Smart Video Capsule Endoscopy: Raw Image-Based Localization for Enhanced GI Tract Investigation

TL;DR

This paper presents an energy-efficient, raw image-based AI approach for medical capsule endoscopy, enabling accurate organ classification with minimal energy consumption on resource-limited edge devices.

Contribution

It introduces a lightweight CNN model and raw Bayer image processing on a low-power hardware platform for improved GI tract investigation.

Findings

Achieved 93.06% accuracy on Bayer images.

Reduced energy consumption by 89.9% compared to traditional methods.

Implemented on a PULPissimo SoC with RISC-V core.

Abstract

For many real-world applications involving low-power sensor edge devices deep neural networks used for image classification might not be suitable. This is due to their typically large model size and require- ment of operations often exceeding the capabilities of such resource lim- ited devices. Furthermore, camera sensors usually capture images with a Bayer color filter applied, which are subsequently converted to RGB images that are commonly used for neural network training. However, on resource-constrained devices, such conversions demands their share of energy and optimally should be skipped if possible. This work ad- dresses the need for hardware-suitable AI targeting sensor edge devices by means of the Video Capsule Endoscopy, an important medical proce- dure for the investigation of the small intestine, which is strongly limited by its battery lifetime. Accurate organ classification is performed with a final accuracy of 93.06% evaluated directly on Bayer images involv- ing a CNN with only 63,000 parameters and time-series analysis in the form of Viterbi decoding. Finally, the process of capturing images with a camera and raw image processing is demonstrated with a customized PULPissimo System-on-Chip with a RISC-V core and an ultra-low power hardware accelerator providing an energy-efficient AI-based image clas- sification approach requiring just 5.31 {\mu}J per image. As a result, it is possible to save an average of 89.9% of energy before entering the small intestine compared to classic video capsules.