Determining Optimal Configurations for Deep Fully Connected Neural Networks to Improve Image Reconstruction in Proton Radiotherapy



Type of Work



Citation of Original Publication


This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.


Proton therapy is a unique form of radiotherapy that utilizes protons to treat cancer by irradiating cancerous tumors while avoiding unnecessary radiation exposure to surrounding healthy tissues. Real-time imaging of prompt gamma rays can be used as a tool to make this form of therapy more effective. The use of Compton cameras is one proposed method for the real-time imaging of prompt gamma rays that are emitted by the proton beams as they travel through a patient’s body. The non-zero time resolution of the Compton camera, during which all interactions are recorded as occurring simultaneously, causes the reconstructed images to be noisy and insufficiently detailed to evaluate the proton delivery for the patient. Deep Learning has been a promising method used to remove and correct the different problems existing within the Compton Camera’s data. Previous papers have demonstrated the effectiveness of using deep fully connected networks to correct improperly detected gamma interactions within the data. More thorough hyperparameter studies than in previous works show that using a combination of larger batch sizes, higher neurons per layer, and higher layer counts tend to produce better performing networks, which show promise in reducing the complexity of previous network architectures. We also experiment with recurrent neural networks to test the viability of this type of architecture and report initial results.