Capsule motion prediction reduces energy use in ingestible cameras
CapsuleMotion: A Lightweight Real-Time Visual Motion Predictor for Capsule Endoscopy
Computer Vision and Pattern Recognition
Summary
Swallowed capsule cameras can look inside the small intestine but have limited battery life. The authors designed CapsuleMotion to predict how much the capsule moves between pictures, letting it adjust the frame rate and save energy. Before reaching the small intestine, the capsule also uses a low power mode to figure out its location when movement is detected. This approach cuts energy use by up to 20% and improves detecting when the capsule enters the small intestine.
What this means in practice
- •For medical device engineers: Optimize battery life and image capture rate in capsule endoscopes to enable longer and more complete GI tract screenings.
- •For wearable medical device designers: Apply dynamic frame rate adjustment based on predicted motion to improve energy use in other ingestible or wearable imaging devices.
Authors
Oliver Bause, Julia Werner, Oliver Bringmann
Abstract
Video Capsule Endoscopy (VCE) is a non-invasive medical examination that allows for the observation of the small intestine, which is otherwise difficult to access. A fundamental challenge persists in the form of their limited size in order to still be swallowable. The resulting restricted battery capacity, however, contradicts with the power-intensive nature of image capture and transmission. Therefore, we propose CapsuleMotion, a patient-specific dynamic capsule behavior that utilizes the available energy in a goal-oriented manner to increase the likelihood of a complete screening of the gastrointestinal tract. By investigating and combining metrics from the on-device image compression, CapsuleMotion predicts the motion between two successive frames. The camera's frame rate will be modified in accordance with the predicted magnitude of motion. Furthermore, prior to entering the small intestine, the capsule operates in a low power mode with a significantly reduced frame rate. In this mode, the LocalizationNet is employed to determine the current organ, provided that motion was predicted. The proposed framework is evaluated on the Rhode Island VCE dataset and deployed on an ultra-low power single-core RISC-V demonstrator with an integrated hardware accelerator. CapsuleMotion demonstrated the capability to reduce electric energy consumption by up to 20.66% in comparison with conventional capsules that lack a dynamic frame rate. Additionally, the accuracy of detecting the entry point of the small intestine has been improved.