TBX11K SSD300 — Tuberculosis Object Detection
SSD300 (VGG16 backbone) optimized and trained on 11701 validated records from the TBX11K dataset.
Per-class Performance (mAP@0.5 Threshold)
| Class | AP@0.5 | Clinical Diagnostic Target |
|---|---|---|
| healthy | 0.2669 | Normal anatomical lung fields & latent signals |
| sick_non_tb | 0.3372 | Non-TB pulmonary anomalies (Pneumonia, Bronchitis) |
| active_tb | 0.2987 | Confirmed active Tuberculosis visual lesions |
Global Summary Scores (900 Isolated Test Samples)
- Global Test mAP@0.5 : 0.3892 (38.9%)
- Global Test COCO mAP@0.5:0.95 : 0.2669 (26.7%)
- Global Test mAP@0.75 : 0.1446 (14.5%)
Classes & Target Deployment Indices
- 0:
__background__(Strict PyTorch Detection Placeholder) - 1:
healthy(Includes clear lungs and latent tuberculosis signals) - 2:
sick_non_tb(Other pulmonary conditions / non-TB sickness) - 3:
active_tb(Active Tuberculosis visual lesions)
Model Configuration
- Input Resolution: 300x300 pixels
- Optimization Engine: AdamW + 5-Epoch Linear Warmup & Cosine Annealing
- Oversampling Strategy: Square-Root Weighted Random Sampler targeting Active TB regions