Search

Manually annotating medical images is extremely expensive, especially for large-scale datasets. Self-supervised contrastive learning has been explored to learn feature representations from unlabeled images. However, unlike natural images, the application of contrastive learning to medical images is relatively limited. In this work, we propose a self-supervised framework, namely lesion-based contrastive learning for automated diabetic retinopathy (DR) grading. Instead of taking entire images as the input in the common contrastive learning scheme, lesion patches are employed to encourage the feature extractor to learn representations that are highly discriminative for DR grading. We also investigate different data augmentation operations in defining our contrastive prediction task. Extensive experiments are conducted on the publicly-accessible dataset EyePACS, demonstrating that our proposed framework performs outstandingly on DR grading in terms of both linear evaluation and transfer capacity evaluation.

Optical coherence tomography angiography (OCTA) is a novel non-invasive imaging technique that allows visualizations of vasculature and foveal avascular zone (FAZ) across retinal layers. Clinical researches suggest that the morphology and contour irregularity of FAZ are important biomarkers of various ocular pathologies. Therefore, precise segmentation of FAZ has great clinical interest. Also, there is no existing research reporting that FAZ features can improve the performance of deep diagnostic classification networks. In this paper, we propose a novel multi-level boundary shape and distance aware joint learning framework, named BSDA-Net, for FAZ segmentation and diagnostic classification from OCTA images. Two auxiliary branches, namely boundary heatmap regression and signed distance map reconstruction branches, are constructed in addition to the segmentation branch to improve the segmentation performance, resulting in more accurate FAZ contours and fewer outliers. Moreover, both low-level and high-level features from the aforementioned three branches, including shape, size, boundary, and signed directional distance map of FAZ, are fused hierarchically with features from the diagnostic classifier. Through extensive experiments, the proposed BSDA-Net is found to yield state-of-the-art segmentation and classification results on the OCTA-500, OCTAGON, and FAZID datasets.

Optical coherence tomography angiography (OCTA) is a recent advance in ophthalmic imaging, which provides detailed visualization of two important anatomical landmarks, namely foveal avascular zone (FAZ) and retinal vessels (RV). Studies have shown that both FAZ and RV play significant roles in the diagnoses of various eye-related diseases. Therefore, accurate segmentation of FAZ and RV from OCTA images is highly in need. However, due to complicated microstructures and inhomogeneous image quality, there is still room for improvement in existing methods. In this paper, we propose a novel and efficient deep learning framework containing two subnetworks for simultaneously segmenting FAZ and RV from en-face OCTA images, named FARGO. For FAZ, we use RV segmentation as an auxiliary task, which may provide supplementary information especially for low-contrast and low-quality OCTA images. A ResNeSt based encoder with split attention and ImageNet pretraining is employed for FAZ segmentation. For RV, we introduce a coarse-to-fine cascaded network composed of a main segmentation model and several small ones for progressive refining. Spatial attention and channel attention modules are utilized for adaptively integrating local features with global dependencies. Through extensive experiments, FARGO is found to yield outstanding segmentation results for both FAZ and RV on the OCTA-500 dataset, performing even better than methods that utilize 3D OCTA volume as an extra input.

Monitoring the condition of retinal vascular network based on a fundus image plays a vital role in the diagnosis of certain ophthalmologic and cardiovascular diseases, for which a prerequisite is to segment out the retinal vessels. The relatively low contrast of retinal vessels and the presence of various types of lesions such as hemorrhages and exudate nevertheless make this task challenging. In this paper, we proposed and validated a novel retinal vessel segmentation method utilizing Separable Spatial and Channel Flow and Densely Adjacent Vessel Prediction to capture maximum spatial correlations between vessels. Image pre-processing was conducted to enhance the retinal vessel contrast. Geometric transformations and overlapped patches were used at both training and prediction stages to effectively utilize the information learned at the training stage and refine the segmentation. Publicly available datasets including DRIVE and CHASE_DB1 were used to evaluate the proposed approach both quantitatively and qualitatively. The proposed method was found to exhibit superior performance, with the average areas under the ROC curve being 0.9826 and 0.9865 and the average accuracies being 0.9579 and 0.9664 for the aforementioned two datasets, which outperforms existing state-of-the-art results.