Hiroshi Ishikawa

Retinal nerve fiber layer thickness (RNFLT), a glaucoma biomarker, has a wide normative range affecting its sensitivity and specificity for abnormality detection. The interindividual RNFLT peak location variability contribution to this wide normative range has not been directly evaluated. The purpose of this study is to assess the effect of RNFLT peak normalization (PN) on normative variability. Circumpapillary RNFLT profiles at 1.7 mm radius from the optic nerve head (ONH) were re-sampled from optical coherence tomography (OCT) volumes (Cirrus HD-OCT, 200 × 200) obtained from one eye of 83 healthy individuals. Fovea-ONH axis (FOA) was calculated from corresponding scanning laser ophthalmoscope images. Supratemporal (ST) and infratemporal (IT) RNFLT peaks of each profile were aligned to respective average peak locations. Normative ranges were calculated by averaging individual profiles before and after PN (with and without FOA to horizontal image axis (HA) alignment). RNFLT-PN resulted in an overall decrease in coefficient of variation (CoV) of the normative range by 4.2% (P = 0.02). CoV was reduced by more than 10% in clock-hours 10 (11.9%), 8 (10.6%), 6 (10.4%) after PN, and 7 (16.3%), 10 (11.4%), and 12 (10.4%) after PN with FOA-HA alignment. RNFLT-PN corrected for abnormality categorization because of peak misalignment in RNFLT profiles of healthy and glaucoma suspect subjects. RNFLT-PN reduces normative variability, especially in the ST and IT regions. RNFLT-PN reduces normative variability and improves sectoral abnormality categorization, potentially leading to better sensitivity and specificity of RNFLT measure in glaucoma detection.

Here, we introduce Artificial Intelligence Ready and Equitable Atlas for Diabetes Insights (AI-READI), a multidisciplinary data-generation project designed to create and share a multimodal dataset optimized for artificial intelligence research in type 2 diabetes mellitus.

Purpose: This study aims to investigate the prevalence of artifacts in optical coherence tomography (OCT) images with acceptable signal strength and evaluate the performance of supervised deep learning models in improving OCT image quality assessment. Methods: We conducted a retrospective study on 4555 OCT images from 546 patients, with each image having an acceptable signal strength (≥6). A comprehensive analysis of prevalent OCT artifacts was performed, and five pretrained convolutional neural network models were trained and tested to infer images based on quality. Results: Our results showed a high prevalence of artifacts in OCT images with acceptable signal strength. Approximately 21% of images were labeled as nonacceptable quality. The EfficientNetV2 model demonstrated superior performance in classifying OCT image quality, achieving an area under the receiver operating characteristic curve of 0.950 ± 0.007 and an area under the precision recall curve of 0.985 ± 0.002. Conclusions: The findings highlight the limitations of relying solely on signal strength for OCT image quality assessment and the potential of deep learning models in accurately classifying image quality. Translational Relevance: Application of the deep learning-based OCT image quality assessment models may improve the OCT image data quality for both clinical applications and research.

Purpose: The presence of imbalanced datasets in medical applications can negatively affect deep learning methods. This study aims to investigate how the performance of convolutional neural networks (CNNs) for glaucoma diagnosis can be improved by addressing imbalanced learning issues through utilizing glaucoma suspect samples, which are often excluded from studies because they are a mixture of healthy and preperimetric glaucomatous eyes, in a semi-supervised learning approach. Methods: A baseline 3D CNN was developed and trained on a real-world glaucoma dataset, which is naturally imbalanced (like many other real-world medical datasets). Then, three methods, including reweighting samples, data resampling to form balanced batches, and semi-supervised learning on glaucoma suspect data were applied to practically assess their impacts on the performances of the trained methods. Results: The proposed method achieved a mean accuracy of 95.24%, an F1 score of 97.42%, and an area under the curve of receiver operating characteristic (AUC ROC) of 95.64%, whereas the corresponding results for the traditional supervised training using weighted cross-entropy loss were 92.88%, 96.12%, and 92.72%, respectively. The obtained results show statistically significant improvements in all metrics. Conclusions: Exploiting glaucoma suspect eyes in a semi-supervised learning method coupled with resampling can improve glaucoma diagnosis performance by mitigating imbalanced learning issues. Translational Relevance: Clinical imbalanced datasets may negatively affect medical applications of deep learning. Utilizing data with uncertain diagnosis, such as glaucoma suspects, through a combination of semi-supervised learning and class-imbalanced learning strategies can partially address the problems of having limited data and learning on imbalanced datasets.