Technical Note: Deep Learning approach for automatic detection and identification of patient positioning devices for radiation therapy.
computer vision
incident learning
machine learning
setup devices
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Oct 2020
Oct 2020
Historique:
received:
14
11
2019
revised:
05
06
2020
accepted:
05
06
2020
pubmed:
21
6
2020
medline:
15
5
2021
entrez:
21
6
2020
Statut:
ppublish
Résumé
Automatic detection and identification of setup devices, using a deep convolutional neural network (CNN) for real-time multiclass object detection, has the potential to reduce errors in the treatment delivery process by avoiding documentation errors. A database of the setup device photos from the most recent 1200 patients treated at our institution was downloaded from the record and verify (R&V) system along with the corresponding setup notes. Images were manually labeled with bounding boxes of each device. A real-time object detection CNN using the "you only look once" (YOLOv2) architecture was trained using transfer learning of a pretrained CNN (ResNet50). The CNN was trained to detect and identify 11 of the most common treatment accessories used at our institution. Using transfer learning of a CNN for multiclass object detection, we are able to automatically detect and identify setup devices in photographs with an accuracy of 96%. Automation in radiation oncology has the potential to reduce risk. Automatic detection of setup devices is possible using a CNN and transfer learning. This work shows both the value of incident learning systems (ILS) in practice knowledge dissemination, and shows how automation of clinical processes and less reliance on manual documentation has the potential for risk reduction in radiation oncology treatments.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
5061-5069Informations de copyright
© 2020 American Association of Physicists in Medicine.
Références
Amaloo C, Hayes L, Manning M, Liu H, Wiant D. Can automated treatment plans gain traction in the clinic? J Appl Clin Med Phys. 2019;20:29-35.
Covington EL, Chen X, Younge KC, et al. Improving treatment plan evaluation with automation. J Appl Clin Med Phys. 2016;17:16-31.
Galvin JM, Ezzell G, Eisbrauch A, et al. Implementing IMRT in clinical practice: a joint document of the American Society for Therapeutic Radiology and Oncology and the American Association of Physicists in Medicine. Int J Radiat Oncol Biol Phys. 2004;58:1616-1634.
Hadley SW, Kessler ML, Litzenberg DW, et al. SafetyNet: streamlining and automating QA in radiotherapy. J Appl Clin Med Phys. 2016;17:387-395.
Hayman JA. Measuring the quality of care in radiation oncology. Semin Radiat Oncol. 2008;18:201-206.
Margalit DN, Chen YH, Catalano PJ, et al. Technological advancements and error rates in radiation therapy delivery. Int J Radiat Oncol Biol Phys. 2011;81:e673-e679.
Ezzell G, Chera B, Dicker A, et al. Common error pathways seen in the RO-ILS data that demonstrate opportunities for improving treatment safety. Pract Radiat Oncol. 2018;8:123-132.
Klein EE, Drzymala RE, Purdy JA, Michalski J. Errors in radiation oncology: a study in pathways and dosimetric impact. J Appl Clin Med Phys. 2005;6:81-94.
ASTRO. Safety is No Accident: A FRAMEWORK FOR QUALITY RADIATION ONCOLOGY CARE. In. Vol 2019. www.astro.org: American Society for Radiation Oncology, Fairfax, VA; 2019; 2019.
Zhao H, Huang Y, Sarkar V, et al. Radiation therapy treatment deviations potentially prevented by a novel combined radio-frequency identification (RFID), biometric and surface matching technology: WE-RAM1-GePD-J (B)-02. Med Phys. 2017;44:2041-2044.
Schubert L, Petit J, Vinogradskiy Y, et al. Implementation and operation of incident learning across a newly-created health system. J Appl Clin Med Phys. 2018;19:298-305.
Talukdar J, Gupta S, Rajpura PS, Hegde RS. Transfer Learning for Object Detection using State-of-the-Art Deep Neural Networks. Paper presented at: 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN); 22-23 Feb. 2018; 2018.
He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. arXiv e-prints; 2015. https://ui.adsabs.harvard.edu/abs/2015arXiv151203385H.Accessed December 01, 2015.
Redmon J, Farhadi A. YOLO9000: Better, Faster, Stronger. arXiv e-prints; 2016. https://ui.adsabs.harvard.edu/abs/2016arXiv161208242R.Accessed December 01, 2016.
Abadi M, Agarwal A, Barham P, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems; 2015.
Ting KM. Confusion matrix. In: Sammut C, Webb GI, eds. Encyclopedia of Machine Learning. Boston, MA: Springer, US; 2010:209-209.
Ford E, Conroy L, Dong L, et al. Strategies for effective physics plan and chart review in radiation therapy: report of AAPM Task Group 275. Med Phys. 2020;47:e236-e272.
Reed S, Lee H, Anguelov D, Szegedy C, Erhan D, Rabinovich A. Training Deep Neural Networks on Noisy Labels with Bootstrapping. arXiv e-prints. 2014. https://ui.adsabs.harvard.edu/abs/2014arXiv1412.6596R.Accessed December 01, 2014.
Han B, Yao Q, Yu X, et al. Co-teaching: Robust training of deep neural networks with extremely noisy labels; 2018:8527-8537.