Update README.md
Browse files
README.md
CHANGED
|
@@ -17,16 +17,17 @@ Input 512×512, ImageNet normalization, scale 0.32 µm/px.
|
|
| 17 |
|
| 18 |
## 1. Segmentation performance (validation, n = 49)
|
| 19 |
|
| 20 |
-
| Class
|
| 21 |
-
|-----------------|-------|
|
| 22 |
-
| Background (0)
|
| 23 |
-
| Epithelium (1)
|
| 24 |
-
| Lumen (2)
|
| 25 |
-
|
|
| 26 |
|
| 27 |
-
-
|
|
|
|
|
|
|
| 28 |
|
| 29 |
-
> Metrics reported on the validation set, never on train.
|
| 30 |
|
| 31 |

|
| 32 |
|
|
@@ -106,10 +107,10 @@ Bias = predicted − manual.
|
|
| 106 |
and fixation variation.
|
| 107 |
|
| 108 |
**Known biases:**
|
| 109 |
-
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
(
|
| 113 |
- **Lumen perimeter**: good mean agreement (CCC 0.93, bias ≈ 0) but wide LoA (±110 µm):
|
| 114 |
varies case by case due to tracing convention.
|
| 115 |
|
|
|
|
| 17 |
|
| 18 |
## 1. Segmentation performance (validation, n = 49)
|
| 19 |
|
| 20 |
+
| Class | IoU | Dice / F1 | clDice |
|
| 21 |
+
|----------------|-------|-----------|--------|
|
| 22 |
+
| Background (0) | 0.990 | 0.995 | — |
|
| 23 |
+
| Epithelium (1) | 0.938 | 0.968 | 0.984 |
|
| 24 |
+
| Lumen (2) | 0.935 | 0.967 | 0.968 |
|
| 25 |
+
| Mean | mIoU 0.954 | 0.977 | — |
|
| 26 |
|
| 27 |
+
Per-image (n = 49): mIoU 0.953 ± 0.013 (min 0.900, median 0.955);
|
| 28 |
+
mDice 0.976 ± 0.007 (min 0.946). No image falls below mIoU 0.90.
|
| 29 |
+
Metrics computed on the post-processed predicted masks vs. reference masks; validation set, never train.
|
| 30 |
|
|
|
|
| 31 |
|
| 32 |

|
| 33 |
|
|
|
|
| 107 |
and fixation variation.
|
| 108 |
|
| 109 |
**Known biases:**
|
| 110 |
+
- Boundary accuracy vs. reference masks (validation, n = 49):
|
| 111 |
+
- Tubule outer boundary: ASSD 0.59 µm, HD95 1.54 µm, mean signed displacement +0.13 µm (Boundary-F1 @1.6 µm = 0.97).
|
| 112 |
+
- Lumen boundary: ASSD 1.47 µm, HD95 4.99 µm, mean signed displacement −0.05 µm (Boundary-F1 @1.6 µm = 0.75); the larger local variation reflects the convoluted scalloped lumen contour, with no systematic offset.
|
| 113 |
+
The model reproduces the reference masks with sub-pixel mean boundary agreement (signed displacement ≈ 0 for both structures; a +0.13 µm shift accounts for ~0.25% area). The ~+12% / +8% area difference vs. manual ImageJ freehand tracing is therefore a convention difference between the reference masks and the freehand protocol — faithfully inherited by the model — not error introduced by the model. It is systematic (r ≈ 0.99) and preserves shape (AR/roundness CCC ≈ 0.99).
|
| 114 |
- **Lumen perimeter**: good mean agreement (CCC 0.93, bias ≈ 0) but wide LoA (±110 µm):
|
| 115 |
varies case by case due to tracing convention.
|
| 116 |
|