seqseg 2.1.6__tar.gz → 2.1.7__tar.gz

{seqseg-2.1.6 → seqseg-2.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: seqseg
-Version: 2.1.6
+Version: 2.1.7
 Summary: A deep learning-based medical image blood vessel tracking and segmentation tool.
 Author-email: Numi Sveinsson Cepero <numi@berkeley.com>
 License: Apache-2.0
@@ -23,12 +23,11 @@ Requires-Dist: SimpleITK>2
 Requires-Dist: PyYAML==6.0.3
 Requires-Dist: nnunetv2>=2.5.1
 Requires-Dist: scipy
+Requires-Dist: vascular-segment-sampler>=0.6.0
 Provides-Extra: dev
 Requires-Dist: pytest>=7; extra == "dev"
 Provides-Extra: viz
 Requires-Dist: matplotlib>=3.5; extra == "viz"
-Provides-Extra: train
-Requires-Dist: vascular-segment-sampler>=0.1.0; extra == "train"
 Dynamic: license-file
 
 ![example workflow](https://github.com/numisveinsson/SeqSeg/actions/workflows/python-app.yml/badge.svg)
@@ -48,10 +47,10 @@ Dynamic: license-file
 <p align="center">
   <a href="https://rdcu.be/dU0wy"><img src="https://img.shields.io/badge/Paper-Annals%20of%20BME-blue" alt="Paper"/></a>
   <a href="https://github.com/numisveinsson/SeqSeg/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-green.svg" alt="License"/></a>
-  <a href="https://python.org"><img src="https://img.shields.io/badge/Python-3.11-blue.svg" alt="Python"/></a>
+  <a href="https://www.python.org"><img src="https://img.shields.io/badge/Python-3.9%2B-blue.svg" alt="Python 3.9+"/></a>
 </p>
 
-> **News:** SeqSeg now outputs a full SimVascular project in the `simvascular/` subdirectory — open it directly in SimVascular with automatic pathlines and contours for every segmented branch.
+> **News:** SeqSeg writes a full SimVascular project in the `simvascular/` subdirectory — open it directly in SimVascular with pathlines and contours for every segmented branch.
 
 ---
 
@@ -64,7 +63,7 @@ SeqSeg segments vessels **sequentially**, taking steps along vessel centerlines
 - 🩻 **Multi-modal** — works with CT and MR 3D medical images
 - 📏 **Scalable** — vessels from ~1mm coronaries to ~30mm aortas
 - ✅ **Clinically validated** — coronary, aortic, cerebral, and pulmonary anatomies (pre-trained weights for aorta CT/MR and coronary CT)
-- ⚡ **Fast** — ~2–10 min per case, Dice > 0.9 on validation, runs on CPU or GPU
+- ⚡ **Fast** — on CPU, about 2–5 minutes for an aorta, 5–15 for a coronary tree, and 10–30 for a cerebral tree. GPU is faster. Details in [Benchmarks](docs/benchmarks.md).
 
 <p align="center">
   <img src="https://raw.githubusercontent.com/numisveinsson/SeqSeg/main/seqseg/assets/mr_model_tracing_fast_shorter.gif" alt="SeqSeg Demo"/><br/>
@@ -73,89 +72,82 @@ SeqSeg segments vessels **sequentially**, taking steps along vessel centerlines
 
 ## What's new in 2.x
 
-SeqSeg **2.0** refactors the package around a clearer CLI and a stable Python API. Existing batch workflows still work; legacy invocations without a subcommand (e.g. `seqseg -data_dir ...`) are rewritten to `seqseg run batch` automatically.
+SeqSeg **2.0** uses subcommands. A command from 1.x that starts with a flag, such as `seqseg -data_dir ...`, still runs: it is rewritten to `seqseg run batch` automatically.
 
