Literature DB >> 34301782

Evaluation of Deep Learning-Based Approaches to Segment Bowel Air Pockets and Generate Pelvic Attenuation Maps from CAIPIRINHA-Accelerated Dixon MR Images.

Hasan Sari1, Ja Reaungamornrat2, Onofrio A Catalano1, Javier Vera-Olmos3, David Izquierdo-Garcia1, Manuel A Morales1, Angel Torrado-Carvajal1,3, Thomas S C Ng4, Norberto Malpica3, Ali Kamen2, Ciprian Catana5.   

Abstract

Attenuation correction remains a challenge in pelvic PET/MRI. In addition to the segmentation/model-based approaches, deep learning methods have shown promise in synthesizing accurate pelvic attenuation maps (μ-maps). However, these methods often misclassify air pockets in the digestive tract, potentially introducing bias in the reconstructed PET images. The aims of this work were to develop deep learning-based methods to automatically segment air pockets and generate pseudo-CT images from CAIPIRINHA-accelerated MR Dixon images.
Methods: A convolutional neural network (CNN) was trained to segment air pockets using 3-dimensional CAIPIRINHA-accelerated MR Dixon datasets from 35 subjects and was evaluated against semiautomated segmentations. A separate CNN was trained to synthesize pseudo-CT μ-maps from the Dixon images. Its accuracy was evaluated by comparing the deep learning-, model-, and CT-based μ-maps using data from 30 of the subjects. Finally, the impact of different μ-maps and air pocket segmentation methods on the PET quantification was investigated.
Results: Air pockets segmented using the CNN agreed well with semiautomated segmentations, with a mean Dice similarity coefficient of 0.75. The volumetric similarity score between 2 segmentations was 0.85 ± 0.14. The mean absolute relative changes with respect to the CT-based μ-maps were 2.6% and 5.1% in the whole pelvis for the deep learning-based and model-based μ-maps, respectively. The average relative change between PET images reconstructed with deep learning-based and CT-based μ-maps was 2.6%.
Conclusion: We developed a deep learning-based method to automatically segment air pockets from CAIPIRINHA-accelerated Dixon images, with accuracy comparable to that of semiautomatic segmentations. The μ-maps synthesized using a deep learning-based method from CAIPIRINHA-accelerated Dixon images were more accurate than those generated with the model-based approach available on integrated PET/MRI scanners.
© 2022 by the Society of Nuclear Medicine and Molecular Imaging.

Entities:  

Keywords:  PET quantification; PET/MRI; attenuation correction; deep learning; pseudo-CT

Mesh:

Year:  2021        PMID: 34301782      PMCID: PMC8978194          DOI: 10.2967/jnumed.120.261032

Source DB:  PubMed          Journal:  J Nucl Med        ISSN: 0161-5505            Impact factor:   11.082


  26 in total

1.  Zero-Echo-Time and Dixon Deep Pseudo-CT (ZeDD CT): Direct Generation of Pseudo-CT Images for Pelvic PET/MRI Attenuation Correction Using Deep Convolutional Neural Networks with Multiparametric MRI.

Authors:  Andrew P Leynes; Jaewon Yang; Florian Wiesinger; Sandeep S Kaushik; Dattesh D Shanbhag; Youngho Seo; Thomas A Hope; Peder E Z Larson
Journal:  J Nucl Med       Date:  2017-10-30       Impact factor: 10.057

2.  VoxelMorph: A Learning Framework for Deformable Medical Image Registration.

Authors:  Guha Balakrishnan; Amy Zhao; Mert R Sabuncu; John Guttag; Adrian V Dalca
Journal:  IEEE Trans Med Imaging       Date:  2019-02-04       Impact factor: 10.048

3.  Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction.

Authors:  Angel Torrado-Carvajal; Javier Vera-Olmos; David Izquierdo-Garcia; Onofrio A Catalano; Manuel A Morales; Justin Margolin; Andrea Soricelli; Marco Salvatore; Norberto Malpica; Ciprian Catana
Journal:  J Nucl Med       Date:  2018-08-30       Impact factor: 10.057

4.  Diagnostic performance of PET/MR in the evaluation of active inflammation in Crohn disease.

Authors:  Onofrio Antonio Catalano; Vincent Wu; Umar Mahmood; Alberto Signore; Mark Vangel; Andrea Soricelli; Marco Salvatore; Debra Gervais; Bruce R Rosen
Journal:  Am J Nucl Med Mol Imaging       Date:  2018-02-05

5.  Augmented deep learning model for improved quantitative accuracy of MR-based PET attenuation correction in PSMA PET-MRI prostate imaging.

Authors:  Andrii Pozaruk; Kamlesh Pawar; Shenpeng Li; Alexandra Carey; Jeremy Cheng; Viswanath P Sudarshan; Marian Cholewa; Jeremy Grummet; Zhaolin Chen; Gary Egan
Journal:  Eur J Nucl Med Mol Imaging       Date:  2020-05-11       Impact factor: 9.236

6.  N4ITK: improved N3 bias correction.

Authors:  Nicholas J Tustison; Brian B Avants; Philip A Cook; Yuanjie Zheng; Alexander Egan; Paul A Yushkevich; James C Gee
Journal:  IEEE Trans Med Imaging       Date:  2010-04-08       Impact factor: 10.048

7.  Dose evaluation of fast synthetic-CT generation using a generative adversarial network for general pelvis MR-only radiotherapy.

Authors:  Matteo Maspero; Mark H F Savenije; Anna M Dinkla; Peter R Seevinck; Martijn P W Intven; Ina M Jurgenliemk-Schulz; Linda G W Kerkmeijer; Cornelis A T van den Berg
Journal:  Phys Med Biol       Date:  2018-09-10       Impact factor: 3.609

8.  Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation.

Authors:  Konstantinos Kamnitsas; Christian Ledig; Virginia F J Newcombe; Joanna P Simpson; Andrew D Kane; David K Menon; Daniel Rueckert; Ben Glocker
Journal:  Med Image Anal       Date:  2016-10-29       Impact factor: 8.545

9.  Feasibility of Deep Learning-Based PET/MR Attenuation Correction in the Pelvis Using Only Diagnostic MR Images.

Authors:  Tyler J Bradshaw; Gengyan Zhao; Hyungseok Jang; Fang Liu; Alan B McMillan
Journal:  Tomography       Date:  2018-09

10.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool.

Authors:  Abdel Aziz Taha; Allan Hanbury
Journal:  BMC Med Imaging       Date:  2015-08-12       Impact factor: 1.930

View more
  2 in total

1.  Quantitative evaluation of a deep learning-based framework to generate whole-body attenuation maps using LSO background radiation in long axial FOV PET scanners.

Authors:  Hasan Sari; Mohammadreza Teimoorisichani; Clemens Mingels; Ian Alberts; Vladimir Panin; Deepak Bharkhada; Song Xue; George Prenosil; Kuangyu Shi; Maurizio Conti; Axel Rominger
Journal:  Eur J Nucl Med Mol Imaging       Date:  2022-07-19       Impact factor: 10.057

2.  Using domain knowledge for robust and generalizable deep learning-based CT-free PET attenuation and scatter correction.

Authors:  Rui Guo; Song Xue; Jiaxi Hu; Hasan Sari; Clemens Mingels; Konstantinos Zeimpekis; George Prenosil; Yue Wang; Yu Zhang; Marco Viscione; Raphael Sznitman; Axel Rominger; Biao Li; Kuangyu Shi
Journal:  Nat Commun       Date:  2022-10-06       Impact factor: 17.694

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.