Implementasi Jaringan Saraf Konvolusional dengan Inception-V3 untuk Deteksi Katarak Menggunakan Gambar Digital Funduskopi
Submission Date: 2022-08-02 13:42:07
Accepted Date: 2023-05-01 00:00:00
Abstract
Katarak merupakan salah satu penyakit mata yang paling serius yang dapat menyebabkan kebutaan. Deteksi dan pengobatan dini dapat mengurangi kebutaan pada pasien katarak. Seiring berkembangnya teknologi pelayanan kesehatan saat ini mengintegrasikan alat kesehatan dan teknologi informasi untuk meningkatkan kualitas dan produktivitas dalam pelayanan kesehatan. Hasil gambar funduskopi atau gambar bagian belakang dan dalam mata (fundus) dapat digunakan untuk memprediksi katarak. Dalam Penelitian ini diimplementasikan Convolutional Neural Network (CNN) dengan arsitektur Inception-V3 dalam deteksi katarak berdasarkan gambar digital funduskopi. Terdapat 3 jenis citra fundus yang digunakan yaitu citra fundus normal, citra fundus katarak, dan citra fundus degenerasi makula. Data gambar fundus dipraproses menggunakan histogram equalization dan Contrast Limited Adaptive Histogram Equalization (CLAHE) terhadap channel hijau. Hasil terbaik pada Penelitian ini adalah model dengan praproses CLAHE dengan Fine Tuning yang memiliki akurasi sebesar 98,33%.
Keywords
Convolutional Neural Network (CNN); Inception-V3; Katarak
CC Licencing
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal 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) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
- Authors retain copyright and grant the journal 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) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Refbacks
- There are currently no refbacks.
Jurnal Sains dan Seni ITS by Lembaga Penelitian dan Pengabdian Kepada Masyarakat, LPPM-ITS is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at https://ejurnal.its.ac.id/index.php/sains_seni.