Screening and Treatment in Retinopathy of Prematurity

Assessing spectral effectiveness in color fundus photography for deep learning classification of retinopathy of prematurity

Significance

Retinopathy of prematurity (ROP) poses a significant global threat to childhood vision, necessitating effective screening strategies. This study addresses the impact of color channels in fundus imaging on ROP diagnosis, emphasizing the efficacy and safety of utilizing longer wavelengths, such as red or green for enhanced depth information and improved diagnostic capabilities.

Aim

This study aims to assess the spectral effectiveness in color fundus photography for the deep learning classification of ROP.

Approach

A convolutional neural network end-to-end classifier was utilized for deep learning classification of normal, stage 1, stage 2, and stage 3 ROP fundus images. The classification performances with individual-color-channel inputs, i.e., red, green, and blue, and multi-color-channel fusion architectures, including early-fusion, intermediate-fusion, and late-fusion, were quantitatively compared.

Results

For individual-color-channel inputs, similar performance was observed for green channel (88.00% accuracy, 76.00% sensitivity, and 92.00% specificity) and red channel (87.25% accuracy, 74.50% sensitivity, and 91.50% specificity), which is substantially outperforming the blue channel (78.25% accuracy, 56.50% sensitivity, and 85.50% specificity). For multi-color-channel fusion options, the early-fusion and intermediate-fusion architecture showed almost the same performance when compared to the green/red channel input, and they outperformed the late-fusion architecture.

Conclusions

This study reveals that the classification of ROP stages can be effectively achieved using either the green or red image alone. This finding enables the exclusion of blue images, acknowledged for their increased susceptibility to light toxicity.

ASSESSMENT OF NEONATAL CARE STANDARD BY THE PREDICTIVE MODEL FOR RETINOPATHY OF PREMATURITY BASED ON WEIGHT GAIN

Care of extremely premature infants is in constant need for evaluation and progress. WINROP, a predictive model based on weight gain, has been developed to reduce the number of stressful examinations for retinopathy for prematurity. Validation studies of WINROP emphasize the difference of applicability in neonatal units of various practice. The aim of the study was to assess the standard of neonatal care by WINROP. Data on extremely premature infants were collected from medical records and entered in WINROP. High- and low-risk WINROP distribution and retinopathy of prematurity outcomes were analyzed. Fifty-four infants, gestational age ≤28 weeks, were included in the study after exclusion of weight related comorbidities. High risk was noted in 74% (n=40) of infants with 24% (n=13) developing retinopathy of prematurity requiring treatment. In low alarm group, there were 3 cases with severe disease. In conclusion, WINROP is not just a provider of predictive information on the severity of retinopathy of prematurity. High-risk alarm indicates the need of adjustment of nutritional strategies. Infants without pathological growth morbidities who develop severe retinopathy of prematurity in low-risk group point to other risk factors for retinopathy of prematurity to be evaluated and changed in future practice.

Refractive outcomes following yttrium aluminum garnet laser (532 nm green laser) in severe retinopathy of prematurity

PURPOSE

To assess the refractive outcomes in eyes with severe Retinopathy of prematurity (ROP) after treatment with the frequency-doubled neodymium-doped yttrium aluminum garnet (Nd-YAG) laser 532 nm (green laser) at 1-2 years of age and compare with eyes that underwent spontaneous regression of ROP and to identify the risk factors associated with the refractive outcomes in laser-treated eyes with severe ROP.

METHODOLOGY

Infants who underwent laser treatment with green laser were enrolled in Group 1 and those who had spontaneous regression of ROP were enrolled in Group 2. All these children underwent a visual assessment, refraction using 1% cyclopentolate eye drops and indirect ophthalmoscopy at 1-2 years of age. Data regarding the gestational age, sex, birth weight, inborn (born in our institution) or outborn (born outside and referred to us), stage and zone of ROP and laser spots given were obtained from the treatment records. Data were analyzed using SSPS 19.0 software for Windows (SSPS Inc., Chicago, Illinois, USA).

RESULTS

A total of 102 infants were enrolled, 51 in each group. Visual acuity ranged from 0.25-1 cycles per cm in both groups. Spherical equivalent (SE) ranged from - 8.25 D to + 5.50 D in Group 1 and -1.00D to +4.00D in Group 2. Group 1 had an incidence of 23.5% Myopia and 33.4% Astigmatism which was significantly more than Group 2. The linear regression model predicted a decrease in the SE by 0.658D if the number of laser spots increased by 1000 (P < 0.001). No other risk factors (gestational age/birth weight) were found to have a significant association with refractive errors in the lasered ROP group.

CONCLUSIONS

Eyes with laser-treated severe ROP are frequently associated with myopia and astigmatism when compared to spontaneously regressed ROP. The number of laser spots delivered has a direct association with the amount of refractive error.

Mesenchymal stem cell-derived secretomes for therapeutic potential of premature infant diseases

Preterm birth is a complex syndrome and remains a substantial public health problem globally. Its common complications include periventricular leukomalacia (PVL), bronchopulmonary dysplasia (BPD), necrotizing enterocolitis (NEC) and retinopathy of prematurity (ROP). Despite great advances in the comprehension of the pathogenesis and improvements in neonatal intensive care and associated medicine, preterm birth-related diseases remain essentially without adequate treatment and can lead to high morbidity and mortality. The therapeutic potential of mesenchymal stem/stromal cells (MSCs) appears promising as evidenced by their efficacy in preclinical models of pathologies relevant to premature infant complications. MSC-based therapeutic efficacy is closely associated with MSC secretomes and a subsequent paracrine action response to tissue injuries, which are complex and abundant in response to the local microenvironment. In the current review, we summarize the paracrine mechanisms of MSC secretomes underlying diverse preterm birth-related diseases, including PVL, BPD, NEC and ROP, are summarized, and focus is placed on MSC-conditioned media (CM) and MSC-derived extracellular vesicles (EVs) as key mediators of modulatory action, thereby providing new insights for future therapies in newborn medicine.

