Name
Title | ||
|---|---|---|
Multiclass U-Net Segmentation of Brain Electron Microscopy Data Using Original and Semi-Synthetic Training Datasets |
Abstract | ||
|---|---|---|
A manual labeling of 20 layers of the known open dataset EPFL for six classes is prepared. These classes are: (1) mitochondria, including their boundaries; (2) boundaries of mitochondria; (3) cell membranes; (4) postsynaptic densities (PSD); (5) axon sheaths; and (6) vesicles. Software for generating synthetic labeled datasets and the dataset itself balancing the representativeness of classes are created. Results of multiclass segmentation of brain electron microscopy (EM) data for each class for the case of binary segmentation and segmentation into five and six classes using a modified U-Net model are investigated. The model was trained on 256 × 256 fragments of the original EM resolution. In the case of six-class segmentation, mitochondria were segmented with the Dice–Sørensen coefficient of 0.908, which is somewhat lower than in the case of binary (0,911) and five-class segmentation (0.91). An extension of the dataset by synthesized images improved the classification results in an experiment. The extension of the manually labeled dataset (860 images of size 256 × 256) by the synthesized dataset (100 images of size 256 × 256 containing the poorly represented classes—axons and PSD) gave a significant increase of accuracy in the six-class U-Net model from 0.228 to 0.790 and from 0.553 to 0.745, respectively. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1134/S0361768822030057 | Programming and Computer Software |
DocType | Volume | Issue |
Journal | 48 | 3 |
ISSN | Citations | PageRank |
0361-7688 | 0 | 0.34 |
References | Authors | |
5 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| A. A. Getmanskaya | 1 | 0 | 0.34 |
| N. A. Sokolov | 2 | 0 | 0.34 |
| V. E. Turlapov | 3 | 0 | 0.34 |