Journal of the Korean Society of Radiology (한국방사선학회논문지)

The Korean Society of Radiology (한국방사선학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning based Brachial Plexus Ultrasound Images Segmentation by Leveraging an Object Detection Algorithm

객체 검출 알고리즘을 활용한 딥러닝 기반 상완 신경총 초음파 영상의 분할에 관한 연구

  • Kukhyun Cho (Department of Computer Engineering, Chonnam National University) ;
  • Hyunseung Ryu (Department of Computer Engineering, Chonnam National University) ;
  • Myeongjin Lee (Department of Computer Engineering, Chonnam National University) ;
  • Suhyung Park (Department of Electronics and Computer Engineering, Chonnam National University)
  • 조국현 (전남대학교 컴퓨터정보통신공학과) ;
  • 류현승 (전남대학교 컴퓨터정보통신공학과) ;
  • 이명진 (전남대학교 컴퓨터정보통신공학과) ;
  • 박수형 (전남대학교 전자컴퓨터공학부)
  • Received : 2024.07.22
  • Accepted : 2024.10.31
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Ultrasound-guided regional anesthesia is one of the most common techniques used in peripheral nerve blockade by enhancing pain control and recovery time. However, accurate Brachial Plexus (BP) nerve detection and identification remains a challenging task due to the difficulty in data acquisition such as speckle and Doppler artifacts even for experienced anesthesiologists. To mitigate the issue, we introduce a BP nerve small target segmentation network by incorporating BP object detection and U-Net based semantic segmentation into a single deep learning framework based on the multi-scale approach. To this end, the current BP detection and identification was estimated: 1) A RetinaNet model was used to roughly locate the BP nerve region using multi-scale based feature representations, and 2) U-Net was then used by feeding plural BP nerve features for each scale. The experimental results demonstrate that our proposed model produces high quality BP segmentation by increasing the accuracies of the BP nerve identification with the assistance of roughly locating the BP nerve area compared to competing methods such as segmentation-only models.

초음파 유도 국소마취는 통증 관리와 회복 시간을 개선하여 말초신경 차단에 널리 사용되는 기법이다. 하지만 능숙한 임상의들에게도 초음파 영상에서 나타나는 speckle 및 Doppler와 같은 영상에 내재되어 있는 artifacts로 인하여 상완 신경총(BP; Brachial Plexus)의 정확한 검출 및 식별이 여전히 난제로 남아있다. 이 문제를 해결하기 위해, 우리는 다중 스케일의 접근법을 기반으로 하는 BP의 객체 검출과 그 결과로부터 U-Net 기반의 의미론적 영상 분할을 수행하는 small target 기반의 BP segmentation 알고리즘을 제안한다. 이를 위해 현재 BP 검출 및 식별은 다음과 같이 진행되었다: 1) 다중 스케일 기반의 RetinaNet 모델을 활용하여 BP 신경 영역을 대략적으로 특정하는 단계와 2) 객체 검출로부터 제한된 영상의 범위를 입력으로 U-Net을 활용함으로서 BP 신경의 영역을 검출하는 단계. 실험 결과는 제안된 모델이 분할 전용 모델 등의 경쟁 방법에 비해 BP 신경 영역을 대략적으로 특정하여 식별 범위를 제한함으로서 BP 신경 범위 분할의 정확도를 높이고 고품질 BP 분할을 생성할 수 있음을 보여준다.

Keywords

Acknowledgement

이 논문은 전남대학교 학술연구비 (과제번호: 2022-2579) 지원에 의하여 연구되었음.

