Background/Objectives: Keratoconus (KC) is a chronic disease that causes progressive corneal thinning and steepening, thereby negatively impacting visual acuity. Although corneal topography and keratometry are the primary measures to diagnose KC, access to these methods can be limited by various factors. To address these limitations, this study evaluates a novel low-cost deep-learning algorithm that infers keratometric categories from smartphone-assisted Placido ring photographs. Methods: Development utilized 1240 healthy control eye images and 188 K1-labeled KC images for pretraining, without using their K1 labels. A Variational Autoencoder with KL divergence regularization (AutoEncoderKL) was trained on this pool; its encoder generated latent features for KC images (n = 535). A held-out set (n = 70) with Pentacam keratometry was labeled by K1 into 47 D. An ensemble classifier chosen via grid search and cross-validation used the encoder features. Performance was assessed for accuracy, precision, recall, and F1-score. Results: The model achieved 91% accuracy across all classes. Precision of the model was 0.77 (47 D); recall was 0.83, 0.91, and 1.00; and F1-scores were 0.80, 0.94, and 0.92, respectively. Notably, the model achieved perfect recall for the >47 D K1 category. Conclusions: A smartphone-assisted Placido ring imaging approach was able to predict K1-based keratometric categories without requiring tomographic or keratometric measurements as model inputs at inference. These findings provide preliminary proof-of-concept for the potential use of smartphone-assisted Placido ring images as a low-cost approach for K1-based stratification. Larger externally validated studies across different sites, devices, operators, printed Placido discs, acquisition conditions, and patient populations are required before clinical utility can be assessed.

To analyze the imaging features of the lateral rectus-superior rectus (LR-SR) band as imaged with magnetic resonance imaging (MRI) at different orbital scan locations. The LR-SR band features of patients who underwent high-resolution MRI for non-orbital pathology were evaluated at pre-defined locations by two independent readers. Analyzed features included (1) visibility, (2) continuity, and (3) superotemporal bowing of LR-SR band in a binary manner at 2.5 mm anterior (Zone I), at (Zone II) and posterior (Zone III) to the globe-optic nerve junction. Forty-eight orbits of 26 patients with an age range of 58-86 years were included. Visualization of the LR-SR band was significantly higher in Zone I (89.6%) compared to Zone II (79.2%) (p=0.03) and to Zone III (47.9%) (p<0.001). Among the orbits in which the LR-SR band was visualized, band continuity was most frequently observed in Zone I (94.7%), compared to Zone II (68.4%) (p=0.002) and in Zone III (52.2%) (p<0.001). Superotemporal bowing was detected with higher frequency posteriorly, rising from 21.1% in Zone I to 47.4% in Zone II (p=0.002) and to 56.5% in Zone III (p<0.001). A higher degree of reproducibility for LR-SR band visibility and continuity was noted in anterior scan locations. The LR-SR band is most consistently visualized on coronal MRI images obtained anterior to the globe-optic nerve junction, while degenerative changes are more frequently observed in posterior scan locations. Establishing and reporting a standardized coronal imaging plane referenced to a consistent anatomic landmark may improve reproducibility and comparability of the LR-SR band across studies and allow for more robust clinical interpretation.

Lacrimal sac epithelial tumors are rare and often present with subtle symptoms. We report 2 cases managed with combined external dacryocystectomy and endoscopic endonasal resection. Case 1 involved a 59-year-old female with lacrimal sac inverted papilloma extending into the nasolacrimal duct and inferior meatus. Case 2 involved a 79-year-old male with a chronically draining medial canthal wound and progressive induration after prior cyst excision, ultimately diagnosed as lacrimal sac oncocytoma. In both cases, preoperative imaging and clinical features demonstrated nasolacrimal duct involvement and adjacent anatomic distortion, prompting combined surgery for direct visualization and controlled resection of the lacrimal sac and ductal components. The combined approach allowed safe excision despite ductal expansion and adjacent tissue involvement. A small localized recurrence in case 1 at 11 months was successfully managed with in-office resection. These cases support case-selected multidisciplinary external-endonasal surgery for lacrimal sac tumors with nasolacrimal duct involvement.