Microaneurysms segmentation with a U-Net based on recurrent residual convolutional neural network

@article{Kou2019MicroaneurysmsSW,
  title={Microaneurysms segmentation with a U-Net based on recurrent residual convolutional neural network},
  author={Caixia Kou and Wei Li and Wei Liang and Zekuan Yu and Jianchen Hao},
  journal={Journal of Medical Imaging},
  year={2019},
  volume={6},
  pages={025008 - 025008}
}
Abstract. Microaneurysms (MAs) play an important role in the diagnosis of clinical diabetic retinopathy at the early stage. Annotation of MAs manually by experts is laborious and so it is essential to develop automatic segmentation methods. Automatic MA segmentation remains a challenging task mainly due to the low local contrast of the image and the small size of MAs. A deep learning-based method called U-Net has become one of the most popular methods for the medical image segmentation task. We… Expand
An Enhanced Residual U-Net for Microaneurysms and Exudates Segmentation in Fundus Images
TLDR
Evaluating the performance of ERU-Net for MAs and EXs segmentation on three public datasets, E-Ophtha, IDRiD, and DDR, shows that the network performs competitively and is a promising network for medical image segmentation. Expand
A Survey on Microaneurysms Detection in Color Fundus Images
Early Detection of Microaneurysms (MA) plays a vital role in preventing the blindness caused by diabetic retinopathy (DR). DR is preventable yet a serious diabetic problem. Treatment at an earlierExpand
Segmentation of Retinal Lesions in Fundus Images: A Patch Based Approach Using Encoder-Decoder Neural Network
  • E. S. Kumar, C. Bindu
  • 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS)
  • 2021
Lesion segmentation is an essential aspect while diagnosing Diabetic Retinopathy (DR) at initial stages. Manual identification becomes exceptionally challenging and time consuming because of theExpand
AOSLO-net: A deep learning-based method for automatic segmentation of retinal microaneurysms from adaptive optics scanning laser ophthalmoscope images
TLDR
AOSLO-net, a deep neural network framework with customized training policies to automatically segment MAs from AOSLO images, is introduced and it is demonstrated that the proposed model outperforms the state-of-the-art segmentation model both in accuracy and cost and enables correct MA morphological classification. Expand
SESV: Accurate Medical Image Segmentation by Predicting and Correcting Errors
TLDR
The proposed SESV framework is capable of improving the accuracy of different DCNNs on different medical image segmentation tasks and introduces a verification network to determine whether to accept or reject the refined mask produced by the re-segmentation network on a region-by-region basis. Expand
Deep Multi-Task Learning for Diabetic Retinopathy Grading in Fundus Images
TLDR
A deep multi-task learning based DR grading (DeepMT-DR) method for LR fundus images, which simultaneously handles the auxiliary tasks of ISR and lesion segmentation and the high-level task of DR grading. Expand
Multiple Lesions Insertion: boosting diabetic retinopathy screening through Poisson editing.
TLDR
The results indicate that the MLI method outperforms most of the traditional augmentation methods, i.e, oversampling, under-sampling, cropping, rotation, and adding other real sample methods in the DR screening task. Expand
Embedded Residual Recurrent Network and Graph Search for the Segmentation of Retinal Layer Boundaries in Optical Coherence Tomography
TLDR
The quantitative results and visual effects show that the proposed method outperforms the state-of-the-art approaches in the segmentation of retinal layer boundaries in OCT images and has good algorithm stability on three datasets with different sizes, characteristics, and segmentation difficulties. Expand
Automated microaneurysms detection for early diagnosis of diabetic retinopathy: A Comprehensive review
TLDR
The challenges that need to be addressed in designing such effective, efficient, and robust algorithms for early DR diagnosis systems are discussed and also the ample scope for future research in this area is discussed. Expand
Coarse-to-fine multiplanar D-SEA UNet for automatic 3D carotid segmentation in CTA images
  • Junjie Wang, Yuanyuan Yu, +4 authors Zekuan Yu
  • Medicine
  • International Journal of Computer Assisted Radiology and Surgery
  • 2021
TLDR
The proposed segmentation method can realize the fully automatic segmentation of the carotid artery and has robust performance with segmentation accuracy, which can be applied into plaque exfoliation and interventional surgery services. Expand
...
1
2
...

References

SHOWING 1-10 OF 30 REFERENCES
Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
TLDR
A Recurrent Convolutional Neural Network (RCNN) based on U-Net as well as a Recurrent Residual convolutional neural Network (RRCNN), which are named RU-Net and R2U-Net respectively are proposed, which show superior performance on segmentation tasks compared to equivalent models including U-nets and residual U- net. Expand
Microaneurysm detection using fully convolutional neural networks
TLDR
Performance, simplicity, and robustness of the proposed method demonstrates its suitability for diabetic retinopathy screening applications and is the first paper that shows how to successfully transfer knowledge between datasets in the microaneurysm detection domain. Expand
Clinical Report Guided Retinal Microaneurysm Detection With Multi-Sieving Deep Learning
TLDR
An efficient microaneurysm detection framework based on the hybrid text/image interleaving technique is built and its performance on challenging clinical data sets acquired from diabetic retinopathy patients is validated. Expand
Improved Microaneurysm Detection using Deep Neural Networks
TLDR
This work proposes a novel microaneurysm (MA) detection for early diabetic retinopathy screening using color fundus images and achieves state-of-the-art accuracy. Expand
Microaneurysm detection using deep learning and interleaved freezing
TLDR
A novel patch-based fully convolutional neural network for detection of microaneurysms is proposed, which outperforms the state-of-the-art methods in terms of free-response receiver operatic characteristic (FROC) metric. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Automated segmentation of exudates, haemorrhages, microaneurysms using single convolutional neural network
TLDR
It is shown that it is possible to get a single convolutional neural network to segment these pathological features on a wide range of fundus images with reasonable accuracy, and that the net achieved a sensitivity of 0.7158 for exudates and dark lesions on the CLEOPATRA database. Expand
Microaneurysm detection in retinal images using a rotating cross-section based model
  • I. Lázár, A. Hajdu
  • Computer Science
  • 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
  • 2011
TLDR
This paper presents a method to construct an MA score map, from which the final MAs can be extracted by simple thresholding for a binary output, or by considering all the regional maxima to obtain probability scores. Expand
Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation
TLDR
A deep learning architecture, named M-Net, is proposed, which solves the OD and OC segmentation jointly in a one-stage multi-label system and introduces the polar transformation, which provides the representation of the original image in the polar coordinate system. Expand
Detection of microaneurysms using multi-scale correlation coefficients
TLDR
This paper presents a new approach to the computer aided diagnosis (CAD) of diabetic retinopathy (DR) based on multi-scale correlation filtering (MSCF) and dynamic thresholding and concludes the method to be effective and efficient. Expand
...
1
2
3
...