Detecting Retinopathy of Prematurity Disease in Premature Baby Based on Fundus Image Data with CNN Model using VGG19's Architecture
The purpose of this project is to explain how the Convolutional Neural Network method works in detecting Retinopathy of prematurity (ROP) in premature babies, knowing the effect of data augmentation on the model in the application of cases of detection of Retinopathy of prematurity (ROP) in premature infants, and analyzing the performance of the model without data augmentation and with data augmentation to get the best model for the application of Retinopathy of prematurity (ROP) detection cases in premature infants.
Mrs. Devvi Sarwinda, S.Si., M.Kom.
- Deep Learning
- Convolutional Neural Network
- VGG-19 Architecture
- Python
- Jupyter
- Numpy
- OpenCV
- Keras
- TensorFlow
- Data taken from kaggle site here.
- Data augmentation for multiplying the amount of data to be used.
- Labeling image data according the class (ROP or Non ROP).
- Data preparation such as changing images to arrays, resizing, and normalizing.
- Dividing data into train, test, and validation data.
- Utilizing VGG19's Architecture in making CNN classification models.
- Train models and provide evaluation reports.
- Data Augmentation
- Data Processing
- Deep Learning Modeling
- Evaluation and Reporting
Name | Github Account |
---|---|
Hosia Josindra Saragih | github.com/hosiajosindra |
Angelica Patricia | github.com/angelpatriciads |
Annisa Zahra | github.com/annisazahra01 |
Arundhati Naysa Ekhaputri | github.com/arundhatinaysa |
Latifa Aulia Esmananda | github.com/latifaesmananda |