Stepwise deep neural network (stepwise-net) for head and neck auto-segmentation on CT images

Daisuke Kawahara; Masato Tsuneda; Shuichi Ozawa; Hiroyuki Okamoto; Mitsuhiro Nakamura; Teiji Nishio; Akito Saito; Yasushi Nagata

doi:10.1016/j.compbiomed.2022.105295

Stepwise deep neural network (stepwise-net) for head and neck auto-segmentation on CT images

Comput Biol Med. 2022 Apr:143:105295. doi: 10.1016/j.compbiomed.2022.105295. Epub 2022 Feb 6.

Authors

Daisuke Kawahara¹, Masato Tsuneda², Shuichi Ozawa³, Hiroyuki Okamoto⁴, Mitsuhiro Nakamura⁵, Teiji Nishio⁶, Akito Saito⁷, Yasushi Nagata⁸

Affiliations

¹ Department of Radiation Oncology, Graduate School of Biomedical Health Sciences, Hiroshima University, Hiroshima, 734-8551, Japan. Electronic address: daika99@hiroshima-u.ac.jp.
² Department of Radiation Oncology, MR Linac ART Division, Graduate School of Medicine, Chiba University, Chiba, 260-8670, Japan.
³ Hiroshima High-Precision Radiotherapy Cancer Center, Hiroshima, 732-0057, Japan.
⁴ Department of Medical Physics, National Cancer Center Hospital, Tokyo, 104-0045, Japan.
⁵ Division of Medical Physics, Department of Information Technology and Medical Engineering, Human Health Sciences, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan.
⁶ Medical Physics Laboratory, Division of Health Science, Graduate School of Medicine, Osaka University, Osaka, 565-0871, Japan.
⁷ Department of Radiation Oncology, Graduate School of Biomedical Health Sciences, Hiroshima University, Hiroshima, 734-8551, Japan.
⁸ Department of Radiation Oncology, Graduate School of Biomedical Health Sciences, Hiroshima University, Hiroshima, 734-8551, Japan; Hiroshima High-Precision Radiotherapy Cancer Center, Hiroshima, 732-0057, Japan.

PMID: 35168082
DOI: 10.1016/j.compbiomed.2022.105295

Abstract

Objective: The current study aims to propose the auto-segmentation model on CT images of head and neck cancer using a stepwise deep neural network (stepwise-net).

Material and methods: Six normal tissue structures in the head and neck region of 3D CT images: Brainstem, optic nerve, parotid glands (left and right), and submandibular glands (left and right) were segmented with deep learning. In addition to a conventional convolutional neural network (CNN) on U-net, a stepwise neural network (stepwise-network) was developed. The stepwise-network was based on 3D FCN. We designed two networks in the stepwise-network. One is identifying the target region for the segmentation with the low-resolution images. Then, the target region is cropped, which used for the input image for the prediction of the segmentation. These were compared with a clinical used atlas-based segmentation.

Results: The DSCs of the stepwise-net was significantly higher than the atlas-based method for all organ at risk structures. Similarly, the JSCs of the stepwise-net was significantly higher than the atlas-based methods for all organ at risk structures. The Hausdorff distance (HD) was significantly smaller than the atlas-based method for all organ at-risk structures. For the comparison of the stepwise-net and U-net, the stepwise-net had a higher DSC and JSC and a smaller HD than the conventional U-net.

Conclusions: We found that the stepwise-network plays a role is superior to conventional U-net-based and atlas-based segmentation. Our proposed model that is a potentially valuable method for improving the efficiency of head and neck radiotherapy treatment planning.

Keywords: CNN; Deep learning; Segmentation.