-### Command-line interface
+### Commands
 
-| Feature | Description |
+| Command | Description |
 | -------- | ----------- |
-| **`seqseg run batch`** | Classic dataset batch tracing (preferred entry point) |
-| **`seqseg run single`** | One volume + seeds: stages under `<outdir>/_seqseg_single_staging/`, then runs like batch |
-| **`seqseg run plus batch`** | Global nnU-Net sweep, then SeqSeg (replaces monolithic `seqseg_plus` script flow) |
-| **`seqseg init dataset`** | Scaffold `images/`, `centerlines/`, `truths/`, and template `seeds.json` |
-| **`seqseg paths init` / `set` / `show`** | Save default nnU-Net / data / out dirs in `~/.seqseg/paths.yaml` |
-| **`seqseg train prepare`** | Extract patches or whole volumes + build nnU-Net Dataset (needs `pip install "seqseg[train]"`) |
-| **`seqseg train nnunet`** | Run nnU-Net plan/preprocess and training |
-| **`seqseg doctor`** | Check imports (SimpleITK, vtk, nnunetv2, scipy, optional sampler) and paths |
-| **`seqseg config dump` / `fingerprint`** | Inspect or diff packaged YAML configs |
-| **`seqseg post global-centerline`** | Post-process segmentations into global centerlines |
-| **`seqseg simvascular init`** | Create or refresh SimVascular project layout under a case directory |
-| **`seqseg --version`** | Print installed package version |
-
-### Python library API
-
-Embed tracing in other Python code without writing SeqSeg output files:
-
-- **`seqseg.api.run_tracing`** — pass a `sitk.Image`, seed definitions, and an nnU-Net trainer folder; get a `TracingResult` with global probability segmentation at `result.assembly.assembly`
-- **`TracingOptions(disk_io=False)`** — skip VTK/MHA debug trees on disk (nnU-Net weights still load from `model_folder`)
-- **`BranchSeed`**, **`branch_seed_at_point`**, **`seeds_to_potential_branches`** — simple seed formats instead of hand-built step dicts
-- **`TracingContext`** / **`trace_centerline_from_context`** — lower-level control with the same in-memory image support
-- Lazy re-exports from **`import seqseg`** (see `seqseg/__init__.py`)
-
-Quick example (seeds and config known):
-
-```python
-from seqseg.api import TracingOptions, branch_seed_at_point, run_tracing
-
-result = run_tracing(
-    my_sitk_image,
-    [branch_seed_at_point([x, y, z], radius)],
-    "/path/to/nnUNetTrainer__nnUNetPlans__3d_fullres",
-    config="global",
-    options=TracingOptions(disk_io=False),
-)
-prob_seg = result.assembly.assembly  # sitk.Image; threshold for binary masks
-```
-
-See [High-level API (`seqseg.api`)](#high-level-api-seqsegapi) for full detail.
-
-### Internal structure (for contributors)
-
-- Pipeline modules: `seqseg.pipeline.classic`, `plus`, `post`, `single_trace`
-- Typed config helpers: `AlgorithmConfig`, `NnUNetModelSpec` in `seqseg.config_models`
-- Tracing core accepts **`sitk.Image`** or file paths for the reference volume and optional prior segmentation
+| **`seqseg run batch`** | Dataset batch tracing |
+| **`seqseg run single`** | One volume and seeds. Stages files under `<outdir>/_seqseg_single_staging/`, then traces |
+| **`seqseg run plus batch`** | Global nnU-Net sweep, then SeqSeg |
+| **`seqseg init dataset`** | Create `images/`, `centerlines/`, `truths/`, and a template `seeds.json` |
+| **`seqseg paths init` / `set` / `show`** | Save default nnU-Net, data, and output directories in `~/.seqseg/paths.yaml` |
+| **`seqseg train prepare`** | Extract patches or whole volumes and build an nnU-Net dataset |
+| **`seqseg train nnunet`** | Run nnU-Net planning, preprocessing, and training |
+| **`seqseg doctor`** | Check imports (SimpleITK, vtk, nnunetv2, scipy, vascular-segment-sampler) and paths |
+| **`seqseg config dump` / `fingerprint`** | Print a packaged YAML config, or list keys that differ from another |
+| **`seqseg post global-centerline`** | Build global centerlines from existing segmentations |
+| **`seqseg simvascular init`** | Create or refresh a SimVascular project under a case directory |
+| **`seqseg --version`** | Print the installed version |
+
+`seqseg run batch` flags use underscores (`-outdir` / `--outdir`). The data folder is `-data_dir` or `--data_directory`. `seqseg run single`, `seqseg train`, and `seqseg paths` use hyphens (`--image`, `--data-dir`).
 
