Deep Reinforcement Learning for Organ Localization in CT
This addresses the need for robust organ localization in medical imaging for tasks like radiotherapy planning, offering a plug-and-play method that reduces annotation requirements compared to existing solutions.
The paper tackles the problem of organ localization in CT scans by proposing a deep reinforcement learning approach, achieving an overall intersection over union of 0.63, a median wall distance of 2.25 mm, and a median centroid distance of 3.65 mm on the VISCERAL dataset.
Robust localization of organs in computed tomography scans is a constant pre-processing requirement for organ-specific image retrieval, radiotherapy planning, and interventional image analysis. In contrast to current solutions based on exhaustive search or region proposals, which require large amounts of annotated data, we propose a deep reinforcement learning approach for organ localization in CT. In this work, an artificial agent is actively self-taught to localize organs in CT by learning from its asserts and mistakes. Within the context of reinforcement learning, we propose a novel set of actions tailored for organ localization in CT. Our method can use as a plug-and-play module for localizing any organ of interest. We evaluate the proposed solution on the public VISCERAL dataset containing CT scans with varying fields of view and multiple organs. We achieved an overall intersection over union of 0.63, an absolute median wall distance of 2.25 mm, and a median distance between centroids of 3.65 mm.