Adopting machine learning to automatically identify candidate patients for corneal refractive surgery

Development of oculomics artificial intelligence for cardiovascular risk factors: A case study in fundus oculomics for HbA1c assessment and clinically relevant considerations for clinicians

Artificial Intelligence (AI) is transforming healthcare, notably in ophthalmology, where its ability to interpret images and data can significantly enhance disease diagnosis and patient care. Recent developments in oculomics, the integration of ophthalmic features to develop biomarkers for systemic diseases, have demonstrated the potential for providing rapid, non-invasive methods of screening leading to enhance in early detection and improve healthcare quality, particularly in underserved areas. However, the widespread adoption of such AI-based technologies faces challenges primarily related to the trustworthiness of the system. We demonstrate the potential and considerations needed to develop trustworthy AI in oculomics through a pilot study for HbA1c assessment using an AI-based approach. We then discuss various challenges, considerations, and solutions that have been developed for powerful AI technologies in the past in healthcare and subsequently apply these considerations to the oculomics pilot study. Building upon the observations in the study we highlight the challenges and opportunities for advancing trustworthy AI in oculomics. Ultimately, oculomics presents as a powerful and emerging technology in ophthalmology and understanding how to optimize transparency prior to clinical adoption is of utmost importance.

Comparison of early visual outcomes after SMILE using VISUMAX 800 and VISUMAX 500 for myopia: a retrospective matched case-control study

VISUMAX 800 was introduced to improve the patient experience and clinical outcomes of small incision lenticule extraction (SMILE). This was a retrospective, matched, and case-control study (1:2) controlled for preoperative central corneal thickness and refractive error that compared early refractive and visual outcomes after SMILE using VISUMAX 800 and VISUMAX 500 to treat myopia. We included 50 eyes that underwent the VISUMAX 800 SMILE and 100 eyes that underwent the VISUMAX 500 SMILE. SMILE using VISUMAX 800 was performed using the CentraLign aid for vertex centration. Cyclotorsion was controlled by an OcuLign assistant in the VISUMAX 800 group after corneal marking. Corneal higher-order aberrations (HOAs) were evaluated using a Pentacam 1 month after surgery. No differences were observed in the pre- and post-operative refractive and visual outcomes at 1 day, 1 month, and 6 months after surgery. VISUMAX 800 induced less total HOAs than VISUMAX 500 (P = 0.036). No statistically significant differences were observed in the amounts of induced spherical aberrations or vertical and horizontal comas. No differences were observed in the 1 month and 6 months refractive and visual outcomes between two SMILE procedures, except for VISUMAX 800, which resulted in lower postoperative total HOAs than VISUMAX 500.

Corneal Stroma Analysis and Related Ocular Manifestations in Recovered COVID-19 Patients

Purpose

The purpose of this study was to assess the impact of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) on corneal stroma characteristics, ocular manifestations, and post-recovery refractive surgery outcomes after varying recovery durations.

Methods

Fresh corneal lenticules from patients with post-coronavirus disease 2019 (COVID-19; recovered within 135 days) and healthy controls (HCs) after small incision lenticule extraction (SMILE) surgery were obtained for experimental validation of SARS-CoV-2 susceptibility, morphological changes, and immune response of the corneal stroma. Corneal optical density (CD) was measured using the Pentacam HR. Corneal epithelium thickness (ET) and endothelium parameters were evaluated by wide-field optical coherence tomography (OCT) and non-contact specular microscopy (SP-1P), respectively. All the patients were assessed after SMILE surgery until 3 month of follow-up.

Results

The cornea was susceptible to SARS-CoV-2 with the presence of SARS-CoV-2 receptors (CD147 and ACE2) and spike protein remnants (4 out of 58) in post-recovery corneal lenticules. Moreover, SARS-CoV-2 infection triggered immune responses in the corneal stroma, with elevated IL-6 levels observed between 45 and 75 days post-recovery, which were then lower at around day 105. Concurrently, corneal mid-stromal nerve length and branching were initially higher in the 60D to 75D group and returned to control levels by day 135. A similar trend was observed in CD within zones 0 to 2 and 2 to 6 and in the hexagonal cells (HEX) ratio in endothelial cells, whereas ET remained consistent. Notably, these changes did not affect the efficacy, safety, or predictability of post-recovery SMILE surgery.

Conclusions

SARS-CoV-2 induces temporal alterations in corneal stromal morphology and function post-recovery. These findings provided a theoretical basis for corneal health and refractive surgery management in the post-COVID-19 milieu.

Diagnosis of Forme Fruste Keratoconus Using Corvis ST Sequences with Digital Image Correlation and Machine Learning

PURPOSE

This study aimed to employ the incremental digital image correlation (DIC) method to obtain displacement and strain field data of the cornea from Corvis ST (CVS) sequences and access the performance of embedding these biomechanical data with machine learning models to distinguish forme fruste keratoconus (FFKC) from normal corneas.

METHODS

100 subjects were categorized into normal (N = 50) and FFKC (N = 50) groups. Image sequences depicting the horizontal cross-section of the human cornea under air puff were captured using the Corvis ST tonometer. The high-speed evolution of full-field corneal displacement, strain, velocity, and strain rate was reconstructed utilizing the incremental DIC approach. Maximum (max-) and average (ave-) values of full-field displacement V, shear strain γxy, velocity VR, and shear strain rate γxyR were determined over time, generating eight evolution curves denoting max-V, max-γxy, max-VR, max-γxyR, ave-V, ave-γxy, ave-VR, and ave-γxyR, respectively. These evolution data were inputted into two machine learning (ML) models, specifically Naïve Bayes (NB) and Random Forest (RF) models, which were subsequently employed to construct a voting classifier. The performance of the models in diagnosing FFKC from normal corneas was compared to existing CVS parameters.

