Purpose: To reconstruct the anophthalmic orbit using a microvascular radial forearm free flap in patients with significant volume loss and socket contracture after exenteration or enucleation. Methods: This is a retrospective observational case series of 22 subjects with acquired anophthalmic orbits after tumor resection or trauma: 14 patients with retinoblastoma who underwent enucleation followed by adjuvant radiation therapy and 8 patients with malignant orbital tumors or orbital trauma who underwent exenteration of the orbit. All patients had large orbital defects or severely contracted eye sockets. Patients underwent orbital reconstruction with implantation of a microvascular radial forearm free flap with or without placement of a hydroxyapatite sphere or conical implant. Results: All patients were followed for 6 months to 6 years. Long-term improvement of socket contracture, prosthesis fit, and cosmetic appearance of patients was observed. The prosthetic eyes were well fitted in the eye socket using this technique. Conclusions: Our results demonstrate successful functional and clinical outcomes for treatment of severe anophthalmic orbital syndrome using microvascular radial forearm free flaps. However, further prospective, long-term studies are recommended.

Eyelid tumors accounts for 5–10% of skin tumors. It is important but difficult to identify malignant eyelid tumors from benign lesions in a cost-effective way. Traditional screening methods for malignancy in eyelid tumors require laborious and time-consuming histopathological process. Therefore, we aimed to develop a deep learning (DL)-based image analysis system for automatic identification of benign and malignant eyelid tumors. Using a common digital camera, we collected clinical images from patients who were histopathologically diagnosed with eyelid tumors. We trained 8 convolutional neural network (CNN) models to identify benign and malignant eyelid tumors, including ResNet-50, ResNet-101, InceptionV3, and InceptionResNetV2. Another group of patients with eyelid tumors were also collected as the prospective validation dataset. Performance of DL models and human clinicians in prospective validation dataset were evaluated and compared. A total of 309 images from 209 patients were used for training DL system, all eight models reached an average accuracy greater than 0.958 in the internal cross-validation. 36 images from 36 patients were included for the prospective validation, the models reached the best performance in accuracy, sensitivity, specificity, and area under curve (AUC) of 0.889 (95% CI 0.747–0.956), 0.933 (95% CI 0.702–0.988), 0.857 (95% CI 0.654–0.950), and 0.966 (95% CI 0.850–0.993), respectively. DL system had a similar performance as the senior ophthalmologists, and outreached the performance of junior ophthalmologists and medical students. DL system can identify benign and malignant tumors through common clinical images, with a better performance than most ophthalmologists. Combining DL system with smartphone may enable patients’ self-monitoring for eyelid tumors and assist in doctors’ clinical decision making.

Background: Studies on the factors related to lacrimal gland prolapse (LGP) in patients with thyroid-associated ophthalmopathy (TAO) are limited. This study aimed to assess the factors associated with LGP on magnetic resonance imaging (MRI) and its relation to TAO activity . Methods: Thirty-six patients (72 orbits) with inactive TAO (43 orbits, Clinical Activity Score [CAS] < 3) or active TAO (29 orbits, CAS ≥3) were investigated retrospectively. All patients underwent ophthalmic evaluation and orbital magnetic resonance imaging. The severity of LGP and proptosis and the extraocular muscle (EOM) volume were measured. LGP and related factors were assessed by correlational and linear regression analyses. The value of LGP for discriminating the activity of TAO was evaluated by receiver-operating characteristic curve analysis. Results: The mean LGP was significantly higher in the active TAO group than in the inactive TAO group (P < 0.001). There were significant positive correlations between LGP severity and the CAS (r = 0.51, P < 0.001), proptosis (r = 0.72, P < 0.001), and EOM volume (superior rectus [r = 0.49, P < 0.001], inferior rectus [r = 0.47, P < 0.001], lateral rectus [r = 0.59, P < 0.001], medial rectus [r = 0.62, P < 0.001], superior oblique [r = 0.48, P < 0.001], and all EOMs [r = 0.59, P < 0.001]). Receiver-operating characteristic curve analysis revealed an LGP of 13.65 mm (area under the curve, 0.824; sensitivity, 79.3%; specificity, 81.4%) to be the cut-off value that differentiated active and inactive TAO. Conclusions: LGP measurements obtained from orbital magnetic resonance images were positively correlated with CAS, proptosis and EOM volume. The extent of LGP appears to be a good indicator of disease activity in patients with TAO.