Artificial intelligence assisted pterygium diagnosis: current status and perspectives

Artificial Intelligence Applications in Ophthalmology

Ophthalmology is well suited for the integration of artificial intelligence (AI) owing to its reliance on various imaging modalities, such as anterior segment photography, fundus photography, and optical coherence tomography (OCT), which generate large volumes of high-resolution digital images. These images provide rich datasets for training AI algorithms, which enables precise diagnosis and monitoring of various ocular conditions. Retinal disease management heavily relies on image recognition. Limited access to ophthalmologists in underdeveloped areas and high image volumes in developed countries make AI a promising, cost-effective solution for screening and diagnosis. In corneal diseases, differential diagnosis is critical yet challenging because of the wide range of potential etiologies. AI and diagnostic technologies offer promise for improving the accuracy and speed of these diagnoses, including the differentiation between infectious and noninfectious conditions. Smartphone imaging coupled with AI technology can advance the diagnosis of anterior segment diseases, democratizing access to eye care and providing rapid and reliable diagnostic results. Other potential areas for AI applications include cataract and vitreous surgeries as well as the use of generative AI in training ophthalmologists. While AI offers substantial benefits, challenges remain, including the need for high-quality images, accurate manual annotations, patient heterogeneity considerations, and the "black-box phenomenon". Addressing these issues is crucial for enhancing the effectiveness of AI and ensuring its successful integration into clinical practice. AI is poised to transform ophthalmology by increasing diagnostic accuracy, optimizing treatment strategies, and improving patient care, particularly in high-risk or underserved populations.

Artificial intelligence in the anterior segment of eye diseases

Ophthalmology is a subject that highly depends on imaging examination. Artificial intelligence (AI) technology has great potential in medical imaging analysis, including image diagnosis, classification, grading, guiding treatment and evaluating prognosis. The combination of the two can realize mass screening of grass-roots eye health, making it possible to seek medical treatment in the mode of "first treatment at the grass-roots level, two-way referral, emergency and slow treatment, and linkage between the upper and lower levels". On the basis of summarizing the AI technology carried out by scholars and their teams all over the world in the field of ophthalmology, quite a lot of studies have confirmed that machine learning can assist in diagnosis, grading, providing optimal treatment plans and evaluating prognosis in corneal and conjunctival diseases, ametropia, lens diseases, glaucoma, iris diseases, etc. This paper systematically shows the application and progress of AI technology in common anterior segment ocular diseases, the current limitations, and prospects for the future.

Diabetic retinopathy identification based on multi-source-free domain adaptation

AIM

To address the challenges of data labeling difficulties, data privacy, and necessary large amount of labeled data for deep learning methods in diabetic retinopathy (DR) identification, the aim of this study is to develop a source-free domain adaptation (SFDA) method for efficient and effective DR identification from unlabeled data.

METHODS

A multi-SFDA method was proposed for DR identification. This method integrates multiple source models, which are trained from the same source domain, to generate synthetic pseudo labels for the unlabeled target domain. Besides, a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class distances. Validation is performed using three color fundus photograph datasets (APTOS2019, DDR, and EyePACS).

RESULTS

The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification tasks. It demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target domains.

CONCLUSION

The multi-SFDA method provides an effective approach to overcome the challenges in DR identification. The method not only addresses difficulties in data labeling and privacy issues, but also reduces the need for large amounts of labeled data required by deep learning methods, making it a practical tool for early detection and preservation of vision in diabetic patients.

Intermittent sliding-lock-knot suture for limbal conjunctival autograft fixation in pterygium surgery: a technique note

AIM

To report a technique used with intermittent sliding-lock-knot (ISLK) fixation for limbal conjunctival autografts in pterygium surgery and compared with those of routine intermittent (RI) fixation.

METHODS

Consecutive patients with primary pterygium who had undergone pterygium excision combined with limbal conjunctival autograft transplantation between March 2021 and March 2022 at our institute were retrospectively analyzed. Primary outcome measures were mean duration of surgery and suture removal, degree of conjunctival hyperemia on postoperative day 1, pain score at suture removal, postoperative symptoms at 6mo, including conjunctival hyperemia, foreign body sensation, and graft stability.

