Real-Time Cataract Diagnosis with GhostYOLO: A GhostConv-enhanced YOLO Model
Received: 1 March 2025 | Revised: 23 March 2025 | Accepted: 4 April 2025 | Online: 14 April 2025
Corresponding author: Lahari Puchakayala Lokesh
Abstract
This study presents GhostYOLO, an enhanced YOLO-based model for cataract detection that incorporates GhostConv layers to offer greater accuracy, faster processing, and less memory consumption for real-time diagnosis. Initially, the performance of YOLO models, namely YOLOv5, YOLOv6, YOLOv7, and YOLOv8, was evaluated using 788 normal and 920 cataract images, with YOLOv8n emerging as the best standard model with excellent precision, speed, and efficiency. GhostYOLO models were developed to further improve speed and accuracy. GhostYoloV8n obtained the highest accuracy, speed, and lowest memory usage, while GhostYoLoV7-tiny also performed well. Incorporating GhostConv layers substantially improved cataract detection, increasing efficiency and real-time usage. Real-time tests using a Jetson Nano board demonstrated its efficiency, with 33.5 FPS in live detection, simplifying diagnosis. GhostYoloV8n, with only 1.6 million parameters, is a small but powerful cataract detection tool that allows for faster and more precise medical intervention. This study highlights the benefits of including GhostConv layers in YOLO models, making cataract diagnosis more accurate, efficient, and scalable for clinical applications.
Keywords:
cataract detection, YOLO models, GhostYOLO, GhostConv layers, real-time diagnosis, Jetson nanoDownloads
References
D. Lam et al., "Cataract," Nature Reviews Disease Primers, vol. 1, no. 1, Jun. 2015, Art. no. 15014.
L. P. L, R. Vaddi, M. O. Elish, V. Gonuguntla, and S. S. Yellampalli, "CSDNet: A Novel Deep Learning Framework for Improved Cataract State Detection," Diagnostics, vol. 14, no. 10, Jan. 2024, Art. no. 983.
M. V. Cicinelli, J. C. Buchan, M. Nicholson, V. Varadaraj, and R. C. Khanna, "Cataracts," The Lancet, vol. 401, no. 10374, pp. 377–389, Feb. 2023.
T. Ganokratanaa, M. Ketcham, and P. Pramkeaw, "Advancements in Cataract Detection: The Systematic Development of LeNet-Convolutional Neural Network Models," Journal of Imaging, vol. 9, no. 10, Oct. 2023, Art. no. 197.
K. Krosl et al., "CatARact: Simulating Cataracts in Augmented Reality," in 2020 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Recife/Porto de Galinhas, Brazil, Nov. 2020, pp. 682–693.
D. Allen and A. Vasavada, "Cataract and surgery for cataract," BMJ, vol. 333, no. 7559, pp. 128–132, Jul. 2006.
T. Reis, V. Lansingh, J. Ramke, J. C. Silva, S. Resnikoff, and J. M. Furtado, "Cataract as a Cause of Blindness and Vision Impairment in Latin America: Progress Made and Challenges Beyond 2020," American Journal of Ophthalmology, vol. 225, pp. 1–10, May 2021.
I. McCormick et al., "Effective cataract surgical coverage in adults aged 50 years and older: estimates from population-based surveys in 55 countries," The Lancet Global Health, vol. 10, no. 12, pp. e1744–e1753, Dec. 2022.
X. Li et al., "The association of cooking fuels with cataract among adults aged 50 years and older in low- and middle-income countries: Results from the WHO Study on global AGEing and adult health (SAGE)," Science of The Total Environment, vol. 790, Oct. 2021, Art. no. 148093.
T. J. Ferguson and J. B. Randleman, "Cataract surgery following refractive surgery: Principles to achieve optical success and patient satisfaction," Survey of Ophthalmology, vol. 69, no. 1, pp. 140–159, Jan. 2024.
