all AI news
Prediction of the Position of External Markers Using a Recurrent Neural Network Trained With Unbiased Online Recurrent Optimization for Safe Lung Cancer Radiotherapy. (arXiv:2106.01100v6 [eess.IV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
During lung radiotherapy, the position of infrared reflective objects on the
chest can be recorded to estimate the tumor location. However, radiotherapy
systems have a latency inherent to robot control limitations that impedes the
radiation delivery precision. Prediction with online learning of recurrent
neural networks (RNN) allows for adaptation to non-stationary respiratory
signals, but classical methods such as RTRL and truncated BPTT are respectively
slow and biased. This study investigates the capabilities of unbiased online
recurrent optimization (UORO) to forecast …
arxiv cancer lung cancer network neural network optimization prediction recurrent neural network unbiased