Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Prediction

Ivan Reyes-Amezcua, Ricardo Espinosa, Christian Daul, Gilberto Ochoa-Ruiz, Andres Mendez-Vazquez

TL;DR

The EndoDepth benchmark is presented, an evaluation framework designed to assess the robustness of monocular depth prediction models in endoscopic scenarios and a novel composite metric called the mean Depth Estimation Robustness Score (mDERS) is presented, which offers an in-depth evaluation of a model's accuracy against errors brought on by endoscopic image corruptions.

Abstract

Accurate depth estimation in endoscopy is vital for successfully implementing computer vision pipelines for various medical procedures and CAD tools. In this paper, we present the EndoDepth benchmark, an evaluation framework designed to assess the robustness of monocular depth prediction models in endoscopic scenarios. Unlike traditional datasets, the EndoDepth benchmark incorporates common challenges encountered during endoscopic procedures. We present an evaluation approach that is consistent and specifically designed to evaluate the robustness performance of the model in endoscopic scenarios. Among these is a novel composite metric called the mean Depth Estimation Robustness Score (mDERS), which offers an in-depth evaluation of a model's accuracy against errors brought on by endoscopic image corruptions. Moreover, we present SCARED-C, a new dataset designed specifically to assess endoscopy robustness. Through extensive experimentation, we evaluate state-of-the-art depth prediction architectures on the EndoDepth benchmark, revealing their strengths and weaknesses in handling endoscopic challenging imaging artifacts. Our results demonstrate the importance of specialized techniques for accurate depth estimation in endoscopy and provide valuable insights for future research directions.

EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Prediction

TL;DR

The EndoDepth benchmark is presented, an evaluation framework designed to assess the robustness of monocular depth prediction models in endoscopic scenarios and a novel composite metric called the mean Depth Estimation Robustness Score (mDERS) is presented, which offers an in-depth evaluation of a model's accuracy against errors brought on by endoscopic image corruptions.

Abstract

Accurate depth estimation in endoscopy is vital for successfully implementing computer vision pipelines for various medical procedures and CAD tools. In this paper, we present the EndoDepth benchmark, an evaluation framework designed to assess the robustness of monocular depth prediction models in endoscopic scenarios. Unlike traditional datasets, the EndoDepth benchmark incorporates common challenges encountered during endoscopic procedures. We present an evaluation approach that is consistent and specifically designed to evaluate the robustness performance of the model in endoscopic scenarios. Among these is a novel composite metric called the mean Depth Estimation Robustness Score (mDERS), which offers an in-depth evaluation of a model's accuracy against errors brought on by endoscopic image corruptions. Moreover, we present SCARED-C, a new dataset designed specifically to assess endoscopy robustness. Through extensive experimentation, we evaluate state-of-the-art depth prediction architectures on the EndoDepth benchmark, revealing their strengths and weaknesses in handling endoscopic challenging imaging artifacts. Our results demonstrate the importance of specialized techniques for accurate depth estimation in endoscopy and provide valuable insights for future research directions.
Paper Structure (11 sections, 2 equations, 3 figures, 2 tables)

This paper contains 11 sections, 2 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. The EndoDepth Benchmark Design
  4. Mean Depth Estimation Robustness Score (mDERS)
  5. Mean Corruption Error for Endoscopy Depth Estimation
  6. Methods and Data
  7. Data
  8. The EndoDepth Benchmark Corruptions
  9. Evaluation of Robustness in Monocular Depth Prediction
  10. Experiments and Evaluation
  11. Conclusion

Figures (3)

  • Figure 1: Example of the EndoDepth Corruptions on an image from the SCARED-C dataset. In the last row are image corruptions that significantly affect the performance of monocular depth estimation in endoscopic imaging, including lens distortion, resolution alterations, specular reflection, and color changes.
  • Figure 2: Boxplot for the absolute relative error of four depth estimation models: Monodepth2 (blue), AF-SfMLearner (orange), MonoViT (green), and EndoSfMLearner (red), under various image corruption types: Lens Distortion (LD), Resolution Change (RC), Specular Reflection (SR), and Color Changes (CC).
  • Figure 3: Visual comparison of depth estimation outputs from multiple models. The first column shows the endoscopic images using the endoscopy corruptions at a severity of 2 using our method, followed by ground truth image and the depth predictions from the Monodepth2, AF-SfMLearner, MonoViT, and EndoSfMLearner models, respectively. The corruptions used are: Lens Distortion (LD), Resolution Change (RC), Specular Reflection (SR), and Color Changes (CC).