H. E. Jazayeri et al., "Does Early Repair of Orbital Fractures Result in Superior Patient Outcomes? A Systematic Review and Meta-Analysis," Journal of Oral and Maxillofacial Surgery, vol. 78, no. 4, pp. 568–577, Apr. 2020.
R. Rampat et al., "Artificial Intelligence in Cornea, Refractive Surgery, and Cataract: Basic Principles, Clinical Applications, and Future Directions," The Asia-Pacific Journal of Ophthalmology, vol. 10, no. 3, Jun. 2021, Art. no. 268.
D. Benet and O. J. Pellicer-Valero, "Artificial intelligence: the unstoppable revolution in ophthalmology," Survey of Ophthalmology, vol. 67, no. 1, pp. 252–270, Jan. 2022.
J. P. O. Li et al., "Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective," Progress in Retinal and Eye Research, vol. 82, May 2021, Art. no. 100900.
D. V. Gunasekeran and T. Y. Wong, "Artificial Intelligence in Ophthalmology in 2020: A Technology on the Cusp for Translation and Implementation," The Asia-Pacific Journal of Ophthalmology, vol. 9, no. 2, Apr. 2020, Art. no. 61.
A. L. Pelletier, J. Thomas, and F. R. Shaw, "Vision Loss in Older Persons," American Family Physician, vol. 79, no. 11, pp. 963–970, Jun. 2009.
T. Diwan, G. Anirudh, and J. V. Tembhurne, "Object detection using YOLO: challenges, architectural successors, datasets and applications," Multimedia Tools and Applications, vol. 82, no. 6, pp. 9243–9275, Mar. 2023.
S. Hu et al., "ACCV: automatic classification algorithm of cataract video based on deep learning," BioMedical Engineering OnLine, vol. 20, no. 1, Aug. 2021, Art. no. 78.
W. Sait and A. Rahaman, "A Lightweight Diabetic Retinopathy Detection Model Using a Deep-Learning Technique," Diagnostics, vol. 13, no. 19, Jan. 2023, Art. no. 3120.
S. Hu et al., "Unified Diagnosis Framework for Automated Nuclear Cataract Grading Based on Smartphone Slit-Lamp Images," IEEE Access, vol. 8, pp. 174169–174178, 2020.
R. Angeline, S. Soorya, M. G. Sathyaa, and U. K. Tharun Suriya, "YOLO V8: The AI-Enabled Cataract Detection System," in Smart Trends in Computing and Communications, Singapore, 2024, pp. 463–474.
T. D. D. Tuason, J. Darius C. Garcia, and C. O. Manlises, "Cat Eye Disease Classifier Using YOLOv5," in 2024 7th International Conference on Information and Computer Technologies (ICICT), Honolulu, HI, USA, Mar. 2024, pp. 199–203.
"Eye Health3 Dataset ," Roboflow. https://universe.roboflow.com/cdacm/eye-health3.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788.
J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, Jul. 2017, pp. 6517–6525.
J. Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement." arXiv, Apr. 08, 2018.
A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection," arXiv.org, Apr. 22, 2020.
Ultralytics, "Comprehensive Guide to Ultralytics YOLOv5." https://docs.ultralytics.com/yolov5.
C. Li et al., "YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications." arXiv, Sep. 07, 2022.
S. Ennaama, H. Silkan, A. Bentajer, and A. Tahiri, "Enhanced Real-Time Object Detection using YOLOv7 and MobileNetv3," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19181–19187, Feb. 2025.
C. Y. Wang, A. Bochkovskiy, and H. Y. M. Liao, "YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors," in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, Jun. 2023, pp. 7464–7475.
Ultralytics, "YOLOv8." https://docs.ultralytics.com/models/yolov8.
Downloads
How to Cite
License
Copyright (c) 2025 Puchakayala Lokesh Lahari, Rahul Gowtham Poola, Leela Prasad Gorrepati, Siva Sankar Yellampalli
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