RESULTS

The Normal group and the FFKC group each included 50 eyes. The FFKC group did not differ from healthy controls for age (p = 0.26) and gender (p = 0.36) at baseline, but they had significantly lower bIOP (p < 0.001) and thinner central cornea thickness (CCT) (p < 0.001). The results demonstrated that the proposed voting ensemble model yielded the highest performance with an AUC of 1.00, followed by the RF model with an AUC of 0.99. Radius and A2 Time emerged as the best-performing CVS parameters with AUC values of 0.948 and 0.938, respectively. Nonetheless, no existing Corvis ST parameters outperformed the ML models. A progressive enhancement in performance of the ML models was observed with incremental time points during the corneal deformation.

CONCLUSION

This study represents the first instance where displacement and strain data following incremental DIC analysis of Corvis ST images were integrated with machine learning models to effectively differentiate FFKC corneas from normal ones, achieving superior accuracy compared to existing CVS parameters. Considering biomechanical responses of the inner cornea and their temporal pattern changes may significantly improve the early detection of keratoconus.

Assessment of Changes in Cap and Residual Stromal Thickness Values during a 6-Month Observation after Refractive Lenticule Extraction Small Incision Lenticule Extraction

Background: In this study, the changes in corneal cap and residual stromal thickness (RST) values during a 180-day observation period after refractive lenticule extraction small incision lenticule extraction (ReLEx SMILE) were assessed. Methods: Fifty patients underwent ReLEx SMILE using the VisuMax 500 femtosecond laser, with corneal imaging conducted pre and post procedure via anterior segment optical coherence tomography (AS-OCT). Cap thickness in the center and 1.5 mm from the center in four meridians was measured at various intervals. Results: The results showed a significant decrease in cap thickness 180 days post procedure compared to earlier intervals (p < 0.05). Similarly, RST decreased gradually and significantly post procedure (p < 0.05). Notably, changes in cap thickness within the central 1.5 mm area were more dynamic than RST changes during the 6-month observation period following SMILE. Conclusions: The corneal cap thickness measured with swept-source AS-OCT within the central 1.5 mm area underwent more dynamic changes than the residual stromal thickness during the 6-month observation following SMILE.

Choice of refractive surgery types for myopia assisted by machine learning based on doctors' surgical selection data

In recent years, corneal refractive surgery has been widely used in clinics as an effective means to restore vision and improve the quality of life. When choosing myopia-refractive surgery, it is necessary to comprehensively consider the differences in equipment and technology as well as the specificity of individual patients, which heavily depend on the experience of ophthalmologists. In our study, we took advantage of machine learning to learn about the experience of ophthalmologists in decision-making and assist them in the choice of corneal refractive surgery in a new case. Our study was based on the clinical data of 7,081 patients who underwent corneal refractive surgery between 2000 and 2017 at the Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences. Due to the long data period, there were data losses and errors in this dataset. First, we cleaned the data and deleted the samples of key data loss. Then, patients were divided into three groups according to the type of surgery, after which we used SMOTE technology to eliminate imbalance between groups. Six statistical machine learning models, including NBM, RF, AdaBoost, XGBoost, BP neural network, and DBN were selected, and a ten-fold cross-validation and grid search were used to determine the optimal hyperparameters for better performance. When tested on the dataset, the multi-class RF model showed the best performance, with agreement with ophthalmologist decisions as high as 0.8775 and Macro F1 as high as 0.8019. Furthermore, the results of the feature importance analysis based on the SHAP technique were consistent with an ophthalmologist's practical experience. Our research will assist ophthalmologists in choosing appropriate types of refractive surgery and will have beneficial clinical effects.

Artificial Intelligence in Ophthalmic Surgery: Current Applications and Expectations

Artificial Intelligence (AI) has found rapidly growing applications in ophthalmology, achieving robust recognition and classification in most kind of ocular diseases. Ophthalmic surgery is one of the most delicate microsurgery, requiring high fineness and stability of surgeons. The massive demand of the AI assist ophthalmic surgery will constitute an important factor in boosting accelerate precision medicine. In clinical practice, it is instrumental to update and review the considerable evidence of the current AI technologies utilized in the investigation of ophthalmic surgery involved in both the progression and innovation of precision medicine. Bibliographic databases including PubMed and Google Scholar were searched using keywords such as "ophthalmic surgery", "surgical selection", "candidate screening", and "robot-assisted surgery" to find articles about AI technology published from 2018 to 2023. In addition to the Editorials and letters to the editor, all types of approaches are considered. In this paper, we will provide an up-to-date review of artificial intelligence in eye surgery, with a specific focus on its application to candidate screening, surgery selection, postoperative prediction, and real-time intraoperative guidance.

Prediction of SMILE surgical cutting formula based on back propagation neural network

AIM

To predict cutting formula of small incision lenticule extraction (SMILE) surgery and assist clinicians in identifying candidates by deep learning of back propagation (BP) neural network.

METHODS

A prediction program was developed by a BP neural network. There were 13 188 pieces of data selected as training validation. Another 840 eye samples from 425 patients were recruited for reverse verification of training results. Precision of prediction by BP neural network and lenticule thickness error between machine learning and the actual lenticule thickness in the patient data were measured.

