Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,19 @@ license: cc-by-nc-sa-4.0
|
|
| 3 |
---
|
| 4 |
This model is an object detection model trained with tensorflow object detection API, published with the paper [Edge Artificial Intelligence for real-time automatic quantification of filariasis in mobile microscopy](https://www.medrxiv.org/content/10.1101/2023.08.02.23293538v1)
|
| 5 |
|
| 6 |
-
Model description:
|
| 7 |
-
Developed by: Spotlab
|
| 8 |
-
Model type: SSD mobilenet v2
|
| 9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
This model is an object detection model trained with tensorflow object detection API, published with the paper [Edge Artificial Intelligence for real-time automatic quantification of filariasis in mobile microscopy](https://www.medrxiv.org/content/10.1101/2023.08.02.23293538v1)
|
| 5 |
|
| 6 |
+
- Model description:
|
| 7 |
+
- Developed by: Spotlab
|
| 8 |
+
- Model type: SSD mobilenet v2
|
| 9 |
+
- Classes: microfilaria
|
| 10 |
+
- Datasets:
|
| 11 |
+
- Training set: 700 field of view images (100 magnification) from 85 samples with 1965 microfilarias
|
| 12 |
+
- Validation set: 173 field of view images (100 magnification) from 30 samples with 328 microfilarias
|
| 13 |
+
- Test set: 453 field of view images (100 magnification) from 30 samples with 328 microfilarias
|
| 14 |
+
|
| 15 |
+
- Results:
|
| 16 |
+
- On validation set: 88.17% precision, 91.62% recall, and 89.85% f1 score.
|
| 17 |
+
- On test set: 94.14% precision, 91.90% recall, and 93.01% f1 score.
|
| 18 |
+
Example detections
|
| 19 |
+

|
| 20 |
+

|
| 21 |
+
|