Interpretable Evaluation of Diabetic Retinopathy Grade Regarding Eye Color Fundus Images

Hsu, Jieh Sheng; Bari, Noaima; Xu, Qiu; Viswanathan, Malvika; Shi, Wenqi; Giuste, Felipe; Zhong, Yishan; Sun, Jimin; Wang, May D.

doi:10.1109/bibe55377.2022.00011

Cited by 7 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rapid improvements in artificial intelligence (AI) have enabled broad application of AI-assisted medical image analysis (classification, segmentation, registration, synthesis) pipelines [4][5][6][7][8][9][10][11][12][13], including semi-automated retinopathy detection systems using machine learning (ML) classifiers [14] based on human-designed features as well as fully-automated deep learning (DL) systems [15,16]. Currently, mainstream DL frameworks include Multilayer Perceptrons (MLP), Transformers [17], and Convolutional Neural Networks (CNN) [18], which can only take in grid or sequence data.…”

Section: Introductionmentioning

confidence: 99%

A vision-GNN framework for retinopathy classification using optical coherence tomography

Wang

Wynne

et al. 2023

Medical Imaging 2023: Computer-Aided Diagnosis

View full text Add to dashboard Cite

Retinopathy refers to pathologies of the retina that can ultimately result in vision impairment and blindness. Optical Coherence Tomography (OCT) is a technique to image these diseases, aiding in the early detection of retinal damage, which may mitigate the risk of vision loss. In this work, we propose an end-to-end Graph Neural Network (GNN) pipeline that can extract deep graph-based features for multi-class retinopathy classification for the first time. To our knowledge, this is also the first work applying Vision-GNN for OCT image analysis. We trained and tested the proposed GNN on a public OCT retina dataset divided into four categories (Normal, Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), and Drusen). Using our method, we achieve an average accuracy of 99.07% over four classes proving the effectiveness of a deep learning classifier for OCT images with graph-based features. This work lays the foundation to apply GNNs for OCT imaging to aid the early detection of retinal damage.

show abstract

Section: Introductionmentioning

confidence: 99%

A vision-GNN framework for retinopathy classification using optical coherence tomography

Wang

Wynne

et al. 2023

Medical Imaging 2023: Computer-Aided Diagnosis

View full text Add to dashboard Cite

show abstract

“…They can automatically extract the image features for precise predictions in various computer vision (CV) tasks [7]. In medical imaging, DL-powered systems have significantly changed the landscape with unprecedented processing speed and accuracy [8][9][10][11][12][13][14]. Currently, convolutional neural networks (CNNs) [15] and Vision Transformers [16] are the most widely used backbone for these frameworks.…”

Section: Introductionmentioning

confidence: 99%

Ultrasound breast tumor detection based on vision graph neural network

Wang

Chang

et al. 2023

Medical Imaging 2023: Ultrasonic Imaging and Tomography

View full text Add to dashboard Cite

Breast cancer is the most commonly diagnosed cancer in women in the United States. Early detection of breast tumors enables prompt determination of cancer status, significantly boosting patient survival rate. Non-invasive and non-ionizing ultrasound imaging is a widely used diagnosing modality in clinic. To assist clinicians in breast cancer diagnosis, we implemented a vision graph neural networks (ViG)-based pipeline that can achieve accurate binary classification (normal vs. breast tumor) and multiclass classification (normal, benign, and malignant) from breast ultrasound images. Our results demonstrated that the average accuracy of ViG is 100.00% for binary and 87.18% for multiclass classification tasks. To the best of our knowledge, this is the first end-to-end, graph-feature-based deep learning pipeline to achieve accurate breast tumor detection from ultrasound images. The proposed ViG-based classifier is accessible for clinical implementation and has the potential to enhance lesion detection from ultrasound images.

show abstract

“…Accordingly, automatic segmentation approaches are proposed as an effective and efficient solution for accurate and reproducible organ delineation. Currently, machine learning and deep learning models are prevalent in various medical tasks, including image classification and detection [1][2][3][4][5], registration [6] and synthesis [7,8], and demonstrates state-of-the-art accuracy and efficiency. Similarly, for the segmentation, deep learning algorithms are frequently applied in this setting due to their superior ability to detect organ contours [9,10].…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based multi-organ CT segmentation with adversarial data augmentation

Pan

Huang

et al. 2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

In this work, we propose an adversarial attack-based data augmentation method to improve the deep-learning-based segmentation algorithm for the delineation of Organs-At-Risk (OAR) in abdominal Computed Tomography (CT) to facilitate radiation therapy. We introduce Adversarial Feature Attack for Medical Image (AFA-MI) augmentation, which forces the segmentation network to learn out-of-distribution statistics and improve generalization and robustness to noises. AFA-MI augmentation consists of three steps: 1) generate adversarial noises by Fast Gradient Sign Method (FGSM) on the intermediate features of the segmentation network's encoder; 2) inject the generated adversarial noises into the network, intentionally compromising performance; 3) optimize the network with both clean and adversarial features. The effectiveness of the AFA-MI augmentation was validated on nnUnet. Experiments are conducted segmenting the heart, left and right kidney, liver, left and right lung, spinal cord, and stomach in an institutional dataset collected from 60 patients. We firstly evaluate the AFA-MI augmentation using nnUnet and Token-based Transformer Vnet (TT-Vnet) on the test data from a public abdominal dataset and an institutional dataset. In addition, we validate how AFA-MI affects the networks' robustness to the noisy data by evaluating the networks with added Gaussian noises of varying magnitudes to the institutional dataset. Network performance is quantitatively evaluated using Dice Similarity Coefficient (DSC) for volume-based accuracy. Also, Hausdorff Distance (HD) is applied for surface-based accuracy. On the public dataset, nnUnet with AFA-MI achieves DSC = 0.85 and HD = 6.16 millimeters (mm); and TT-Vnet achieves DSC = 0.86 and HD = 5.62 mm. On the robustness experiment with the institutional data, AFA-MI is observed to improve the segmentation DSC score ranging from 0.055 to 0.010 across all organs relative to clean inputs. AFA-MI augmentation further improves all contour accuracies up to 0.527 as measured by the DSC score when tested on images with Gaussian noises. AFA-MI augmentation is therefore demonstrated to improve segmentation performance and robustness in CT multi-organ segmentation.

show abstract

Interpretable Evaluation of Diabetic Retinopathy Grade Regarding Eye Color Fundus Images

Cited by 7 publications

References 12 publications

A vision-GNN framework for retinopathy classification using optical coherence tomography

A vision-GNN framework for retinopathy classification using optical coherence tomography

Ultrasound breast tumor detection based on vision graph neural network

Deep learning-based multi-organ CT segmentation with adversarial data augmentation

Contact Info

Product

Resources

About