Literature DB >> 31650265

Postoperative glioma segmentation in CT image using deep feature fusion model guided by multi-sequence MRIs.

Fan Tang1,2,3, Shujun Liang1,2, Tao Zhong1,2, Xia Huang1,4, Xiaogang Deng3, Yu Zhang5,6, Linghong Zhou7.   

Abstract

OBJECTIVES: Computed tomography (CT) and magnetic resonance imaging (MRI) are the most commonly selected methods for imaging gliomas. Clinically, radiotherapists always delineate the CT glioma region with reference to multi-modal MR image information. On this basis, we develop a deep feature fusion model (DFFM) guided by multi-sequence MRIs for postoperative glioma segmentation in CT images.
METHODS: DFFM is a multi-sequence MRI-guided convolutional neural network (CNN) that iteratively learns the deep features from CT images and multi-sequence MR images simultaneously by utilizing a multi-channel CNN architecture, and then combines these two deep features together to produce the segmentation result. The whole network is optimized together via a standard back-propagation. A total of 59 CT and MRI datasets (T1/T2-weighted FLAIR, T1-weighted contrast-enhanced, T2-weighted) of postoperative gliomas as tumor grade II (n = 24), grade III (n = 18), or grade IV (n = 17) were included. Dice coefficient (DSC), precision, and recall were used to measure the overlap between automated segmentation results and manual segmentation. The Wilcoxon signed-rank test was used for statistical analysis.
RESULTS: DFFM showed a significantly (p < 0.01) higher DSC of 0.836 than U-Net trained by single CT images and U-Net trained by stacking the CT and multi-sequence MR images, which yielded 0.713 DSC and 0.818 DSC, respectively. The precision values showed similar behavior as DSC. Moreover, DSC and precision values have no significant statistical difference (p > 0.01) with difference grades.
CONCLUSIONS: DFFM enables the accurate automated segmentation of CT postoperative gliomas of profit guided by multi-sequence MR images and may thus improve and facilitate radiotherapy planning. KEY POINTS: • A fully automated deep learning method was developed to segment postoperative gliomas on CT images guided by multi-sequence MRIs. • CT and multi-sequence MR image integration allows for improvements in deep learning postoperative glioma segmentation method. • This deep feature fusion model produces reliable segmentation results and could be useful in delineating GTV in postoperative glioma radiotherapy planning.

Entities:  

Keywords:  Glioma; Machine learning; Magnetic resonance imaging; Radiotherapy

Year:  2019        PMID: 31650265     DOI: 10.1007/s00330-019-06441-z

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  19 in total

Review 1.  Anatomical imaging for radiotherapy.

Authors:  Philip M Evans
Journal:  Phys Med Biol       Date:  2008-05-21       Impact factor: 3.609

Review 2.  Magnetic resonance imaging (MRI): considerations and applications in radiotherapy treatment planning.

Authors:  V S Khoo; D P Dearnaley; D J Finnigan; A Padhani; S F Tanner; M O Leach
Journal:  Radiother Oncol       Date:  1997-01       Impact factor: 6.280

Review 3.  Deep Learning in Medical Image Analysis.

Authors:  Dinggang Shen; Guorong Wu; Heung-Il Suk
Journal:  Annu Rev Biomed Eng       Date:  2017-03-09       Impact factor: 9.590

4.  MRI-based treatment planning for radiotherapy: dosimetric verification for prostate IMRT.

Authors:  Lili Chen; Robert A Price; Lu Wang; Jinsheng Li; Lihong Qin; Shawn McNeeley; C-M Charlie Ma; Gary M Freedman; Alan Pollack
Journal:  Int J Radiat Oncol Biol Phys       Date:  2004-10-01       Impact factor: 7.038

5.  Decision forests for tissue-specific segmentation of high-grade gliomas in multi-channel MR.

Authors:  Darko Zikic; Ben Glocker; Ender Konukoglu; Antonio Criminisi; C Demiralp; J Shotton; O M Thomas; T Das; R Jena; S J Price
Journal:  Med Image Comput Comput Assist Interv       Date:  2012

