Evaluation of super-resolution on 50 pancreatic cancer patients with real-time cine MRI from 0.35T MRgRT

Jaehee Chun; Benjamin Lewis; Zhen Ji; Jae Ik Shin; Justin C. Park; Jin Sung Kim; Taeho Kim

doi:10.1088/2057-1976/ac1c51

Evaluation of super-resolution on 50 pancreatic cancer patients with real-time cine MRI from 0.35T MRgRT

Jaehee Chun, Benjamin Lewis, Zhen Ji, Jae Ik Shin, Justin C. Park, Jin Sung Kim, Taeho Kim

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

MR-guided radiotherapy (MRgRT) systems provide excellent soft tissue imaging immediately prior to and in real time during radiation delivery for cancer treatment. However, 2D cine MRI often has limited spatial resolution due to high temporal resolution. This work applies a super resolution machine learning framework to 3.5 mm pixel edge length, low resolution (LR), sagittal 2D cine MRI images acquired on a MRgRT system to generate 0.9 mm pixel edge length, super resolution (SR), images originally acquired at 4 frames per second (FPS). LR images were collected from 50 pancreatic cancer patients treated on a ViewRay MR-LINAC. SR images were evaluated using three methods. 1) The first method utilized intrinsic image quality metrics for evaluation. 2) The second used relative metrics including edge detection and structural similarity index (SSIM). 3) Finally, automatically generated tumor contours were created on both low resolution and super resolution images to evaluate target delineation and compared with DICE and SSIM. Intrinsic image quality metrics all had statistically significant improvements for SR images versus LR images, with mean (±1 SD) BRISQUE scores of 29.65 ± 2.98 and 42.48 ± 0.98 for SR and LR, respectively. SR images showed good agreement with LR images in SSIM evaluation, indicating there was not significant distortion of the images. Comparison of LR and SR images with paired high resolution (HR) 3D images showed that SR images had a mean (±1 SD) SSIM value of 0.633 ± 0.063 and LR a value of 0.587 ± 0.067 (p = 0.05). Contours generated on SR images were also more robust to noise addition than those generated on LR images. This study shows that super resolution with a machine learning framework can generate high spatial resolution images from 4fps low spatial resolution cine MRI acquired on the ViewRay MR-LINAC while maintaining tumor contour quality and without significant acquisition or post processing delay.

Original language	English (US)
Article number	055020
Journal	Biomedical Physics and Engineering Express
Volume	7
Issue number	5
DOIs	https://doi.org/10.1088/2057-1976/ac1c51
State	Published - Sep 2021

Keywords

Cine MRI
MRgRT
Pancreatic cancer

ASJC Scopus subject areas

Biophysics
Bioengineering
Biomaterials
Physiology
Biomedical Engineering
Radiology Nuclear Medicine and imaging
Computer Science Applications
Health Informatics

Access to Document

10.1088/2057-1976/ac1c51

Cite this

@article{c297662d0f9344ff929426bc624373f1,

title = "Evaluation of super-resolution on 50 pancreatic cancer patients with real-time cine MRI from 0.35T MRgRT",

abstract = "MR-guided radiotherapy (MRgRT) systems provide excellent soft tissue imaging immediately prior to and in real time during radiation delivery for cancer treatment. However, 2D cine MRI often has limited spatial resolution due to high temporal resolution. This work applies a super resolution machine learning framework to 3.5 mm pixel edge length, low resolution (LR), sagittal 2D cine MRI images acquired on a MRgRT system to generate 0.9 mm pixel edge length, super resolution (SR), images originally acquired at 4 frames per second (FPS). LR images were collected from 50 pancreatic cancer patients treated on a ViewRay MR-LINAC. SR images were evaluated using three methods. 1) The first method utilized intrinsic image quality metrics for evaluation. 2) The second used relative metrics including edge detection and structural similarity index (SSIM). 3) Finally, automatically generated tumor contours were created on both low resolution and super resolution images to evaluate target delineation and compared with DICE and SSIM. Intrinsic image quality metrics all had statistically significant improvements for SR images versus LR images, with mean (±1 SD) BRISQUE scores of 29.65 ± 2.98 and 42.48 ± 0.98 for SR and LR, respectively. SR images showed good agreement with LR images in SSIM evaluation, indicating there was not significant distortion of the images. Comparison of LR and SR images with paired high resolution (HR) 3D images showed that SR images had a mean (±1 SD) SSIM value of 0.633 ± 0.063 and LR a value of 0.587 ± 0.067 (p = 0.05). Contours generated on SR images were also more robust to noise addition than those generated on LR images. This study shows that super resolution with a machine learning framework can generate high spatial resolution images from 4fps low spatial resolution cine MRI acquired on the ViewRay MR-LINAC while maintaining tumor contour quality and without significant acquisition or post processing delay.",

keywords = "Cine MRI, MRgRT, Pancreatic cancer",

author = "Jaehee Chun and Benjamin Lewis and Zhen Ji and Shin, {Jae Ik} and Park, {Justin C.} and Kim, {Jin Sung} and Taeho Kim",

note = "Funding Information: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2020R1A4A101661911) Washington University School of Medicine in St Louis Department of Radiation Oncology provided the research funding for this work to Dr Kim. Washington University in St Louis has a master research agreement and receives research funding from ViewRay unrelated to this study. This research was supported by the Alvin J. Siteman Cancer Center through The Foundation for Barnes-Jewish Hospital and the National Cancer Institute (P30 CA091842). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. Publisher Copyright: {\textcopyright} 2021 IOP Publishing Ltd.",

year = "2021",

month = sep,

doi = "10.1088/2057-1976/ac1c51",

language = "English (US)",

volume = "7",

journal = "Biomedical Physics and Engineering Express",

issn = "2057-1976",

publisher = "IOP Publishing Ltd.",

number = "5",

}

TY - JOUR

T1 - Evaluation of super-resolution on 50 pancreatic cancer patients with real-time cine MRI from 0.35T MRgRT

AU - Chun, Jaehee

AU - Lewis, Benjamin

AU - Ji, Zhen

AU - Shin, Jae Ik

AU - Park, Justin C.

