Отрывок: Since the Dice metrics compare two sets, in the case of multiclass classification the result will be a vector of Dice metrics for each class. For training a neural network, a scalar error function is used. Therefore, for multiclass segmentation, we should convolve the metrics vector. To convolve a vector into a scalar, we use the linear convolution 1 1 , 0, 1, N N scalar i i i i i i W W ...
Полная запись метаданных
Поле DC | Значение | Язык |
---|---|---|
dc.contributor.author | Sokolov, N.A. | - |
dc.contributor.author | Vasiliev, E.P. | - |
dc.contributor.author | Getmanskaya, A.A. | - |
dc.date.accessioned | 2024-03-19 10:30:32 | - |
dc.date.available | 2024-03-19 10:30:32 | - |
dc.date.issued | 2023-09 | - |
dc.identifier | Dspace\SGAU\20240315\109027 | ru |
dc.identifier.citation | Sokolov NA, Vasiliev EP, Getmanskaya AA. Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose. Computer Optics 2023; 47(5): 778-787. DOI: 10.18287/-6179-CO-1273. | ru |
dc.identifier.uri | https://dx.doi.org/10.18287/-6179-CO-1273 | - |
dc.identifier.uri | http://repo.ssau.ru/handle/Zhurnal-Komputernaya-optika/Generation-and-study-of-the-synthetic-brain-electron-microscopy-dataset-for-segmentation-purpose-109027 | - |
dc.description.abstract | 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. | ru |
dc.description.sponsorship | The work was carried out with the support of the Priority 2030 program. | ru |
dc.language.iso | en | ru |
dc.publisher | Самарский национальный исследовательский университет | ru |
dc.relation.ispartofseries | 47;5 | - |
dc.subject | multi-class segmentation | ru |
dc.subject | electron microscopy | ru |
dc.subject | neural network | ru |
dc.subject | image segmentation | ru |
dc.subject | machine learning | ru |
dc.title | Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose | ru |
dc.type | Article | ru |
dc.textpart | Since the Dice metrics compare two sets, in the case of multiclass classification the result will be a vector of Dice metrics for each class. For training a neural network, a scalar error function is used. Therefore, for multiclass segmentation, we should convolve the metrics vector. To convolve a vector into a scalar, we use the linear convolution 1 1 , 0, 1, N N scalar i i i i i i W W ... | - |
Располагается в коллекциях: | Журнал "Компьютерная оптика" |
Файлы этого ресурса:
Файл | Описание | Размер | Формат | |
---|---|---|---|---|
2412-6179_2023_47_5_778-787.pdf | 10.6 MB | Adobe PDF | Просмотреть/Открыть |
Показать базовое описание ресурса
Просмотр статистики
Поделиться:
Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.