A Comparative Study of Deep Learning and Transfer Learning in Detection of Diabetic Retinopathy
| dc.contributor.author | Kamiri, Jackson | |
| dc.contributor.author | Wambugu, Geoffrey M. | |
| dc.contributor.author | Oirere, Aaron M. | |
| dc.date.accessioned | 2022-06-24T07:06:39Z | |
| dc.date.available | 2022-06-24T07:06:39Z | |
| dc.date.issued | 2022 | |
| dc.identifier.citation | International Journal of Computer Applications Technology and Research Volume 11–Issue 07, 247-254, 2022, ISSN:-2319–8656 DOI:10.7753/IJCATR1107.1001 | en_US |
| dc.identifier.issn | 2319–8656 | |
| dc.identifier.uri | https://www.researchgate.net/publication/361435221_A_Comparative_Study_of_Deep_Learning_and_Transfer_Learning_in_Detection_of_Diabetic_Retinopathy | |
| dc.identifier.uri | http://hdl.handle.net/123456789/6107 | |
| dc.description.abstract | Computer vision has gained momentum in medical imaging tasks. Deep learning and Transfer learning are some of the approaches used in computer vision. The aim of this research was to do a comparative study of deep learning and transfer learning in the detection of diabetic retinopathy. To achieve this objective, experiments were conducted that involved training four state-ofthe-art neural network architectures namely; EfficientNetB0, DenseNet169, VGG16, and ResNet50. Deep learning involved training the architectures from scratch. Transfer learning involved using the architectures which are pre-trained using the ImageNet dataset and then fine-tuning them to solve the task at hand. The results show that transfer learning outperforms learning from scratch in all three models. VGG16 achieved the highest accuracy of 84.12% in transfer learning. Another notable finding is that transfer learning is able to not only achieve high accuracy with very few epochs but also starts higher than deep learning in the first epoch. This study has also demonstrated that in image processing tasks there are a lot of transferrable features since the ImageNet weights worked well in the Diabetic retinopathy detection task. | en_US |
| dc.language.iso | en | en_US |
| dc.subject | Meta-Learning, Transfer learning, Deep learning, Medical Image processing, Diabetic Retinopathy. | en_US |
| dc.title | A Comparative Study of Deep Learning and Transfer Learning in Detection of Diabetic Retinopathy | en_US |
| dc.type | Article | en_US |
Files in this item
This item appears in the following Collection(s)
-
Journal Articles (CI) [104]
Related items
Showing items related by title, author, creator and subject.
-
E-LEARNING IN SELECTED PUBLIC MIDDLE LEVEL AND HIGHER LEARNING INSTITUTIONS IN UASIN GISHU COUNTY, KENYA
(2015-10)With the current technological innovations and the potential to provide high quality education unconstrained by time and space, e-Learning is increasingly becoming a popular and significant mode of delivering instructions ... -
Diversity of African forest mollusc faunas: what we have learned since Solem (1984)
(2005)We report on studies in Tanzania, Kenya, Uganda and South Africa over the past 22 years that have yielded estimates of land-snail diversity in the main forest types occurring in East and eastern southern Africa. ... -
A Novel Hybrid Deep Learning Model for Early Detection of Diabetic Retinopathy
(, 2021)Diabetic retinopathy is one of the most frightening complications of diabetes mellitus affecting the working-age population worldwide leading to irreversible blindness if left untreated. A major challenge is early detection, ...
