Weakly-Supervised Simultaneous Evidence Identification and Segmentation for Automated Glaucoma Diagnosis

Zhao, Rongchang; Liao, Wangmin; Zou, Beiji; Chen, Zailiang; Li, Shuo

doi:10.1609/aaai.v33i01.3301809

Cited by 34 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pal et al [17] presented a multi-model network consisting of an autoencoder and a CNN classifier that shared the encoder framework. Zhao et al [18] performed an optic disc segmentation using a weakly-supervised multi-task Learning model. Li et al [19] detected glaucoma using a CNN with attention mechanism, which forces the network to pay more attention to a specific region of the image.…”

Section: A Related Workmentioning

confidence: 99%

A Comparative Study of Deep Learning Models for Diagnosing Glaucoma From Fundus Images

Ghamdi

Abdel-Mottaleb

2021

IEEE Access

View full text Add to dashboard Cite

Glaucoma is an eye disease that damages the optic nerve head (ONH) causing loss of vision. Therefore, early diagnosis and treatment are important in preventing possible blindness caused by glaucoma. Its current identification is based on the manual segmentation of the optic cup and disc to examine the cup-to-disc ratio (CDR). However, experts' annotation of these regions is a rather difficult and tedious task. Employing a convolutional neural network (CNN) for diagnosing glaucoma could be an alternative solution. However, its performance depends on the availability of a large number of labeled samples for the training phase. This paper presents an automatic glaucoma diagnosing framework based on three convolutional neural network (CNN) models with different learning methods, and compares the performance of these models with ophthalmologists. We use transfer and semi-supervised learning methods based on both labeled and unlabeled data. First, the transfer learning model starts with a pre-trained CNN model that was trained with non-medical data and fine-tunes it with our labeled data. Secondly, a semi-supervised framework is developed and trained using both labeled and unlabeled data based on two different unsupervised methods. The experimental results using two datasets, RIM-ONE and RIGA, demonstrate the efficacy of deep learning models when applied to glaucoma, which is a promising step towards automated screening for identifying individuals with early-stage glaucoma. Compared with annotations by two ophthalmologists, all the presented models achieve better performances, demonstrating the capability of artificial intelligence in diagnosing glaucoma with a high level of reliability.INDEX TERMS Deep Learning, semi-supervised learning, glaucoma, transfer learning, autoencoder.

show abstract

Section: A Related Workmentioning

confidence: 99%

A Comparative Study of Deep Learning Models for Diagnosing Glaucoma From Fundus Images

Ghamdi

Abdel-Mottaleb

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Inspired by [17], weakly-supervised learning for medical lesions segmentation task [1], [2], [4] has attracted growing research interests. Generally, they require effective prior [4] and constraints [1], [5] to explore discriminative lesions representation associated with image-level labels while producing inaccurate and coarse lesions localization. [18] introduces a differentiable penalty for the loss function to avoid expensive Lagrangian dual iterations and proposal generation.…”

Section: A Semantic Segmentation Of Medical Lesionsmentioning

confidence: 99%

“…great contributions to assisting the clinical experts by learning a semantic lesions segmentation model for pixel-level predictions with only accessing weakly-annotated (image-level) labels. To improve the accuracy and efficiency of medical lesions diagnosis, it has been successfully applied into a large amount of clinical diagnosis tasks until now, e.g., thoracic disease localization [4], automated glaucoma detection [5], histopathology segmentation [1], etc.…”

Section: Introductionmentioning

confidence: 99%

Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation

Dong

Cong

Sun

et al. 2021

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Weakly-supervised learning has attracted growing research attention on medical lesions segmentation due to significant saving in pixel-level annotation cost. However, 1) most existing methods require effective prior and constraints to explore the intrinsic lesions characterization, which only generates incorrect and rough prediction; 2) they neglect the underlying semantic dependencies among weakly-labeled target enteroscopy diseases and fully-annotated source gastroscope lesions, while forcefully utilizing untransferable dependencies leads to the negative performance. To tackle above issues, we propose a new weakly-supervised lesions transfer framework, which can not only explore transferable domain-invariant knowledge across different datasets, but also prevent the negative transfer of untransferable representations. Specifically, a Wasserstein quantified transferability framework is developed to highlight widerange transferable contextual dependencies, while neglecting the irrelevant semantic characterizations. Moreover, a novel selfsupervised pseudo label generator is designed to equally provide confident pseudo pixel labels for both hard-to-transfer and easyto-transfer target samples. It inhibits the enormous deviation of false pseudo pixel labels under the self-supervision manner. Afterwards, dynamically-searched feature centroids are aligned to narrow category-wise distribution shift. Comprehensive theoretical analysis and experiments show the superiority of our model on the endoscopic dataset and several public datasets.

show abstract

“…Another way to incorporate geometric properties of lesions is based on CNN detector (i.e. binary classification) architectures [13], [14].…”

Section: B Weakly-supervised Learningmentioning

confidence: 99%

Weakly Supervised Fine Tuning Approach for Brain Tumor Segmentation Problem

Павлов

Artemov

Sharaev

et al. 2019

2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain. In contrast, image-level annotations, where only the presence of lesion is marked, are generally cheap, generated in far larger volumes compared to pixel-level labels, and contain less labeling noise. In the context of brain tumor segmentation, both pixel-level and image-level annotations are commonly available; thus, a natural question arises whether a segmentation procedure could take advantage of both. In the present work we: 1) propose a learning-based framework that allows simultaneous usage of both pixel-and image-level annotations in MRI images to learn a segmentation model for brain tumor; 2) study the influence of comparative amounts of pixel-and image-level annotations on the quality of brain tumor segmentation; 3) compare our approach to the traditional fully-supervised approach and show that the performance of our method in terms of segmentation quality may be competitive.

show abstract

Weakly-Supervised Simultaneous Evidence Identification and Segmentation for Automated Glaucoma Diagnosis

Cited by 34 publications

References 19 publications

A Comparative Study of Deep Learning Models for Diagnosing Glaucoma From Fundus Images

A Comparative Study of Deep Learning Models for Diagnosing Glaucoma From Fundus Images

Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation

Weakly Supervised Fine Tuning Approach for Brain Tumor Segmentation Problem

Contact Info

Product

Resources

About