Related Experiment Video
Updated: Jan 16, 2026
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Deep learning-based prediction of cardiopulmonary disease in retinal images of premature infants
Praveer Singh1, Sourav Kumar1, Riya Tyagi2
1Ophthalmology, University of Colorado School of Medicine, Aurora, CO.
Insights
Retinal images from retinopathy of prematurity screening can predict bronchopulmonary dysplasia and pulmonary hypertension in premature infants. This multimodal approach may enable earlier diagnosis and reduce invasive testing.
Area of Science:
- Neonatal Medicine
- Ophthalmology
- Artificial Intelligence
Background:
- Bronchopulmonary dysplasia (BPD) and pulmonary hypertension (PH) are significant causes of mortality in premature infants.
- Early detection of BPD and PH is crucial for timely intervention and improved outcomes.
Purpose of the Study:
- To investigate if retinal images from retinopathy of prematurity (ROP) screening contain features predictive of BPD and PH.
- To evaluate a multimodal deep learning model integrating imaging and demographic data for BPD and PH prediction.
Main Methods:
- A deep learning model (Resnet18) analyzed retinal images from 493 infants at risk for ROP.
- A support vector machine model predicted BPD and PH using imaging features, demographics, or both.
- Models were validated on held-out test sets, with secondary models trained on images without ROP signs.
Main Results:
- The multimodal model achieved diagnostic accuracy of 0.82 for BPD and 0.91 for PH.
- This outperformed models using only demographics (0.72 for BPD, 0.68 for PH) or imaging alone (0.72 for BPD, 0.91 for PH).
- Predictive associations remained significant even when excluding images with clinical ROP signs.
Conclusions:
- Retinal images from ROP screening hold predictive value for BPD and PH in preterm infants.
- A multimodal AI model integrating imaging and clinical data can enhance diagnostic accuracy.
- This approach may facilitate earlier diagnosis and potentially reduce the need for invasive procedures.
Importance:
Bronchopulmonary dysplasia (BPD) and pulmonary hypertension (PH) are leading causes of morbidity and mortality in premature infants.
Objective:
To determine whether images obtained as part of retinopathy of prematurity (ROP) screening might contain features associated with BPD and PH in infants, and whether a multimodal model integrating imaging features with demographic risk factors might outperform a model based on demographic risk alone.
Design:
A deep learning model was used to study retinal images collected from patients enrolled in the multi-institutional Imaging and Informatics in Retinopathy of Prematurity (i-ROP) study.
Setting:
Seven neonatal intensive care units.
Participants:
493 infants at risk for ROP undergoing routine ROP screening examinations from 2012 to 2020. Images were limited to <=34 weeks post-menstrual age (PMA) so as to precede the clinical diagnosis of BPD or PH.
Exposure:
BPD was diagnosed by the presence of an oxygen requirement at 36 weeks PMA, and PH was diagnosed by echocardiogram at 34 weeks. A support vector machine model was trained to predict BPD, or PH, diagnosis using: A) image features alone (extracted using Resnet18), B) demographics alone, C) image features concatenated with demographics. To reduce the possibility of confounding with ROP, secondary models were trained using only images without clinical signs of ROP.
Main Outcome Measure:
For both BPD and PH, we report performance on a held-out testset (99 patients from the BPD cohort and 37 patients from the PH cohort), assessed by the area under receiver operating characteristic curve.
Results:
For BPD, the diagnostic accuracy of a multimodal model was 0.82 (95% CI: 0.72-0.90), compared to demographics 0.72 (0.60-0.82; P=0.07) or imaging 0.72 (0.61-0.82; P=0.002) alone. For PH, it was 0.91 (0.71-1.0) combined compared to 0.68 (0.43-0.9; P=0.04) for demographics and 0.91 (0.78-1.0; P=0.4) for imaging alone. These associations remained even when models were trained on the subset of images without any clinical signs of ROP.
Conclusions And Relevance:
Retinal images obtained during ROP screening can be used to predict the diagnosis of BPD and PH in preterm infants, which may lead to earlier diagnosis and avoid the need for invasive diagnostic testing in the future.
