Название исследуемой задачи:	Undersampled MRI reconstruction
Тип научной работы:	M1P
Автор:	Bair Mikhailov
Научный руководитель:	PH.D., Dmitry Dylov
Научный консультант:	Artem Razumov

Abstract

Magnetic Resonance Imaging (MRI) examination times can vary from fifteen minutes to one hour, which is inconvenient for both the doctor and the patient. Additionally, human motion during the scan can significantly decrease the quality of the images. Undersampled MRI allows for fewer measurements in Fourier-space, thereby reducing the scan time by 4-8 times. However, in this approach, some information is lost according to the Nyquist-Shannon sampling theorem. The main hypothesis of this study is the possibility of using general information from the scan space through machine learning to mitigate this problem.

Research publications

Presentations at conferences on the topic of research

Software modules developed as part of the study

1. A python package mylib with all implementation here.
2. A code with all experiment visualisation here. Can use colab.