Detection of abnormalities on chest X-ray images.
We need to find several abnormalities on chest X-ray images.
Example of images
For solving this problem we will apply FasterRCNN, Yolo_v5 using PyTorch and PyTorch_Lightning libraries
And additionally we will build binary classifier to classify image - normal/abnormal
As a result of our work we will build simple web app using Flask which is capable of taking image and detecting abnormalities on it.
For install Yolo v5 run following commands:
- !git clone https://github.com/ultralytics/yolov5
- !mv yolov5/* ./
- !pip install -r requirements.txt
We follow the next steps:
- EDA (notebooks/EDA.ipynb)
- Modeling : Yolo v5 (notebooks/Yolov5.ipynb)
- Modeling : FasterRCNN (notebooks/FasterRCNN.ipynb)
- Modeling : binary classifier - abnormal/normal image (notebooks/binary_classifier.ipynb)
-
https://www.kaggle.com/raddar/vinbigdata-competition-jpg-data-2x-downsampled
-
https://www.kaggle.com/c/vinbigdata-chest-xray-abnormalities-detection/data
Example of web app for abnormalities detection
Step 1. Uploading image
Step 2. Click submit and see the result