| --- |
| license: mit |
| tags: |
| - biology |
| - plant-biology |
| - microscopy |
| - image-segmentation |
| - cell-type-classification |
| - cellpose |
| - dinov2 |
| - lightgbm |
| library_name: rootscope |
| pipeline_tag: image-classification |
| --- |
| |
| # RootScope: Cross-species Root Cell-Type Classification from Confocal Microscopy Images |
|
|
| Trained weights for [RootScope](https://github.com/ct-tranchau/Rootscope). |
| Give RootScope a confocal cross-section TIFF of a root. It segments every cell |
| with Cellpose-SAM and labels each one as one of nine cell types: root cap, |
| epidermis, exodermis, cortex, endodermis, pericycle, stele, xylem, phloem. |
| The package downloads these weights on first use. |
|
|
| ## Files |
|
|
| | File | Size | What it is | |
| |---|---|---| |
| | `v4/backbone.pt` | 346 MB | DINOv2 ViT-B/14, fine-tuned on cell crops (`meta.json` next to it records the architecture; keep them together) | |
| | `v4/lgbm_s42.joblib` | 170 MB | LightGBM, seed 42: one model per refinement round, scaler, feature names, class order | |
| | `v4/lgbm_s1.joblib`, `v4/lgbm_s7.joblib` | 170 MB each | the other two seeds; seed 42 alone works, all three reproduce the published result | |
|
|
| ## Performance |
|
|
| | | accuracy | macro-F1 | |
| |---|---|---| |
| | round 1 (no neighbor context) | 0.845 | | |
| | final | 0.881 (95% CI 0.858 to 0.905) | 0.852 | |
|
|
| Per class F1: root cap 97.7, epidermis 89.8, exodermis 85.6, cortex 93.4, |
| endodermis 88.8, pericycle 86.5, stele 84.0, xylem 71.4, phloem 69.5. |
| Stele, xylem and phloem are the hard classes; most of their confusion is |
| among themselves. |
|
|
| ## Author |
|
|
| Tran Chau (tnchau@vt.edu) |
|
|
