Update README.md
Browse files
README.md
CHANGED
|
@@ -15,13 +15,13 @@ tags:
|
|
| 15 |
|
| 16 |
**Sequence-agnostic whole-liver segmentation on abdominal MRI.**
|
| 17 |
|
| 18 |
-
LiverSegMRI is a
|
| 19 |
|
| 20 |
- T1-weighted in- and opposed-phase
|
| 21 |
-
- pre-contrast and dynamic post-contrast (early and late arterial, portal venous, transitional or delayed)
|
| 22 |
-
- hepatobiliary phase
|
| 23 |
- T2-weighted
|
| 24 |
-
-
|
| 25 |
|
| 26 |
| Resource | Link |
|
| 27 |
|---|---|
|
|
@@ -108,7 +108,7 @@ External test set, LiverSegMRI vs comparators:
|
|
| 108 |
|
| 109 |
Radar plots of patient-wise mean Dice for the three models, by MRI sequence type (**A**, internal test; **B**, external test) and by morphologic subgroup (**C**, internal; **D**, external). Each axis is one sequence type or subgroup; the values under each plot list the models in the same order as the axes. LiverSegMRI encloses both comparators on every axis.
|
| 110 |
|
| 111 |
-
|
| 112 |
|
| 113 |
ADC = apparent diffusion coefficient, AP = arterial phase, DWI = diffusion-weighted imaging, EAP = early arterial phase, HBP = hepatobiliary phase, PVP = portal venous phase, T1W = T1-weighted, T2W = T2-weighted, TP/DP = transitional/delayed phase.
|
| 114 |
|
|
@@ -116,13 +116,13 @@ ADC = apparent diffusion coefficient, AP = arterial phase, DWI = diffusion-weigh
|
|
| 116 |
|
| 117 |

|
| 118 |
|
| 119 |
-
|
| 120 |
|
| 121 |
-
- **A–D,
|
| 122 |
-
- **E–H, T2-weighted imaging
|
| 123 |
-
- **I–L,
|
| 124 |
|
| 125 |
-
|
| 126 |
|
| 127 |
See the paper for sequence-wise, subgroup, failure, and label-matched analyses.
|
| 128 |
|
|
|
|
| 15 |
|
| 16 |
**Sequence-agnostic whole-liver segmentation on abdominal MRI.**
|
| 17 |
|
| 18 |
+
LiverSegMRI is a nnU-Net v2 (`3d_fullres`, `nnUNetTrainerNoMirroring`) based, sequence agnostic MRI segmentation model that segments the whole liver (3D) on a single abdominal MRI sequence. It handles:
|
| 19 |
|
| 20 |
- T1-weighted in- and opposed-phase
|
| 21 |
+
- T1W pre-contrast and dynamic post-contrast (early and late arterial, portal venous, transitional or delayed)
|
| 22 |
+
- T1W hepatobiliary phase
|
| 23 |
- T2-weighted
|
| 24 |
+
- Diffusion-weighted (DWI) and ADC
|
| 25 |
|
| 26 |
| Resource | Link |
|
| 27 |
|---|---|
|
|
|
|
| 108 |
|
| 109 |
Radar plots of patient-wise mean Dice for the three models, by MRI sequence type (**A**, internal test; **B**, external test) and by morphologic subgroup (**C**, internal; **D**, external). Each axis is one sequence type or subgroup; the values under each plot list the models in the same order as the axes. LiverSegMRI encloses both comparators on every axis.
|
| 110 |
|
| 111 |
+
Relative to conventional T1-weighted phases, Dice falls by 0.011 on DWI and 0.016 on ADC for LiverSegMRI, against 0.071 and 0.085 for TotalSegmentator MRI and 0.181 and 0.145 for MRAnnotator. Subgroup performance (**C**, **D**) stays close to the whole-cohort level for LiverSegMRI in cirrhosis, irregular borders, prior resection, left lobe extension, exophytic lesions and ascites.
|
| 112 |
|
| 113 |
ADC = apparent diffusion coefficient, AP = arterial phase, DWI = diffusion-weighted imaging, EAP = early arterial phase, HBP = hepatobiliary phase, PVP = portal venous phase, T1W = T1-weighted, T2W = T2-weighted, TP/DP = transitional/delayed phase.
|
| 114 |
|
|
|
|
| 116 |
|
| 117 |

|
| 118 |
|
| 119 |
+
Representative qualitative comparison of liver segmentation across MRI sequences and challenging morphologic subgroups. Examples from external and internal test cohorts comparing reference annotations (red) with segmentations generated by LiverSegMRI (blue), TotalSegmentator MRI (orange), and MRAnnotator (green).
|
| 120 |
|
| 121 |
+
- **A–D,** Portal venous phase T1-weighted imaging in a cirrhotic patient with left lobe elongation.
|
| 122 |
+
- **E–H,** T2-weighted imaging in a cirrhotic patient with severe ascites.
|
| 123 |
+
- **I–L,** Diffusion-weighted imaging in a patient with a large intrahepatic cholangiocarcinoma extending to the liver margins.
|
| 124 |
|
| 125 |
+
LiverSegMRI demonstrates more consistent boundary delineation across heterogeneous sequences and complex liver morphologies.
|
| 126 |
|
| 127 |
See the paper for sequence-wise, subgroup, failure, and label-matched analyses.
|
| 128 |
|