RESULTS

After training 2313 epochs, the predictive SMILE cutting formula BP neural network models performed best. The values of mean squared error and gradient are 0.248 and 4.23, respectively. The scatterplot with linear regression analysis showed that the regression coefficient in all samples is 0.99994. The final error accuracy of the BP neural network is -0.003791±0.4221102 µm.

CONCLUSION

With the help of the BP neural network, the program can calculate the lenticule thickness and residual stromal thickness of SMILE surgery accurately. Combined with corneal parameters and refraction of patients, the program can intelligently and conveniently integrate medical information to identify candidates for SMILE surgery.

Comparison of Vision Correction and Corneal Thickness at 180-Day Follow-Up After Femtosecond Laser-Assisted In-Situ Keratomileusis (FS-LASIK), Photorefractive Keratectomy (PRK), and Small Incision Lenticule Extraction (SMILE): A Study from a Single Center in Poland of 120 Patients with Myopia

BACKGROUND This study from a single center in Poland included 120 patients with myopia, and the aim was to compare vision correction and corneal thickness at the 180-day follow-up after femtosecond laser-assisted in-situ keratomileusis (FS-LASIK), photorefractive keratectomy (PRK), or small incision lenticule extraction (SMILE). MATERIAL AND METHODS The effectiveness and safety of laser vision correction (LVC) procedures were evaluated by determining pre- and post-procedure uncorrected distance visual acuity (UDVA) and corrected distance visual acuity (CDVA) values on the Snell chart. Twenty patients with diagnosed mild myopia (sphere maximum -3.0 diopters D; cylinder maximum 0.5 D) were qualified for PRK surgery. Fifty patients with diagnosed intolerance (sphere maximum -6.0 D; cylinder maximum 5.0 D) were eligible for the FS-LASIK procedure. Fifty patients with diagnosed myopia (sphere maximum -6.0 D cylinder 3.5 D) were qualified for the SMILE procedure. RESULTS Regardless of which procedure was performed, both UDVA and CDVA improved significantly postoperatively (P<0.05). In addition, the UDVA and CDVA values were similar in the postoperative period (P>0.05). For each procedure, the EI was no less than 0.94. Regardless of which type of LVC procedure was performed, CET at the center and 1.5 mm from the center in 4 meridians thickened, and this change was not statistically significant over the observation period (P>0.05). CONCLUSIONS Our analysis demonstrated similar effectiveness of the 3 methods - PRK, FS-LASIK, and SMILE - in patients with mild and moderate myopia.

Predicting Postoperative Anterior Chamber Angle for Phakic Intraocular Lens Implantation Using Preoperative Anterior Segment Metrics

Purpose

The anterior chamber angle (ACA) is a critical factor in posterior chamber phakic intraocular lens (EVO Implantable Collamer Lens [ICL]) implantation. Herein, we predicted postoperative ACAs to select the optimal ICL size to reduce narrow ACA-related complications.

Methods

Regression models were constructed using pre-operative anterior segment optical coherence tomography metrics to predict postoperative ACAs, including trabecular-iris angles (TIAs) and scleral-spur angles (SSAs) at 500 µm and 750 µm from the scleral spur (TIA500, TIA750, SSA500, and SSA750). Data from three expert surgeons were assigned to the development (N = 430 eyes) and internal validation (N = 108 eyes) datasets. Additionally, data from a novice surgeon (N = 42 eyes) were used for external validation.

Results

Postoperative ACAs were highly predictable using the machine-learning (ML) technique (extreme gradient boosting regression [XGBoost]), with mean absolute errors (MAEs) of 4.42 degrees, 3.77 degrees, 5.25 degrees, and 4.30 degrees for TIA500, TIA750, SSA500, and SSA750, respectively, in internal validation. External validation also showed MAEs of 3.93 degrees, 3.86 degrees, 5.02 degrees, and 4.74 degrees for TIA500, TIA750, SSA500, and SSA750, respectively. Linear regression using the pre-operative anterior chamber depth, anterior chamber width, crystalline lens rise, TIA, and ICL size also exhibited good performance, with no significant difference compared with XGBoost in the validation sets.

Conclusions

We developed linear regression and ML models to predict postoperative ACAs for ICL surgery anterior segment metrics. These will prevent surgeons from overlooking the risks associated with the narrowing of the ACA.

Translational Relevance

Using the proposed algorithms, surgeons can consider the postoperative ACAs to increase surgical accuracy and safety.

Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives

Background

The ophthalmology field was among the first to adopt artificial intelligence (AI) in medicine. The availability of digitized ocular images and substantial data have made deep learning (DL) a popular topic.

Main text

At the moment, AI in ophthalmology is mostly used to improve disease diagnosis and assist decision-making aiming at ophthalmic diseases like diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), cataract and other anterior segment diseases. However, most of the AI systems developed to date are still in the experimental stages, with only a few having achieved clinical applications. There are a number of reasons for this phenomenon, including security, privacy, poor pervasiveness, trust and explainability concerns.

Conclusions

This review summarizes AI applications in ophthalmology, highlighting significant clinical considerations for adopting AI techniques and discussing the potential challenges and future directions.