RESULTS

Ninety-eight patients underwent monocular surgery and were divided into ISLK (51 eyes) and RI (47 eyes) groups according to the type of conjunctiva autograft fixation method planned. There was no significant difference in mean duration of surgery between the two groups (18.59±2.39min vs 18.15±2.20min, P=0.417); however, compared to the RI group, shorter suture removal times were observed in the ISLK group [0.58min (0.42-0.87) vs 3.00min (2.21-4.15), P<0.001]. The degree of conjunctival hyperemia on postoperative day 1 was milder in the ISLK group (P<0.001). Pain scores at suture removal were lower in the ISLK group than in RI group [1 (0-3) vs 2 (1-4), P<0.001]. Postoperative symptoms at 6mo were comparable between the groups (P=0.487), with no recurrence.

CONCLUSION

ISLK is an innovative method for limbal conjunctival autograft fixation after pterygium excision. Compared to RI fixation, ISLK facilitates suture removal and reduces discomfort, with comparable surgery duration and less conjunctival hyperemia.

An ensemble deep learning diagnostic system for determining Clinical Activity Scores in thyroid-associated ophthalmopathy: integrating multi-view multimodal images from anterior segment slit-lamp photographs and facial images

Background

Thyroid-associated ophthalmopathy (TAO) is the most prevalent autoimmune orbital condition, significantly impacting patients' appearance and quality of life. Early and accurate identification of active TAO along with timely treatment can enhance prognosis and reduce the occurrence of severe cases. Although the Clinical Activity Score (CAS) serves as an effective assessment system for TAO, it is susceptible to assessor experience bias. This study aimed to develop an ensemble deep learning system that combines anterior segment slit-lamp photographs of patients with facial images to simulate expert assessment of TAO.

Method

The study included 156 patients with TAO who underwent detailed diagnosis and treatment at Shanxi Eye Hospital Affiliated to Shanxi Medical University from May 2020 to September 2023. Anterior segment slit-lamp photographs and facial images were used as different modalities and analyzed from multiple perspectives. Two ophthalmologists with more than 10 years of clinical experience independently determined the reference CAS for each image. An ensemble deep learning model based on the residual network was constructed under supervised learning to predict five key inflammatory signs (redness of the eyelids and conjunctiva, and swelling of the eyelids, conjunctiva, and caruncle or plica) associated with TAO, and to integrate these objective signs with two subjective symptoms (spontaneous retrobulbar pain and pain on attempted upward or downward gaze) in order to assess TAO activity.

Results

The proposed model achieved 0.906 accuracy, 0.833 specificity, 0.906 precision, 0.906 recall, and 0.906 F1-score in active TAO diagnosis, demonstrating advanced performance in predicting CAS and TAO activity signs compared to conventional single-view unimodal approaches. The integration of multiple views and modalities, encompassing both anterior segment slit-lamp photographs and facial images, significantly improved the prediction accuracy of the model for TAO activity and CAS.

Conclusion

The ensemble multi-view multimodal deep learning system developed in this study can more accurately assess the clinical activity of TAO than traditional methods that solely rely on facial images. This innovative approach is intended to enhance the efficiency of TAO activity assessment, providing a novel means for its comprehensive, early, and precise evaluation.

DBPF-net: dual-branch structural feature extraction reinforcement network for ocular surface disease image classification

Pterygium and subconjunctival hemorrhage are two common types of ocular surface diseases that can cause distress and anxiety in patients. In this study, 2855 ocular surface images were collected in four categories: normal ocular surface, subconjunctival hemorrhage, pterygium to be observed, and pterygium requiring surgery. We propose a diagnostic classification model for ocular surface diseases, dual-branch network reinforced by PFM block (DBPF-Net), which adopts the conformer model with two-branch architectural properties as the backbone of a four-way classification model for ocular surface diseases. In addition, we propose a block composed of a patch merging layer and a FReLU layer (PFM block) for extracting spatial structure features to further strengthen the feature extraction capability of the model. In practice, only the ocular surface images need to be input into the model to discriminate automatically between the disease categories. We also trained the VGG16, ResNet50, EfficientNetB7, and Conformer models, and evaluated and analyzed the results of all models on the test set. The main evaluation indicators were sensitivity, specificity, F1-score, area under the receiver operating characteristics curve (AUC), kappa coefficient, and accuracy. The accuracy and kappa coefficient of the proposed diagnostic model in several experiments were averaged at 0.9789 and 0.9681, respectively. The sensitivity, specificity, F1-score, and AUC were, respectively, 0.9723, 0.9836, 0.9688, and 0.9869 for diagnosing pterygium to be observed, and, respectively, 0.9210, 0.9905, 0.9292, and 0.9776 for diagnosing pterygium requiring surgery. The proposed method has high clinical reference value for recognizing these four types of ocular surface images.