Automatic segmentation of corneal dystrophy on photographic images based on texture analysis.

PURPOSE: To develop an automatic algorithm to analyze dystrophic lesions on photographic images of corneal dystrophy. METHODS: The dataset included 32 images of corneal dystrophy. The dystrophic area was manually segmented twice. Manually labeled dystrophy areas were compared with automatically segmented images. First, we manually removed the light reflex from the image of the cornea. Using an automatic approach, we extracted the brown color of the iris. Then, the program detected the circular region of the pupil and the corneal surface. A whitish dystrophy area was defined based on the image intensity on the iris and the pupil. The sliding square kernel was applied to clearly define the dystrophic region. RESULTS: For the manual analysis and the twice automatic approach, the Dice similarity was 0.804 and 0.801, respectively. The Pearson correlation coefficient was 0.807 and 0.806, respectively. The total number of distinct dystrophic areas showed no significant difference between the manual and automatic approaches according to the Wilcoxon signed-rank test (p < 0.0001, both). CONCLUSIONS: We proposed an automatic algorithm for detecting the dystrophy areas on photographic images with an accuracy of approximately 0.80. This system can be applied to detect and predict the progression of corneal dystrophy.

Correlation between Topographic Progression of Geographic Atrophy and Visual Acuity Changes.

PURPOSE: To analyze topographic progression of geographic atrophy with different concentric circles centered on the fovea in correlation with decrease of visual acuity. METHODS: We retrospectively analyzed 36 eyes of 26 patients diagnosed with geographic atrophy and followed at least 1 year. One millimeter circular area at the foveal center were defined as zone 1, and doughnut shape areas from between 1 and 2 mm to between 5 and 6 mm were defined as zone 2 to 6. Then, changes of geographic atrophy area in each zone were measured with semi-automatic software. Correlation analysis and regression analysis were performed to determine the relationship between changes in visual acuity and atrophic area in each zone. RESULTS: Mean age was 76.9 years and follow-up period were 3.38 years. The mean atrophic area increased from 8.09 to 16.34 mm2 and visual acuity decreased from 0.39 to 0.69 on logarithm of the minimal angle of resolution. Mean change of total geographic atrophy area was not significantly correlated with visual acuity decrease. While geographic atrophy progression within zone 1, 2, and 3 showed significant causal relationship with decrease of visual acuity (all, p < 0.05). CONCLUSIONS: In contrast to the total geographic atrophy area, progression of geographic atrophy in parafoveal area was significantly correlated with decrease of visual acuity.

Convolutional Network With Twofold Feature Augmentation for Diabetic Retinopathy Recognition From Multi-Modal Images.

OBJECTIVE: With the scenario of limited labeled dataset, this paper introduces a deep learning-based approach that leverages Diabetic Retinopathy (DR) severity recognition performance using fundus images combined with wide-field swept-source optical coherence tomography angiography (SS-OCTA). METHODS: The proposed architecture comprises a backbone convolutional network associated with a Twofold Feature Augmentation mechanism, namely TFA-Net. The former includes multiple convolution blocks extracting representational features at various scales. The latter is constructed in a two-stage manner, i.e., the utilization of weight-sharing convolution kernels and the deployment of a Reverse Cross-Attention (RCA) stream. RESULTS: The proposed model achieves a Quadratic Weighted Kappa rate of 90.2% on the small-sized internal KHUMC dataset. The robustness of the RCA stream is also evaluated by the single-modal Messidor dataset, of which the obtained mean Accuracy (94.8%) and Area Under Receiver Operating Characteristic (99.4%) outperform those of the state-of-the-arts significantly. CONCLUSION: Utilizing a network strongly regularized at feature space to learn the amalgamation of different modalities is of proven effectiveness. Thanks to the widespread availability of multi-modal retinal imaging for each diabetes patient nowadays, such approach can reduce the heavy reliance on large quantity of labeled visual data. SIGNIFICANCE: Our TFA-Net is able to coordinate hybrid information of fundus photos and wide-field SS-OCTA for exhaustively exploiting DR-oriented biomarkers. Moreover, the embedded feature-wise augmentation scheme can enrich generalization ability efficiently despite learning from small-scale labeled data.

Oral-Facial-Digital Syndrome Type IX with Subfoveal Drusenoid Deposit.

We describe a patient with oral-facial-digital syndrome (OFDS) with the following anomalies: cleft lip, cleft palate, micrognathia, hypertelorism, nasal septum deviation, thumb polydactyly in the right hand, and partial agenesis of the corpus callosum. In addition, the patient had optic disc coloboma in the left eye and subfoveal drusenoid deposit in the right eye, features of OFDS type IX. Subfoveal drusenoid deposit has not been previously reported in OFDS type IX. Evaluation of the fundus is necessary for diagnosis of OFDS.