References

  1. J. Yang, A. Amini, R. Williamson, L. Zhang, Y. Zhang, R. Komaki, Z. Liao, J. Cox, J. Welsh, L. Court, L. Dong, "Automatic Contouring of Brachial Plexus Using a Multi-Atlas Approach for Lung Cancer Radiation Therapy", Practical Radiation Oncology, Vol. 3, No. 4, pp. 139-147, 2013. http://dx.doi.org/10.1016/j.prro.2013.01.002 
  2. S. S. Liu, J. E. Ngeow, J. T. Yadeau, "Ultrasound-Guided Regional Anesthesia and Analgesia: A Qualitative Systematic Review", Regional Anesthesia & Pain Medicine, Vol. 34, No. 1, pp. 47-59, 2009. http://dx.doi.org/10.1097/AAP.0b013e3181933ec3 
  3. J. P. A. van Boxtel, V. R. J. Vousten, J. Pluim, N. M. Rad, "Hybrid Deep Neural Network for Brachial Plexus Nerve Segmentation in Ultrasound Images", 2021 29th European Signal Processing Conference, Dublin, Ireland, pp. 1686-1690, 2021. http://dx.doi.org/10.23919/EUSIPCO54536.2021.9616329 
  4. O. Ronneberger, P. Fischer, T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation", 2015 Medical image computing and computer- assisted intervention MICCAI: 18th international conference, pp. 234-241, 2015. https://doi.org/10.48550/arXiv.1505.04597 
  5. N. Abraham, K. Illanko, N. Khan, D. Androutsos, "Deep Learning for Semantic Segmentation of Brachial Plexus Nerves in Ultrasound Images Using U-Net and M-Net", 2019 3rd International Conference on Imaging, Signal Processing and Communication, pp. 85-89, 2019. https://doi.org/10.1109/ICISPC.2019.8935668 
  6. D. Erhan, C. Szegedy, A. Toshev, D. Anguelov, "Scalable Object Detection Using Deep Neural Networks", 2014 The IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2147-2154, 2013. https://doi.org/10.48550/arXiv.1312.2249 
  7. S. Bell, C. L. Zitnick, K. Bala, R. Girshick, "Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks", 2016 The IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2874-2883, 2015. https://doi.org/10.48550/arXiv.1512.04143 
  8. B. Kong, X. Wang, Z. Li, Q. Song, S. Zhang, "Cancer Metastasis Detection via Spatially Structured Deep Network", in Lecture Notes in Computer Science, Springer International Publishing, pp. 236-248, 2017. https://doi.org/10.1007/978-3-319-59050-9_19 
  9. T. Y. Lin, P. Goyal, R. Girshick, K. He, P. Dollar, "Focal Loss for Dense Object Detection", 2018 Proceedings of the IEEE International Conference on Computer Vision, pp. 2980-2988, 2017. https://doi.org/10.48550/arXiv.1708.02002 
  10. T. Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, S. Belongie, "Feature Pyramid Networks for Object Detection", 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, pp. 2117-2125, 2016. https://doi.org/10.48550/arXiv.1612.03144 
  11. K. He, X. Zhang, S. Ren, J. Sun, "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 37, No. 9, pp. 1904-1916, 2015. http://dx.doi.org/10.1109/TPAMI.2015.2389824 
  12. K. He, X. Zhang, S. Ren, J. Sun, "Deep Residual Learning for Image Recognition", 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 770-778, 2015. https://doi.org/10.48550/arXiv.1512.03385 
  13. J. Hu, L. Shen, S. Albanie, G. Sun, E. Wu, "Squeeze-and-Excitation Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42, No. 8, pp. 2011-2023, 2020. https://doi.org/10.1109/TPAMI.2019.2913372 
  14. S. Woo, J. Park, J. Y. Lee, I. S. Kweon, "CBAM: Convolutional Block Attention Module", European Conference on Computer Vision, pp. 3-19, 2018. https://doi.org/10.1007/978-3-030-01234-2_1 
  15. fizyr, keras-retinanet, "Keras-Retinanet", 2019 Model Retrieved from Github, From URL; https://github.com/fizyr/keras-retinanet/ 
  16. Kaggle, "Ultrasound Nerve Segmentation Dataset", 2016 Data Retrieved From URL; https://www.kaggle.com/c/ultrasound-nerve-segmentation/