 ### Migrating from 1.x
 
-1. **CLI:** Prefer `seqseg run batch` (or keep legacy flags — they still work).
-2. **Plus workflow:** Use `seqseg run plus batch` instead of `python -m seqseg.seqseg_plus` with the same nnU-Net path flags.
-3. **Library:** Use `run_tracing` or `TracingContext` rather than calling `trace_centerline` with only file paths.
-4. **Version:** `pip install -U seqseg` and check with `seqseg --version` (expects **2.1.0**).
+1. Prefer `seqseg run batch`. The old flag-only form still works.
+2. Use `seqseg run plus batch` in place of `python -m seqseg.seqseg_plus`. The nnU-Net path flags are unchanged.
+3. Check the install with `seqseg --version` after `pip install -U seqseg`.
 
 ## Quick Start
 
+Python 3.9 or newer. 3.11 is the version used in the tutorial and conda example.
+
 ```bash
-# Install
 pip install seqseg
 
-# Download pre-trained weights (see Installation docs for links)
-# Run segmentation
-seqseg -data_dir your_data/ -nnunet_results_path path/to/weights/ -config_name aorta_tutorial
+# Aorta and femoral weights (MR and CT). Coronary weights are a separate zip; see Installation.
+curl -L -o nnUNet_results.zip https://zenodo.org/records/15020477/files/nnUNet_results.zip
+unzip nnUNet_results.zip
+```
+
+`-nnunet_results_path` is the folder that contains `Dataset005_SEQAORTANDFEMOMR` (and the other dataset folders in that zip).
+
+**First run:** follow the [step-by-step tutorial](seqseg/tutorial/tutorial.md). It includes an abdominal-aorta MR scan, seed points, and Windows notes. The tutorial caps the number of steps so the example finishes in a few minutes; a real case should use the defaults.
+
+**Your own data** needs `images/` and `seeds.json` (see [Usage](docs/usage.md)). This command is an aorta MR case. Change `-train_dataset`, `-config_name`, and `-img_ext` to match your images and weights:
+
+```bash
+seqseg run batch \
+    -data_dir your_data/ \
+    -nnunet_results_path nnUNet_results/ \
+    -train_dataset Dataset005_SEQAORTANDFEMOMR \
+    -config_name global_aorta \
+    -img_ext .mha \
+    -outdir results/
 ```
 
-**📖 New here? Follow the [step-by-step tutorial](seqseg/tutorial/tutorial.md)** with example data and detailed instructions.
+| Anatomy | `-train_dataset` | `-config_name` |
+|---------|------------------|----------------|
+| Aorta / femoral MR | `Dataset005_SEQAORTANDFEMOMR` | `global_aorta` |
+| Aorta / femoral CT | `Dataset006_SEQAORTANDFEMOCT` | `global_aorta` |
+| Coronary CT | `Dataset010_SEQCOROASOCACT` | `global_coro` |
+
+The tutorial uses `-config_name aorta_tutorial` for its sample scan. Download links and the trainer-folder layout are in [Installation](docs/installation.md).
 
 ## Documentation
 
 | Guide | Description |
 |-------|-------------|
 | [Installation](docs/installation.md) | Setup, dependencies, and pre-trained model weights |
-| [Usage](docs/usage.md) | Data preparation, CLI arguments, and output files |
-| [Configuration](docs/configuration.md) | YAML configs and key tracking parameters |
+| [Tutorial](seqseg/tutorial/tutorial.md) | End-to-end aorta example with sample data |
+| [Usage](docs/usage.md) | Data layout, seeds, CLI arguments, and output files |
+| [Configuration](docs/configuration.md) | YAML configs and tracking parameters |
 | [Algorithm Overview](docs/algorithm.md) | Methodology, workflow, and training strategy |
-| [Training](docs/training.md) | Train nnU-Net models on a new dataset for SeqSeg |
+| [Training](docs/training.md) | Train nnU-Net models on a new dataset |
 | [Performance & Benchmarks](docs/benchmarks.md) | Accuracy, timing, and qualitative comparisons |
-| [Research & Development](docs/development.md) | SimVascular / Slicer integrations and related tooling |
+| [API](docs/api.md) | Call tracing from Python |
+| [Research & Development](docs/development.md) | SimVascular, 3D Slicer, and repository layout |
 
