Image Classification Method in DR Image Based on Transfer Learning

Until now many cancer cases have been discovered in their early stages based on Computer Aided Diagnosis (CAD) system. There are many methods in the medical image processing field have been proposed to address this issue, and the result of these methods was deficient. Further, the application of AI...

Full description

Saved in:
Bibliographic Details
Main Authors: Alsabahi, Y. A. L., Fan, Lei, Feng, Xiaoyi
Format: Conference Proceeding
Language:English
Subjects:
Biomedical image processing
Breast cancer
CAD
Deep learning
DR images
Image processing
Medical diagnostic imaging
medical image
Training
Transfer Learning
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Until now many cancer cases have been discovered in their early stages based on Computer Aided Diagnosis (CAD) system. There are many methods in the medical image processing field have been proposed to address this issue, and the result of these methods was deficient. Further, the application of AI in DR images is not widespread in hospitals. The classification process in the DR image is more difficult than other types of images. In this paper, we use transfer learning which is based on Inception V3 model to classify the DR images. We used the weight of Inception V3 model which was trained in the ImageNet dataset, and fine-tuning in our own dataset. Comparing to other proposed methods, our result had a higher accuracy.
ISSN:2154-512X
DOI:10.1109/IPTA.2018.8608157