Recent advances of aggregation-induced emission materials for fluorescence image-guided surgery

Real-time intraoperative guidance is essential during various surgical treatment of many diseases. Aggregation-induced emission (AIE) materials have shown great potential for guiding surgeons during complex interventions, with the merits of deep tissue penetration, high quantum yield, high molar absorptivity, low background, good targeting ability and excellent photostability. Herein, we provided insights to design efficient AIE materials regarding three key parameters, i.e., deep-tissue penetration ability, high brightness of AIE luminogens (AIEgens), and precise tumor/other pathology nidus targeting strategies, for realizing better application of fluorescence image-guided surgery. Representative interdisciplinary achievements were outlined for the demonstration of this emerging field. Challenges and future opportunities of AIE materials were briefly discussed. The aim of this review is to provide a comprehensive view of AIE materials for intraoperative guidance for researchers and surgeons, and to inspire more further correlational studies in the new frontiers of image-guided surgery.

Machine learning predicting myopic regression after corneal refractive surgery using preoperative data and fundus photography

PURPOSE

Myopic regression after surgery is the most common long-term complication of refractive surgery, but it is difficult to identify myopic regression without long-term observation. This study aimed to develop machine learning models to identify high-risk patients for refractive regression based on preoperative data and fundus photography.

METHODS

This retrospective study assigned subjects to the training (n = 1606 eyes) and validation (n = 403 eyes) datasets with chronological data splitting. Machine learning models with ResNet50 (for image analysis) and XGBoost (for integration of all variables and fundus photography) were developed based on subjects who underwent corneal refractive surgery. The primary outcome was the predictive performance for the presence of myopic regression at 4 years of follow-up examination postoperatively.

RESULTS

By integrating all factors and fundus photography, the final combined machine learning model showed good performance to predict myopic regression of more than 0.5 D (area under the receiver operating characteristic curve [ROC-AUC], 0.753; 95% confidence interval [CI], 0.710-0.793). The performance of the final model was better than the single ResNet50 model only using fundus photography (ROC-AUC, 0.673; 95% CI, 0.627-0.716). The top-five most important input features were fundus photography, preoperative anterior chamber depth, planned ablation thickness, age, and preoperative central corneal thickness.

CONCLUSION

Our machine learning algorithm provides an efficient strategy to identify high-risk patients with myopic regression without additional labor, cost, and time. Surgeons might benefit from preoperative risk assessment of myopic regression, patient counseling before surgery, and surgical option decisions.

Evaluation of machine learning algorithms for trabeculectomy outcome prediction in patients with glaucoma

The purpose of this study was to evaluate the performance of machine learning algorithms to predict trabeculectomy surgical outcomes. Preoperative systemic, demographic and ocular data from consecutive trabeculectomy surgeries from a single academic institution between January 2014 and December 2018 were incorporated into models using random forest, support vector machine, artificial neural networks and multivariable logistic regression. Mean area under the receiver operating characteristic curve (AUC) and accuracy were used to evaluate the discrimination of each model to predict complete success of trabeculectomy surgery at 1 year. The top performing model was optimized using recursive feature selection and hyperparameter tuning. Calibration and net benefit of the final models were assessed. Among the 230 trabeculectomy surgeries performed on 184 patients, 104 (45.2%) were classified as complete success. Random forest was found to be the top performing model with an accuracy of 0.68 and AUC of 0.74 using 5-fold cross-validation to evaluate the final optimized model. These results provide evidence that machine learning models offer value in predicting trabeculectomy outcomes in patients with refractory glaucoma.

Underrepresented Populations in Pediatric Epilepsy Surgery

As awareness of pediatric epilepsy increases, accompanied by advancements in technology and research, it is important to identify certain types of patients that are overlooked for surgical management of epilepsy. Identifying these populations will allow us to study and elucidate the factors contributing to the underutilization and/or delayed application of surgical interventions. Demographically, African-American and Hispanic patients, as well as patients of certain Asian ethnicities, have relatively lower rates of undergoing epilepsy surgery than non-Hispanic and white patients. Among patients with epilepsy, those with higher odds of seizure-freedom following surgery are more likely to be referred for surgical evaluation by their neurologists, with the most common diagnosis being lesional focal epilepsy. However, patients with multifocal or generalized epilepsy, genetic etiologies, or normal (non-lesional) brain magnetic resonance imaging (MRI) are less likely be to referred for evaluation for resective surgery. With an increasing number of high-quality imaging modalities to help localize the epileptogenic zone as well as new techniques for both curative and palliative epilepsy surgery, there are very few populations of patients and/or types of epilepsy that should be precluded from evaluation to determine the suitability of epilepsy surgery. Ultimately, a clearer understanding of the populations who are underrepresented among those considered for epilepsy surgery, coupled with further study of the underlying reasons for this trend, will lead to less disparity in access to this critical treatment among patients with epilepsy.

Development of a Web-Based Ensemble Machine Learning Application to Select the Optimal Size of Posterior Chamber Phakic Intraocular Lens

Purpose

Selecting the optimal lens size by predicting the postoperative vault can reduce complications after implantation of an implantable collamer lens with a central-hole (ICL with KS-aquaport). We built a web-based machine learning application that incorporated clinical measurements to predict the postoperative ICL vault and select the optimal ICL size.

Methods

We applied the stacking ensemble technique based on eXtreme Gradient Boosting (XGBoost) and a light gradient boosting machine to pre-operative ocular data from two eye centers to predict the postoperative vault. We assigned the Korean patient data to a training (N = 2756 eyes) and internal validation (N = 693 eyes) datasets (prospective validation). Japanese patient data (N = 290 eyes) were used as an independent external dataset from different centers to validate the model.

