Liver segmentation from low-radiation-dose pediatric computed tomography using patient-specific, statistical modeling
- 18 Downloads
The pediatric computed tomography (CT) volume is acquired at a low dose because radiation is harmful to young children. Consequently, the pediatric CT volume has lower signal-to-noise ratio, which makes organ segmentation difficult. In this paper, we propose a liver segmentation algorithm for pediatric CT scan using a patient-specific level set distribution model (LSDM).
The patient-specific LSDM was constructed using a conditional LSDM (C-LSDM) conditioned on age. Furthermore, a patient-specific probabilistic atlas (PA) was generated using the model, which became a priori to the maximum a posteriori-based segmentation. The patient-specific PA generation by the C-LSDM using kernel density estimation was quicker than the conventional PA generation method using random numbers, and also, it was more accurate as it did not include any approximations.
The liver segmentation algorithm was tested on 42 CT volumes of children aged between 2 weeks and 7 years. In the proposed method, the calculation time of the PA was about 9 s for the single Gaussian method, while it was 337 s for the conventional PA generation method using random numbers. Furthermore, using the kernel density estimation, median and 25%/75% tile of the generalized Dice similarity index between the PA and the correct liver region were found to be 0.3443 and 0.3191/0.3595. The Dice similarity index in the segmentation was 0.8821 and 0.8545/0.9085, which are higher than those obtained by the conventional method, and requires lower computational cost.
We proposed a method to quickly and accurately generate a PA, combined with C-LSDM using kernel density estimation, which enabled efficient calculation and improved segmentation accuracy.
KeywordsPediatrics Computed tomography Liver segmentation Conditional statistical shape model Patient-specific probabilistic atlas
This work was partly supported by KAKENHI (Nos. 26108002 and 18H03255) and the Sheikh Zayed Institute at Children’s National Health System in Washington, DC, USA.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
All the procedures of the study with human participants were performed in compliance with the ethical standards of the institutional and/or national research committee and with the 1975 Helsinki Declaration, as revised in 2008(5). The study was approved by the Ethics Committee at Children’s National Medical Center (Approval No. 00003792) and Tokyo University of Agriculture and Technology (Approval No. 30-31).
Informed consent was obtained from all the participants included in the study.
- 4.Miglioretti DL, Johnson E, Williams A, Greenlee RT, Weinmann S, Solberg LI, Feigelson HS, Roblin D, Flynn MJ, Vanneman N, Smith-Bindman R (2013) The use of computed tomography in pediatrics and the associated radiation exposure and estimated cancer risk. JAMA Pediatr 167:700–707. https://doi.org/10.1001/jamapediatrics.2013.311 CrossRefGoogle Scholar
- 8.Roth HR, Oda H, Meng Q, Hayashi Y, Oda M, Shimizu N, Mori K, Fujiwara M, Misawa K (2017) Automated multi-organ segmentation in abdominal CT with hierarchical 3D fully-convolutional networks. Radiological Society of North America PH223-SD-MOB4, p 267Google Scholar
- 9.Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley-Interscience, HobokenGoogle Scholar
- 13.Tomoshige S, Oost E, Shimizu A, Watanabe H, Nawano S (2014) A conditional statistical shape model with integrated error estimation of the conditions; application to liver segmentation in non-contrast CT images. Med Image Anal 18(1):130–143. https://doi.org/10.1016/j.media.2013.10.003 CrossRefGoogle Scholar
- 15.Kainmüller D, Lange T, Lamecker H (2007) Shape constrained automatic segmentation of the liver based on a heuristic intensity model. In: Proceedings of MICCAI Workshop 3D segmentation in the clinic: a grand challenge, pp 109–116Google Scholar
- 18.Al-Shaikhli SDS, Yang MY, Rosenhahn B (2015) Automatic 3D liver segmentation using sparse representation of global and local image information via level set formulation. arXiv:1508.01521v2
- 21.Hanaoka S, Shimizu A, Nemoto M, Nomura Y, Miki S, Yoshikawa T, Hayashi N, Ohtomo K, Masutani Y (2017) Automatic detection of over 100 anatomical landmarks in medical CT images: a framework with independent detectors and combinatorial optimization. Med Image Anal 35:192–214. https://doi.org/10.1016/j.media.2016.04.001 CrossRefGoogle Scholar
- 23.Arthur D, Vassilvitskii S (2007) k-means++: the advantages of careful seeding. In: Proceedings of the eighteen annual ACM-SIAM symposium on discrete algorithms, pp 1027–1035Google Scholar