Noninvasive Anemia Detection and Hemoglobin Estimation from Retinal Images Using Deep Learning: A Scalable Solution for Resource-Limited Settings
Translational Vision Science & Technology · 2025
DOI: 10.1167/tvst.14.1.20 ↗Kurz gefasst
Fachartikel in der Zeitschrift Translational Vision Science & Technology, 2025. Verfasst von Rehana Khan und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Optometry and Vision Science, University of New South Wales, Sydney, Australia. Hauptthemen laut MEDLINE: Deep Learning, Anemia, Hemoglobins, Retina. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Purpose
The purpose of this study was to develop and validate a deep-learning model for noninvasive anemia detection, hemoglobin (Hb) level estimation, and identification of anemia-related retinal features using fundus images.
Methods
The dataset included 2265 participants aged 40 years and above from a population-based study in South India. The dataset included ocular and systemic clinical parameters, dilated retinal fundus images, and hematological data such as complete blood counts and Hb concentration levels. Eighty percent of the dataset was used for algorithm development and 20% for validation. A deep-convolutional neural network, utilizing VGG16, ResNet50, and InceptionV3 architectures, was trained to predict anemia and estimate Hb levels. Sensitivity, specificity, and accuracy were calculated, and receiver operating characteristic (ROC) curves were generated for comparison with clinical anemia data. GradCAM saliency maps highlighted regions linked to anemia and image processing techniques to quantify anemia-related features.
Results
For predicting anemia, the InceptionV3 model demonstrated the best performance, achieving 98% accuracy, 99% sensitivity, 97% specificity, and an area under the curve (AUC) of 0.98 (95% confidence interval [CI] = 0.97-0.99). For estimating Hb levels, the mean absolute error for the InceptionV3 model was 0.58 g/dL (95% CI = 0.57-0.59 g/dL). The model focused on the area around the optic disc and the neighboring retinal vessels, revealing that anemic subjects exhibited significantly increased vessel tortuosity and reduced vessel density (P < 0.001), with variable effects on vessel thickness.
Conclusions
The InceptionV3 model accurately predicted anemia and Hb levels, highlighting the potential of deep learning and vessel analysis for noninvasive anemia detection. Translational Relevance: The proposed method offers the possibility to quantitatively predict hematological parameters in a noninvasive manner.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Optometry and Vision Science, University of New South Wales, Sydney, Australia.
- Department of Ophthalmology, Columbia University, New York, NY, USA.
- Shri Bhagwan Mahavir Vitreoretinal Services, Sankara Nethralaya, Chennai, India.
Zitieren
APA
Khan, R., Maseedupally, V., Thakoor, K. A., Raman, R., & Roy, M. (2025). Noninvasive Anemia Detection and Hemoglobin Estimation from Retinal Images Using Deep Learning: A Scalable Solution for Resource-Limited Settings. Translational Vision Science & Technology. https://doi.org/10.1167/tvst.14.1.20
Vancouver
Khan R, Maseedupally V, Thakoor KA, Raman R, Roy M. Noninvasive Anemia Detection and Hemoglobin Estimation from Retinal Images Using Deep Learning: A Scalable Solution for Resource-Limited Settings. Translational Vision Science & Technology. 2025. doi:10.1167/tvst.14.1.20
BibTeX
@article{Khan2025,
author = {Khan, Rehana and Maseedupally, Vinod and Thakoor, Kaveri A and Raman, Rajiv and Roy, Maitreyee},
title = {Noninvasive Anemia Detection and Hemoglobin Estimation from Retinal Images Using Deep Learning: A Scalable Solution for Resource-Limited Settings},
journal = {Translational Vision Science & Technology},
year = {2025},
doi = {10.1167/tvst.14.1.20}
}
EUVIMED