Improved Microaneurysm Detection using Deep Neural Networks

Haloi, Mrinal

doi:10.48550/arxiv.1505.04424

Cited by 15 publications

(28 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Silberman et al [29] extract SIFT (scale invariant feature transform) features in the image patches and utilized SVM (support vector machine) to distinguish patches with exudates. Haloi et al [2], [30] achieve promising performance in MA and exudate detection based on sliding windows and CNN classifiers. Van Grinsven et al [31] propose a selective sampling method for fast hemorrhage detection.…”

Section: Related Workmentioning

confidence: 99%

“…By this network design, a single forward pass can obtain the fourdimension probabilistic vectors of 16 × 16 patches in spatial order. This is equivalent to splitting the input image via a 68 × 68 sliding window with the stride 64 then performing forward pass individually 2 .…”

Section: A Lesion Attention Generatormentioning

confidence: 99%

“…Diabetes is a universal chronic disease that affects one in every eleven adults worldwide, and approximately 40% to 45% of patients with diabetes may develop diabetic retinopathy (DR) in their lifetime [1], [2], [3], [4]. According to [5], [6], DR is one of the leading causes of irreversible blindness, while most parts of the world are short of qualified ophthalmologists.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image

Yang

Shang

et al. 2020

Preprint

View full text Add to dashboard Cite

Currently, diabetic retinopathy (DR) grading from fundus images has attracted incremental interests in both academic and industrial communities. Most convolutional neural networks (CNNs) based algorithms treat DR grading as a classification task via image-level annotations. However, they have not fully explored the valuable information from the DR-related lesions. In this paper, we present a robust framework, which can collaboratively utilize both patch-level lesion and image-level grade annotations, for DR severity grading. By end-to-end optimizing the entire framework, the fine-grained lesion and image-level grade information can be bidirectionally exchanged to exploit more discriminative features for DR grading. Compared with the recent state-of-the-art algorithms and three over 9-years clinical experienced ophthalmologists, the proposed algorithm shows favorable performance. Testing on the datasets from totally different scenarios and distributions (such as label and camera), our algorithm is proved robust in facing image quality and distribution problems that commonly exist in real-world practice. Extensive ablation studies dissect the proposed framework and indicate the effectiveness and necessity of each motivation. The code and some valuable annotations are now publicly available.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: A Lesion Attention Generatormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image

Yang

Shang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Diabetics is an universal chronic disease around some developed countries and developing countries including China and India [1], [2], [3]. The individuals with diabetic have high probabilistic for having diabetic retinopathy (DR) which is one of the most major cause of irreversible blindness [4], [5].…”

Section: Introductionmentioning

confidence: 99%

“…Haloi et al [9] achieve promising performance in exudates and cotton wool spots detection. Later, Haloi [3] try to find MAs in color fundus images via deep neural networks. van Grinsven et al [6] propose a selective sampling method for fast hemorrhage detection.…”

Section: Introductionmentioning

confidence: 99%

Lesion Detection and Grading of Diabetic Retinopathy via Two-Stages Deep Convolutional Neural Networks

Yang

Wensi³

et al. 2017

Lecture Notes in Computer Science

175

View full text Add to dashboard Cite

We propose an automatic diabetic retinopathy (DR) analysis algorithm based on two-stages deep convolutional neural networks (DCNN). Compared to existing DCNN-based DR detection methods, the proposed algorithm have the following advantages: (1) Our method can point out the location and type of lesions in the fundus images, as well as giving the severity grades of DR. Moreover, since retina lesions and DR severity appear with different scales in fundus images, the integration of both local and global networks learn more complete and specific features for DR analysis.(2) By introducing imbalanced weighting map, more attentions will be given to lesion patches for DR grading, which significantly improve the performance of the proposed algorithm. In this study, we label 12, 206 lesion patches and re-annotate the DR grades of 23, 595 fundus images from Kaggle competition dataset. Under the guidance of clinical ophthalmologists, the experimental results show that our local lesion detection net achieve comparable performance with trained human observers, and the proposed imbalanced weighted scheme also be proved to significantly improve the capability of our DCNN-based DR grading algorithm.Index Terms-Diabetic retinopathy, deep convolutional neural networks, fundus images, retinopathy lesions 1 End-to-end DCNN grading means that directly feed the input images into DCNN, then output the DR grades of the images.

show abstract

Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey

Asiri

Hussain

Adel

et al. 2019

Artificial Intelligence in Medicine

225

View full text Add to dashboard Cite

Diabetic retinopathy (DR) results in vision loss if not treated early. A computer-aided diagnosis (CAD) system based on retinal fundus images is an efficient and effective method for early DR diagnosis and assisting experts. A computer-aided diagnosis (CAD) system involves various stages like detection, segmentation and classification of lesions in fundus images. Many traditional machine-learning (ML) techniques based on hand-engineered features have been introduced. The recent emergence of deep learning (DL) and its decisive victory over traditional ML methods for various applications motivated the researchers to employ it for DR diagnosis, and many deeplearning-based methods have been introduced. In this paper, we review these methods, highlighting their pros and cons. In addition, we point out the challenges to be addressed in designing and learning about efficient, effective and robust deep-learning algorithms for various problems in DR diagnosis and draw attention to directions for future research.

show abstract

Improved Microaneurysm Detection using Deep Neural Networks

Cited by 15 publications

References 15 publications

Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image

Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image

Lesion Detection and Grading of Diabetic Retinopathy via Two-Stages Deep Convolutional Neural Networks

Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey

Contact Info

Product

Resources

About