 ## Citation
 

seqseg-2.1.7/README.md

@@ -0,0 +1,137 @@
+![example workflow](https://github.com/numisveinsson/SeqSeg/actions/workflows/python-app.yml/badge.svg)
+![example workflow](https://github.com/numisveinsson/SeqSeg/actions/workflows/test.yml/badge.svg)
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/numisveinsson/SeqSeg/main/seqseg/assets/seqseg_logo.png" alt="SeqSeg — Sequential Vessel Segmentation" width="480"/><br/>
+  <img src="https://raw.githubusercontent.com/numisveinsson/SeqSeg/main/seqseg/assets/coronary.png" alt="Example coronary segmentation (SeqSeg)" width="260"/>
+</p>
+
+<h1 align="center">SeqSeg: Sequential Vessel Segmentation and Tracking</h1>
+
+<p align="center">
+  <b>Automatic tracking and segmentation of blood vessels in CT and MR images using deep learning and geometric tracking.</b>
+</p>
+
+<p align="center">
+  <a href="https://rdcu.be/dU0wy"><img src="https://img.shields.io/badge/Paper-Annals%20of%20BME-blue" alt="Paper"/></a>
+  <a href="https://github.com/numisveinsson/SeqSeg/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-green.svg" alt="License"/></a>
+  <a href="https://www.python.org"><img src="https://img.shields.io/badge/Python-3.9%2B-blue.svg" alt="Python 3.9+"/></a>
+</p>
+
+> **News:** SeqSeg writes a full SimVascular project in the `simvascular/` subdirectory — open it directly in SimVascular with pathlines and contours for every segmented branch.
+
+---
+
+## Why SeqSeg?
+
+SeqSeg segments vessels **sequentially**, taking steps along vessel centerlines and detecting bifurcations to grow complete vascular trees from just **1–2 seed points**. By combining local deep-learning predictions (nnU-Net) with geometric tracking, it stays robust across vessel scales — from small coronaries to large aortas.
+
+- 🌱 **Minimal supervision** — only 1–2 seed points to initialize
+- 🌿 **Robust bifurcation detection** — automatically follows every branch
+- 🩻 **Multi-modal** — works with CT and MR 3D medical images
+- 📏 **Scalable** — vessels from ~1mm coronaries to ~30mm aortas
+- ✅ **Clinically validated** — coronary, aortic, cerebral, and pulmonary anatomies (pre-trained weights for aorta CT/MR and coronary CT)
+- ⚡ **Fast** — on CPU, about 2–5 minutes for an aorta, 5–15 for a coronary tree, and 10–30 for a cerebral tree. GPU is faster. Details in [Benchmarks](docs/benchmarks.md).
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/numisveinsson/SeqSeg/main/seqseg/assets/mr_model_tracing_fast_shorter.gif" alt="SeqSeg Demo"/><br/>
+  <i>Real-time demonstration: automatic segmentation of an abdominal aorta in a 3D MR scan.</i>
+</p>
+
+## What's new in 2.x
+
+SeqSeg **2.0** uses subcommands. A command from 1.x that starts with a flag, such as `seqseg -data_dir ...`, still runs: it is rewritten to `seqseg run batch` automatically.
+
+### Commands
+
+| Command | Description |
+| -------- | ----------- |
+| **`seqseg run batch`** | Dataset batch tracing |
+| **`seqseg run single`** | One volume and seeds. Stages files under `<outdir>/_seqseg_single_staging/`, then traces |
+| **`seqseg run plus batch`** | Global nnU-Net sweep, then SeqSeg |
+| **`seqseg init dataset`** | Create `images/`, `centerlines/`, `truths/`, and a template `seeds.json` |
+| **`seqseg paths init` / `set` / `show`** | Save default nnU-Net, data, and output directories in `~/.seqseg/paths.yaml` |
+| **`seqseg train prepare`** | Extract patches or whole volumes and build an nnU-Net dataset |
+| **`seqseg train nnunet`** | Run nnU-Net planning, preprocessing, and training |
+| **`seqseg doctor`** | Check imports (SimpleITK, vtk, nnunetv2, scipy, vascular-segment-sampler) and paths |
+| **`seqseg config dump` / `fingerprint`** | Print a packaged YAML config, or list keys that differ from another |