Results

We developed an ensemble model that showed statistically better performance with a lower mean absolute error for ICL vault prediction (106.88 µm and 143.69 µm in the internal and external validation, respectively) than the other machine learning techniques and the classic ICL sizing methods did when applied to both validation datasets. Considering the lens size selection accuracy, our proposed method showed the best performance for both reference datasets (75.9% and 67.4% in the internal and external validation, respectively).

Conclusions

Applying the ensemble approach to a large dataset of patients who underwent ICL implantation resulted in a more accurate prediction of vault size and selection of the optimal ICL size.

Translational Relevance

We developed a web-based application for ICL sizing to facilitate the use of machine learning calculators for clinicians.

Adopting low-shot deep learning for the detection of conjunctival melanoma using ocular surface images

BACKGROUND AND OBJECTIVE

The purpose of the present study was to investigate low-shot deep learning models applied to conjunctival melanoma detection using a small dataset with ocular surface images.

METHODS

A dataset was composed of anonymized images of four classes; conjunctival melanoma (136), nevus or melanosis (93), pterygium (75), and normal conjunctiva (94). Before training involving conventional deep learning models, two generative adversarial networks (GANs) were constructed to augment the training dataset for low-shot learning. The collected data were randomly divided into training (70%), validation (10%), and test (20%) datasets. Moreover, 3D melanoma phantoms were designed to build an external validation set using a smartphone. The GoogleNet, InceptionV3, NASNet, ResNet50, and MobileNetV2 architectures were trained through transfer learning and validated using the test and external validation datasets.

RESULTS

The deep learning model demonstrated a significant improvement in the classification accuracy of conjunctival lesions using synthetic images generated by the GAN models. MobileNetV2 with GAN-based augmentation displayed the highest accuracy of 87.5% in the four-class classification and 97.2% in the binary classification for the detection of conjunctival melanoma. It showed an accuracy of 94.0% using 3D melanoma phantom images captured using a smartphone camera.

CONCLUSIONS

The present study described a low-shot deep learning model that can detect conjunctival melanomas using ocular surface images. To the best of our knowledge, this study is the first to develop a deep learning model to detect conjunctival melanoma using a digital imaging device such as smartphone camera.

Computer-aided detection and abnormality score for the outer retinal layer in optical coherence tomography

BACKGROUND

To develop computer-aided detection (CADe) of ORL abnormalities in the retinal pigmented epithelium, interdigitation zone and ellipsoid zone via optical coherence tomography (OCT).

METHODS

In this retrospective study, healthy participants with normal ORL, and patients with abnormality of ORL including choroidal neovascularisation (CNV) or retinitis pigmentosa (RP) were included. First, an automatic segmentation deep learning (DL) algorithm, CADe, was developed for the three outer retinal layers using 120 handcraft masks of ORL. This automatic segmentation algorithm generated 4000 segmentations, which included 2000 images with normal ORL and 2000 (1000 CNV and 1000 RP) images with focal or wide defects in ORL. Second, based on the automatically generated segmentation images, a binary classifier (normal vs abnormal) was developed. Results were evaluated by area under the receiver operating characteristic curve (AUC).

RESULTS

The DL algorithm achieved an AUC of 0.984 (95% CI 0.976 to 0.993) for individual image evaluation in the internal test set of 797 images. In addition, performance analysis of a publicly available external test set (n=968) had an AUC of 0.957 (95% CI 0.944 to 0.970) and a second clinical external test set (n=1124) had an AUC of 0.978 (95% CI 0.970 to 0.986). Moreover, the CADe highlighted well normal parts of ORL and omitted highlights in abnormal ORLs of CNV and RP.

CONCLUSION

The CADe can use OCT images to segment ORL and differentiate between normal ORL and abnormal ORL. The CADe classifier also performs visualisation and may aid future physician diagnosis and clinical applications.

Neuronal-epithelial cell alignment: A determinant of health and disease status of the cornea

PURPOSE

How sensory neurons and epithelial cells interact with one another, and whether this association can be considered an indicator of health or disease is yet to be elucidated.

METHODS

Herein, we used the cornea, Confetti mice, a novel image segmentation algorithm for intraepithelial corneal nerves which was compared to and validated against several other analytical platforms, and three mouse models to delineate this paradigm. For aging, eyes were collected from 2 to 52 week-old normal C57BL/6 mice (n ≥ 4/time-point). For wound-healing and limbal stem cell deficiency, 7 week-old mice received a limbal-sparing or limbal-to-limbal epithelial debridement to their right cornea, respectively. Eyes were collected 2-16 weeks post-injury (n=4/group/time-point), corneas procured, immunolabelled with βIII-tubulin, flat-mounted, imaged by scanning confocal microscopy and analyzed for nerve and epithelial-specific parameters.

RESULTS

Our data indicate that nerve features are dynamic during aging and their curvilinear arrangement align with corneal epithelial migratory tracks. Moderate corneal injury prompted axonal regeneration and recovery of nerve fiber features. Limbal stem cell deficient corneas displayed abnormal nerve morphology, and fibers no longer aligned with corneal epithelial migratory tracks. Mechanistically, we discovered that nerve pattern restoration relies on the number and distribution of stromal-epithelial nerve penetration sites.

CONCLUSIONS

Microstructural changes to innervation may explain corneal complications related to aging and/or disease and facilitate development of new assays for diagnosis and/or classification of ocular and systemic diseases.

