Development of mobile application for detection and grading of diabetic retinopathy
The key to preventing blindness caused by diabetic retinopathy (DR) is regular screening and early recognition during its early stages. Currently, DR grading is done manually by ophthalmologists and trained graders where the process is time-consuming. Therefore, this paper aims to develop a mobile a...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Book Section |
| Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
| Subjects: |
| _version_ | 1796866997409021952 |
|---|---|
| author | Kipli, Kuryati Lee, Yee Hui Tajudin, Nurul Mirza Afiqah Sapawi, Rohana Sahari, Siti Kudnie Awang Mat, Dayang Azra A. Jalil, M. Ray, Kanad Kaiser, M. Shamim Mahmud, Mufti |
| author_facet | Kipli, Kuryati Lee, Yee Hui Tajudin, Nurul Mirza Afiqah Sapawi, Rohana Sahari, Siti Kudnie Awang Mat, Dayang Azra A. Jalil, M. Ray, Kanad Kaiser, M. Shamim Mahmud, Mufti |
| author_sort | Kipli, Kuryati |
| collection | ePrints |
| description | The key to preventing blindness caused by diabetic retinopathy (DR) is regular screening and early recognition during its early stages. Currently, DR grading is done manually by ophthalmologists and trained graders where the process is time-consuming. Therefore, this paper aims to develop a mobile app that can provide DR detection and grading without a professional or doctor. The patients will be referred to ophthalmologists if further evaluations are required. This research builds an image classification within a mobile application by using deep learning techniques which utilized the Google AI technologies: Google TensorFlow and Google Cloud Platform (Cloud AutoML and Cloud storage). Image classification is performed in two layers which involve DR detection and grading. A total of 12,062 fundus images are chosen from the dataset collected and undergo image preprocessing. The preprocessed images are used to train the model in TensorFlow and Cloud AutoML, respectively. The model will be implemented into the mobile application after being trained with high accuracy. The final test accuracy for the MobileNet pretrained model is 82.9%, while averaging precision for the model of Cloud AutoML is 75%. Further research is required to improve the stability of this algorithm and mobile app for real clinical environment settings. |
| first_indexed | 2024-03-05T21:20:34Z |
| format | Book Section |
| id | utm.eprints-101088 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T21:20:34Z |
| publishDate | 2022 |
| publisher | Springer Science and Business Media Deutschland GmbH |
| record_format | dspace |
| spelling | utm.eprints-1010882023-05-27T07:45:23Z http://eprints.utm.my/101088/ Development of mobile application for detection and grading of diabetic retinopathy Kipli, Kuryati Lee, Yee Hui Tajudin, Nurul Mirza Afiqah Sapawi, Rohana Sahari, Siti Kudnie Awang Mat, Dayang Azra A. Jalil, M. Ray, Kanad Kaiser, M. Shamim Mahmud, Mufti QA75 Electronic computers. Computer science The key to preventing blindness caused by diabetic retinopathy (DR) is regular screening and early recognition during its early stages. Currently, DR grading is done manually by ophthalmologists and trained graders where the process is time-consuming. Therefore, this paper aims to develop a mobile app that can provide DR detection and grading without a professional or doctor. The patients will be referred to ophthalmologists if further evaluations are required. This research builds an image classification within a mobile application by using deep learning techniques which utilized the Google AI technologies: Google TensorFlow and Google Cloud Platform (Cloud AutoML and Cloud storage). Image classification is performed in two layers which involve DR detection and grading. A total of 12,062 fundus images are chosen from the dataset collected and undergo image preprocessing. The preprocessed images are used to train the model in TensorFlow and Cloud AutoML, respectively. The model will be implemented into the mobile application after being trained with high accuracy. The final test accuracy for the MobileNet pretrained model is 82.9%, while averaging precision for the model of Cloud AutoML is 75%. Further research is required to improve the stability of this algorithm and mobile app for real clinical environment settings. Springer Science and Business Media Deutschland GmbH 2022 Book Section PeerReviewed Kipli, Kuryati and Lee, Yee Hui and Tajudin, Nurul Mirza Afiqah and Sapawi, Rohana and Sahari, Siti Kudnie and Awang Mat, Dayang Azra and A. Jalil, M. and Ray, Kanad and Kaiser, M. Shamim and Mahmud, Mufti (2022) Development of mobile application for detection and grading of diabetic retinopathy. In: Proceedings of Trends in Electronics and Health Informatics TEHI 2021. Lecture Notes in Networks and Systems, 376 (NA). Springer Science and Business Media Deutschland GmbH, Singapore, pp. 339-349. ISBN 978-981168825-6 http://dx.doi.org/10.1007/978-981-16-8826-3_29 DOI:10.1007/978-981-16-8826-3_29 |
| spellingShingle | QA75 Electronic computers. Computer science Kipli, Kuryati Lee, Yee Hui Tajudin, Nurul Mirza Afiqah Sapawi, Rohana Sahari, Siti Kudnie Awang Mat, Dayang Azra A. Jalil, M. Ray, Kanad Kaiser, M. Shamim Mahmud, Mufti Development of mobile application for detection and grading of diabetic retinopathy |
| title | Development of mobile application for detection and grading of diabetic retinopathy |
| title_full | Development of mobile application for detection and grading of diabetic retinopathy |
| title_fullStr | Development of mobile application for detection and grading of diabetic retinopathy |
| title_full_unstemmed | Development of mobile application for detection and grading of diabetic retinopathy |
| title_short | Development of mobile application for detection and grading of diabetic retinopathy |
| title_sort | development of mobile application for detection and grading of diabetic retinopathy |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT kiplikuryati developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy AT leeyeehui developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy AT tajudinnurulmirzaafiqah developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy AT sapawirohana developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy AT saharisitikudnie developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy AT awangmatdayangazra developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy AT ajalilm developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy AT raykanad developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy AT kaisermshamim developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy AT mahmudmufti developmentofmobileapplicationfordetectionandgradingofdiabeticretinopathy |