AU - Kim, Jin Sung

AU - Kim, Taeho

N1 - Funding Information: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2020R1A4A101661911) Washington University School of Medicine in St Louis Department of Radiation Oncology provided the research funding for this work to Dr Kim. Washington University in St Louis has a master research agreement and receives research funding from ViewRay unrelated to this study. This research was supported by the Alvin J. Siteman Cancer Center through The Foundation for Barnes-Jewish Hospital and the National Cancer Institute (P30 CA091842). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. Publisher Copyright: © 2021 IOP Publishing Ltd.

PY - 2021/9

Y1 - 2021/9

N2 - MR-guided radiotherapy (MRgRT) systems provide excellent soft tissue imaging immediately prior to and in real time during radiation delivery for cancer treatment. However, 2D cine MRI often has limited spatial resolution due to high temporal resolution. This work applies a super resolution machine learning framework to 3.5 mm pixel edge length, low resolution (LR), sagittal 2D cine MRI images acquired on a MRgRT system to generate 0.9 mm pixel edge length, super resolution (SR), images originally acquired at 4 frames per second (FPS). LR images were collected from 50 pancreatic cancer patients treated on a ViewRay MR-LINAC. SR images were evaluated using three methods. 1) The first method utilized intrinsic image quality metrics for evaluation. 2) The second used relative metrics including edge detection and structural similarity index (SSIM). 3) Finally, automatically generated tumor contours were created on both low resolution and super resolution images to evaluate target delineation and compared with DICE and SSIM. Intrinsic image quality metrics all had statistically significant improvements for SR images versus LR images, with mean (±1 SD) BRISQUE scores of 29.65 ± 2.98 and 42.48 ± 0.98 for SR and LR, respectively. SR images showed good agreement with LR images in SSIM evaluation, indicating there was not significant distortion of the images. Comparison of LR and SR images with paired high resolution (HR) 3D images showed that SR images had a mean (±1 SD) SSIM value of 0.633 ± 0.063 and LR a value of 0.587 ± 0.067 (p = 0.05). Contours generated on SR images were also more robust to noise addition than those generated on LR images. This study shows that super resolution with a machine learning framework can generate high spatial resolution images from 4fps low spatial resolution cine MRI acquired on the ViewRay MR-LINAC while maintaining tumor contour quality and without significant acquisition or post processing delay.

AB - MR-guided radiotherapy (MRgRT) systems provide excellent soft tissue imaging immediately prior to and in real time during radiation delivery for cancer treatment. However, 2D cine MRI often has limited spatial resolution due to high temporal resolution. This work applies a super resolution machine learning framework to 3.5 mm pixel edge length, low resolution (LR), sagittal 2D cine MRI images acquired on a MRgRT system to generate 0.9 mm pixel edge length, super resolution (SR), images originally acquired at 4 frames per second (FPS). LR images were collected from 50 pancreatic cancer patients treated on a ViewRay MR-LINAC. SR images were evaluated using three methods. 1) The first method utilized intrinsic image quality metrics for evaluation. 2) The second used relative metrics including edge detection and structural similarity index (SSIM). 3) Finally, automatically generated tumor contours were created on both low resolution and super resolution images to evaluate target delineation and compared with DICE and SSIM. Intrinsic image quality metrics all had statistically significant improvements for SR images versus LR images, with mean (±1 SD) BRISQUE scores of 29.65 ± 2.98 and 42.48 ± 0.98 for SR and LR, respectively. SR images showed good agreement with LR images in SSIM evaluation, indicating there was not significant distortion of the images. Comparison of LR and SR images with paired high resolution (HR) 3D images showed that SR images had a mean (±1 SD) SSIM value of 0.633 ± 0.063 and LR a value of 0.587 ± 0.067 (p = 0.05). Contours generated on SR images were also more robust to noise addition than those generated on LR images. This study shows that super resolution with a machine learning framework can generate high spatial resolution images from 4fps low spatial resolution cine MRI acquired on the ViewRay MR-LINAC while maintaining tumor contour quality and without significant acquisition or post processing delay.

KW - Cine MRI

KW - MRgRT

KW - Pancreatic cancer

UR - http://www.scopus.com/inward/record.url?scp=85114151176&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85114151176&partnerID=8YFLogxK

U2 - 10.1088/2057-1976/ac1c51

DO - 10.1088/2057-1976/ac1c51

M3 - Article

C2 - 34375963

AN - SCOPUS:85114151176

SN - 2057-1976

VL - 7

JO - Biomedical Physics and Engineering Express

JF - Biomedical Physics and Engineering Express

IS - 5

M1 - 055020

ER -

Evaluation of super-resolution on 50 pancreatic cancer patients with real-time cine MRI from 0.35T MRgRT

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this