Skip to content

Latest commit

 

History

History
36 lines (24 loc) · 862 Bytes

README.md

File metadata and controls

36 lines (24 loc) · 862 Bytes

COVID-19 CT Detection

Overview

Pretrained (imagenet) ResNet50 with 3 classification. Achieves 97.2% test accuracy. Use Grad-CAM for infected area segmentation.

Image Enhancement

Gamma transform and CLAHE avatar avatar avatar avatar

Datasets:

[1]Chowdhury [2]IEEE

Train-Validation Split

COVID-19 Viral Pneumonia Normal
Total 756 1361 1422
Train 600 1200 1200
Test 156 161 222

Train Accuracy

avatar

Confusion Matrix

avatar

Heatmap for Infected Area

avatar