Deep retinal image non-uniform illumination removal

Chongyi LI*, Huazhu FU, Miao YANG, Runmin CONG, Chunle GUO

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsBook ChapterResearchpeer-review

Abstract

Retinal images have been widely used by clinicians for early diagnosis of ocular diseases. However, the quality of retinal images is often clinically unsatisfactory due to eye lesions and imperfect imaging processes. The non-uniform or poor illumination on retinal images hinders the pathological information and further impairs the diagnosis of ophthalmologists. To solve these issues, we propose a deep learning-based retinal image nonuniform illumination removal called NuI-Go, which combines the powerful capabilities of convolutional neural networks (CNNs) with the characteristics of retinal images with non-uniform illumination. Concretely, the proposed NuI-Go consists of three Recursive non-local encoder-decoder residual blocks (NEDRBs) for progressively enhancing the degraded retinal images. Each NEDRB contains a feature encoder module that captures the hierarchical feature representations, a non-local context module that models the context information, and a feature decoder module that recovers the details and spatial dimension. Extensive experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods on both synthetic dataset and real retinal images. Besides, we further demonstrate the advantages of the proposed method for improving the performance of retinal vessel segmentation.

Original languageEnglish
Title of host publicationGeneralization With Deep Learning : For Improvement On Sensing Capability
EditorsZhenghua CHEN, Min WU, Xiaoli LI
Place of PublicationSingapore
PublisherWorld Scientific Publishing Co. Pte Ltd
Chapter10
Pages235-257
Number of pages23
ISBN (Electronic)9789811218842
ISBN (Print)9789811218835
DOIs
Publication statusPublished - Apr 2021
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2021 World Scientific Publishing Company.

Keywords

  • Deep learning
  • Image enhancement
  • Non-uniform illumination
  • Quality degradation
  • Retinal image
  • Vessel segmentation

Fingerprint

Dive into the research topics of 'Deep retinal image non-uniform illumination removal'. Together they form a unique fingerprint.

Cite this