Data Preprocessing Via Compositions Multi-Channel MRI Images to Improve Brain Tumor Segmentation

N. Tolstokulakov, E. Pavlovskiy, B. Tuchinov, E. Amelina, M. Amelin, A. Letyagin, S. Golushko, V. Groza

Результат исследования: Публикации в книгах, отчётах, сборниках, трудах конференцийстатья в сборнике материалов конференциинаучнаярецензирование

Аннотация

Magnetic resonance imaging (MRI) stays one of the most essential noninvasive methods for brain diagnostics. It allows obtaining the detailed 3D image of the brain, including various types of soft tissues. In this paper, we compare the influence of the multichannel data composition approach on the model's performance. We consider the binary brain tumor segmentation problem evaluating the Dice, Recall and Precision metrics. One common way to process the medical images with the use of neural networks is to use 2D slices as the input. In contrast to the RGB images, there are plenty of methods of how to combine the multi-channel MRI data structure into the common format for ML-based algorithms. After evaluating several possible combinations we demonstrate the most performance improvement by 6-7% in Dice Recall metrics using the pseudo-RGB approach.

Язык оригиналаанглийский
Название основной публикацииISBI Workshops 2020 - International Symposium on Biomedical Imaging Workshops, Proceedings
ИздательInstitute of Electrical and Electronics Engineers Inc.
Число страниц4
ISBN (электронное издание)9781728174013
ISBN (печатное издание)978-1-7281-7402-0
DOI
СостояниеОпубликовано - 1 апр 2020
Событие17th IEEE International Symposium on Biomedical Imaging Workshops, ISBI Workshops 2020 - Iowa City, Соединенные Штаты Америки
Продолжительность: 4 апр 2020 → …

Серия публикаций

НазваниеISBI Workshops 2020 - International Symposium on Biomedical Imaging Workshops, Proceedings

Конференция

Конференция17th IEEE International Symposium on Biomedical Imaging Workshops, ISBI Workshops 2020
СтранаСоединенные Штаты Америки
ГородIowa City
Период04.04.2020 → …

Fingerprint Подробные сведения о темах исследования «Data Preprocessing Via Compositions Multi-Channel MRI Images to Improve Brain Tumor Segmentation». Вместе они формируют уникальный семантический отпечаток (fingerprint).

  • Цитировать

    Tolstokulakov, N., Pavlovskiy, E., Tuchinov, B., Amelina, E., Amelin, M., Letyagin, A., Golushko, S., & Groza, V. (2020). Data Preprocessing Via Compositions Multi-Channel MRI Images to Improve Brain Tumor Segmentation. В ISBI Workshops 2020 - International Symposium on Biomedical Imaging Workshops, Proceedings [9153416] (ISBI Workshops 2020 - International Symposium on Biomedical Imaging Workshops, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISBIWorkshops50223.2020.9153416