Technical Note: Dose prediction for radiation therapy using feature‐based losses and One Cycle Learning. Issue 9 (22nd June 2021)

• Record Type: Journal Article
• Authors: Zimmermann, Lukas; Faustmann, Erik; Ramsl, Christian; Georg, Dietmar; Heilemann, Gerd
• Is Part Of: Medical physics. Volume 48:Issue 9(2021)
• Page Start: 5562
• Page End: 5566
• Publication Date: 2021-06-22
• Subjects: deep learning -- dose prediction -- radiation therapy; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1002/mp.14774
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: To present the technical details of the runner‐up model in the open knowledge‐based planning (OpenKBP) challenge for the dose–volume histogram (DVH) stream. The model was designed to ensure simple and reproducible training, without the necessity of costly advanced generative adversarial network (GAN) techniques. Methods: The model was developed based on the OpenKBP challenge dataset, consisting of 200 and 40 head‐and‐neck patients for training and validation, respectively. The final model is a U‐Net with additional ResNet blocks between up‐ and down convolutions. The results were obtained by training the model with AdamW with the One Cycle scheduler. The loss function is a combination of the L1 loss with a feature loss, which uses a pretrained video classifier as a feature extractor. The performance was evaluated on another 100 patients in the OpenKBP test dataset. The DVH metrics of the test data were evaluated, where D 0.1 c c, and D mean were calculated for the organs at risk (OARs) and D 1 %, D 95 %, and D 99 % were computed for the target structures. DVH metric differences between predicted and true dose are reported in percentage. Results: The model achieved 2nd and 4th place in the DVH and dose stream of the OpenKBP challenge, respectively. The dose and DVH score were 2.62 ± 1.10 and 1.52 ± 1.06, respectively. Mean dose differences for the different structures and DVH parameters were within ±1%. Conclusion: This straightforward approach produced excellent results. It incorporated One Cycle Learning, ResNet, and feature‐based losses, which are common computer vision techniques.