Single-offset and multi-offset super-resolution for CEST MRI using deep transfer learning

Rohith Saai Pemmasani Prabakaran; Zilin Chen; Joseph H.C. Lai; Se Weon Park; Yang Liu; Jianpan Huang; Kannie W.Y. Chan

Single-offset and multi-offset super-resolution for CEST MRI using deep transfer learning

Rohith Saai Pemmasani Prabakaran
, Zilin Chen
, Joseph H.C. Lai
, Se Weon Park
, Yang Liu
, Jianpan Huang^*
, Kannie W.Y. Chan^*

^*Corresponding author for this work

Research output: Conference Papers › RGC 32 - Refereed conference paper (without host publication) › peer-review

Abstract

CEST MRI is an unique molecular imaging approach to reveal the exchangeable proton information related to physiology and pathology. However, long scanning time has hindered its translation into clinics. While deep-learning based super-resolution methods have been explored to reduce scanning time in conventional MRI, adaptation of these methods to CEST MRI has been limited due to lack of large public CEST datasets. Therefore, this study proposes two transfer learning based super-resolution methods, Single-Offset UNet and Multi-Offset UNet, for accelerating CEST MRI acquisition by using public MRI databases for pretraining and a very small CEST dataset for training.

Original language	English
Publication status	Published - May 2022
Event	2022 Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting - Hybrid, London, United Kingdom Duration: 7 May 2022 → 12 May 2022 https://www.ismrm.org/22m/

Conference

Conference	2022 Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting
Place	United Kingdom
City	London
Period	7/05/22 → 12/05/22
Internet address	https://www.ismrm.org/22m/

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@conference{7ae5b97aadcb476b8b872138add7b052,

title = "Single-offset and multi-offset super-resolution for CEST MRI using deep transfer learning",

abstract = "CEST MRI is an unique molecular imaging approach to reveal the exchangeable proton information related to physiology and pathology. However, long scanning time has hindered its translation into clinics. While deep-learning based super-resolution methods have been explored to reduce scanning time in conventional MRI, adaptation of these methods to CEST MRI has been limited due to lack of large public CEST datasets. Therefore, this study proposes two transfer learning based super-resolution methods, Single-Offset UNet and Multi-Offset UNet, for accelerating CEST MRI acquisition by using public MRI databases for pretraining and a very small CEST dataset for training.",

author = "\{Pemmasani Prabakaran\}, \{Rohith Saai\} and Zilin Chen and Lai, \{Joseph H.C.\} and Park, \{Se Weon\} and Yang Liu and Jianpan Huang and Chan, \{Kannie W.Y.\}",

year = "2022",

month = may,

language = "English",

note = "2022 Joint Annual Meeting ISMRM-ESMRMB \& ISMRT 31st Annual Meeting ; Conference date: 07-05-2022 Through 12-05-2022",

url = "https://www.ismrm.org/22m/",

}

Single-offset and multi-offset super-resolution for CEST MRI using deep transfer learning. / Pemmasani Prabakaran, Rohith Saai; Chen, Zilin ; Lai, Joseph H.C. et al.
2022. Paper presented at 2022 Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting, London, United Kingdom.

Research output: Conference Papers › RGC 32 - Refereed conference paper (without host publication) › peer-review

TY - CONF

T1 - Single-offset and multi-offset super-resolution for CEST MRI using deep transfer learning

AU - Pemmasani Prabakaran, Rohith Saai

AU - Chen, Zilin

AU - Lai, Joseph H.C.

AU - Park, Se Weon

AU - Liu, Yang

AU - Huang, Jianpan

AU - Chan, Kannie W.Y.

PY - 2022/5

Y1 - 2022/5

N2 - CEST MRI is an unique molecular imaging approach to reveal the exchangeable proton information related to physiology and pathology. However, long scanning time has hindered its translation into clinics. While deep-learning based super-resolution methods have been explored to reduce scanning time in conventional MRI, adaptation of these methods to CEST MRI has been limited due to lack of large public CEST datasets. Therefore, this study proposes two transfer learning based super-resolution methods, Single-Offset UNet and Multi-Offset UNet, for accelerating CEST MRI acquisition by using public MRI databases for pretraining and a very small CEST dataset for training.

AB - CEST MRI is an unique molecular imaging approach to reveal the exchangeable proton information related to physiology and pathology. However, long scanning time has hindered its translation into clinics. While deep-learning based super-resolution methods have been explored to reduce scanning time in conventional MRI, adaptation of these methods to CEST MRI has been limited due to lack of large public CEST datasets. Therefore, this study proposes two transfer learning based super-resolution methods, Single-Offset UNet and Multi-Offset UNet, for accelerating CEST MRI acquisition by using public MRI databases for pretraining and a very small CEST dataset for training.

M3 - RGC 32 - Refereed conference paper (without host publication)

T2 - 2022 Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting

Y2 - 7 May 2022 through 12 May 2022

ER -

Single-offset and multi-offset super-resolution for CEST MRI using deep transfer learning

Abstract

Conference

Other Access Options

Permanent Link

Fingerprint

Cite this