Segmentation of retinal vessels in fundus images based on U-Net with self-calibrated convolutions and spatial attention modules
Authors:
- 10 March 2023
- journal article
- research article
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 61 (7) , 1745-1755
Abstract
Automated and accurate segmentation of retinal vessels in fundus images is an important step for screening and diagnosing various ophthalmologic diseases. However, many factors, including the variations of vessels in color, shape and size, make this task become an intricate challenge. One kind of the most popular methods for vessel segmentation is U-Net based methods. However, in the U-Net based methods, the size of the convolution kernels is generally fixed. As a result, the receptive field for an individual convolution operation is single, which is not conducive to the segmentation of retinal vessels with various thicknesses. To overcome this problem, in this paper, we employed self-calibrated convolutions to replace the traditional convolutions for the U-Net, which can make the U-Net learn discriminative representations from different receptive fields. Besides, we proposed an improved spatial attention module, instead of using traditional convolutions, to connect the encoding part and decoding part of the U-Net, which can improve the ability of the U-Net to detect thin vessels. The proposed method has been tested on Digital Retinal Images for Vessel Extraction (DRIVE) database and Child Heart and Health Study in England Database (CHASE DB1). The metrics used to evaluate the performance of the proposed method are accuracy (ACC), sensitivity (SE), specificity (SP), F1-score (F1) and the area under the receiver operating characteristic curve (AUC). The ACC, SE, SP, F1 and AUC obtained by the proposed method are 0.9680, 0.8036, 0.9840, 0.8138 and 0.9840 respectively on DRIVE database, and 0.9756, 0.8118, 0.9867, 0.8068 and 0.9888 respectively on CHASE DB1, which are better than those obtained by the traditional U-Net (the ACC, SE, SP, F1 and AUC obtained by U-Net are 0.9646, 0.7895, 0.9814, 0.7963 and 0.9791 respectively on DRIVE database, and 0.9733, 0.7817, 0.9862, 0.7870 and 0.9810 respectively on CHASE DB1). The experimental results indicate that the proposed modifications in the U-Net are effective for vessel segmentation. The structure of the proposed networkKeywords
Funding Information
- Science and Technology Planning Project of Guangdong Province (180917144960530)
- Project of Educational Commission of Guangdong Province of China (2017KZDXM032)
- Science Research Startup Foundation of Shantou University (NTF20021)
- State Key Lab of Digital Manufacturing Equipment and Technology (DMETKF2019020)
- robot automatic design platform combining multi-objective evolutionary computation and deep neural network (2019A050519008)
- Guangdong Natural Science Foundation (2022A1515011396)
- National Key R&D Program of China (2021ZD0111502)
This publication has 31 references indexed in Scilit:
- Deep learningNature, 2015
- Automated Vessel Segmentation Using Infinite Perimeter Active Contour Model with Hybrid Region Information with Application to Retinal ImagesIEEE Transactions on Medical Imaging, 2015
- Trainable COSFIRE filters for vessel delineation with application to retinal imagesMedical Image Analysis, 2015
- Blood vessel segmentation methodologies in retinal images – A surveyComputer Methods and Programs in Biomedicine, 2012
- AdaBoost with SVM-based component classifiersEngineering Applications of Artificial Intelligence, 2008
- Segmentation of retinal blood vessels using a novel clustering algorithm (RACAL) with a partial supervision strategyMedical & Biological Engineering & Computing, 2007
- Ridge-Based Vessel Segmentation in Color Images of the RetinaIEEE Transactions on Medical Imaging, 2004
- A gabor filter-based method for recognizing handwritten numeralsPattern Recognition, 1998
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Recursive tracking of vascular networks in angiograms based on the detection-deletion schemeIEEE Transactions on Medical Imaging, 1993