Workflow Phase Detection in Fluoroscopic Images Using Convolutional Neural Networks
In image guided interventions, the radiation dose to the patient and personnel can be reduced by positioning the blades of a collimator to block off unnecessary X-rays and restrict the irradiated area to a region of interest. In a certain stage of the operation workflow phase detection can define objects of interest to enable automatic collimation. Workflow phase detection can be beneficial for clinical time management or operating rooms of the future. In this work, we propose a learning-based approach for an automatic classification of three surgical workflow phases. Our data consists of 24 congenital cardiac interventions with a total of 2985 fluoroscopic 2D X-ray images. We compare two different convolutional neural network architectures and investigate their performance regarding each phase. Using a residual network, a class-wise averaged accuracy of 86:14% was achieved. The predictions of the trained models can then be used for context specific collimation.
Unable to display preview. Download preview PDF.
- 4.DiPietro R, Stauder R, Kayis E, et al. Automated surgical-phase recognition using rapidly-deployable sensors. Proc MICCAI Workshop M2CAI. 2015;.Google Scholar
- 5.Twinanda AP, Yengera G, Mutter D, et al. RSDNet: learning to predict remaining surgery duration from laparoscopic videos without manual annotations. arXiv:180203243. 2018;.
- 6.Alhrishy M, Toth D, Narayan SA, et al. A machine learning framework for context specific collimation and workflow phase detection. Comput Methods Biomech Biomed Engin. 2018;.Google Scholar
- 7.Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012; p. 1097–1105.Google Scholar
- 8.He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. Proc CVPR. 2016; p. 770–778.Google Scholar
- 9.He K, Zhang X, Ren S, et al. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. Proc ICCV. 2015; p. 1026–1034.Google Scholar