D-ConvNet: Deep learning model for enhancement of brain MR images

Bibliographic Details
Parent link:Basic and Clinical Pharmacology and Toxicology
Vol. 124, iss. S2.— 2019.— [P. 3-4]
Corporate Author: Национальный исследовательский Томский политехнический университет Инженерная школа информационных технологий и робототехники Научно-образовательный центр "Автоматизация и информационные технологии"
Other Authors: Srinivasan К. Kathiravan, Sharma V. Vishal, Dzhayakodi (Jayakody) Arachshiladzh D. N. K. Dushanta Nalin Kumara, Vincent D. R. Durai Raj
Summary:Title screen
In clinical and medical imaging, the magnetic resonance (MR) images obtained, generally do not have a very high resolution because of the several factors like patient's comfort, scanning time, scanning equipment limitations, long sampling times, and so on. However, the MR imaging is always favored by physicians as one of the most trusted modes for clinical pathology, disease diagnosis, and treatment. Therefore, the enhancement of low-resolution MR image to a high-resolution MR image is critical for precise and effective clinical diagnosis. Furthermore, single-image super-resolution is an inverse problem because of its ill-posed characteristics. This problem can be surpassed by using deep learning models such as deep convolutional neural networks (D-ConvNet).
Режим доступа: по договору с организацией-держателем ресурса
Published: 2019
Subjects:
Online Access:https://doi.org/10.1111/bcpt.13173
Format: Electronic Book Chapter
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=663948