+| **`seqseg post global-centerline`** | Build global centerlines from existing segmentations |
+| **`seqseg simvascular init`** | Create or refresh a SimVascular project under a case directory |
+| **`seqseg --version`** | Print the installed version |
+
+`seqseg run batch` flags use underscores (`-outdir` / `--outdir`). The data folder is `-data_dir` or `--data_directory`. `seqseg run single`, `seqseg train`, and `seqseg paths` use hyphens (`--image`, `--data-dir`).
+
+### Migrating from 1.x
+
+1. Prefer `seqseg run batch`. The old flag-only form still works.
+2. Use `seqseg run plus batch` in place of `python -m seqseg.seqseg_plus`. The nnU-Net path flags are unchanged.
+3. Check the install with `seqseg --version` after `pip install -U seqseg`.
+
+## Quick Start
+
+Python 3.9 or newer. 3.11 is the version used in the tutorial and conda example.
+
+```bash
+pip install seqseg
+
+# Aorta and femoral weights (MR and CT). Coronary weights are a separate zip; see Installation.
+curl -L -o nnUNet_results.zip https://zenodo.org/records/15020477/files/nnUNet_results.zip
+unzip nnUNet_results.zip
+```
+
+`-nnunet_results_path` is the folder that contains `Dataset005_SEQAORTANDFEMOMR` (and the other dataset folders in that zip).
+
+**First run:** follow the [step-by-step tutorial](seqseg/tutorial/tutorial.md). It includes an abdominal-aorta MR scan, seed points, and Windows notes. The tutorial caps the number of steps so the example finishes in a few minutes; a real case should use the defaults.
+
+**Your own data** needs `images/` and `seeds.json` (see [Usage](docs/usage.md)). This command is an aorta MR case. Change `-train_dataset`, `-config_name`, and `-img_ext` to match your images and weights:
+
+```bash
+seqseg run batch \
+    -data_dir your_data/ \
+    -nnunet_results_path nnUNet_results/ \
+    -train_dataset Dataset005_SEQAORTANDFEMOMR \
+    -config_name global_aorta \
+    -img_ext .mha \
+    -outdir results/
+```
+
+| Anatomy | `-train_dataset` | `-config_name` |
+|---------|------------------|----------------|
+| Aorta / femoral MR | `Dataset005_SEQAORTANDFEMOMR` | `global_aorta` |
+| Aorta / femoral CT | `Dataset006_SEQAORTANDFEMOCT` | `global_aorta` |
+| Coronary CT | `Dataset010_SEQCOROASOCACT` | `global_coro` |
+
+The tutorial uses `-config_name aorta_tutorial` for its sample scan. Download links and the trainer-folder layout are in [Installation](docs/installation.md).
+
+## Documentation
+
+| Guide | Description |
+|-------|-------------|
+| [Installation](docs/installation.md) | Setup, dependencies, and pre-trained model weights |
+| [Tutorial](seqseg/tutorial/tutorial.md) | End-to-end aorta example with sample data |
+| [Usage](docs/usage.md) | Data layout, seeds, CLI arguments, and output files |
+| [Configuration](docs/configuration.md) | YAML configs and tracking parameters |
+| [Algorithm Overview](docs/algorithm.md) | Methodology, workflow, and training strategy |
+| [Training](docs/training.md) | Train nnU-Net models on a new dataset |
+| [Performance & Benchmarks](docs/benchmarks.md) | Accuracy, timing, and qualitative comparisons |
+| [API](docs/api.md) | Call tracing from Python |
+| [Research & Development](docs/development.md) | SimVascular, 3D Slicer, and repository layout |
+
+## Citation
+
+When using SeqSeg, please cite the following [paper](https://rdcu.be/dU0wy):
+
+```
+@Article{SveinssonCepero2024,
+author={Sveinsson Cepero, Numi
+and Shadden, Shawn C.},
+title={SeqSeg: Learning Local Segments for Automatic Vascular Model Construction},
+journal={Annals of Biomedical Engineering},
+year={2024},
+month={Sep},
+day={18},
+issn={1573-9686},
+doi={10.1007/s10439-024-03611-z},
+url={https://doi.org/10.1007/s10439-024-03611-z},
+}
+```

