Fully automated detection of retinal disorders by image-based deep learning

Li, Feng; Chen, Hua; Liu, Zheng; Zhang, Xuedian; Wu, Zhizheng

doi:10.1007/s00417-018-04224-8

Cited by 159 publications

(93 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The OCT image modality increased its popularity over the recent years as it offers crosssectional visualizations of the retinal tissues in a non-invasive way [13,14]. OCT scans are frequently used in the detection and analysis of retinal diseases that produce structural alterations of the retina [15] as happens, for example, with macular edemas or cysts [16].…”

Section: Introductionmentioning

confidence: 99%

Automatic identification and characterization of the epiretinal membrane in OCT images

Baamonde

Moura

Novo

et al. 2019

Biomed. Opt. Express

View full text Add to dashboard Cite

Optical coherence tomography (OCT) is a medical image modality that is used to capture, non-invasively, high-resolution cross-sectional images of the retinal tissue. These images constitute a suitable scenario for the diagnosis of relevant eye diseases like the vitreomacular traction or the diabetic retinopathy. The identification of the epiretinal membrane (ERM) is a relevant issue as its presence constitutes a symptom of diseases like the macular edema, deteriorating the vision quality of the patients. This work presents an automatic methodology for the identification of the ERM presence in OCT scans. Initially, a complete and heterogeneous set of features was defined to capture the properties of the ERM in the OCT scans. Selected features went through a feature selection process to further improve the method efficiency. Additionally, representative classifiers were trained and tested to measure the suitability of the proposed approach. The method was tested with a dataset of 285 OCT scans labeled by a specialist. In particular, 3,600 samples were equally extracted from the dataset, representing zones with and without ERM presence. Different experiments were conducted to reach the most suitable approach. Finally, selected classifiers were trained and compared using different metrics, providing in the best configuration an accuracy of 89.35%.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic identification and characterization of the epiretinal membrane in OCT images

Baamonde

Moura

Novo

et al. 2019

Biomed. Opt. Express

View full text Add to dashboard Cite

show abstract

“…They fine-tuned the pre-trained convolution neural network (CNN) GoogleLeNet to train and classify OCT images so that the neural network can be trained and good results can be achieved by using limited data. In 2019, Feng et al [23] also used transfer learning to classify OCT images in order to reduce the dependence on dataset size. They finetuned and trained the pre-trained VGG16.…”

Section: Related Workmentioning

confidence: 99%

“…In [21] the network structure was improved and the local and overall information was combined with the multi-scale method to extract and retain the effective features as much as possible, thus good results was achieved. In [22] and [23], transfer learning was proposed to reduce the training parameters of neural networks, which reduces the dependence on the size of datasets, but such method has poor adaptation to the differences among different datasets.…”

Section: Related Workmentioning

confidence: 99%

“…Combining the ideas in [19], [20], [21], [23], this study proposes to use the characteristics of the network structure to reduce the dependence on the size of the dataset and enhance the adaptability to the differences among different datasets. Meanwhile, related research has been performed on the diagnosis and analysis of AMD and DME by two published OCT datasets proposed by Srinivasan et al and Rasti et al.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

On OCT Image Classification via Deep Learning

Wang

2019

IEEE Photonics J.

View full text Add to dashboard Cite

Computer-aided diagnosis of retinopathy is a research hotspot in the field of medical image classification. Diabetic macular edema (DME) and age-related macular degeneration (AMD) are two common ocular diseases that can result in partial or complete loss of vision. Optical coherence tomography imaging (OCT) is widely applied to the diagnosis of ocular diseases including DME and AMD. In this paper, an automatic method based on deep learning is proposed to detect AME and AMD lesions, in which two publicly available OCT datasets of retina were adopted and a network model with effective feature of reuse feature was applied to solve the problem of small datasets and enhance the adaptation to the difference of different datasets of the approach. Several network models with effective feature of reusable feature were compared and the transfer learning on networks with pretrained models was realized. CliqueNet achieves better, classification results compared with other network models with a more than 0.98 accuracy and 0.99 of area under the curve (AUC) value finally.

show abstract

“…17 CNNs can effectively reduce the complexity of the network, reduce the number of training parameters, and make the model relatively invariant to translation, distortion, and scaling; they are robust and have good fault tolerance; and it is easy to train and optimize the network structure. 18 In recent years, deep learning has made significant progress in brain diseases, 19 retinopathy, 20 detection and prognosis of pulmonary nodules, 21,22 breast cancer, 23 and other diseases. [24][25][26] However, because sports injuries such as ligament tears are subtle abnormalities and the 3D orientation of ligaments makes it difficult to evaluate on a single 2D image slice, the application of deep learning in sports injury of the knee joint is limited and has mainly been used in the evaluation of cartilage.…”

mentioning

confidence: 99%

Deep Learning Approach for Anterior Cruciate Ligament Lesion Detection: Evaluation of Diagnostic Performance Using Arthroscopy as the Reference Standard

Zhang

Zhou

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background: MRI is the most commonly used imaging method for diagnosing anterior cruciate ligament (ACL) injuries. However, the interpretation of knee MRI is time-intensive and depends on the clinical experience of the reader. An automated detection system based on a deep-learning algorithm may improve interpretation time and reliability. Purpose: To determine the feasibility of using a deep learning approach to detect ACL injuries within the knee joint on MRI. Study Type: Retrospective. Population: In all, 163 subjects with an ACL tear and 245 subjects with an intact ACL. There were 285, 81, and 42 volumes for training, validation, and test sets, respectively. Field Strength/Sequence: 2D sagittal proton density-weighted spectral attenuated inversion recovery sequences at 1.5T and 3.0T. Assessment: Based on the architecture of 3D DenseNet, we constructed a classification convolutional neural network. We tested this deep learning approach with different inputs and two other algorithms, including VGG16 and ResNet. Then we had both inexperienced radiologists and senior radiologists read the MR images. Statistical Tests: Using arthroscopic results as the reference standard, the performance of three different inputs and three different algorithms, the residents and senior radiologists assessed the classification accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC). Results: The accuracy, sensitivity, specificity, PPV, and NPV of our customized 3D deep learning architecture was 0.957, 0.976, 0.944, 0.940, and 0.976, respectively. The average AUCs were 0.946, 0.859, 0.960 for ResNet, VGG16, and our proposed network, respectively. The diagnostic accuracy of our model, residents, and senior radiologists was 0.957, 0.814, and 0.899, respectively. Data Conclusion: Our study demonstrated the feasibility of using an automated deep-learning-based detection system to evaluate ACL injury. Level of Evidence: 3 Technical Efficacy Stage: 1

show abstract

Fully automated detection of retinal disorders by image-based deep learning

Cited by 159 publications

References 21 publications

Automatic identification and characterization of the epiretinal membrane in OCT images

Automatic identification and characterization of the epiretinal membrane in OCT images

On OCT Image Classification via Deep Learning

Deep Learning Approach for Anterior Cruciate Ligament Lesion Detection: Evaluation of Diagnostic Performance Using Arthroscopy as the Reference Standard

Contact Info

Product

Resources

About