Skip to content

Latest commit

 

History

History
19 lines (15 loc) · 916 Bytes

README.md

File metadata and controls

19 lines (15 loc) · 916 Bytes

Pneumonia Detection

Training classification model that can analyze the chest X-rays and help in the accurate diagnosis of Pneumonia

Dataset

https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia

Overview:

  1. Imported chest X-ray images, resized to 256*256 pixel size and flattened the images
  2. Fed into Autoencoder model for dimension reduction
  3. Trained SVM on dimensionally reduced data with RBF kernel
  4. Carried out image augmentation on X-ray images and trained CNN model on augmented data
  5. Used F1 Score as evaluation metric for early stopping

Architecture:

AutoEncoder

nndig

CNN

Screenshot 2022-08-06 003035