{seqseg-2.1.6 → seqseg-2.1.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "seqseg"
-version = "2.1.6"
+version = "2.1.7"
 description = "A deep learning-based medical image blood vessel tracking and segmentation tool."
 readme = "README.md"
 requires-python = ">=3.9"
@@ -42,6 +42,7 @@ dependencies = [
     "PyYAML==6.0.3",
     "nnunetv2>=2.5.1",
     "scipy",
+    "vascular-segment-sampler>=0.6.0",
 ]
 
 [project.scripts]
@@ -62,9 +63,6 @@ dev = [
 viz = [
   "matplotlib>=3.5",
 ]
-train = [
-  "vascular-segment-sampler>=0.1.0",
-]
 
 [tool.pytest.ini_options]
 testpaths = ["seqseg/tests"]

{seqseg-2.1.6 → seqseg-2.1.7}/seqseg/cli.py

@@ -225,7 +225,8 @@ def _validate_trace_batch(ns: argparse.Namespace) -> None:
             + "\n  ".join(missing)
             + "\n\nMinimal example:\n"
             "  seqseg paths init\n"
-            "  seqseg paths set --data-dir /path/to/dataset --outdir /path/to/out\n"
+            "  seqseg paths set --nnunet-root ~/nnunet_data "
+            "--data-dir /path/to/dataset --outdir /path/to/out\n"
             "  seqseg run batch -img_ext .nii.gz "
             "-train_dataset Dataset010_SEQCOROASOCACT\n",
             file=sys.stderr,
@@ -435,7 +436,6 @@ def _cmd_init_dataset(ns: argparse.Namespace) -> None:
         f"  seqseg run batch -data_dir {root}/ -outdir ... -img_ext .nii.gz "
         "-nnunet_results_path ...\n"
         "\nNext (train a new model): also fill centerlines/ and truths/, then:\n"
-        f'  pip install "seqseg[train]"\n'
         f"  seqseg paths init --data-dir {root}/ --outdir ~/seqseg_train\n"
         "  seqseg train prepare --name MYDATA --dataset-number 999 --modality CT\n"
     )
@@ -550,10 +550,7 @@ def _cmd_doctor(ns: argparse.Namespace) -> None:
         try:
             importlib.import_module(modname)
         except ImportError as e:
-            extra = ""
-            if modname == "vascular_segment_sampler":
-                extra = ' — optional; pip install "seqseg[train]"'
-            print(f"  {label}: MISSING ({e}){extra}")
+            print(f"  {label}: MISSING ({e})")
         else:
             print(f"  {label}: OK")
 
@@ -592,19 +589,9 @@ def _cmd_paths_init(ns: argparse.Namespace) -> None:
 
 
 def _cmd_paths_set(ns: argparse.Namespace) -> None:
-    fields = (
-        ns.nnunet_root,
-        ns.nnunet_raw,
-        ns.nnunet_preprocessed,
-        ns.nnunet_results,
-        ns.data_dir,
-        ns.outdir,
-    )
-    if not any(f is not None for f in fields):
+    if not ns.nnunet_root:
         print(
-            "seqseg paths set: provide at least one of "
-            "--nnunet-root, --nnunet-raw, --nnunet-preprocessed, "
-            "--nnunet-results, --data-dir, --outdir",
+            "seqseg paths set: --nnunet-root is required",
             file=sys.stderr,
         )
         sys.exit(2)
@@ -673,10 +660,21 @@ def _cmd_train_prepare(ns: argparse.Namespace) -> None:
             verbose=ns.verbose,
             img_ext=ns.img_ext,
             global_volumes=ns.global_volumes,
+            keep_extracted=ns.keep_extracted,
         )
     except TrainDependencyError as e:
         print(str(e), file=sys.stderr)
         sys.exit(1)
+    except FileNotFoundError as e:
+        message = str(e)
+        if message.startswith("Sampler config"):
+            print(message, file=sys.stderr)
+            sys.exit(2)
+        import traceback
+
+        traceback.print_exc()
+        print(f"seqseg train prepare failed: {e}", file=sys.stderr)
+        sys.exit(1)
     except Exception as e:  # noqa: BLE001
         import traceback
 
