Neural Network Segmentation of Cell Ultrastructure Using Incomplete Annotation
This work addresses a practical annotation bottleneck in biomedical imaging for diabetes research, though it appears incremental as it builds on existing neural network segmentation approaches.
The researchers tackled the problem of segmenting pancreatic beta cell ultrastructure from soft X-ray tomography images when only incomplete manual annotations are available, proposing a method that leverages partially labeled data alongside fully annotated data to improve segmentation performance over using only complete annotations.
The Pancreatic beta cell is an important target in diabetes research. For scalable modeling of beta cell ultrastructure, we investigate automatic segmentation of whole cell imaging data acquired through soft X-ray tomography. During the course of the study, both complete and partial ultrastructure annotations were produced manually for different subsets of the data. To more effectively use existing annotations, we propose a method that enables the application of partially labeled data for full label segmentation. For experimental validation, we apply our method to train a convolutional neural network with a set of 12 fully annotated data and 12 partially annotated data and show promising improvement over standard training that uses fully annotated data alone.