Deep Reinforcement Learning for Detecting Breast Lesions from DCE-MRI

We present a detection model that is capable of accelerating the inference time of lesion detection from breast dynamically contrast-enhanced magnetic resonance images (DCE-MRI) at state-of-the-art accuracy. In contrast to previous methods based on computationally expensive exhaustive search strategies, our method reduces the inference time with a search approach that gradually focuses on lesions by progressively transforming a bounding volume until the lesion is detected. Such detection model is trained with reinforcement learningReinforcement learning and is modeled by a deep Q-network (DQN) that iteratively outputs the next transformation to the current bounding volume. We evaluate our proposed approach in a breast MRIMagnetic Resonance Imaging (MRI) data set containing the T1-weighted and the first DCE-MRI subtraction volume from 117 patients and a total of 142 lesions. Results show that our proposed reinforcement learningReinforcement learning based detection model reaches a true positive rate (TPR) of 0.8 at around three false positive detections and a speedup of at least 1.78 times compared to baselines methods.