Related Experiment Video
Updated: Jul 11, 2025
10:14
Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration
Published on: May 26, 2023
3.2K
OIMHS: An Optical Coherence Tomography Image Dataset Based on Macular Hole Manual Segmentation
Xin Ye1, Shucheng He1, Xiaxing Zhong2
1Center for Rehabilitation Medicine, Department of Ophthalmology, Zhejiang Provincial People's Hospital (Affiliated People's Hospital, Hangzhou Medical College), Hangzhou, Zhejiang, China.
Scientific Data
|November 6, 2023
Summary
A new dataset of Optical Coherence Tomography (OCT) images aids in segmenting macular holes, improving diagnosis for this common macular disease. This resource supports research into retinal diseases and lesion quantification.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Vision
Background:
- Macular holes are common macular diseases requiring prompt treatment.
- Optical Coherence Tomography (OCT) enables direct observation of macular hole morphology.
- Accurate segmentation of OCT images is crucial for identifying and quantifying macular hole lesions.
Purpose of the Study:
- To address the lack of high-quality datasets for macular hole segmentation in OCT images.
- To establish a comprehensive dataset for training and evaluating segmentation algorithms.
- To facilitate research into macular diseases through quantitative analysis of retinal structures.
Main Methods:
- Creation of the OCT Image Macular Hole Segmentation (OIMHS) dataset.
- Inclusion of 3859 B-scan OCT images from 119 patients.
- Annotation of images with four segmentation labels: retina, macular hole, intraretinal cysts, and choroid.
Main Results:
- The OIMHS dataset provides a large-scale, high-quality resource for macular hole segmentation research.
- The dataset enables investigation into the accuracy and reliability of various segmentation algorithms.
- Facilitates quantitative analysis of the retina, lesions, and choroid in macular diseases.
Conclusions:
- The established OIMHS dataset is a valuable resource for advancing macular hole segmentation techniques.
- This dataset will drive further development in clinical research for macular diseases.
- Supports improved diagnostic and quantitative analysis capabilities for ophthalmologists.
