A Lightweight Deep Learning Model for Retinopathy of Prematurity Classification in eHealth Applications

Basit Öğe Kaydı
dc.contributor.authorMowla, Neazmul
dc.contributor.authorMowla, Md. Najmul
dc.contributor.authorRabie, Khaled
dc.contributor.authorAlsinglawi, Belal
dc.date.accessioned2026-02-27T07:33:18Z
dc.date.available2026-02-27T07:33:18Z
dc.date.issued2025
dc.description21st International Wireless Communications and Mobile Computing-IWCMC-Annual
dc.description.abstractRetinopathy of Prematurity (ROP) is a vision-threatening condition in premature infants requiring timely and accurate diagnosis to prevent blindness. While electronic health (eHealth) technologies promise to improve neonatal care, automating ROP diagnosis faces challenges such as limited labeled datasets, architectural complexity, and high computational demands. This study introduces LightEyeNet, a lightweight deep-learning architecture optimized for eHealth applications in ROP severity classification. By integrating DenseNet121 and a channel-wise residual attention network block, LightEyeNet enhances diagnostic accuracy and efficiency. Explainable AI techniques, including Grad-CAM and LIME, further improve transparency and clinical interpretability. LightEyeNet achieves 96.28% testing accuracy, outperforming state-of-the-art pre-trained networks, including DenseNet201 (95.78%, + 0.5%), Inception-V3 (93.80%, + 2.48%), Xception (94.54%, + 1.74%), and EfficientDense (87.10%, + 9.18%). Furthermore, LightEyeNet is the most compact architecture among these, with a size of 2.45 MB, compared to Efficient-Dense (6.88 MB), Inception-V3 (3.56 MB), Xception (21.48 MB), and DenseNet201 (5.05 MB). With a specificity of 0.99, a sensitivity of 0.95, and an AUC score of 0.99 across five ROP severity classes, LightEyeNet demonstrates a balance of superior performance and efficiency.
dc.identifier.doi10.1109/IWCMC65282.2025.11059591
dc.identifier.endpage232
dc.identifier.isbn979-8-3315-0888-3; 979-8-3315-0887-6
dc.identifier.issn2376-6492
dc.identifier.startpage227
dc.identifier.urihttp://dx.doi.org/10.1109/IWCMC65282.2025.11059591
dc.identifier.urihttps://hdl.handle.net/20.500.14669/4537
dc.identifier.wosWOS:001547037100039
dc.indekslendigikaynakWeb of Science
dc.language.isoen
dc.publisherIEEE
dc.relation.ispartof2025 International Wireless Communications and Mobile Computing, Iwcmc
dc.relation.ispartofseriesInternational Wireless Communications and Mobile Computing Conference
dc.relation.publicationcategoryKonferans ��esi - Uluslararas� - Kurum ��retim Eleman�
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20260302
dc.subjectRetinopathy of Prematurity (ROP)
dc.subjecteHealth
dc.subjectResidual Attention Network Block
dc.subjectConvolutional Neural Network
dc.subjectMedical Imaging Classification
dc.titleA Lightweight Deep Learning Model for Retinopathy of Prematurity Classification in eHealth Applications
dc.typeProceedings Paper

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu