Convolutional Neural Network Based on Fluorescein Angiography Images for Retinopathy of Prematurity Management

Vascular imaging findings in retinopathy of prematurity

Retinopathy of prematurity (ROP) is a vascular disease among preterm infants involving incomplete or abnormal retinal vascularization and is a leading cause of preventable blindness globally. Measurements of ocular blood flow originating from a variety of imaging modalities, including colour Doppler imaging (CDI), fluorescein angiography (FA) and ocular coherence tomography angiography (OCTA), have been associated with changes in ROP patients. Herein, we discuss and summarize the relevant current literature on vascular imaging and ROP reviewed through December 2022. Differences in vascular imaging parameters between ROP patients and healthy controls are reviewed and summarized. The available data identify significantly increased peak systolic velocity (PSV) in the central retinal artery and ophthalmic artery as measured by CDI, increased vascular tortuosity as measured by FA, smaller foveal avascular zone (FAZ) as measured by FA and OCTA, and increased foveal vessel density (VD) and reduced parafoveal VD as measured by OCTA in ROP patients compared with controls. None of the above findings appear to reliably correlate with visual acuity. The studies currently available, however, are inconclusive and lack robust longitudinal data. Vascular imaging demonstrates the potential to aid in the diagnosis, management and monitoring of ROP, alongside retinal examination via indirect ophthalmoscopy and fundus photography.

Image-free recognition of moderate ROP from mild with machine learning algorithm on plasma Raman spectrum

The retinopathy of prematurity (ROP) can cause serious clinical consequences and, fortunately, it is remediable while the time window for treatment is relatively narrow. Therefore, it is urgent to screen all premature infants and diagnose ROP degree timely, which has become a large workload for pediatric ophthalmologists. We developed a retinal image-free procedure using small amount of blood samples based on the plasma Raman spectrum with the machine learning model to automatically classify ROP cases before medical intervention was performed. Statistical differences in infrared Raman spectra of plasma samples were found among the control, mild (ZIIIS1), moderate (ZIIIS2 & ZIIS1), and advanced (ZIIS2) ROP groups. With the different wave points of Raman spectra as the inputs, the outputs of our support vector machine showed that the area under the curves in the receiver operating characteristic (AUC) were 0.763 for the pair comparisons of the control with the mild groups, 0.821 between moderate and advanced groups (ZIIS2), while more than 90% in comparisons of the other four pairs: control vs. moderate (0.981), control vs. advanced (0.963), mild vs. moderate (0.936), and mild vs. advanced (0.953), respectively. Our study could advance principally the ROP diagnosis in two dimensions: the moderate ROPs have been classified remarkably from the mild ones, which leaves more time for the medical treatments, and the procedure of Raman spectrum with a machine learning model based on blood samples can be conveniently promoted to those hospitals lacking of the pediatric ophthalmologists with experience in reading retinal images.

Research hotspots and trends in retinopathy of prematurity from 2003 to 2022: a bibliometric analysis

Background

In order to understand the research hotspots and trends in the field of retinopathy of prematurity (ROP), our study analyzed the relevant publications from 2003 to 2022 by using bibliometric analysis.

Methods

The Citespace 6.2.R3 system was used to analyze the publications collected from the Web of Science Core Collection (WoSCC) database.

Results

In total, 4,957 publications were included in this study. From 2003 to 2022, the number of publications gradually increased and peaked in 2022. The United States was the country with the most publications, while Harvard University was the most productive institution. The top co-cited journal PEDIATRICS is published by the United States. Author analysis showed that Hellström A was the author with the most publications, while Good WV was the top co-cited author. The co-citation analysis of references showed seven major clusters: genetic polymorphism, neurodevelopmental outcome, threshold retinopathy, oxygen-induced retinopathy, low birth weight infant, prematurity diagnosis cluster and artificial intelligence (AI). For the citation burst analysis, there remained seven keywords in their burst phases until 2022, including ranibizumab, validation, trends, type 1 retinopathy, preterm, deep learning and artificial intelligence.

Conclusion

Intravitreal anti-vascular endothelial growth factor therapy and AI-assisted clinical decision-making were two major topics of ROP research, which may still be the research trends in the coming years.

The future of neonatal lung ultrasound: Validation of an artificial intelligence model for interpreting lung scans. A multicentre prospective diagnostic study

BACKGROUND

Artificial intelligence (AI) is a promising field in the neonatal field. We focused on lung ultrasound (LU), a useful tool for the neonatologist. Our aim was to train a neural network to create a model able to interpret LU.

METHODS

Our multicentric, prospective study included newborns with gestational age (GA) ≥ 33 + 0 weeks with early tachypnea/dyspnea/oxygen requirements. For each baby, three LU were performed: within 3 h of life (T0), at 4-6 h of life (T1), and in the absence of respiratory support (T2). Each scan was processed to extract the region of interest used to train a neural network to classify it according to the LU score (LUS). We assessed sensitivity, specificity, positive and negative predictive value of the AI model's scores in predicting the need for respiratory assistance with nasal continuous positive airway pressure and for surfactant, compared to an already studied and established LUS.

RESULTS

We enrolled 62 newborns (GA = 36 ± 2 weeks). In the prediction of the need for CPAP, we found a cutoff of 6 (at T0) and 5 (at T1) for both the neonatal lung ultrasound score (nLUS) and AI score (AUROC 0.88 for T0 AI model, 0.80 for T1 AI model). For the outcome "need for surfactant therapy", results in terms of area under receiver operator characteristic (AUROC) are 0.84 for T0 AI model and 0.89 for T1 AI model. In the prediction of surfactant therapy, we found a cutoff of 9 for both scores at T0, at T1 the nLUS cutoff was 6, while the AI's one was 5. Classification accuracy was good both at the image and class levels.

CONCLUSIONS

This is, to our knowledge, the first attempt to use an AI model to interpret early neonatal LUS and can be extremely useful for neonatologists in the clinical setting.

Fairness and generalisability in deep learning of retinopathy of prematurity screening algorithms: a literature review

BACKGROUND

Retinopathy of prematurity (ROP) is a vasoproliferative disease responsible for more than 30 000 blind children worldwide. Its diagnosis and treatment are challenging due to the lack of specialists, divergent diagnostic concordance and variation in classification standards. While artificial intelligence (AI) can address the shortage of professionals and provide more cost-effective management, its development needs fairness, generalisability and bias controls prior to deployment to avoid producing harmful unpredictable results. This review aims to compare AI and ROP study's characteristics, fairness and generalisability efforts.

METHODS

Our review yielded 220 articles, of which 18 were included after full-text assessment. The articles were classified into ROP severity grading, plus detection, detecting treatment requiring, ROP prediction and detection of retinal zones.

RESULTS

All the article's authors and included patients are from middle-income and high-income countries, with no low-income countries, South America, Australia and Africa Continents representation.Code is available in two articles and in one on request, while data are not available in any article. 88.9% of the studies use the same retinal camera. In two articles, patients' sex was described, but none applied a bias control in their models.

CONCLUSION

The reviewed articles included 180 228 images and reported good metrics, but fairness, generalisability and bias control remained limited. Reproducibility is also a critical limitation, with few articles sharing codes and none sharing data. Fair and generalisable ROP and AI studies are needed that include diverse datasets, data and code sharing, collaborative research, and bias control to avoid unpredictable and harmful deployments.

Artificial intelligence for the diagnosis of retinopathy of prematurity: A systematic review of current algorithms

BACKGROUND/OBJECTIVES

With the increasing survival of premature infants, there is an increased demand to provide adequate retinopathy of prematurity (ROP) services. Wide field retinal imaging (WFDRI) and artificial intelligence (AI) have shown promise in the field of ROP and have the potential to improve the diagnostic performance and reduce the workload for screening ophthalmologists. The aim of this review is to systematically review and provide a summary of the diagnostic characteristics of existing deep learning algorithms.

SUBJECT/METHODS

Two authors independently searched the literature, and studies using a deep learning system from retinal imaging were included. Data were extracted, assessed and reported using PRISMA guidelines.

RESULTS

Twenty-seven studies were included in this review. Nineteen studies used AI systems to diagnose ROP, classify the staging of ROP, diagnose the presence of pre-plus or plus disease, or assess the quality of retinal images. The included studies reported a sensitivity of 71%-100%, specificity of 74-99% and area under the curve of 91-99% for the primary outcome of the study. AI techniques were comparable to the assessment of ophthalmologists in terms of overall accuracy and sensitivity. Eight studies evaluated vascular severity scores and were able to accurately differentiate severity using an automated classification score.

CONCLUSION

Artificial intelligence for ROP diagnosis is a growing field, and many potential utilities have already been identified, including the presence of plus disease, staging of disease and a new automated severity score. AI has a role as an adjunct to clinical assessment; however, there is insufficient evidence to support its use as a sole diagnostic tool currently.

