Deep Reinforcement Learning for Organ Localization in CT

TL;DR

This paper introduces a deep reinforcement learning method that enables an artificial agent to accurately localize organs in CT scans, reducing the need for extensive annotated data and improving efficiency in medical imaging tasks.

Contribution

It presents a novel reinforcement learning approach with tailored actions for organ localization in CT, adaptable as a plug-and-play module for any organ of interest.

Findings

Achieved an intersection over union of 0.63 on the VISCERAL dataset.

Median wall distance of 2.25 mm indicates precise localization.

Median centroid distance of 3.65 mm demonstrates accuracy in organ positioning.

Abstract

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.