Increase in treatment of retinopathy of prematurity in the Netherlands from 2010 to 2017

Purpose

Compare patients treated for Retinopathy of Prematurity (ROP) in two consecutive periods.

Methods

Retrospective inventory of anonymized neonatal and ophthalmological data of all patients treated for ROP from 2010 to 2017 in the Netherlands, subdivided in period (P)1: 1‐1‐2010 to 31‐3‐2013 and P2: 1‐4‐2013 to 31‐12‐2016. Treatment characteristics, adherence to early treatment for ROP (ETROP) criteria, outcome of treatment and changes in neonatal parameters and policy of care were compared.

Results

Overall 196 infants were included, 57 infants (113 eyes) in P1 and 139 (275 eyes) in P2, indicating a 2.1‐fold increase in ROP treatment. No differences were found in mean gestational age (GA) (25.9 ± 1.7 versus 26.0 ± 1.7 weeks, p = 0.711), mean birth weight (791 ± 311 versus 764 ± 204 grams, p = 0.967) and other neonatal risk factors for ROP. In P2, the number of premature infants born <25 weeks increased by factor 1.23 and higher oxygen saturation levels were aimed at in most centres. At treatment decision, 59.6% (P1) versus 83.5% (P2) (p = 0.263) infants were classified as Type 1 ROP (ETROP classification). Infants were treated with laser photocoagulation (98 versus 96%) and intravitreal bevacizumab (2 versus 4%). Retreatment was necessary in 10 versus 21 (p = 0.160). Retinal detachment developed in 6 versus 13 infants (p = 0.791) of which 2 versus 6 bilateral (p = 0.599).

Conclusion

In period 2, the number of infants treated according to the ETROP criteria (Type 1) increased, the number of ROP treatments, retinal detachments and retreatments doubled and the absolute number of retinal detachments increased. Neonatal data did not provide a decisive explanation, although changes in neonatal policy were reported.

Automated identification of retinopathy of prematurity by image-based deep learning

BACKGROUND

Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide but can be a treatable retinal disease with appropriate and timely diagnosis. This study was performed to develop a robust intelligent system based on deep learning to automatically classify the severity of ROP from fundus images and detect the stage of ROP and presence of plus disease to enable automated diagnosis and further treatment.

METHODS

A total of 36,231 fundus images were labeled by 13 licensed retinal experts. A 101-layer convolutional neural network (ResNet) and a faster region-based convolutional neural network (Faster-RCNN) were trained for image classification and identification. We applied a 10-fold cross-validation method to train and optimize our algorithms. The accuracy, sensitivity, and specificity were assessed in a four-degree classification task to evaluate the performance of the intelligent system. The performance of the system was compared with results obtained by two retinal experts. Moreover, the system was designed to detect the stage of ROP and presence of plus disease as well as to highlight lesion regions based on an object detection network using Faster-RCNN.

RESULTS

The system achieved an accuracy of 0.903 for the ROP severity classification. Specifically, the accuracies in discriminating normal, mild, semi-urgent, and urgent were 0.883, 0.900, 0.957, and 0.870, respectively; the corresponding accuracies of the two experts were 0.902 and 0.898. Furthermore, our model achieved an accuracy of 0.957 for detecting the stage of ROP and 0.896 for detecting plus disease; the accuracies in discriminating stage I to stage V were 0.876, 0.942, 0.968, 0.998 and 0.999, respectively.

CONCLUSIONS

Our system was able to detect ROP and differentiate four-level classification fundus images with high accuracy and specificity. The performance of the system was comparable to or better than that of human experts, demonstrating that this system could be used to support clinical decisions.

Effects of microRNA-29a on retinopathy of prematurity by targeting AGT in a mouse model

BACKGROUND

This study aimed to explore the effects of microRNA-29a (miR-29a) on retinopathy of prematurity (ROP) by targeting angiotensinogen (AGT) expression in a mouse model.

METHODS

Ninety-six C57BL/6J mice were selected and divided into the normal control group (n = 12) and the oxygen-induced retinopathy (OIR) group (n = 84). All the mice in the OIR group were assigned to the following seven groups (12 mice in each group): the blank, miR-29a mimics, miR-29a inhibitors, empty plasmid, miR-29a mimics + si-AGT, miR-29a inhibitors + si-AGT and si-AGT groups. ADPase histochemical staining was conducted to detect the morphology of retinal neovascularization. H&E staining was performed to quantify retinal neovascularization. The qRT-PCR assay was applied to detect the expression levels of miR-29a and the AGT mRNA. Western blotting was used to detect the protein expressions of AGT, vascular endothelial growth factor (VEGF), hepatocyte growth factor (HGF), angiotensin (ANG) and angiotensin II (AngII).

RESULTS

Compared with the normal control group, miR-29a expression decreased, while the AGT mRNA expression and the protein expression levels of AGT, VEGF, HGF, ANG and AngII increased, and retinal vascular density and neovascularization also increased in the OIR group. In the OIR group, compared with the blank, empty plasmid, miR-29a inhibitors and miR-29a inhibitors + si-AGT groups, miR-29a expression increased, while the AGT mRNA expression and protein expression levels of AGT, VEGF, HGF, ANG and AngII decreased, and retinal vascular density and neovascularization also decreased in the miR-29a mimics, miR-29a mimics + si-AGT and si-AGT groups.

CONCLUSION

MiR-29a could inhibit retinal neovascularization to prevent the development and progression of ROP by down-regulating AGT.