DeepIGeoS-V2: Deep Interactive Segmentation of Multiple Organs from Head and Neck Images with Lightweight CNNs

Accurate segmentation of organs-at-risks (OARs) from Computed Tomography (CT) image is a key step for efficient planning of radiation therapy for nasopharyngeal carcinoma (NPC) treatment. Convolutional Neural Networks (CNN) have recently become the state-of-the-art automated OARs image segmentation method. However, due to the low contrast of head and neck organism tissues in CT, the fully automatic segmentation may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based multi-organ interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentation. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose a dimension separate lightweight network that gives a faster and better dense predictions. In addition, we propose a mis-segmentation-based weighting strategy combined with loss functions to achieve more accurate segmentation. We validated the proposed framework in the context of 3D head and neck organism segmentation from CT images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains higher accuracy with fewer user interventions and less time compared with traditional interactive segmentation method.

Authors and Affiliations

1. School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, China

   Wenhui Lei, Huan Wang, Ran Gu, Shaoting Zhang & Guotai Wang

2. Department of Radiation Oncology, Sichuan Cancer Hospital and Institute, University of Electronic Science and Technology of China, Chengdu, China

   Shichuan Zhang

Corresponding author

Correspondence to Guotai Wang .

Editors and Affiliations

1. University of Sydney, Sydney, NSW, Australia

   Luping Zhou

2. University of Minnesota, Minneapolis, MN, USA

   Nicholas Heller

3. University of Notre Dame, Notre Dame, IN, USA

   Yiyu Shi

4. Western University, London, ON, Canada

   Yiming Xiao

5. University of Bern, Bern, Switzerland

   Raphael Sznitman

6. Eindhoven University of Technology, Eindhoven, The Netherlands

   Veronika Cheplygina

7. École Centrale de Nantes, Nantes, France

   Diana Mateus

8. University of Dundee, Dundee, UK

   Emanuele Trucco

9. University of Notre Dame, Notre Dame, IN, USA

   X. Sharon Hu

10. University of Notre Dame, Notre Dame, IN, USA

    Danny Chen

11. University of Grenoble Alpes, Grenoble, France

    Matthieu Chabanas

12. Concordia University, Montréal, QC, Canada

    Hassan Rivaz

13. Health Research, SINTEF Digital, Trondheim, Norway

    Ingerid Reinertsen

Reprints and permissions

© 2019 Springer Nature Switzerland AG

Policies and ethics