Deep multitask learning for accelerating Magnetic Resonance Imaging

D. Karkalousos

Deep multitask learning for accelerating Magnetic Resonance Imaging

D. Karkalousos

Research output: PhD Thesis › Phd-Thesis - Research and graduation internal

Abstract

This dissertation advances the acceleration of Magnetic Resonance Imaging (MRI) through novel Artificial Intelligence approaches combining Deep Learning (DL) and MultiTask Learning (MTL). The first contribution introduces the Cascades of Independently Recurrent Inference Machines (CIRIM), a physics-informed DL network achieving superior performance compared to a

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	University of Amsterdam
Supervisors/Advisors	Marquering, Henk, Supervisor Isgum, Ivana, Supervisor Caan, Matthan, Co-supervisor
Award date	26 Feb 2025
Publication status	Published - 2025

Access to Document

https://pure.uva.nl/ws/files/219977195/Thesis.pdf

Cite this

@phdthesis{2648422c5aa24752931a1d594b032e0b,

title = "Deep multitask learning for accelerating Magnetic Resonance Imaging",

abstract = "This dissertation advances the acceleration of Magnetic Resonance Imaging (MRI) through novel Artificial Intelligence approaches combining Deep Learning (DL) and MultiTask Learning (MTL). The first contribution introduces the Cascades of Independently Recurrent Inference Machines (CIRIM), a physics-informed DL network achieving superior performance compared to a",

author = "D. Karkalousos",

year = "2025",

language = "English",

type = "Phd-Thesis - Research and graduation internal",

school = "University of Amsterdam",

}

TY - THES

T1 - Deep multitask learning for accelerating Magnetic Resonance Imaging

AU - Karkalousos, D.

PY - 2025

Y1 - 2025

N2 - This dissertation advances the acceleration of Magnetic Resonance Imaging (MRI) through novel Artificial Intelligence approaches combining Deep Learning (DL) and MultiTask Learning (MTL). The first contribution introduces the Cascades of Independently Recurrent Inference Machines (CIRIM), a physics-informed DL network achieving superior performance compared to a

AB - This dissertation advances the acceleration of Magnetic Resonance Imaging (MRI) through novel Artificial Intelligence approaches combining Deep Learning (DL) and MultiTask Learning (MTL). The first contribution introduces the Cascades of Independently Recurrent Inference Machines (CIRIM), a physics-informed DL network achieving superior performance compared to a

M3 - Phd-Thesis - Research and graduation internal

ER -

Deep multitask learning for accelerating Magnetic Resonance Imaging

Abstract

Access to Document

Fingerprint

Cite this