Literature DB >> 28756622

Fully automatic, multiorgan segmentation in normal whole body magnetic resonance imaging (MRI), using classification forests (CFs), convolutional neural networks (CNNs), and a multi-atlas (MA) approach.

Ioannis Lavdas1, Ben Glocker2, Konstantinos Kamnitsas2, Daniel Rueckert2, Henrietta Mair3, Amandeep Sandhu4, Stuart A Taylor3, Eric O Aboagye1, Andrea G Rockall5.   

Abstract

PURPOSE: As part of a program to implement automatic lesion detection methods for whole body magnetic resonance imaging (MRI) in oncology, we have developed, evaluated, and compared three algorithms for fully automatic, multiorgan segmentation in healthy volunteers.
METHODS: The first algorithm is based on classification forests (CFs), the second is based on 3D convolutional neural networks (CNNs) and the third algorithm is based on a multi-atlas (MA) approach. We examined data from 51 healthy volunteers, scanned prospectively with a standardized, multiparametric whole body MRI protocol at 1.5 T. The study was approved by the local ethics committee and written consent was obtained from the participants. MRI data were used as input data to the algorithms, while training was based on manual annotation of the anatomies of interest by clinical MRI experts. Fivefold cross-validation experiments were run on 34 artifact-free subjects. We report three overlap and three surface distance metrics to evaluate the agreement between the automatic and manual segmentations, namely the dice similarity coefficient (DSC), recall (RE), precision (PR), average surface distance (ASD), root-mean-square surface distance (RMSSD), and Hausdorff distance (HD). Analysis of variances was used to compare pooled label metrics between the three algorithms and the DSC on a 'per-organ' basis. A Mann-Whitney U test was used to compare the pooled metrics between CFs and CNNs and the DSC on a 'per-organ' basis, when using different imaging combinations as input for training.
RESULTS: All three algorithms resulted in robust segmenters that were effectively trained using a relatively small number of datasets, an important consideration in the clinical setting. Mean overlap metrics for all the segmented structures were: CFs: DSC = 0.70 ± 0.18, RE = 0.73 ± 0.18, PR = 0.71 ± 0.14, CNNs: DSC = 0.81 ± 0.13, RE = 0.83 ± 0.14, PR = 0.82 ± 0.10, MA: DSC = 0.71 ± 0.22, RE = 0.70 ± 0.34, PR = 0.77 ± 0.15. Mean surface distance metrics for all the segmented structures were: CFs: ASD = 13.5 ± 11.3 mm, RMSSD = 34.6 ± 37.6 mm and HD = 185.7 ± 194.0 mm, CNNs; ASD = 5.48 ± 4.84 mm, RMSSD = 17.0 ± 13.3 mm and HD = 199.0 ± 101.2 mm, MA: ASD = 4.22 ± 2.42 mm, RMSSD = 6.13 ± 2.55 mm, and HD = 38.9 ± 28.9 mm. The pooled performance of CFs improved when all imaging combinations (T2w + T1w + DWI) were used as input, while the performance of CNNs deteriorated, but in neither case, significantly. CNNs with T2w images as input, performed significantly better than CFs with all imaging combinations as input for all anatomical labels, except for the bladder.
CONCLUSIONS: Three state-of-the-art algorithms were developed and used to automatically segment major organs and bones in whole body MRI; good agreement to manual segmentations performed by clinical MRI experts was observed. CNNs perform favorably, when using T2w volumes as input. Using multimodal MRI data as input to CNNs did not improve the segmentation performance.
© 2017 American Association of Physicists in Medicine.

Entities:  

Keywords:  classification forests; convolutional neural networks; fully automatic segmentation; multi-atlas segmentation; whole body MRI

Mesh:

Year:  2017        PMID: 28756622     DOI: 10.1002/mp.12492

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  8 in total

1.  Automated Segmentation of Tissues Using CT and MRI: A Systematic Review.

Authors:  Leon Lenchik; Laura Heacock; Ashley A Weaver; Robert D Boutin; Tessa S Cook; Jason Itri; Christopher G Filippi; Rao P Gullapalli; James Lee; Marianna Zagurovskaya; Tara Retson; Kendra Godwin; Joey Nicholson; Ponnada A Narayana
Journal:  Acad Radiol       Date:  2019-08-10       Impact factor: 3.173

Review 2.  Current development and prospects of deep learning in spine image analysis: a literature review.

Authors:  Biao Qu; Jianpeng Cao; Chen Qian; Jinyu Wu; Jianzhong Lin; Liansheng Wang; Lin Ou-Yang; Yongfa Chen; Liyue Yan; Qing Hong; Gaofeng Zheng; Xiaobo Qu
Journal:  Quant Imaging Med Surg       Date:  2022-06

Review 3.  Detection of Lung Contour with Closed Principal Curve and Machine Learning.

Authors:  Tao Peng; Yihuai Wang; Thomas Canhao Xu; Lianmin Shi; Jianwu Jiang; Shilang Zhu
Journal:  J Digit Imaging       Date:  2018-08       Impact factor: 4.056

4.  Cascaded atrous convolution and spatial pyramid pooling for more accurate tumor target segmentation for rectal cancer radiotherapy.

Authors:  Kuo Men; Pamela Boimel; James Janopaul-Naylor; Haoyu Zhong; Mi Huang; Huaizhi Geng; Chingyun Cheng; Yong Fan; John P Plastaras; Edgar Ben-Josef; Ying Xiao
Journal:  Phys Med Biol       Date:  2018-09-17       Impact factor: 3.609

5.  A deep learning-based self-adapting ensemble method for segmentation in gynecological brachytherapy.

Authors:  Zhen Li; Qingyuan Zhu; Lihua Zhang; Xiaojing Yang; Zhaobin Li; Jie Fu
Journal:  Radiat Oncol       Date:  2022-09-05       Impact factor: 4.309

6.  Development of machine learning support for reading whole body diffusion-weighted MRI (WB-MRI) in myeloma for the detection and quantification of the extent of disease before and after treatment (MALIMAR): protocol for a cross-sectional diagnostic test accuracy study.

Authors:  Laura Satchwell; Linda Wedlake; Emily Greenlay; Xingfeng Li; Christina Messiou; Ben Glocker; Tara Barwick; Theodore Barfoot; Simon Doran; Martin O Leach; Dow Mu Koh; Martin Kaiser; Stefan Winzeck; Talha Qaiser; Eric Aboagye; Andrea Rockall
Journal:  BMJ Open       Date:  2022-10-05       Impact factor: 3.006

7.  Multi-part segmentation for porcine offal inspection with auto-context and adaptive atlases.

Authors:  Stephen McKenna; Telmo Amaral; Thomas Plötz; Ilias Kyriazakis
Journal:  Pattern Recognit Lett       Date:  2018-09-01       Impact factor: 3.756

Review 8.  How molecular imaging will enable robotic precision surgery : The role of artificial intelligence, augmented reality, and navigation.

Authors:  Thomas Wendler; Fijs W B van Leeuwen; Nassir Navab; Matthias N van Oosterom
Journal:  Eur J Nucl Med Mol Imaging       Date:  2021-06-29       Impact factor: 9.236

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.