Reinforced learning from serial CT to improve the early diagnosis of lung cancer in screening

We developed a radiomic-based reinforcement learning (R-RL) model for the early diagnosis of lung cancer. We formulated the classification of malignant and benign lung nodules with multiple years of screening as a Markov decision process. The reinforcement learning method learned a policy mapping from the set of states (patients' clinical conditions) of the environment (patients) to the set of possible actions (decisions). The customary mapping between the two sets was based on a value function with the expected reward designed to be associated with lung cancer risk which was increased when the patient was diagnosed with lung cancer and vice versa in the Markov chains. The trained model can be deployed to a single baseline CT scan for early diagnosis of malignant nodules. 215 NLST cases including 108 positive and 107 negative cases with 431 LDCT scans collected from 3 years of screening were used as the training set and another 70 cases with 35 positive and 35 negative cases were used as the independent test set. For each screen-detected nodule in a CT exam, forty-three texture features were extracted and used as the state in reinforcement learning. An offline model-free value iteration method was used to build the R-RL model. Our R-RL model trained with 3 years of serial CT exams achieved an AUC of 0.824 +/- 0.003 when deployed to the first year CT exams of the test set. In comparison, the R-RL model trained with only the first year CT scans achieved a significantly (P<0.05) lower test AUC of 0.736 +/- 0.004. Our study demonstrated that the R-RL model built with serial CT scans has the potential to improve early diagnosis of indeterminate lung nodules in screening programs, thus reducing follow-up exams or unnecessary biopsy and the associated costs.

Automated summary

A radiomic-based reinforcement learning model was developed for early diagnosis of lung cancer, utilizing a Markov decision process to classify lung nodules as malignant or benign. The model learned a policy mapping between patients' clinical conditions and decisions based on expected rewards associated with lung cancer risk. This model, trained with multi-year CT scans, showed potential to improve early diagnosis of lung nodules, reducing unnecessary follow-up exams and costs.