Journal of the Korea Computer Graphics Society (한국컴퓨터그래픽스학회논문지)

Korea Computer Graphics Society (한국컴퓨터그래픽스학회)
권호 표지
DOI QR코드

DOI QR Code

Automatic Sagittal Plane Detection for the Identification of the Mandibular Canal

치아 신경관 식별을 위한 자동 시상면 검출법

  • Pak, Hyunji (Dept. of Computer Science and Engineering, Seoul National University) ;
  • Kim, Dongjoon (Dept. of Computer Science and Engineering, Seoul National University) ;
  • Shin, Yeong-Gil (Dept. of Computer Science and Engineering, Seoul National University)
  • Received : 2020.06.12
  • Accepted : 2020.06.25
  • Published : 2020.07.01
Download PDF
⟨ Previous Next ⟩

Abstract

Identification of the mandibular canal path in Computed Tomography (CT) scans is important in dental implantology. Typically, prior to the implant planning, dentists find a sagittal plane where the mandibular canal path is maximally observed, to manually identify the mandibular canal. However, this is time-consuming and requires extensive experience. In this paper, we propose a deep-learning-based framework to detect the desired sagittal plane automatically. This is accomplished by utilizing two main techniques: 1) a modified version of the iterative transformation network (ITN) method for obtaining initial planes, and 2) a fine searching method based on a convolutional neural network (CNN) classifier for detecting the desirable sagittal plane. This combination of techniques facilitates accurate plane detection, which is a limitation of the stand-alone ITN method. We have tested on a number of CT datasets to demonstrate that the proposed method can achieve more satisfactory results compared to the ITN method. This allows dentists to identify the mandibular canal path efficiently, providing a foundation for future research into more efficient, automatic mandibular canal detection methods.

CT 스캔에서 치아 신경관 식별은 치과 임플란트에서 중요하다. 임플란트 계획 전에, 치과 의사들은 신경관을 수동으로 식별하기 위해 신경관 경로가 최대로 관찰되는 시상면을 찾는다. 그러나 이는 시간 소모적이며 많은 임상 경험을 필요로 한다. 위 논문에서 우리는 원하는 시상면을 자동으로 검출하기 위한 깊은 학습 기반의 프레임 워크를 제안한다. 이는 두가지 주요 기술들을 사용하여 획득된다: 1) 초기 평면들을 획득하기 위한 반복 변환 네트워크 (ITN) 방법의 수정 버전과 2) 원하는 시상면을 검출하기 위한 합성곱 신경망 기반의 정밀 탐색 법. 이 기술들의 결합은 ITN 방법을 단독으로 사용하였을 때의 한계인, 정확한 평면 검출을 용이하게 한다. 우리는 여러 개의 CT 데이터 셋에서 실험하여 우리가 제안한 방법이 ITN 방법과 비교하여 훨씬 뛰어난 결과를 얻을 수 있음을 증명하였다. 이는 치과 의사들이 신경관 경로를 효율적으로 식별할 수 있어 보다 효율적인 자동신경관 검출법에 대한 향후 연구의 기반을 제공한다.

Keywords

References

  1. G. Tognola, M. Parazzini, G. Pedretti, P. Ravazzani, F. Grandori, A. Pesatori, M. Norgia, and C. Svelto, "Gradient-vector-flow snake method for quantitative image reconstruction applied to mandibular distraction surgery," IEEE Transactions on Instrumentation and Measurement, vol. 58, no. 7, pp. 2087-2093, 2009. https://doi.org/10.1109/TIM.2009.2015525
  2. G. Kim, J. Lee, H. Lee, J. Seo, Y.-M. Koo, Y.-G. Shin, and B. Kim, "Automatic extraction of inferior alveolar nerve canal using feature-enhancing panoramic volume rendering," IEEE Transactions on Biomedical Engineering, vol. 58, no. 2, pp. 253-264, 2010. https://doi.org/10.1109/TBME.2010.2089053
  3. R. LloreNs, V. Naranjo, F. LoPez, and M. AlcanIz, "Jaw tissues segmentation in dental 3d ct images using fuzzy-connectedness and morphological processing," Computer Methods and Programs in Biomedicine, vol. 108, no. 2, pp. 832-843, 2012. https://doi.org/10.1016/j.cmpb.2012.05.014
  4. H. Ryou, M. Yaqub, A. Cavallaro, F. Roseman, A. Papageorghiou, and J. A. Noble, "Automated 3d ultrasound biometry planes extraction for first trimester fetal assessment," in International Workshop on Machine Learning in Medical Imaging. Springer, 2016, pp. 196-204.
  5. Y. Li, B. Khanal, B. Hou, A. Alansary, J. J. Cerrolaza, M. Sinclair, J. Matthew, C. Gupta, C. Knight, B. Kainz, et al., "Standard plane detection in 3d fetal ultrasound using an iterative transformation network," in International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2018, pp. 392-400.
  6. C. E. Misch, "Contemporary implant dentistry," Implant Dentistry, vol. 8, no. 1, p. 90, 1999. https://doi.org/10.1097/00008505-199901000-00013
  7. J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 3431-3440.
  8. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "Imagenet: A large-scale hierarchical image database," in 2009 IEEE Conference on Computer Vision and Pattern Recognition. Ieee, 2009, pp. 248-255.
  9. J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, "How transferable are features in deep neural networks?" in Advances in neural information processing systems, 2014, pp. 3320-3328.
  10. S. Klein, M. Staring, and J. P. Pluim, "Evaluation of optimization methods for nonrigid medical image registration using mutual information and b-splines," IEEE transactions on image processing, vol. 16, no. 12, pp. 2879-2890, 2007. https://doi.org/10.1109/TIP.2007.909412
  11. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
  12. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770-778.
  13. H. Chen, Q. Dou, D. Ni, J.-Z. Cheng, J. Qin, S. Li, and P.-A. Heng, "Automatic fetal ultrasound standard plane detection using knowledge transferred recurrent neural networks," in International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2015, pp. 507-514.
  14. B. A. Ardekani, J. Kershaw, M. Braun, and I. Kanuo, "Automatic detection of the mid-sagittal plane in 3-d brain images," IEEE transactions on medical imaging, vol. 16, no. 6, pp. 947-952, 1997. https://doi.org/10.1109/42.650892
  15. E. Naziri, A. Schramm, and F. Wilde, "Accuracy of computer-assisted implant placement with insertion templates," GMS Interdisciplinary plastic and reconstructive surgery DGPW, vol. 5, 2016.