{"title":"Model-based Deep Learning Reconstruction Using a Folded Image Training Strategy for Abdominal 3D T1-weighted Imaging.","authors":"Satoshi Funayama, Utaroh Motosugi, Shintaro Ichikawa, Hiroyuki Morisaka, Yoshie Omiya, Hiroshi Onishi","doi":"10.2463/mrms.mp.2021-0103","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the feasibility of folded image training strategy (FITS) and the quality of images reconstructed using the improved model-based deep learning (iMoDL) network trained with FITS (FITS-iMoDL) for abdominal MR imaging.</p><p><strong>Methods: </strong>This retrospective study included abdominal 3D T1-weighted images of 122 patients. In the experimental analyses, peak SNR (PSNR) and structure similarity index (SSIM) of images reconstructed with FITS-iMoDL were compared with those with the following reconstruction methods: conventional model-based deep learning (conv-MoDL), MoDL trained with FITS (FITS-MoDL), total variation regularized compressed sensing (CS), and parallel imaging (CG-SENSE). In the clinical analysis, SNR and image contrast were measured on the reference, FITS-iMoDL, and CS images. Three radiologists evaluated the image quality using a 5-point scale to determine the mean opinion score (MOS).</p><p><strong>Results: </strong>The PSNR of FITS-iMoDL was significantly higher than that of FITS-MoDL, conv-MoDL, CS, and CG-SENSE (P < 0.001). The SSIM of FITS-iMoDL was significantly higher than those of the others (P < 0.001), except for FITS-MoDL (P = 0.056). In the clinical analysis, the SNR of FITS-iMoDL was significantly higher than that of the reference and CS (P < 0.0001). Image contrast was equivalent within an equivalence margin of 10% among these three image sets (P < 0.0001). MOS was significantly improved in FITS-iMoDL (P < 0.001) compared with CS images in terms of liver edge and vessels conspicuity, lesion depiction, artifacts, blurring, and overall image quality.</p><p><strong>Conclusion: </strong>The proposed method, FITS-iMoDL, allowed a deeper MoDL reconstruction network without increasing memory consumption and improved image quality on abdominal 3D T1-weighted imaging compared with CS images.</p>","PeriodicalId":18119,"journal":{"name":"Magnetic Resonance in Medical Sciences","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/c7/90/mrms-22-515.PMC10552667.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Magnetic Resonance in Medical Sciences","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2463/mrms.mp.2021-0103","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2022/11/8 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose: To evaluate the feasibility of folded image training strategy (FITS) and the quality of images reconstructed using the improved model-based deep learning (iMoDL) network trained with FITS (FITS-iMoDL) for abdominal MR imaging.
Methods: This retrospective study included abdominal 3D T1-weighted images of 122 patients. In the experimental analyses, peak SNR (PSNR) and structure similarity index (SSIM) of images reconstructed with FITS-iMoDL were compared with those with the following reconstruction methods: conventional model-based deep learning (conv-MoDL), MoDL trained with FITS (FITS-MoDL), total variation regularized compressed sensing (CS), and parallel imaging (CG-SENSE). In the clinical analysis, SNR and image contrast were measured on the reference, FITS-iMoDL, and CS images. Three radiologists evaluated the image quality using a 5-point scale to determine the mean opinion score (MOS).
Results: The PSNR of FITS-iMoDL was significantly higher than that of FITS-MoDL, conv-MoDL, CS, and CG-SENSE (P < 0.001). The SSIM of FITS-iMoDL was significantly higher than those of the others (P < 0.001), except for FITS-MoDL (P = 0.056). In the clinical analysis, the SNR of FITS-iMoDL was significantly higher than that of the reference and CS (P < 0.0001). Image contrast was equivalent within an equivalence margin of 10% among these three image sets (P < 0.0001). MOS was significantly improved in FITS-iMoDL (P < 0.001) compared with CS images in terms of liver edge and vessels conspicuity, lesion depiction, artifacts, blurring, and overall image quality.
Conclusion: The proposed method, FITS-iMoDL, allowed a deeper MoDL reconstruction network without increasing memory consumption and improved image quality on abdominal 3D T1-weighted imaging compared with CS images.
期刊介绍:
Magnetic Resonance in Medical Sciences (MRMS or Magn
Reson Med Sci) is an international journal pursuing the
publication of original articles contributing to the progress
of magnetic resonance in the field of biomedical sciences
including technical developments and clinical applications.
MRMS is an official journal of the Japanese Society for
Magnetic Resonance in Medicine (JSMRM).