# eNCApsulate: NCA for Precision Diagnosis on Capsule Endoscopes

arXiv: https://arxiv.org/abs/2504.21562 · HTML: https://mlsanity.com/paper/2504.21562/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Builds on (most cited first, 8 of 8)

- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Med-NCA: Robust and Lightweight Segmentation with Neural Cellular Automata](https://mlsanity.com/paper/2302.03473/) (2023)
- [VR-Caps: A Virtual Environment for Capsule Endoscopy](https://mlsanity.com/paper/2008.12949/) (2020)
- [M3D-NCA: Robust 3D Segmentation with Built-in Quality Control](https://mlsanity.com/paper/2309.02954/) (2023)
- [Depth Anything in Medical Images: A Comparative Study](https://mlsanity.com/paper/2401.16600/) (2024)
- [Unsupervised Training of Neural Cellular Automata on Edge Devices](https://mlsanity.com/paper/2407.18114/) (2024)
- [Advancing Depth Anything Model for Unsupervised Monocular Depth Estimation in Endoscopy](https://mlsanity.com/paper/2409.07723/) (2024)
- [From Labels to Priors in Capsule Endoscopy: A Prior Guided Approach for Improving Generalization with Few Labels](https://mlsanity.com/paper/2206.05288/) (2022)

## Abstract (arXiv)

Wireless Capsule Endoscopy is a non-invasive imaging method for the entire gastrointestinal tract, and is a pain-free alternative to traditional endoscopy. It generates extensive video data that requires significant review time, and localizing the capsule after ingestion is a challenge. Techniques like bleeding detection and depth estimation can help with localization of pathologies, but deep learning models are typically too large to run directly on the capsule. Neural Cellular Automata (NCA) for bleeding segmentation and depth estimation are trained on capsule endoscopic images. For monocular depth estimation, we distill a large foundation model into the lean NCA architecture, by treating the outputs of the foundation model as pseudo ground truth. We then port the trained NCA to the ESP32 microcontroller, enabling efficient image processing on hardware as small as a camera capsule. NCA are more accurate (Dice) than other portable segmentation models, while requiring more than 100x fewer parameters stored in memory than other small-scale models. The visual results of NCA depth estimation look convincing, and in some cases beat the realism and detail of the pseudo ground truth. Runtime optimizations on the ESP32-S3 accelerate the average inference speed significantly, by more than factor 3. With several algorithmic adjustments and distillation, it is possible to eNCApsulate NCA models into microcontrollers that fit into wireless capsule endoscopes. This is the first work that enables reliable bleeding segmentation and depth estimation on a miniaturized device, paving the way for precise diagnosis combined with visual odometry as a means of precise localization of the capsule -- on the capsule.