Deep neural networks for neuro-oncology: Towards patient individualized design of chemo-radiation therapy for Glioblastoma patients.

BACKGROUND AND OBJECTIVES: Glioblastoma multiforme (GBM) is the most common and deadly type of primary cancers of the brain and central nervous system in adults. Despite the importance of designing a personalized treatment regimen for the patient, clinical trials prescribe a set of conventional regimens for GBM patients. We propose a computerized framework for designing chemo-radiation therapy (CRT) regimen based on patient characteristics. METHODS: An intelligent agent, based on deep reinforcement learning, interacts with a virtual personalized GBM. The proposed deep Q network (DQN) uses a deep neural network to estimate the state - action value function. The algorithm stores agent experiences in a replay memory to be used for training of the deep neural network. Also, the proliferation-invasion model is used to simulate spatiotemporal dynamics of GBM growth and its response to therapeutic agents. RESULTS: Assuming tumor size at the end of the treatment course as a measure of the quality of the treatment regimen, experiments show that the proposed DQN is superior to the Q learning. Also, while the quality of the protocols obtained by the Q learning as well as its convergence speed decreases sharply with the increase in the dimensions of the state-action value function, the DQN is relatively robust against increasing the initial tumor size or lengthening the treatment period. CONCLUSION: Our results suggest that the optimal personalized treatment regimen may differ from the conventional regimens suggested by clinical trials. Given the scalability of the proposed DQN in designing treatment regimen for real size tumors, as well as its superiority over previous models, it is a suitable tool for designing personalized CRT regimen for GBM patients.

A neuro evolutionary algorithm for patient calibrated prediction of survival in Glioblastoma patients.

BACKGROUND AND OBJECTIVES: Glioblastoma multiforme (GBM) is the most common and malignant type of primary brain tumors. Radiation therapy (RT) plus concomitant and adjuvant Temozolomide (TMZ) constitute standard treatment of GBM. Existing models for GBM growth do not consider the effect of different schedules on tumor growth and patient survival. However, clinical trials show that treatment schedule and drug dosage significantly affect patient survival. The goal is to provide a patient calibrated model for predicting survival according to the treatment schedule. METHODS: We propose a top-down method based on artificial neural networks (ANN) and genetic algorithm (GA) to predict survival of GBM patients. A feed forward undercomplete Autoencoder network is integrated with the neuro-evolutionary (NE) algorithm in order to extract a compressed representation of input clinical data. The proposed NE algorithm uses GA to obtain optimal architecture of a multi-layer perceptron (MLP). Taguchi L16 orthogonal design of experiments is used to tune parameters of the proposed NE algorithm. Finally, the optimal MLP is used to predict survival of GBM patients. RESULTS: Data from 8 related clinical trials have been collected and integrated to train the model. From 847 evaluable cases, 719 were used for train and validation and the remaining 128 cases were used to test the model. Mean absolute error of the predictions on the test data is 0.087 months which shows excellent performance of the proposed model in predicting survival of the patients. Also, the results show that the proposed NE algorithm is superior to other existing models in both the mean and variability of the prediction error.

Reinforcement learning for optimal scheduling of Glioblastoma treatment with Temozolomide.

BACKGROUND: Glioblastoma multiforme (GBM) is the most frequent primary brain tumor in adults and Temozolomide (TMZ) is an effective chemotherapeutic agent for its treatment. In Silico models of GBM growth provide an appropriate foundation for analysis and comparison of different regimens. We propose a mathematical frame for patient specific design of optimal chemotherapy regimens for GBM patients. METHODS: The proposed frame includes online interaction of a virtual GBM with an optimizing agent. Spatiotemporal dynamics of GBM growth and its response to TMZ are simulated with a three dimensional hybrid cellular automaton. Q learning is tailored to the virtual GBM for treatment optimization aimed at minimizing tumor size at the end of treatment course. Q learning consists of a learning agent that interacts with the virtual GBM. System state is affected by the agent decisions and the obtained rewards guide Q learning to the optimal schedule. RESULTS: Computational results confirm that the optimal chemotherapy schedule depends on some patient specific parameters including body weight, tumor size and its position in the brain. Furthermore, the algorithm is used for scheduling 2100 mg of TMZ on a virtual GBM and the obtained schedule is to administer150 mg of TMZ every other day. The obtained schedule is compared to the standard 7/14 regimen and the results show that it is superior to the 7/14 regimen in minimizing tumor size. CONCLUSION: The proposed frame is an appropriate decision support system for patient specific design of TMZ administration regimens on GBM patients. Also, since the obtained optimal schedule outperforms the standard 7/14 regimen, it is worthy of further clinical testing.