vksfdc2025 commited on
Commit
26c55dc
·
verified ·
1 Parent(s): 2bb6e61

Add model card

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -22,19 +22,19 @@ A VGG16 model fine-tuned for binary classification of chest X-ray images.
22
  ## Model Performance
23
  | Metric | Value |
24
  |--------|-------|
25
- | AUC-ROC | 0.8623 |
26
- | Accuracy | 0.7637 |
27
- | F1-Score | 0.6075 |
28
- | Recall | 0.8115 |
29
- | Specificity | 0.7498 |
30
- | Precision | 0.4854 |
31
 
32
  ## Training Details
33
  - **Base Model:** VGG16 (ImageNet pre-trained)
34
  - **Fine-tuning:** 2-phase (feature extraction + fine-tuning)
35
  - **Dataset:** RSNA Pneumonia Detection Challenge (26,684 patients)
36
  - **Input Size:** 224x224x3
37
- - **Optimal Threshold:** 0.4584 (Youden's J)
38
 
39
  ## Usage
40
  ```python
 
22
  ## Model Performance
23
  | Metric | Value |
24
  |--------|-------|
25
+ | AUC-ROC | 0.8679 |
26
+ | Accuracy | 0.7679 |
27
+ | F1-Score | 0.6156 |
28
+ | Recall | 0.8248 |
29
+ | Specificity | 0.7514 |
30
+ | Precision | 0.4911 |
31
 
32
  ## Training Details
33
  - **Base Model:** VGG16 (ImageNet pre-trained)
34
  - **Fine-tuning:** 2-phase (feature extraction + fine-tuning)
35
  - **Dataset:** RSNA Pneumonia Detection Challenge (26,684 patients)
36
  - **Input Size:** 224x224x3
37
+ - **Optimal Threshold:** 0.4961 (Youden's J)
38
 
39
  ## Usage
40
  ```python