Application of Artificial Intelligence in the Diagnosis and Management of Corneal Diseases

Diagnosis and treatment planning in ophthalmology heavily depend on clinical examination and advanced imaging modalities, which can be time-consuming and carry the risk of human error. Artificial intelligence (AI) and deep learning (DL) are being used in different fields of ophthalmology and in particular, when running diagnostics and predicting outcomes of anterior segment surgeries. This review will evaluate the recent developments in AI for diagnostics, surgical interventions, and prognosis of corneal diseases. It also provides a brief overview of the newer AI dependent modalities in corneal diseases.

Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing

The macroscopic properties of permanent magnets and the resultant performance required for real implementations are determined by the magnets’ microscopic features. However, earlier micromagnetic simulations and experimental studies required relatively a lot of work to gain any complete and comprehensive understanding of the relationships between magnets’ macroscopic properties and their microstructures. Here, by means of supervised learning, we predict reliable values of coercivity (μ₀H_c) and maximum magnetic energy product (BH_max) of granular NdFeB magnets according to their microstructural attributes (e.g. inter-grain decoupling, average grain size, and misalignment of easy axes) based on numerical datasets obtained from micromagnetic simulations. We conducted several tests of a variety of supervised machine learning (ML) models including kernel ridge regression (KRR), support vector regression (SVR), and artificial neural network (ANN) regression. The hyper-parameters of these models were optimized by a very fast simulated annealing (VFSA) algorithm with an adaptive cooling schedule. In our datasets of randomly generated 1,000 polycrystalline NdFeB cuboids with different microstructural attributes, all of the models yielded similar results in predicting both μ₀H_c and BH_max. Furthermore, some outliers, which deteriorated the normality of residuals in the prediction of BH_max, were detected and further analyzed. Based on all of our results, we can conclude that our ML approach combined with micromagnetic simulations provides a robust framework for optimal design of microstructures for high-performance NdFeB magnets.

Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification

Deep learning (DL) has been successfully applied to the diagnosis of ophthalmic diseases. However, rare diseases are commonly neglected due to insufficient data. Here, we demonstrate that few-shot learning (FSL) using a generative adversarial network (GAN) can improve the applicability of DL in the optical coherence tomography (OCT) diagnosis of rare diseases. Four major classes with a large number of datasets and five rare disease classes with a few-shot dataset are included in this study. Before training the classifier, we constructed GAN models to generate pathological OCT images of each rare disease from normal OCT images. The Inception-v3 architecture was trained using an augmented training dataset, and the final model was validated using an independent test dataset. The synthetic images helped in the extraction of the characteristic features of each rare disease. The proposed DL model demonstrated a significant improvement in the accuracy of the OCT diagnosis of rare retinal diseases and outperformed the traditional DL models, Siamese network, and prototypical network. By increasing the accuracy of diagnosing rare retinal diseases through FSL, clinicians can avoid neglecting rare diseases with DL assistance, thereby reducing diagnosis delay and patient burden.

Part 1: Artificial intelligence technology in surgery

Artificial intelligence (AI) is one of the disruptive technologies of the fourth Industrial Revolution that is changing our work practices. This technology is in use in highly diverse industries including health care, defence, insurance and e-commerce. This review focuses on the relevance of AI to surgery. AI will aid surgeons with diagnostic decision-making, patient selection for surgery as well as improve patient pre- and post-operative care and management. Ethical considerations of AI with respect to patient rights and data privacy are highlighted. A further challenge is how best to present to national regulators a pragmatic way to assess AI as 'software as a medical device'. This relates to the ramifications for the adoption of AI technology in clinical practice, and its subsequent public funding support and reimbursement. It is evident that AI technology has important applications in surgery in the 21st century. The establishment of a key work programme in this area will be important if surgeons are to fully utilize AI in surgery.

Detection of features associated with neovascular age-related macular degeneration in ethnically distinct data sets by an optical coherence tomography: trained deep learning algorithm

BACKGROUND

The ability of deep learning (DL) algorithms to identify eyes with neovascular age-related macular degeneration (nAMD) from optical coherence tomography (OCT) scans has been previously established. We herewith evaluate the ability of a DL model, showing excellent performance on a Korean data set, to generalse onto an American data set despite ethnic differences. In addition, expert graders were surveyed to verify if the DL model was appropriately identifying lesions indicative of nAMD on the OCT scans.

METHODS

Model development data set-12 247 OCT scans from South Korea; external validation data set-91 509 OCT scans from Washington, USA. In both data sets, normal eyes or eyes with nAMD were included. After internal testing, the algorithm was sent to the University of Washington, USA, for external validation. Area under the receiver operating characteristic curve (AUC) and precision-recall curve (AUPRC) were calculated. For model explanation, saliency maps were generated using Guided GradCAM.

RESULTS

On external validation, AUC and AUPRC remained high at 0.952 (95% CI 0.942 to 0.962) and 0.891 (95% CI 0.875 to 0.908) at the individual level. Saliency maps showed that in normal OCT scans, the fovea was the main area of interest; in nAMD OCT scans, the appropriate pathological features were areas of model interest. Survey of 10 retina specialists confirmed this.

CONCLUSION

Our DL algorithm exhibited high performance for nAMD identification in a Korean population, and generalised well to an ethnically distinct, American population. The model correctly focused on the differences within the macular area to extract features associated with nAMD.

