Erythrocyte classification using Alexnet and simple CNN
Penulis/Author
Prof. Drs. Agus Harjoko, M.Sc., Ph.D. (1); Dr. Dyah Aruming Tyas, S.Si. (2); Prof. Dra. Sri Hartati, M.Sc., Ph.D. (3); Dr. dr. Tri Ratnaningsih, Sp.PK(K).,M.Kes. (4)
Tanggal/Date
2023
Kata Kunci/Keyword
Abstrak/Abstract
One examination method to support thalassemia diagnosis is a blood morphological examination of the patient’s peripheral blood smear. However, manual analysis of peripheral blood smears requires a lot of time, special expertise, and expert eye fatigue. This paper proposes a computer vision method using deep learning to assist experts in examining peripheral blood smears. The dataset consists of nine types of erythrocytes that appear in thalassemia patients. The image size normalization was conducted before the deep learning model uses the image. Data augmentation was undertaken to increase the number of data in the datasets. The transfer learning approach is used to improve classification results. The erythrocyte classification result using Alexnet and simple CNN has been compared. The best performance of Alexnet model reached 95.92?curacy, 91.46% sensitivity, and 99.48% specificity.
