Explore the vast range of titles available.

Strabismus, or eye misalignment, is a common condition affecting individuals of all ages. Early detection and accurate classification are essential for proper treatment and avoiding long-term complications. This research presents a new deep-learning-based approach for automatically identifying and classifying strabismus from facial images. The proposed methodology leverages Convolutional Neural Networks (CNNs) to achieve high accuracy in both binary (strabismus vs. normal) and multi-class (eight-class deviation angle for esotropia and exotropia) classification tasks. The dataset for binary classification consisted of 4,257 facial images, including 1,599 normal cases and 2,658 strabismus cases, while the multi-class classification involved 480 strabismic and 142 non-strabismic images. These images were labeled based on ophthalmologist measurements using the Alternate Prism Cover Test (APCT) or the Modified Krimsky Test (MK). Five-fold cross-validation was employed, and performance was evaluated using sensitivity, accuracy, F1-score, and recall metrics. The proposed deep learning model achieved an accuracy of 86.38% for binary classification and 92.7% for multi-class classification. These results demonstrate the potential of our approach to assist healthcare professionals in early strabismus detection and treatment planning, ultimately improving patient outcomes.

In this study, we propose a generative data augmentation technique to overcome the challenges of severely limited data when designing a deep learning-based automated strabismus diagnosis system. We implement a generative model based on the StyleGAN2-ADA model for system design and assess strabismus classification performance using two classifiers. We evaluate the capability of our proposed method against traditional data augmentation techniques and confirm a substantial enhancement in performance. Furthermore, we conduct experiments to explore the relationship between the diagnosis agreement among ophthalmologists and the generation performance of the generative model. Beyond FID, we validate the generative samples on the classifier to establish their practicality. Through these experiments, we demonstrate that the generative model-based data augmentation improves overall quantitative performance in scenarios of extreme data scarcity and effectively mitigates overfitting issues during deep learning model training.

Background Strabismus is a common ocular misalignment that can impair binocular vision if untreated. Conventional diagnosis and treatment rely on clinical prism diopter (PD) readings, which quantify deviation along with base direction. However, these values are coarse, manual, and subject to inter-clinician variability. Methods We present the development and results of StrabNet-CQ (Strabismus Network for Classification and Quantification), a newly developed deep learning-based framework for automated strabismus classification and quantification. Six hundred eye images, with and without strabismus, were analyzed by the model. A YOLOv8 model performs classification into normal and abnormal as well as subsequent classification (normal, esotropia, exotropia, hypertropia, hypotropia), with refined classification via ResNet101 on segmented eye regions from the images. Ocular landmarks are detected using ResNet18, from which horizontal and vertical deviation indices and angular deviation are computed. Results The system achieved 94% accuracy in strabismus detection and 90% in strabismus classification, with high sensitivity for normal (0.91–1.00), esotropia (0.89), and hypotropia (0.90). The derived parameters show a good correlation with manual PD values( r  = 0.733) that can be utilized for quantification of strabismus. Conclusion StrabNet-CQ supports objective diagnosis and holds promise for deployment in clinical settings for strabismus detection as well as quantification.

Background. Pediatricians are regularly involved in the initial examination of children presenting with strabismus, a common ocular condition occurring in 3% of children. The objective of this review was to gain insight into pediatric residents, fellows and attendings` understanding of strabismus, and to propose an etiology-based strabismus classification scheme to aid this understanding. Methods. A survey was conducted in a single Department of Pediatrics in a university academic institution in order to assess the degree of understanding of the classification, etiology and nomenclature of strabismus. A targeted literature review, pertinent to our classification scheme for strabismus in the pediatric age group, is provided to clarify the various underlying etiological conditions for pediatricians. Results. The surveyed cohort (n=26) consisted of 10 (38.5%) attendings and 16 (61.5%) pediatricians-in-training. Although 69% of survey participants felt comfortable performing an ocular motility evaluation, only 19% had a clear understanding of the underlying etiology of strabismus, 8% had a clear understanding of strabismus nomenclature and none of the participants had clear knowledge of a classification scheme of strabismus. We propose an etiologic-based strabismus classification scheme with streamlined nomenclature geared towards Pediatricians to facilitate the management of pediatric patients with various ocular misalignments. Eight major categories of this classification scheme include (1) physiologic, (2) comitant, (3) paralytic, (4) sensory, (5) syndromic, (6) orbital, (7) supranuclear and (8) pseudostrabismus. Conclusions. Pediatricians at all levels of professional experience have a limited command of strabismus. An etiology-based classification scheme of strabismus may assist in understanding the underlying causes and facilitate the management of strabismus in the pediatrician`s office.