6.  Nonlinear Image Representation Using Divisive Normalization.

Authors:  Siwei Lyu; Eero P Simoncelli
Journal:  Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit       Date:  2008

7.  Early postoperative MRI overestimates residual tumour after resection of gliomas with no or minimal enhancement.

Authors:  Sinan M K Belhawi; Friso W A Hoefnagels; Johannes C Baaijen; Esther Sanchez Aliaga; Jaap C Reijneveld; Jan J Heimans; Frederik Barkhof; W Peter Vandertop; Philip C De Witt Hamer
Journal:  Eur Radiol       Date:  2011-02-18       Impact factor: 5.315

8.  Why is real-world visual object recognition hard?

Authors:  Nicolas Pinto; David D Cox; James J DiCarlo
Journal:  PLoS Comput Biol       Date:  2008-01       Impact factor: 4.475

Review 9.  The 2007 WHO classification of tumours of the central nervous system.

Authors:  David N Louis; Hiroko Ohgaki; Otmar D Wiestler; Webster K Cavenee; Peter C Burger; Anne Jouvet; Bernd W Scheithauer; Paul Kleihues
Journal:  Acta Neuropathol       Date:  2007-07-06       Impact factor: 17.088

10.  Metal artifact reduction on cervical CT images by deep residual learning.

Authors:  Xia Huang; Jian Wang; Fan Tang; Tao Zhong; Yu Zhang
Journal:  Biomed Eng Online       Date:  2018-11-27       Impact factor: 2.819

View more
  8 in total

1.  Integrated Gene Expression and Methylation Analyses Identify DLL3 as a Biomarker for Prognosis of Malignant Glioma.

Authors:  Aierpati Maimaiti; Xixian Wang; Yujun Hao; Lei Jiang; Xin Shi; Yinan Pei; Zhaohai Feng; Maimaitijiang Kasimu
Journal:  J Mol Neurosci       Date:  2021-03-13       Impact factor: 3.444

2.  Segmentation of infected region in CT images of COVID-19 patients based on QC-HC U-net.

Authors:  Qin Zhang; Xiaoqiang Ren; Benzheng Wei
Journal:  Sci Rep       Date:  2021-11-24       Impact factor: 4.379

3.  Back Propagation Neural Network-Based Magnetic Resonance Imaging Image Features in Treating Intestinal Obstruction in Digestive Tract Diseases with Chengqi Decoction.

Authors:  Yongfeng Li; Kaina Wang; Li Gao; Xiaojun Lu
Journal:  Contrast Media Mol Imaging       Date:  2021-12-24       Impact factor: 3.161

4.  Deep Learning-Based Image Segmentation of Cone-Beam Computed Tomography Images for Oral Lesion Detection.

Authors:  Xueling Wang; Xianmin Meng; Shu Yan
Journal:  J Healthc Eng       Date:  2021-09-21       Impact factor: 2.682

5.  A Novel Prediction Model for Brain Glioma Image Segmentation Based on the Theory of Bose-Einstein Condensate.

Authors:  Tian Chi Zhang; Jing Zhang; Shou Cun Chen; Bacem Saada
Journal:  Front Med (Lausanne)       Date:  2022-03-18

6.  Characteristics of Computed Tomography Images for Patients with Acute Liver Injury Caused by Sepsis under Deep Learning Algorithm.

Authors:  Huijun Wang; Qianqian Bao; Donghang Cao; Shujing Dong; Lili Wu
Journal:  Contrast Media Mol Imaging       Date:  2022-03-20       Impact factor: 3.161

Review 7.  Alternations and Applications of the Structural and Functional Connectome in Gliomas: A Mini-Review.

Authors:  Ziyan Chen; Ningrong Ye; Chubei Teng; Xuejun Li
Journal:  Front Neurosci       Date:  2022-04-11       Impact factor: 5.152

Review 8.  Performance of machine learning algorithms for glioma segmentation of brain MRI: a systematic literature review and meta-analysis.

Authors:  Evi J van Kempen; Max Post; Manoj Mannil; Richard L Witkam; Mark Ter Laan; Ajay Patel; Frederick J A Meijer; Dylan Henssen
Journal:  Eur Radiol       Date:  2021-05-21       Impact factor: 5.315

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.