springer, 2024.
Abstract
Volumetric microscopic images show cells in their natural
state and solve various problems inherent to 2D projections. The develop-
ment of competent Deep Learning methods to segment cells in 3D images
is, however, held back by the extremely time-consuming and error-prone
process of manual ground truth creation. To reduce the burden of manual
annotation in 3D, we propose a weakly supervised 2.5D cell segmenta-
tion approach that learns to accurately predict 3D segmentation masks
from weak, slice-wise point labels. We show that even a single point per
cell as ground truth label is sufficient to train a network on par with
a fully supervised model that outperforms a top contender of the ISBI
Cell Tracking Challenge, and with performance close to that of a fully 3D
approach while requiring only a fraction of the resources. The slice-wise,
point-based annotation scheme, not only reduces the time required to
annotate 3D cell datasets by an estimated factor of 6, but also simplifies
the complex and error-prone process of manually segmenting cells using
3D software.