Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-Scale Structural-aware Exposure Correction for Endoscopic Imaging

Axel Garcia-Vega, Ricardo Espinosa, Luis Ramirez-Guzman, Thomas Bazin, Luis Falcon-Morales, Gilberto Ochoa-Ruiz, Dominique Lamarque, Christian Daul

TL;DR

This contribution presents an extension to the objective function of LMSPEC, a method originally introduced to enhance images from natural scenes, used here for the exposure correction in endoscopic imaging and the preservation of structural information.

Abstract

Endoscopy is the most widely used imaging technique for the diagnosis of cancerous lesions in hollow organs. However, endoscopic images are often affected by illumination artefacts: image parts may be over- or underexposed according to the light source pose and the tissue orientation. These artifacts have a strong negative impact on the performance of computer vision or AI-based diagnosis tools. Although endoscopic image enhancement methods are greatly required, little effort has been devoted to over- and under-exposition enhancement in real-time. This contribution presents an extension to the objective function of LMSPEC, a method originally introduced to enhance images from natural scenes. It is used here for the exposure correction in endoscopic imaging and the preservation of structural information. To the best of our knowledge, this contribution is the first one that addresses the enhancement of endoscopic images using deep learning (DL) methods. Tested on the Endo4IE dataset, the proposed implementation has yielded a significant improvement over LMSPEC reaching a SSIM increase of 4.40% and 4.21% for over- and underexposed images, respectively.

Multi-Scale Structural-aware Exposure Correction for Endoscopic Imaging

TL;DR

This contribution presents an extension to the objective function of LMSPEC, a method originally introduced to enhance images from natural scenes, used here for the exposure correction in endoscopic imaging and the preservation of structural information.

Abstract

Endoscopy is the most widely used imaging technique for the diagnosis of cancerous lesions in hollow organs. However, endoscopic images are often affected by illumination artefacts: image parts may be over- or underexposed according to the light source pose and the tissue orientation. These artifacts have a strong negative impact on the performance of computer vision or AI-based diagnosis tools. Although endoscopic image enhancement methods are greatly required, little effort has been devoted to over- and under-exposition enhancement in real-time. This contribution presents an extension to the objective function of LMSPEC, a method originally introduced to enhance images from natural scenes. It is used here for the exposure correction in endoscopic imaging and the preservation of structural information. To the best of our knowledge, this contribution is the first one that addresses the enhancement of endoscopic images using deep learning (DL) methods. Tested on the Endo4IE dataset, the proposed implementation has yielded a significant improvement over LMSPEC reaching a SSIM increase of 4.40% and 4.21% for over- and underexposed images, respectively.
Paper Structure (11 sections, 5 equations, 3 figures, 2 tables)

This paper contains 11 sections, 5 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. State of the Art
  3. Materials
  4. Dataset
  5. Metrics
  6. Proposed DL Method
  7. Experimental Setup and Model tuning
  8. Results and Discussion
  9. Quantitative Results
  10. Qualitative Results
  11. Conclusions and Future Work

Figures (3)

  • Figure 1: Strong illumination change example in almost consecutive frames of a colonoscopic image sequence. (a) This image was acquired in appropriate lighting conditions. (b) Few frames later, the image is overexposed in its lower left region and underexposed in the remaining frame part.
  • Figure 2: DL-mode. On the left: Laplacian pyramid decomposition over patches I' with exposure artefacts and Gaussian pyramid decomposition over ground truth patches T. On the right: $\pazocal{L}_{pyr}$ is computed with the up-sampled output from sub-networks 1,2 and 3, whereas $\pazocal{L}_{rec}$, $\pazocal{L}_{SSIM}$ and $\pazocal{L}_{adv}$ are computed with the final up-sampled output Y from the sub-network 4. In addition, when the discriminator network is enabled, it is simultaneously trained with the final output and its respective ground truth.
  • Figure 3: Visual assessment of the exposure correction and structure preservation. The structural enhancement is perceptible in the zoomed areas. The complete images include less artifacts.