An improved supervoxel 3D region growing method based on PET/CT multimodal data for segmentation and reconstruction of GGNs
- 16 Downloads
Among the various types of lung nodules, ground glass nodules (GGNs) are difficult to segment accurately due to complex morphological characteristics. Moreover, GGNs are associated with a higher malignancy probability. Three-dimensional (3D) segmentation and reconstruction techniques can help physicians intuitively elucidate the relationship between lung nodules and their surrounding tissues. We propose an improved supervoxel 3D region growing approach based on positron emission tomography/computed tomography (PET/CT) multimodal data for the segmentation and reconstruction of GGNs. First, the seed point is automatically located with PET information and a 3D mask is generated. Then, a fuzzy connectivity (FC) map is generated based on the 3D mask, and an improved supervoxel 3D region growing is utilized on a fuzzy connectivity map under the constraints of the 3D mask. Finally, 3D GGNs segmentation and reconstruction results are obtained. Qualitative and quantitative comparisons between our proposed method and other region growing methods shows great superiority of our proposed method, with the Jaccard similarity coefficient between our proposed method and physician manual segmentation reaching 95.61%; the average processing time is 16.38 s. Experimental results show that our proposed supervoxel-based 3D region growing method is very promising for assisting physicians in diagnosis.
KeywordsMultimodal data Supervoxel Fuzzy connectivity map Region growing
This research was funded in part by National Natural Science Foundation of China, grant number 61872261, in part by the open funding project of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University (Grant No. VRLAB2018B07) and in part by Research Project Supported by Shanxi Natural Science Foundation (201801D121139).
writing—review and editing Q.Y and D.Y.; methodology Y.W. and C.Q; software W.J., validation Z.Z.; formal analysis, W.S.
Compliance with ethical standards
Conflict of interest
The authors declare no conflict of interest.
- 3.AlZu’bi S, Jararweh Y, Al-Zoubi H, Elbes M, Kanan T, Gupta B (2018) Multi-orientation geometric medical volumes segmentation using 3d multiresolution analysis. Multimed Tools Appl:1–26Google Scholar
- 11.Cui Q, Qiang Z, Zhao J, Qiang Y, Liao X (2017) A 3D Segmentation Method for Pulmonary Nodule Image Sequences based on Supervoxels and Multimodal Data. International Journal of Performability Engineering 13(5):682Google Scholar
- 15.Feng Y, Hao P, Zhang P, Liu X, Wu F, Wang H (2019) Supervoxel based weakly-supervised multi-level 3D CNNs for lung nodule detection and segmentation. Journal of Ambient Intelligence and Humanized Computing:1–11Google Scholar
- 16.Fu G, Lu H, Tan J, Kim H, Zhu X, Lu J (2018) Segmentation of Spinal Canal Region in CT Images using 3D Region Growing Technique. In 2018 International Conference on Information and Communication Technology Robotics (ICT-ROBOT) (pp. 1-4). IEEE.Google Scholar
- 17.Gonzalez R et al (2002) Digital Image Processing, 2nd ed. Upper Saddle River, NJ: Prentice-Hall, 2002:125-134;534-536Google Scholar
- 20.Huang S, Liu X, Han G, Zhao X, Zhao Y, Zhou C (2018) 3D GGO candidate extraction in lung CT images using multilevel thresholding on supervoxels. In Medical Imaging 2018: Computer-Aided Diagnosis (Vol. 10575, p. 1057533). International Society for Optics and Photonics.Google Scholar
- 23.Irving B, Cifor A, Papież B, Franklin J, Anderson E, Brady M, Schnabel J (2014) Automated colorectal tumour segmentation in DCE-MRI using supervoxel neighbourhood contrast characteristics. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 609-616). Springer, Cham.CrossRefGoogle Scholar
- 25.Jiang Y (2017) Research on Supervoxel Based Region Growing Segmentation for Point Cloud Data. Xidian University, Xi’anGoogle Scholar
- 27.Kadkhodaei M et al (2016) Automatic segmentation of multimodal brain tumor images based on classification of super-voxels. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 5945-5948). IEEE.Google Scholar
- 30.Li S, Liu X, Yang A, Pang K, Zhou C, Zhao X, Zhao Y (2013) A novel approach of computer-aided detection of focal ground-glass opacity in 2D lung CT images. In Medical Imaging 2013: Computer-Aided Diagnosis, 8670:86702W-86702W-6.Google Scholar
- 38.Qi Y et al. (2008). Semi-automatic segmentation of liver tumors from CT scans using Bayesian rule-based 3D region growing. In MICCAI workshop (Vol. 41, No. 43, p. 201).Google Scholar
- 40.Rose J, Revol-Muller C, Langlois J, Janier M, Odet C (2008) 3D region growing integrating adaptive shape prior. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro (pp. 967-970). IEEE.Google Scholar
- 43.Sun M, Hu R, Yu H, Zhao B, Ren H (2015) Intracranial hemorrhage detection by 3D voxel segmentation on brain CT images. In 2015 International Conference on Wireless Communications & Signal Processing (WCSP) (pp. 1-5). IEEE.Google Scholar
- 45.Tian Z, Liu L, Fei B. (2015). A supervoxel-based segmentation method for prostate MR images. In Medical Imaging 2015: Image Processing (Vol. 9413, p. 941318). International Society for Optics and Photonics.Google Scholar
- 46.Tong Y et al (2017). Interactive iterative relative fuzzy connectedness lung segmentation on thoracic 4D dynamic MR images. In Medical Imaging 2017: Biomedical Applications in Molecular, Structural, and Functional Imaging (Vol. 10137, p. 1013723). International Society for Optics and Photonics.Google Scholar
- 55.Yang J (2017) Solitary Lung nodules Detection based on Hybird Imaging. Taiyuan University of Technology, TaiyuanGoogle Scholar
- 59.Zhu S, Xia X, Zhang Q, Belloulata K (2007). An image segmentation algorithm in image processing based on threshold segmentation. In 2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System (pp. 673-678). IEEE.Google Scholar