Application of Artificial Intelligence in the Early Detection of Retinopathy of Prematurity: Review of the Literature

Retinopathy of prematurity (ROP) is a potentially blinding disease in premature neonates that requires a skilled workforce for diagnosis, monitoring, and treatment. Artificial intelligence is a valuable tool that clinicians employ to reduce the screening burden on ophthalmologists and neonatologists and improve the detection of treatment-requiring ROP. Neural networks such as convolutional neural networks and deep learning (DL) systems are used to calculate a vascular severity score (VSS), an important component of various risk models. These DL systems have been validated in various studies, which are reviewed here. Most importantly, we discuss a promising study that validated a DL system that could predict the development of ROP despite a lack of clinical evidence of disease on the first retinal examination. Additionally, there is promise in utilizing these systems through telemedicine in more rural and resource-limited areas. This review highlights the value of these DL systems in early ROP diagnosis.

Deep learning for automated detection of neovascular leakage on ultra-widefield fluorescein angiography in diabetic retinopathy

Diabetic retinopathy is a leading cause of blindness in working-age adults worldwide. Neovascular leakage on fluorescein angiography indicates progression to the proliferative stage of diabetic retinopathy, which is an important distinction that requires timely ophthalmic intervention with laser or intravitreal injection treatment to reduce the risk of severe, permanent vision loss. In this study, we developed a deep learning algorithm to detect neovascular leakage on ultra-widefield fluorescein angiography images obtained from patients with diabetic retinopathy. The algorithm, an ensemble of three convolutional neural networks, was able to accurately classify neovascular leakage and distinguish this disease marker from other angiographic disease features. With additional real-world validation and testing, our algorithm could facilitate identification of neovascular leakage in the clinical setting, allowing timely intervention to reduce the burden of blinding diabetic eye disease.

Ocular Brachytherapy (Interventional Radiotherapy): Preserving the Vision

Uveal melanoma represents the most common intraocular neoplasia among adults. Brachytherapy (interventional radiotherapy; IRT) has a great advantage, when compared with enucleation, both in terms of organ and function sparing. The Collaborative Ocular Melanoma Study introduced into clinical practice a standardised procedure that allowed the equivalence of IRT with enucleation in terms of overall survival to be demonstrated. IRT is carried out by placing a plaque in direct contact with the sclera under the uveal melanoma. Several radioactive sources may be used, including 106-ruthenium, 125-iodine, 103-palladium and 90-strontium. It is a multidisciplinary procedure requiring the collaboration of interventional radiation oncologists and ophthalmologists in the operating theatre and medical physicists for an accurate treatment time calculation. It also relies on ultrasound imaging to identify the lesion and verifiy the correct plaque placement. An emerging tool of paramount importance could be the use of artificial intelligence and predictive models to identify those patients at higher risk of developing late side-effects and therefore who may deserve preventive and supportive therapies.

Artificial Intelligence and OCT Angiography in Full Thickness Macular Hole. New Developments for Personalized Medicine

Purpose: To evaluate the 1-year visual acuity predictive performance of an artificial intelligence (AI) based model applied to optical coherence tomography angiography (OCT-A) vascular layers scans from eyes with a full-thickness macular hole (FTMH). Methods: In this observational cross-sectional, single-center study, 35 eyes of 35 patients with FTMH were analyzed by OCT-A before and 1-year after surgery. Superficial vascular plexus (SVP) and deep vascular plexus (DVP) images were collected for the analysis. AI approach based on convolutional neural networks (CNN) was used to generate a continuous predictive variable based on both SVP and DPV. Different pre-trained CNN networks were used for feature extraction and compared for predictive accuracy. Results: Among the different tested models, the inception V3 network, applied on the combination of deep and superficial OCT-A images, showed the most significant differences between the two obtained image clusters defined in C1 and C2 (best-corrected visual acuity (BCVA) C1 = 66.67 (16.00 SD) and BCVA C2 = 49.10 (18.60 SD, p = 0.005)). Conclusions: The AI-based analysis of preoperative OCT-A images of eyes affected by FTMH may be a useful support system in setting up visual acuity recovery prediction. The combination of preoperative SVP and DVP images showed a significant morphological predictive performance for visual acuity recovery.

Building an Artificial Intelligence Laboratory Based on Real World Data: The Experience of Gemelli Generator

The problem of transforming Real World Data into Real World Evidence is becoming increasingly important in the frameworks of Digital Health and Personalized Medicine, especially with the availability of modern algorithms of Artificial Intelligence high computing power, and large storage facilities.Even where Real World Data are well maintained in a hospital data warehouse and are made available for research purposes, many aspects need to be addressed to build an effective architecture enabling researchers to extract knowledge from data.We describe the first year of activity at Gemelli Generator RWD, the challenges we faced and the solutions we put in place to build a Real World Data laboratory at the service of patients and health researchers. Three classes of services are available today: retrospective analysis of existing patient data for descriptive and clustering purposes; automation of knowledge extraction, ranging from text mining, patient selection for trials, to generation of new research hypotheses; and finally the creation of Decision Support Systems, with the integration of data from the hospital data warehouse, apps, and Internet of Things.