Objective This study aimed to analyze the distribution of different types of strabismus surgery in a tertiary hospital in Central China during the three-year period of the COVID-19 pandemic. Methods A retrospective analysis was conducted on the clinical data of strabismus patients who underwent surgery and were admitted to the Department of Strabismus and Pediatric Ophthalmology at the First Affiliated Hospital of Zhengzhou University between January 2020 and December 2022. Results A total of 3939 strabismus surgery patients were collected, including 1357 in 2020, 1451 in 2021, and 1131 in 2022. The number of surgeries decreased significantly in February 2020, August 2021, and November and December 2022. Patients aged 0–6 years accounted for 37% of the total number of strabismus surgery patientsr. The majority (60%) of all strabismus surgery patients were diagnosed with exotropia, with intermittent exotropia accounting for the highest proportion (53%). There was no statistically significant difference in the proportion of intermittent exotropia and constant exotropia during the three-year period ( χ 2  = 2.642, P  = 0.267 and χ 2  = 3.012, P  = 0.221, respectively). Among patients with intermittent exotropia, insufficient convergence type was the most common form of strabismus (accounting for over 70%). Non-accommodative esotropia accounted for more than 50% of all internal strabismus cases. Conclusion During the period from 2020 to 2022, the total number of strabismus surgeries in our hospital did not show significant fluctuations, but there was a noticeable decrease in the number of surgeries during months affected by the pandemic. Exotropia accounted for the highest proportion among strabismus surgery patients. Intermittent exotropia was the most common type among patients undergoing surgery for exotropia, and the most prevalent subtype was the insufficient convergence type. The age distribution of patients varied in different months, with a concentration of surgeries for strabismus patients in the 7–12 years old age group during the months of July and August each year.

PurposeTo describe the types of strabismus operated on, the surgical procedures performed, and the 2-year reoperation rate in France.MethodsEntire population 5-year cross-sectional analysis of a national medico-administrative database in France between January 2013 and December 2017 included all patients who underwent a first strabismus surgery, with a 2-year follow-up. Patient identification was based on the diagnostic codes of the 10th International Classification of Diseases and surgical procedures on the codes of the Common Classification of Medical Acts. A subgroup analysis comparing non-paralytic and paralytic strabismus was performed.ResultsAmong the 56,654 patients included (women: 50.8%), 26,892 (47.5%) patients were under 10 years old. Overall, 52,711 (93%) were diagnosed with non-paralytic strabismus and 3,943 (7%) with paralytic strabismus. Among the non-paralytics, the most frequent diagnosis was esotropia (21,282, 37.6%), followed by exotropia (14,392, 25.4%) and vertical strabismus (2,017, 3.6%). Among the paralytics, fourth cranial nerve palsy (1,499, 2.6%) was more frequent than sixth cranial nerve palsy (691, 1.2%) and third cranial nerve palsy (431, 0.8%). The 2-year reoperation rate was 7.7% (4,362 patients), the lowest for non-paralytic (7.4%) and the highest for paralytic (11.4%).ConclusionThis first French population-based study about strabismus will contribute to the evaluation of practices at a national level and permit comparisons between countries. Although the 2-year reoperation rate was found to be 1 out of 13 patients, it should be interpreted with caution. Long-term follow-up is still warranted due to considerable variability of the type and severity of strabismus as well as surgical practices.

Strabismus (misalignment of the eyes; also known as “squint”) comprises a common heterogeneous group of disorders characterised by a constant or intermittent ocular deviation often associated with amblyopia (uniocular failure of normal visual development) and reduced or absent binocular vision. The associated poor cosmetic appearance may also interfere with social and psychological development. Extensive twin and family studies suggest a significant genetic component to the aetiology of strabismus. The complexity of the molecular basis of strabismus is now beginning to be elucidated with the identification of genetic loci and disease causing genes. Currently greater insights have been gained into the incomitant subtype (differing magnitude of ocular misalignment according to direction of gaze), whereas less is known about the pathogenesis of the more common childhood concomitant strabismus. It is hoped that a greater understanding of the molecular genetics of these disorders will lead to improved knowledge of disease mechanisms and ultimately to more effective treatment. The aim of this paper is to review current knowledge of the molecular genetics of both incomitant and concomitant strabismus.

To develop and validate an artificial intelligence pipeline for binary screening of horizontal strabismus versus orthotropia using smartphone-acquired facial images and geometric landmark analysis. This two-stage system combines Real-Time Detection Transformer (RT-DETR) to localize nine ocular landmarks per eye across three gaze directions (left, center, right), and supervised machine learning classifiers. A feature set of five biometric ratios was derived from coordinates including the canthi, limbi, and corneal light reflexes. The model was trained on facial images from 150 participants (96 with strabismus and 54 controls). To address class imbalance and improve generalizability, Synthetic Minority Oversampling Technique (SMOTE) and 4-fold cross-validation were applied. RT-DETR achieved an intersection over union of 0.62 and a mean center-point error of 6.52 pixels in landmark localization. The Random Forest classifier achieved an accuracy of 0.95, sensitivity of 0.96, specificity of 0.94, positive predictive value of 0.97, and negative predictive value of 0.92. This study demonstrates the feasibility of combining transformer-based landmark detection with geometric ratios for strabismus screening. The framework shows high performance under controlled conditions. While the use of biometric ratios allows for feature-level inspection, further research is required to establish full clinical interpretability and performance in uncontrolled environments.

Intermittent exotropia is classified according to the AC/A ratio. Convergence amplitude measured on a light includes accommodative convergence. Amplitude measured while maintaining clear, single, binocular vision on 20/30 print utilizes only true fusional convergence.