Artificial intelligence for anterior segment diseases: Emerging applications in ophthalmology

With the advancement of computational power, refinement of learning algorithms and architectures, and availability of big data, artificial intelligence (AI) technology, particularly with machine learning and deep learning, is paving the way for 'intelligent' healthcare systems. AI-related research in ophthalmology previously focused on the screening and diagnosis of posterior segment diseases, particularly diabetic retinopathy, age-related macular degeneration and glaucoma. There is now emerging evidence demonstrating the application of AI to the diagnosis and management of a variety of anterior segment conditions. In this review, we provide an overview of AI applications to the anterior segment addressing keratoconus, infectious keratitis, refractive surgery, corneal transplant, adult and paediatric cataracts, angle-closure glaucoma and iris tumour, and highlight important clinical considerations for adoption of AI technologies, potential integration with telemedicine and future directions.

Combining magnetoencephalography with magnetic resonance imaging enhances learning of surrogate-biomarkers

Electrophysiological methods, that is M/EEG, provide unique views into brain health. Yet, when building predictive models from brain data, it is often unclear how electrophysiology should be combined with other neuroimaging methods. Information can be redundant, useful common representations of multimodal data may not be obvious and multimodal data collection can be medically contraindicated, which reduces applicability. Here, we propose a multimodal model to robustly combine MEG, MRI and fMRI for prediction. We focus on age prediction as a surrogate biomarker in 674 subjects from the Cam-CAN dataset. Strikingly, MEG, fMRI and MRI showed additive effects supporting distinct brain-behavior associations. Moreover, the contribution of MEG was best explained by cortical power spectra between 8 and 30 Hz. Finally, we demonstrate that the model preserves benefits of stacking when some data is missing. The proposed framework, hence, enables multimodal learning for a wide range of biomarkers from diverse types of brain signals.

CycleGAN-based deep learning technique for artifact reduction in fundus photography

PURPOSE

A low quality of fundus photograph with artifacts may lead to false diagnosis. Recently, a cycle-consistent generative adversarial network (CycleGAN) has been introduced as a tool to generate images without matching paired images. Therefore, herein, we present a deep learning technique that removes the artifacts automatically in a fundus photograph using a CycleGAN model.

METHODS

This study included a total of 2206 anonymized retinal images including 1146 with artifacts and 1060 without artifacts. In this experiment, we applied the CycleGAN model to color fundus photographs with a pixel resolution of 256 × 256 × 3. To apply the CycleGAN to an independent dataset, we randomly divided the data into training (90%) and test (10%) datasets. Additionally, we adopted the automated quality evaluation (AQE) to assess the retinal image quality.

RESULTS

From the results, we observed that the artifacts such as overall haze, edge haze, lashes, arcs, and uneven illumination were successfully reduced by the CycleGAN in the generated images, and the main information of the retina was essentially retained. Further, we observed that most of the generated images exhibited improved AQE grade values when compared with the original images with artifacts.

CONCLUSION

Thus, we could conclude that the CycleGAN technique can effectively reduce the artifacts and improve the quality of fundus photographs, and it may be beneficial for clinicians in analyzing the low-quality fundus photographs. Future studies should improve the quality and resolution of the generated image to provide a more detailed fundus photography.

Deep learning-based smart speaker to confirm surgical sites for cataract surgeries: A pilot study

Wrong-site surgeries can occur due to the absence of an appropriate surgical time-out. However, during a time-out, surgical participants are unable to review the patient's charts due to their aseptic hands. To improve the conditions in surgical time-outs, we introduce a deep learning-based smart speaker to confirm the surgical information prior to cataract surgeries. This pilot study utilized the publicly available audio vocabulary dataset and recorded audio data published by the authors. The audio clips of the target words, such as left, right, cataract, phacoemulsification, and intraocular lens, were selected to determine and confirm surgical information in the time-out speech. A deep convolutional neural network model was trained and implemented in the smart speaker that was developed using a mini development board and commercial speakerphone. To validate our model in the consecutive speeches during time-outs, we generated 200 time-out speeches for cataract surgeries by randomly selecting the surgical statuses of the surgical participants. After the training process, the deep learning model achieved an accuracy of 96.3% for the validation dataset of short-word audio clips. Our deep learning-based smart speaker achieved an accuracy of 93.5% for the 200 time-out speeches. The surgical and procedural accuracy was 100%. Additionally, on validating the deep learning model by using web-generated time-out speeches and video clips for general surgery, the model exhibited a robust and good performance. In this pilot study, the proposed deep learning-based smart speaker was able to successfully confirm the surgical information during the time-out speech. Future studies should focus on collecting real-world time-out data and automatically connecting the device to electronic health records. Adopting smart speaker-assisted time-out phases will improve the patients' safety during cataract surgeries, particularly in relation to wrong-site surgeries.

Explainable Machine Learning Approach as a Tool to Understand Factors Used to Select the Refractive Surgery Technique on the Expert Level

Purpose

Recently, laser refractive surgery options, including laser epithelial keratomileusis, laser in situ keratomileusis, and small incision lenticule extraction, successfully improved patients' quality of life. Evidence-based recommendation for an optimal surgery technique is valuable in increasing patient satisfaction. We developed an interpretable multiclass machine learning model that selects the laser surgery option on the expert level.

Methods

A multiclass XGBoost model was constructed to classify patients into four categories including laser epithelial keratomileusis, laser in situ keratomileusis, small incision lenticule extraction, and contraindication groups. The analysis included 18,480 subjects who intended to undergo refractive surgery at the B&VIIT Eye center. Training (n = 10,561) and internal validation (n = 2640) were performed using subjects who visited between 2016 and 2017. The model was trained based on clinical decisions of highly experienced experts and ophthalmic measurements. External validation (n = 5279) was conducted using subjects who visited in 2018. The SHapley Additive ex-Planations technique was adopted to explain the output of the XGBoost model.

