Deep learning-based neural network for regions of interest retrieval in T2*-weighted brain perfusion MRI

Скорочена інформація про документ
dc.contributor.authorAlkhimova, Svitlana Mykolaivna
dc.contributor.authorDiumin, Oleksii Dmytrovych
dc.date.accessioned2023-01-31T15:15:10Z
dc.date.available2023-01-31T15:15:10Z
dc.date.issued2022
dc.description.abstractenBrain region segmentation is usually the first step for dynamic susceptibility contrast perfusion analysis. Although manual segmentation is more accurate, it is a time-consuming and not sufficiently reproducible process. Clinicians still rely on manual segmentation especially for cases with abnormal brain anatomy, as removing brain parts or inclusion of non-brain tissues can be a potential source of falsely high or falsely low values of perfusion parameters. This study proposes an effective deep learning-based neural network for fully automatic segmentation of brain from non-brain tissues in T2*-weighted magnetic resonance images with abnormal brain anatomy. Our neural network architecture combines U-Net and ResNet with plugged spatial and channel squeeze and excitation attention modules into the ResNet backbone. The train, validation, and test processes are conducted on 32 three-dimensional volumes of different subjects from the TCGA glioblastoma multiforme collection. Four performance metrics are used in our experiments: Dice coefficient, sensitivity, specificity, and accuracy. Quantitative results (i.e., Dice coefficient of 0.9726 +/- 0.004, sensitivity of 0.9514+/-0.007, specificity of 0.9983+/-0.001, and accuracy of 0.9864+/-0.003) reveal that the proposed neural network architecture is efficient and accurate for brain segmentation. The obtained results also demonstrate that the training model using the proposed U-Net+ResNet architecture of the neural network provides the best Dice coefficient, specificity, and accuracy metric values compared to current methods under the same hardware conditions and using the same test dataset of magnetic resonance images of a human head with abnormal brain anatomy. Moreover, obtained results also indicate that the proposed U-Net+ResNet architecture of deep learning-based neural network could be good enough in a clinical setup to reduce the need for time-consuming and non-reproducible manual segmentation.uk
dc.format.pagerangeС. 301-314uk
dc.identifier.citationAlkhimova, S. M. Deep learning-based neural network for regions of interest retrieval in T2*-weighted brain perfusion MRI / S. M. Alkhimova, O. D. Diumin // Science and Technology Today. – 2022. – V. 14, N. 14. – P. 301-314.uk
dc.identifier.doihttps://doi.org/10.52058/2786-6025-2022-14(14)-301-314
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/52237
dc.language.isoenuk
dc.publisherВидавнича група «Наукові перспективи»uk
dc.publisher.placeКиївuk
dc.source«Наука і техніка сьогодні» (Серія «Педагогіка», Серія «Право», Серія «Економіка», Серія «Фізико-математичні науки», Серія «Техніка»)»: журнал, 2022, No 14(14)uk
dc.subjectbrainuk
dc.subjectsegmentationuk
dc.subjectregion of interestuk
dc.subjectdeep neural networkuk
dc.subjectdynamic susceptibility contrast perfusionuk
dc.subjectmagnetic resonance imaginguk
dc.subject.udc004.932:616-073.756.8uk
dc.titleDeep learning-based neural network for regions of interest retrieval in T2*-weighted brain perfusion MRIuk
dc.title.alternativeНейронна мережа на основі глибокого навчання для отримання зон інтересу на T2*-зважених перфузійних зображеннях МРТ мозкуuk
dc.typeArticleuk

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
Alkhimova_Diumin.pdf
Розмір:
639.55 KB
Формат:
Adobe Portable Document Format
Опис:
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
1.71 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Статті (БМК)