Comparison of Segmentation Methods in Analysis of MR and CT Images of Pediatric Spine

被引:0
作者
Mikulka, J. [1 ]
Chalupa, D. [1 ]
Kolarik, M. [2 ]
Riha, K. [2 ]
Bartusek, K. [1 ]
Filipovic, M. [3 ]
机构
[1] Brno Univ Technol, FEEC, DTEEE, Brno, Czech Republic
[2] Brno Univ Technol, Dept Telecommun, FEEC, Brno, Czech Republic
[3] Univ Hosp Brno, Dept Orthoped Surg, Brno, Czech Republic
来源
2021 PHOTONICS & ELECTROMAGNETICS RESEARCH SYMPOSIUM (PIERS 2021) | 2021年
关键词
D O I
10.1109/PIERS53385.2021.9694940
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Scoliosis is the most common spinal deformity in children. Only early treatment during spinal growth can significantly reduce the associated problems caused by the deformity in adults. The aim of this study is to use a spine model to numerically simulate the changes in spinal stresses during correction of congenital deformity by vertebral osteotomy. In the first stage, CT imaging was used as a reference to obtain correctly segmented vertebral groups due to the low quality of MRI image data. Registration techniques were optimized to process all MRI and CT image sequences. An SVM classifier was used with Dice coefficients of 0.98 for CT and 0.95, 0.97, 0.91 and 0.92 for T1 hard, T2 hard, T1 soft and T2 soft, respectively. In the next phase of the project, deep learning algorithms were used to obtain MRI segmentation. Two different segmentation algorithms were proposed using the U-Net network. Standard and patchwise approach with rotational averaging for both CT and MRI dataset. The standard segmentation produced more accurate results with a Dice coefficient of 0.96 for the CT dataset and 0.94 for the MRI dataset. The patchwise method provided slightly better results when processing the actual dataset containing the new data acquired by our MRI scanner. With the smaller MRI dataset, we achieved comparable Dice coefficients in both datasets. The presented results suggest the possibility of using CT and even MR imaging exclusively for spine segmentation if visualization of surrounding tissues and automatic 3D spine modeling is desired.
引用
收藏
页码:449 / 454
页数:6
相关论文
共 9 条
[1]  
Abadi M, 2015, ARXIV160304467, DOI 10.5555/3026877.3026899
[2]  
Buslaev A., 2018, Albumentations: fast and flexible image augmentations
[3]  
Chollet F., 2015, KERAS GITHUB REPOSIT
[4]   Test-time augmentation for deep learning-based cell segmentation on microscopy images [J].
Moshkov, Nikita ;
Mathe, Botond ;
Kertesz-Farkas, Attila ;
Hollandi, Reka ;
Horvath, Peter .
SCIENTIFIC REPORTS, 2020, 10 (01)
[5]  
Pedregosa F, 2011, Journal of Machine Learning Research, V12, P2825
[6]   U-Net: Convolutional Networks for Biomedical Image Segmentation [J].
Ronneberger, Olaf ;
Fischer, Philipp ;
Brox, Thomas .
MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION, PT III, 2015, 9351 :234-241
[7]   Nonrigid registration using free-form deformations: Application to breast MR images [J].
Rueckert, D ;
Sonoda, LI ;
Hayes, C ;
Hill, DLG ;
Leach, MO ;
Hawkes, DJ .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1999, 18 (08) :712-721
[8]  
Yao JH, 2012, LECT NOTES COMPUT SC, V7512, P509, DOI 10.1007/978-3-642-33454-2_63
[9]   Robust Detection and Segmentation for Diagnosis of Vertebral Diseases Using Routine MR Images [J].
Zukic, Dzenan ;
Vlasak, Ales ;
Egger, Jan ;
Horinek, Daniel ;
Nimsky, Christopher ;
Kolb, Andreas .
COMPUTER GRAPHICS FORUM, 2014, 33 (06) :190-204