Results

The multiclass XGBoost model exhibited an accuracy of 81.0% and 78.9% when tested on the internal and external validation datasets, respectively. The SHapley Additive ex-Planations explanations for the results were consistent with prior knowledge from ophthalmologists. The explanation from one-versus-one and one-versus-rest XGBoost classifiers was effective for easily understanding users in the multicategorical classification problem.

Conclusions

This study suggests an expert-level multiclass machine learning model for selecting the refractive surgery for patients. It also provided a clinical understanding in a multiclass problem based on an explainable artificial intelligence technique.

Translational Relevance

Explainable machine learning exhibits a promising future for increasing the practical use of artificial intelligence in ophthalmic clinics.

Polarized skylight compass based on a soft-margin support vector machine working in cloudy conditions

The skylight polarization pattern, which is a result of the scattering of unpolarized sunlight by particles in the atmosphere, can be used by many insects for navigation. Inspired by insects, several polarization navigation sensors have been designed and combined with various heading determination methods in recent years. However, up until now, few of these studies have fully considered the influences of different meteorological conditions, which play key roles in navigation accuracy, especially in cloudy weather. Therefore, this study makes a major contribution to the study on bio-inspired heading determination by designing a skylight compass method to suppress cloud disturbances. The proposed method transforms the heading determination problem into a binary classification problem by segmentation, connected component detection, and inversion. Considering the influences of noise and meteorological conditions, the binary classification problem is solved by the soft-margin support vector machine. In addition, to verify this method, a pixelated polarization compass platform is constructed that can take polarization images at four different orientations simultaneously in real time. Finally, field experimental results show that the designed method can more effectively suppress the interference of clouds compared with other methods.

A generative adversarial network approach to predicting postoperative appearance after orbital decompression surgery for thyroid eye disease

PURPOSE

Orbital decompression for thyroid-associated ophthalmopathy (TAO) is an ophthalmic plastic surgery technique to prevent optic neuropathy and reduce exophthalmos. Because the postoperative appearance can significantly change, sometimes it is difficult to make decisions regarding decompression surgery. Herein, we present a deep learning technique to synthesize the realistic postoperative appearance for orbital decompression surgery.

METHODS

This data-driven approach is based on a conditional generative adversarial network (GAN) to transform preoperative facial input images into predicted postoperative images. The conditional GAN model was trained on 109 pairs of matched pre- and postoperative facial images through data augmentation.

RESULTS

When the conditional variable was changed, the synthesized facial image was transferred from a preoperative image to a postoperative image. The predicted postoperative images were similar to the ground truth postoperative images. We also found that GAN-based synthesized images can improve the deep learning classification performance between the pre- and postoperative status using a small training dataset. However, a relatively low quality of synthesized images was noted after a readout by clinicians.

CONCLUSIONS

Using this framework, we synthesized TAO facial images that can be queried using conditioning on the orbital decompression status. The synthesized postoperative images may be helpful for patients in determining the impact of decompression surgery. However, the quality of the generated image should be further improved. The proposed deep learning technique based on a GAN can rapidly synthesize such realistic images of the postoperative appearance, suggesting that a GAN can function as a decision support tool for plastic and cosmetic surgery techniques.

Modern perioperative medicine - past, present, and future

Modern perioperative medicine has dramatically altered the care for patients undergoing major surgery. Anaesthetic and surgical practice has been directed at mitigating the surgical stress response and reducing physiological insult. The development of standardised enhanced recovery programmes combined with minimally invasive surgical techniques has lead to reduction in length of stay, morbidity, costs, and improved outcomes. The enhanced recovery after surgery (ERAS) society and its national chapters provide a means for sharing best practice in this field and developing evidence based guidelines. Research has highlighted persisting challenges with compliance as well as ensuring the effectiveness and sustainability of ERAS. There is also a growing need for increasingly personalised care programmes as well as complex geriatric assessment of frailer patients. Continuous collection of outcome and process data combined with machine learning, offers a potentially powerful solution to delivering bespoke care pathways and optimising individual management. Long-term data from ERAS programmes remain scarce and further evaluation of functional recovery and quality of life is required.

Translating genomic testing results for pediatric critical care: Opportunities for genetic counselors

Genomic sequencing (GS), such as whole genome and exome sequencing, is rapidly being integrated into pediatric critical care settings. Results are being used to make high impact decisions including declarations of futility, withdrawal of care, and rationing of scarce resources. In this qualitative study, we conducted interviews with clinicians involved in the care of critically ill children with congenital heart disease (CHD) to investigate their views on implementation of GS into clinical practice. Interviews were transcribed and inductively analyzed for major themes using grounded theory and thematic analysis. Three major themes emerged surrounding the use of genomic information in the high-stakes, time pressured decision making that characterizes clinical care of critically ill children with CHD: (a) that clinicians felt they did not have sufficient training to accurately assess genetic results despite pressure to incorporate results into clinical decisions; (b), that they desire knowledge support from genetic specialists, such as genetic counselors, who both understand the critical care context and are available within the time constraints of critical care clinical pressures; and (c), that clinicians feel a pressing need for increased genetics education to be able to safely and appropriately incorporate GS results into clinical decisions Our data suggest that genetics specialists may need a stronger presence in the pediatric critical care setting.