@@ -693,8 +691,17 @@ def _cmd_train_prepare(ns: argparse.Namespace) -> None:
         sys.exit(1)
 
     print("\nPrepare complete.")
-    kind = "Whole volumes" if ns.global_volumes else "Patches"
-    print(f"  {kind}: {result.extracted_dir}")
+    if result.removed_staging:
+        print(
+            "  Extracted volumes were linked into nnU-Net raw and the "
+            "temporary folder was removed."
+        )
+    else:
+        kind = "Whole volumes" if ns.global_volumes else "Patches"
+        print(f"  {kind}: {result.extracted_dir}")
+    results = resolve_path("nnunet_results")
+    if results:
+        print(f"  Trained models will be written under: {results}")
     for name, path in zip(result.dataset_names, result.dataset_dirs):
         try:
             ds_id = dataset_id_from_name(name)
@@ -734,6 +741,7 @@ def _cmd_train_nnunet(ns: argparse.Namespace) -> None:
             np=ns.np,
             trainer=ns.trainer,
             plans=ns.plans,
+            cleanup=ns.cleanup,
         )
     except Exception as e:  # noqa: BLE001
         print(f"seqseg train nnunet failed: {e}", file=sys.stderr)
@@ -921,8 +929,18 @@ def _build_parser() -> argparse.ArgumentParser:
     g1 = gcl_sub.add_parser("single", formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     g1.add_argument("--seg", required=True, type=str)
     g1.add_argument("--out", required=True, type=str)
-    g1.add_argument("--seeds-json", required=True, type=str)
-    g1.add_argument("--case-name", required=True, type=str)
+    g1.add_argument(
+        "--seeds-json",
+        default=None,
+        type=str,
+        help="Dataset seeds.json. Omit to place one seed in each disconnected body",
+    )
+    g1.add_argument(
+        "--case-name",
+        default=None,
+        type=str,
+        help="Case name in seeds.json. Required when --seeds-json is set",
+    )
     g1.add_argument("--config-name", default=None, type=str)
     g1.add_argument("--merge-method", default="clean", type=str)
     g1.add_argument("--directory-data", default=None, type=str)
@@ -932,7 +950,12 @@ def _build_parser() -> argparse.ArgumentParser:
     g2 = gcl_sub.add_parser("batch", formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     g2.add_argument("--seg-dir", required=True, type=str)
     g2.add_argument("--seg-glob", required=True, type=str)
-    g2.add_argument("--seeds-json", required=True, type=str)
+    g2.add_argument(
+        "--seeds-json",
+        default=None,
+        type=str,
+        help="Dataset seeds.json. Omit to place one seed in each disconnected body",
+    )
     g2.add_argument("--out-dir", default=None, type=str)
     g2.add_argument("--config-name", default=None, type=str)
     g2.add_argument("--merge-method", default="clean", type=str)
@@ -1014,8 +1037,9 @@ def _build_parser() -> argparse.ArgumentParser:
         "-outdir",
         default=None,
         type=str,
-        help="Directory for extracted patches or whole volumes "
-        "(default: seqseg paths outdir, else ./extracted_data/)",
+        help="Optional scratch directory for extracted patches or whole volumes. "
+        "Default: <parent of nnUNet_raw>/_seqseg_extracted, removed after "
+        "conversion. Pass this to keep extracts or resume with --skip-sample.",
     )
     p_prep.add_argument(
         "--name",
@@ -1050,7 +1074,7 @@ def _build_parser() -> argparse.ArgumentParser:
         default=None,
         type=str,
         help="Write DatasetXXX_* here "
-        "(default: seqseg paths nnunet_raw / $nnUNet_raw; else --outdir)",
+        "(default: seqseg paths nnunet_raw / $nnUNet_raw)",
     )
     p_prep.add_argument(
         "--img-ext",
@@ -1103,6 +1127,11 @@ def _build_parser() -> argparse.ArgumentParser:
     )
     p_prep.add_argument("--yes", action="store_true", help="Non-interactive confirms")
     p_prep.add_argument("--verbose", action="store_true")
+    p_prep.add_argument(
+        "--keep-extracted",
+        action="store_true",
+        help="Keep <nnunet-root>/_seqseg_extracted after conversion into nnUNet_raw",
+    )
     p_prep.set_defaults(_handler=_cmd_train_prepare, img_ext=None)
 
     p_nn = train_sub.add_parser(
@@ -1152,6 +1181,13 @@ def _build_parser() -> argparse.ArgumentParser:
     )
     p_nn.add_argument("--trainer", default="nnUNetTrainer", type=str)
     p_nn.add_argument("--plans", default="nnUNetPlans", type=str)
+    p_nn.add_argument(
+        "--cleanup",
+        action="store_true",
+        help="After training succeeds, delete this dataset's nnUNet_raw and "
+        "nnUNet_preprocessed folders. Leaves nnUNet_results. "
+        "Ignored with --plan-only.",
+    )
     p_nn.set_defaults(_handler=_cmd_train_nnunet)
 
