M2U-Net: Effective and Efficient Retinal Vessel Segmentation for Real-World Applications
- 1 June 2019
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 115-124
- https://doi.org/10.1109/cvprw.2019.00020
Abstract
In this paper, we present a novel neural network architecture for retinal vessel segmentation that improves over the state of the art on two benchmark datasets, is the first to run in real time on high resolution images, and its small memory and processing requirements make it deployable in mobile and embedded systems. The M2U-Net has a new encoder-decoder architecture that is inspired by the U-Net. It adds pretrained components of MobileNetV2 in the encoder part and novel contractive bottleneck blocks in the decoder part that, combined with bilinear upsampling, drastically reduce the parameter count to 0.55M compared to 31.03M in the original U-Net. We have evaluated its performance against a wide body of previously published results on three public datasets. On two of them, the M2U-Net achieves new state-of-the-art performance by a considerable margin. When implemented on a GPU, our method is the first to achieve real-time inference speeds on high-resolution fundus images. We also implemented our proposed network on an ARM-based embedded system where it segments images in between 0.6 and 15 sec, depending on the resolution. Thus, the M2U-Net enables a number of applications of retinal vessel structure extraction, such as early diagnosis of eye diseases, retinal biometric authentication systems, and robot assisted microsurgery.Keywords
This publication has 33 references indexed in Scilit:
- Leveraging Multiscale Hessian-Based Enhancement With a Novel Exudate Inpainting Technique for Retinal Vessel SegmentationIEEE Journal of Biomedical and Health Informatics, 2015
- Trainable COSFIRE filters for vessel delineation with application to retinal imagesMedical Image Analysis, 2015
- GPU-based segmentation of retinal blood vesselsJournal of Real-Time Image Processing, 2014
- Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and Sub-Image ClassificationIEEE Journal of Biomedical and Health Informatics, 2014
- A high performance hardware architecture for portable, low-power retinal vessel segmentationIntegration, 2014
- Retina based biometric authentication using phase congruencyInternational Journal of Machine Learning and Cybernetics, 2013
- Retinal vessel segmentation by improved matched filtering: evaluation on a new high‐resolution fundus image databaseIET Image Processing, 2013
- Personal verification based on extraction and characterisation of retinal feature pointsJournal of Visual Languages & Computing, 2009
- Personal authentication using digital retinal imagesPattern Analysis and Applications, 2006
- Ridge-Based Vessel Segmentation in Color Images of the RetinaIEEE Transactions on Medical Imaging, 2004