1. Clinical utility of convolutional neural networks for treatment planning in radiotherapy for spinal metastases
- Author
-
Sebastiaan R.S. Arends, Mark H.F. Savenije, Wietse S.C. Eppinga, Joanne M. van der Velden, Cornelis A.T. van den Berg, and Joost J.C. Verhoeff
- Subjects
Spinal metastases ,Deep learning ,Artificial intelligence ,Auto-segmentation ,Medical physics. Medical radiology. Nuclear medicine ,R895-920 ,Neoplasms. Tumors. Oncology. Including cancer and carcinogens ,RC254-282 - Abstract
Background and purpose: Spine delineation is essential for high quality radiotherapy treatment planning of spinal metastases. However, manual delineation is time-consuming and prone to interobserver variability. Automatic spine delineation, especially using deep learning, has shown promising results in healthy subjects. We aimed to evaluate the clinical utility of deep learning-based vertebral body delineations for radiotherapy planning purposes. Materials and methods: A multi-scale convolutional neural network (CNN) was used for automatic segmentation and labeling. Two approaches were tested: the combined approach using one CNN for both segmentation and labeling, and the sequential approach using separate CNN’s for these tasks. Training and internal validation data included 580 vertebrae, external validation data included 202 vertebrae. For quantitative assessment, Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used. Axial slices from external images were presented to radiation oncologists for subjective evaluation. Results: Both approaches performed comparably during the internal validation (DSC: 96.7%, HD: 3.6 mm), but the sequential approach proved more robust during the external validation (DSC: 94.5% vs 94.4%, p
- Published
- 2022
- Full Text
- View/download PDF