     paths_p = sub.add_parser(
@@ -1194,10 +1230,15 @@ def _build_parser() -> argparse.ArgumentParser:
 
     p_set = paths_sub.add_parser(
         "set",
-        help="Update one or more saved paths",
+        help="Update saved paths (requires --nnunet-root)",
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
     )
-    p_set.add_argument("--nnunet-root", default=None, type=str)
+    p_set.add_argument(
+        "--nnunet-root",
+        required=True,
+        type=str,
+        help="Parent directory for nnUNet_raw / preprocessed / results",
+    )
     p_set.add_argument("--nnunet-raw", default=None, type=str)
     p_set.add_argument("--nnunet-preprocessed", default=None, type=str)
     p_set.add_argument("--nnunet-results", default=None, type=str)

{seqseg-2.1.6 → seqseg-2.1.7}/seqseg/config/global.yaml

@@ -14,6 +14,7 @@ TREE_ANALYSIS: False
 
 VOLUME_SIZE_RATIO: 5 # default 5, 5.5 for coronaries, 4 for segs
 MAGN_RADIUS: 1
+ADD_RADIUS: 0 # mm (keep in mm)
 MAX_PERC_ENLARGE: 0.3 # if percent of blood in a given volume goes above this, we try enlarging volume, default 0.33 for coronaries
 MIN_RADIUS: 0.3 # mm (keep in mm)
 MIN_RES: 6

{seqseg-2.1.6 → seqseg-2.1.7}/seqseg/config/global_cereb.yaml

@@ -2,7 +2,7 @@
 # True if we have a segmentation, False if we are predicting
 SEGMENTATION: False # usually False
 
-DEBUG: True
+DEBUG: False
 DEBUG_STEP: 200
 
 ANIMATION: True # to write out animation files

{seqseg-2.1.6 → seqseg-2.1.7}/seqseg/config/global_debug.yaml

@@ -14,6 +14,7 @@ TREE_ANALYSIS: False
 
 VOLUME_SIZE_RATIO: 6 # default 5, 5.5 for coronaries, 4 for segs
 MAGN_RADIUS: 1
+ADD_RADIUS: 0 # mm (keep in mm)
 MAX_PERC_ENLARGE: 0.5 # if percent of blood in a given volume goes above this, we try enlarging volume, default 0.33 for coronaries
 MIN_RADIUS: 0.3 # mm (keep in mm)
 MIN_RES: 6

{seqseg-2.1.6 → seqseg-2.1.7}/seqseg/modules/assembly.py

@@ -978,8 +978,13 @@ def calc_centerline_global(predicted_vessels, initial_seeds,
             Centerline merge method for post-processing. Supported values are
             ``'clean'`` (default) and ``'tree'``.
     """
-    print(f"""Calculating global centerline
-          with {len(initial_seeds)} initial seeds""")
+    if nr_seeds is None:
+        print(
+            "Calculating global centerline; "
+            "identifying one seed per disconnected body"
+        )
+    else:
+        print(f"Calculating global centerline with {len(initial_seeds)} initial seeds")
     # Use multi-component centerline extraction so disconnected bodies are
     # handled in one unified workflow.
     centerline_poly, success_info = calc_multi_component_centerlines(

{seqseg-2.1.6 → seqseg-2.1.7}/seqseg/modules/nnunet.py

@@ -56,6 +56,24 @@ _CHECKPOINT_CANDIDATES = (
 )
 
 
+def select_training_device():
+    """nnU-Net ``-device`` name: CUDA, then MPS, then CPU.
+
+    Returns ``cpu`` when torch is not installed. Training itself still needs
+    torch; this keeps command construction usable in tests that mock it.
+    """
+    try:
+        import torch
+    except ImportError:
+        return 'cpu'
+    if torch.cuda.is_available():
+        return 'cuda'
+    mps = getattr(getattr(torch, 'backends', None), 'mps', None)
+    if mps is not None and mps.is_available():
+        return 'mps'
+    return 'cpu'
+
+
 def select_inference_device(model_folder, force_cpu=False):
     """Pick torch device for nnU-Net inference.