Purpose: To develop an algorithm to detect and quantify hyperreflective dots (HRDs) on optical coherence tomography (OCT) in patients with diabetic macular edema (DME).Materials and Methods: Twenty OCTs (each OCT contains 128 b scans) from 20 patients diagnosed with DME were included in this study. Two types of HRDs, hard exudates and small HRDs (hypothesized to be activated microglia), were identified and labeled independently by two raters. An algorithm using deep learning technology was developed based on input (in total 2,560 OCT b scans) of manual labeling and differentiation of HRDs from rater 1. 4-fold cross-validation was used to train and validate the algorithm. Dice coefficient, intraclass coefficient (ICC), correlation coefficient, and Bland–Altman plot were used to evaluate agreement of the output parameters between two methods (either between two raters or between one rater and proposed algorithm).Results: The Dice coefficients of total HRDs, hard exudates, and small HRDs area of the algorithm were 0.70 ± 0.10, 0.72 ± 0.11, and 0.46 ± 0.06, respectively. The correlations between rater 1 and proposed algorithm (range: 0.95–0.99, all p < 0.001) were stronger than the correlations between the two raters (range: 0.84–0.96, all p < 0.001) for all parameters. The ICCs were higher for all the parameters between rater 1 and proposed algorithm (range: 0.972–0.997) than those between the two raters (range: 0.860–0.953).Conclusions: Our proposed algorithm is a good tool to detect and quantify HRDs and can provide objective and repeatable information of OCT for DME patients in clinical practice and studies.

Corneal ulcer is a common leading cause of corneal blindness. It is difficult to accurately segment corneal ulcers due to the following problems: large differences in the pathological shapes between point-flaky and flaky corneal ulcers, blurred boundary, noise interference, and the lack of sufficient slit-lamp images with ground truth. To address these problems, in this paper, we proposed a novel semi-supervised multi-scale self-transformer generative adversarial network (Semi-MsST-GAN) that can leverage unlabeled images to improve the performance of corneal ulcer segmentation in fluorescein staining of slit-lamp images. Firstly, to improve the performance of segmenting the corneal ulcer regions with complex pathological features, we proposed a novel multi-scale self-transformer network (MsSTNet) as the MsST-GAN generator, which can guide the model to aggregate the low-level weak semantic features with the high-level strong semantic information and adaptively learn the spatial correlation in feature maps. Then, to further improve the segmentation performance by leveraging unlabeled data, the semi-supervised approach based on the proposed MsST-GAN was explored to solve the problem of the lack of slit-lamp images with corresponding ground truth. The proposed Semi-MsST-GAN was comprehensively evaluated on the public SUSTech-SYSU dataset, which contains 354 labeled and 358 unlabeled fluorescein staining slit-lamp images. The results showed that, compared with other state-of-the-art methods, our proposed method achieves better performance with comparable efficiency.

No abstract

No abstract

No abstract