Spaces:
Sleeping
Sleeping
dcavadia commited on
Commit Β·
34f59b7
1
Parent(s): 39b64b3
update info
Browse files
app.py
CHANGED
|
@@ -8,27 +8,29 @@ def create_demo():
|
|
| 8 |
|
| 9 |
**Performance Metrics:**
|
| 10 |
- **88% mAP\\@0.5** detection accuracy
|
| 11 |
-
- **
|
| 12 |
- **35+ FPS** real-time processing
|
| 13 |
-
- **YOLOv8 + U-Net** dual architecture
|
| 14 |
|
| 15 |
### π₯ Clinical Capabilities
|
| 16 |
-
- Real-time polyp detection and localization
|
| 17 |
-
- Precise boundary segmentation with
|
| 18 |
-
-
|
|
|
|
| 19 |
- Optimized for endoscopy workflow integration
|
| 20 |
|
| 21 |
### π― Technical Highlights
|
| 22 |
- **Multi-modal AI**: Combined object detection and segmentation
|
| 23 |
- **Clinical-grade performance**: Sub-second processing times
|
| 24 |
-
- **
|
|
|
|
| 25 |
- **Real-time inference**: GPU-accelerated deployment ready
|
| 26 |
|
| 27 |
---
|
| 28 |
|
| 29 |
## π₯ Live System Demonstration
|
| 30 |
|
| 31 |
-
**Real-time EndoSight AI in action** - showcasing automated polyp detection, segmentation,
|
| 32 |
"""
|
| 33 |
|
| 34 |
footer = """
|
|
@@ -49,7 +51,7 @@ def create_demo():
|
|
| 49 |
### π Professional Contact
|
| 50 |
|
| 51 |
**Technical Lead**: Daniel Cavadia
|
| 52 |
-
**Email**: dan.cavadia@gmail.com
|
| 53 |
|
| 54 |
---
|
| 55 |
|
|
@@ -64,16 +66,20 @@ def create_demo():
|
|
| 64 |
# Simple video display (no fancy features in older version)
|
| 65 |
video = gr.Video(
|
| 66 |
value="demo_video.mp4",
|
| 67 |
-
label="EndoSight AI Real-time Detection & Segmentation"
|
| 68 |
)
|
| 69 |
|
| 70 |
gr.Markdown("""
|
| 71 |
### π What You're Seeing:
|
| 72 |
-
- **
|
| 73 |
-
- **
|
| 74 |
-
- **
|
| 75 |
-
- **
|
| 76 |
-
- **
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
""")
|
| 78 |
|
| 79 |
gr.Markdown(footer)
|
|
|
|
| 8 |
|
| 9 |
**Performance Metrics:**
|
| 10 |
- **88% mAP\\@0.5** detection accuracy
|
| 11 |
+
- **75.6% Dice Score** segmentation accuracy
|
| 12 |
- **35+ FPS** real-time processing
|
| 13 |
+
- **YOLOv8 + U-Net** dual architecture with intelligent stabilization
|
| 14 |
|
| 15 |
### π₯ Clinical Capabilities
|
| 16 |
+
- Real-time polyp detection and localization with smooth tracking
|
| 17 |
+
- Precise boundary segmentation with fluid heatmap visualization
|
| 18 |
+
- Intelligent measurement system with anti-fluctuation technology
|
| 19 |
+
- Automated size classification and risk assessment
|
| 20 |
- Optimized for endoscopy workflow integration
|
| 21 |
|
| 22 |
### π― Technical Highlights
|
| 23 |
- **Multi-modal AI**: Combined object detection and segmentation
|
| 24 |
- **Clinical-grade performance**: Sub-second processing times
|
| 25 |
+
- **Intelligent measurement**: Size, area, and morphometric analysis with temporal stabilization
|
| 26 |
+
- **Adaptive visualization**: Real-time heatmaps that adjust to camera movement
|
| 27 |
- **Real-time inference**: GPU-accelerated deployment ready
|
| 28 |
|
| 29 |
---
|
| 30 |
|
| 31 |
## π₯ Live System Demonstration
|
| 32 |
|
| 33 |
+
**Real-time EndoSight AI in action** - showcasing automated polyp detection, intelligent segmentation, stabilized measurement analysis, and clinical classification on endoscopy footage.
|
| 34 |
"""
|
| 35 |
|
| 36 |
footer = """
|
|
|
|
| 51 |
### π Professional Contact
|
| 52 |
|
| 53 |
**Technical Lead**: Daniel Cavadia
|
| 54 |
+
**Email**: [dan.cavadia@gmail.com](mailto:dan.cavadia@gmail.com)
|
| 55 |
|
| 56 |
---
|
| 57 |
|
|
|
|
| 66 |
# Simple video display (no fancy features in older version)
|
| 67 |
video = gr.Video(
|
| 68 |
value="demo_video.mp4",
|
| 69 |
+
label="EndoSight AI Real-time Detection & Segmentation with Intelligent Measurements"
|
| 70 |
)
|
| 71 |
|
| 72 |
gr.Markdown("""
|
| 73 |
### π What You're Seeing:
|
| 74 |
+
- **Cyan bounding boxes**: Real-time polyp detection with smooth tracking
|
| 75 |
+
- **Fluid heatmaps**: Dynamic segmentation visualization that adapts to movement
|
| 76 |
+
- **Bottom-left panels**: Stabilized measurement displays with clinical classifications
|
| 77 |
+
- **Size categories**: Diminutive (<5mm), Small (5-9mm), Large (β₯10mm) classifications
|
| 78 |
+
- **Risk assessment**: Low/Moderate/High risk indicators based on polyp size
|
| 79 |
+
- **Measurement accuracy**: Diameter and area calculations with error margins
|
| 80 |
+
- **Anti-fluctuation**: Intelligent system prevents measurement swings during camera movement
|
| 81 |
+
- **Processing metrics**: Real-time FPS and confidence indicators
|
| 82 |
+
- **Multi-polyp detection**: Simultaneous analysis capability with unique tracking IDs
|
| 83 |
""")
|
| 84 |
|
| 85 |
gr.Markdown(footer)
|