Simplify model card with concise usage and MedMLX branding

README.md

@@ -17,38 +17,35 @@ pipeline_tag: image-segmentation
 base_model: MONAI/renalStructures_CECT_segmentation
 ---
 
-# SegResNet Renal CECT Segmentation
+<img src="https://huggingface.co/MedMLX/segresnet-renal-cect-mlx/resolve/main/banner.png" alt="MedMLX — Segment. RENAL CECT / SEGRESNET" width="100%">
 
-Native MLX port of [MONAI renal structures CECT segmentation](https://huggingface.co/MONAI/renalStructures_CECT_segmentation).
-Segment renal structures from three-phase contrast-enhanced CT locally on Apple Silicon.
+# SegResNet · Renal CECT
 
-- Arterial, venous and excretory CT inputs
-- Five renal structure labels
-- Converted MONAI SegResNet checkpoint included
+Segment renal structures from three-phase contrast-enhanced CT with native MLX.
 
-MLX implementation by [MedMLX](https://github.com/MedMLX).
-[GitHub](https://github.com/MedMLX/segresnet-mlx) · [Usage](https://github.com/MedMLX/segresnet-mlx#quick-start) · [Upstream](https://huggingface.co/MONAI/renalStructures_CECT_segmentation)
+[GitHub](https://github.com/MedMLX/segresnet-mlx) · [Files](https://huggingface.co/MedMLX/segresnet-renal-cect-mlx/tree/main) · [Docs](https://github.com/MedMLX/segresnet-mlx/blob/main/README.md#quick-start)
 
-**Requires the companion `segresnet-mlx` runtime.** Follow the quick start below.
+| Input | Output |
+| :--- | :--- |
+| Arterial, venous + excretory CT | Five renal structure labels |
 
-## Requirements
-
-Apple Silicon Mac with Metal GPU access, Python 3.13 or 3.14 and [uv](https://docs.astral.sh/uv/).
-The weights are included here; checkpoint conversion is not needed.
+**Apple Silicon · Metal · Python 3.13 / 3.14**
 
 ## Quick start
 
 ```bash
 uv venv --python 3.13
 source .venv/bin/activate
-uv pip install "segresnet-mlx @ https://github.com/MedMLX/segresnet-mlx/releases/download/v0.2.1/segresnet_mlx-0.2.1-py3-none-any.whl"
+
+repo="https://github.com/MedMLX/segresnet-mlx"
+release="$repo/releases/download/v0.2.1"
+uv pip install "$release/segresnet_mlx-0.2.1-py3-none-any.whl"
 uv tool install huggingface-hub
 
 hf download MedMLX/segresnet-renal-cect-mlx --local-dir models
 ```
 
-Authenticate with `hf auth login` if repository access is required.
-Run this example in the same environment, replacing the input paths with your own:
+Replace the example input paths with your own files.
 
 ```python
 from segresnet_mlx.medmlx import run
@@ -64,66 +61,10 @@ result = run(
 print(result["outputs"])
 ```
 
-## Input and output
-
-Input is three 3D NIfTI CT volumes on the same voxel grid: arterial, venous
-and excretory phases, in that order.
-
-Output is `renalStructures_CECT_segmentation_mask.nii.gz` on the input grid.
-Labels: 0 background, 1 artery, 2 vein, 3 ureter, 4 neoplasm, 5 parenchyma.
-
-## Technical details
-
-The companion runtime is [v0.2.1](https://github.com/MedMLX/segresnet-mlx/releases/tag/v0.2.1), source `b5cc265cd0426fe8f64b40a8ed9be4c42a599724`, with `medmlx-core==0.2.3`. All 89 tensors here exactly match a fresh CPU host conversion of the pinned renal checkpoint through that installed release's public `convert_state_dict` API. The weights were retained unchanged.
-
-Its fresh installed-wheel suite passed 145 tests with zero skips, including 12 released renal-checkpoint cases with independent MONAI references and unchanged numerical gates. The default runtime arithmetic profile is `torch-order-fp32`; compensated profiles and their reference precision are separate contracts. The current release already contains the renal operator correction: the retained patch below documents the historical comparison and is not an installation step.
-
-The following full-volume measurements retain their original source revision, arithmetic profile and single-case scope. They do not establish clinical or tumor anatomical accuracy.
-
-Historical native result: **success**. Original-code comparison: **pass**, `minimum per-label mask Dice` = `1.0`.
-
-Corrected October 12 native path matches all 85,089,840 raw FP32 logits and all 5,935,600 exported mask voxels in a fresh MONAI CPU comparison. The unchanged tolerance is rtol=atol=1e-4. Tumor anatomical correctness is unverified.
-
-These are recorded results for one configuration, not a new benchmark or an
-estimate of clinical accuracy. The [native run](https://huggingface.co/MedMLX/segresnet-renal-cect-mlx/blob/main/native-run.json)
-and [original-code comparison](https://huggingface.co/MedMLX/segresnet-renal-cect-mlx/blob/main/reference-comparison.json)
-retain the commands, precision, geometry and output checks.
-
-<details>
-<summary>Checkpoint provenance and recorded configuration</summary>
-
-Recorded configuration: **MONAI renalStructures_CECT_segmentation (SegResNet, 3-phase CECT)**.
-
-Evaluated package revision: `0503a9a3ad1c1c4f2fa0abd033b31c223763b43f` plus the retained [renal correction](https://huggingface.co/MedMLX/segresnet-renal-cect-mlx/blob/main/segresnet-mlx-renal-fix.patch).
-
-Recorded input: CPTAC-CCRCC (TCIA), patient C3L-01458, CC BY 4.0.
-
-Original publisher: MONAI.
-Original implementation: [upstream source](https://huggingface.co/MONAI/renalStructures_CECT_segmentation).
-Source revision or version: `8ccbcd9573c004dc435d1913c0459ccd1a110ed1`.
-Original checkpoint: [pinned checkpoint](https://huggingface.co/MONAI/renalStructures_CECT_segmentation/resolve/8ccbcd9573c004dc435d1913c0459ccd1a110ed1/models/model.pt).
-
-Weights were converted with the companion MLX package, without retraining.
-Conversion changes tensor layout or storage as required by that implementation.
-
-The [replay harness](https://github.com/MedMLX/Med-MLX/blob/main/benchmarks/README.md)
-describes how to reproduce the recorded configuration with local paths.
-
-</details>
-
-## Intended use
-
-Research and education. Outputs require human review and are not intended for
-clinical diagnosis or treatment decisions.
-
-## License
+All three CT phases must share the same voxel grid.
 
-Weights: **Apache-2.0** ([license](https://huggingface.co/MedMLX/segresnet-renal-cect-mlx/blob/main/LICENSE)).
-Upstream code: **Apache-2.0**. MLX port code:
-[Apache-2.0](https://github.com/MedMLX/segresnet-mlx/blob/main/LICENSE).
+## Use & license
 
-Retain the [attribution and notices](https://huggingface.co/MedMLX/segresnet-renal-cect-mlx/blob/main/NOTICE) when redistributing
-the bundle or a conversion:
+For research and education. Not validated for clinical use.
 
-- Retain the applicable license, copyright and attribution notices; identify the upstream checkpoint, authors, and MLX conversion changes.
-- Include Apache-2.0, retain applicable upstream NOTICE content, and mark modifications.
+Weights: [Apache-2.0](https://huggingface.co/MedMLX/segresnet-renal-cect-mlx/blob/main/LICENSE). [Notices](https://huggingface.co/MedMLX/segresnet-renal-cect-mlx/blob/main/NOTICE).