Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training data
Affiliation
The University of Manchester, Oxford Rd, Manchester M13 9PL, UKIssue Date
2022
Metadata
Show full item recordAbstract
Background and purpose: Convolutional neural networks (CNNs) are increasingly used to automate segmentation for radiotherapy planning, where accurate segmentation of organs-at-risk (OARs) is crucial. Training CNNs often requires large amounts of data. However, large, high quality datasets are scarce. The aim of this study was to develop a CNN capable of accurate head and neck (HN) 3D auto-segmentation of planning CT scans using a small training dataset (34 CTs). Materials and method: Elements of our custom CNN architecture were varied to optimise segmentation performance. We tested and evaluated the impact of: using multiple contrast channels for the CT scan input at specific soft tissue and bony anatomy windows, resize vs. transpose convolutions, and loss functions based on overlap metrics and cross-entropy in different combinations. Model segmentation performance was compared with the inter-observer deviation of two doctors' gold standard segmentations using the 95th percentile Hausdorff distance and mean distance-to-agreement (mDTA). The best performing configuration was further validated on a popular public dataset to compare with state-of-the-art (SOTA) auto-segmentation methods. Results: Our best performing CNN configuration was competitive with current SOTA methods when evaluated on the public dataset with mDTA of (0.81±0.31) mm for the brainstem, 0.20±0.08) mm for the mandible, 0.77±0.14) mm for the left parotid and (0.81±0.28)m for the right parotid. Conclusions: Through careful tuning and customisation we trained a 3D CNN with a small dataset to produce segmentations of HN OARs with an accuracy that is comparable with inter-clinician deviations. Our proposed model performed competitively with current SOTA methods.Citation
Henderson EGA, Vasquez Osorio EM, van Herk M, Green AF. Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training data. Vol. 22, Physics and Imaging in Radiation Oncology. Elsevier BV; 2022. p. 44–50.Journal
Physics and Imaging in Radiation OncologyDOI
10.1016/j.phro.2022.04.003PubMed ID
35514528Additional Links
https://dx.doi.org/10.1016/j.phro.2022.04.003Type
ArticleLanguage
enae974a485f413a2113503eed53cd6c53
10.1016/j.phro.2022.04.003
Scopus Count
Collections
Related articles
- Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks.
- Authors: Tong N, Gou S, Yang S, Ruan D, Sheng K
- Issue date: 2018 Oct
- Shape constrained fully convolutional DenseNet with adversarial training for multiorgan segmentation on head and neck CT and low-field MR images.
- Authors: Tong N, Gou S, Yang S, Cao M, Sheng K
- Issue date: 2019 Jun
- Recurrent Convolutional Neural Networks for 3D Mandible Segmentation in Computed Tomography.
- Authors: Qiu B, Guo J, Kraeima J, Glas HH, Zhang W, Borra RJH, Witjes MJH, van Ooijen PMA
- Issue date: 2021 May 31
- Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks.
- Authors: Ibragimov B, Xing L
- Issue date: 2017 Feb
- Cascaded deep learning-based auto-segmentation for head and neck cancer patients: Organs at risk on T2-weighted magnetic resonance imaging.
- Authors: Korte JC, Hardcastle N, Ng SP, Clark B, Kron T, Jackson P
- Issue date: 2021 Dec