Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose
Advanced microscopy technologies such as electron microscopy have opened up a new field of vision for biomedical researchers. The use of artificial intelligence methods for processing EM data is largely difficult due to the small amount of annotated data at the training stage. Therefore, we add synt...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Samara National Research University
2023-10-01
|
| Series: | Компьютерная оптика |
| Subjects: | |
| Online Access: | https://www.computeroptics.ru/eng/KO/Annot/KO47-5/470512e.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591360416284672 |
|---|---|
| author | N.A. Sokolov E.P. Vasiliev A.A. Getmanskaya |
| author_facet | N.A. Sokolov E.P. Vasiliev A.A. Getmanskaya |
| author_sort | N.A. Sokolov |
| collection | DOAJ |
| description | Advanced microscopy technologies such as electron microscopy have opened up a new field of vision for biomedical researchers. The use of artificial intelligence methods for processing EM data is largely difficult due to the small amount of annotated data at the training stage. Therefore, we add synthetic images to an annotated real EM dataset or use a fully synthetic training dataset. In this work, we present an algorithm for the synthesis of 6 types of organelles. Based on the EPFL dataset, a training set of 1161 real fragments 256×256 (ORG) and 2000 synthetic ones (SYN), as well as their combination (MIX), were generated. The experiment of training models for 6, 5-classes and binary segmentation showed that, despite the imperfections of synthetics, training on a mixed (MIX) dataset gave a significant increase (about 0.1) in the Dice metric for 6 and 5 and same results at binary. The synthetic data strategy gives annotations for free, but shifts the effort to producing sufficiently realistic images. |
| format | Article |
| id | doaj-art-2d100a6754444721924349e087fbe010 |
| institution | Kabale University |
| issn | 0134-2452 2412-6179 |
| language | English |
| publishDate | 2023-10-01 |
| publisher | Samara National Research University |
| record_format | Article |
| series | Компьютерная оптика |
| spelling | doaj-art-2d100a6754444721924349e087fbe0102025-01-22T12:37:18ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792023-10-0147577878710.18287/-6179-CO-1273Generation and study of the synthetic brain electron microscopy dataset for segmentation purposeN.A. Sokolov0E.P. Vasiliev1A.A. Getmanskaya2Lobachevsky UniversityLobachevsky UniversityLobachevsky UniversityAdvanced microscopy technologies such as electron microscopy have opened up a new field of vision for biomedical researchers. The use of artificial intelligence methods for processing EM data is largely difficult due to the small amount of annotated data at the training stage. Therefore, we add synthetic images to an annotated real EM dataset or use a fully synthetic training dataset. In this work, we present an algorithm for the synthesis of 6 types of organelles. Based on the EPFL dataset, a training set of 1161 real fragments 256×256 (ORG) and 2000 synthetic ones (SYN), as well as their combination (MIX), were generated. The experiment of training models for 6, 5-classes and binary segmentation showed that, despite the imperfections of synthetics, training on a mixed (MIX) dataset gave a significant increase (about 0.1) in the Dice metric for 6 and 5 and same results at binary. The synthetic data strategy gives annotations for free, but shifts the effort to producing sufficiently realistic images.https://www.computeroptics.ru/eng/KO/Annot/KO47-5/470512e.htmlmulti-class segmentationelectron microscopyneural networkimage segmentationmachine learning |
| spellingShingle | N.A. Sokolov E.P. Vasiliev A.A. Getmanskaya Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose Компьютерная оптика multi-class segmentation electron microscopy neural network image segmentation machine learning |
| title | Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose |
| title_full | Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose |
| title_fullStr | Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose |
| title_full_unstemmed | Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose |
| title_short | Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose |
| title_sort | generation and study of the synthetic brain electron microscopy dataset for segmentation purpose |
| topic | multi-class segmentation electron microscopy neural network image segmentation machine learning |
| url | https://www.computeroptics.ru/eng/KO/Annot/KO47-5/470512e.html |
| work_keys_str_mv | AT nasokolov generationandstudyofthesyntheticbrainelectronmicroscopydatasetforsegmentationpurpose AT epvasiliev generationandstudyofthesyntheticbrainelectronmicroscopydatasetforsegmentationpurpose AT aagetmanskaya generationandstudyofthesyntheticbrainelectronmicroscopydatasetforsegmentationpurpose |