Multi-Scale Pathological Fluid Segmentation in OCT With a Novel Curvature Loss in Convolutional Neural Network
- 11 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 41 (6) , 1547-1559
Abstract
The segmentation of pathological fluid lesions in optical coherence tomography (OCT), including intraretinal fluid, subretinal fluid, and pigment epithelial detachment, is of great importance for the diagnosis and treatment of various eye diseases such as neovascular age-related macular degeneration and diabetic macular edema. Although significant progress has been achieved with the rapid development of fully convolutional neural networks (FCN) in recent years, some important issues remain unsolved. First, pathological fluid lesions in OCT show large variations in location, size, and shape, imposing challenges on the design of FCN architecture. Second, fluid lesions should be continuous regions without holes inside. But the current architectures lack the capability to preserve the shape prior information. In this study, we introduce an FCN architecture for the simultaneous segmentation of three types of pathological fluid lesions in OCT. First, attention gate and spatial pyramid pooling modules are employed to improve the ability of the network to extract multi-scale objects. Then, we introduce a novel curvature regularization term in the loss function to incorporate shape prior information. The proposed method was extensively evaluated on public and clinical datasets with significantly improved performance compared with the state-of-the-art methods.Keywords
Funding Information
- Shaanxi National Science Foundation (2020JQ-071 2021KW-50)
- Open Research Fund of the Jiangsu Key Laboratory for Design and Manufacture of Micro-Nano Biomedical Instruments (KF202005)
This publication has 37 references indexed in Scilit:
- Three-dimensional continuous max flow optimization-based serous retinal detachment segmentation in SD-OCT for central serous chorioretinopathyBiomedical Optics Express, 2017
- Fully-Automated Segmentation of Fluid/Cyst Regions in Optical Coherence Tomography Images with Diabetic Macular Edema using Neutrosophic Sets and Graph AlgorithmsIEEE Transactions on Biomedical Engineering, 2017
- ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networksBiomedical Optics Express, 2017
- Automated framework for intraretinal cystoid macular edema segmentation in three-dimensional optical coherence tomography images with macular holeJournal of Biomedical Optics, 2017
- Automatic Subretinal Fluid Segmentation of Retinal SD-OCT Images With Neurosensory Retinal Detachment Guided by Enface Fundus ImagingIEEE Transactions on Biomedical Engineering, 2017
- Curvature Filters Efficiently Reduce Certain Variational EnergiesIEEE Transactions on Image Processing, 2017
- Label propagation and higher-order constraint-based segmentation of fluid-associated regions in retinal SD-OCT imagesInformation Sciences, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Kernel regression based segmentation of optical coherence tomography images with diabetic macular edemaBiomedical Optics Express, 2015
- Stratified Sampling Voxel Classification for Segmentation of Intraretinal and Subretinal Fluid in Longitudinal Clinical OCT DataIEEE Transactions on Medical Imaging, 2015