slide2vec 4.1.0__tar.gz → 4.2.0__tar.gz

{slide2vec-4.1.0 → slide2vec-4.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: slide2vec
-Version: 4.1.0
+Version: 4.2.0
 Summary: Embedding of whole slide images with Foundation Models
 Author-email: Clément Grisi <clement.grisi@radboudumc.nl>
 License-Expression: Apache-2.0
@@ -15,7 +15,7 @@ Classifier: Programming Language :: Python :: 3.13
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: hs2p[asap,cucim,openslide,vips]>=3.1.4
+Requires-Dist: hs2p[asap,cucim,openslide,vips]>=3.2.1
 Requires-Dist: omegaconf
 Requires-Dist: matplotlib
 Requires-Dist: numpy<2
@@ -50,6 +50,8 @@ Requires-Dist: xformers==0.0.31; extra == "prism"
 Provides-Extra: hibou
 Requires-Dist: scipy~=1.8.1; extra == "hibou"
 Requires-Dist: scikit-image~=0.19.3; extra == "hibou"
+Provides-Extra: moozy
+Requires-Dist: huggingface_hub<1.0,>=0.30.0; extra == "moozy"
 Provides-Extra: titan
 Requires-Dist: torch==2.0.1; extra == "titan"
 Requires-Dist: timm==1.0.3; extra == "titan"
@@ -63,7 +65,7 @@ Requires-Dist: numpy<2; extra == "fm"
 Requires-Dist: pandas; extra == "fm"
 Requires-Dist: pillow; extra == "fm"
 Requires-Dist: rich; extra == "fm"
-Requires-Dist: hs2p[asap,cucim,openslide,vips]>=3.1.4; extra == "fm"
+Requires-Dist: hs2p[asap,cucim,openslide,vips]>=3.2.1; extra == "fm"
 Requires-Dist: wandb; extra == "fm"
 Requires-Dist: torch<2.8,>=2.3; extra == "fm"
 Requires-Dist: torchvision>=0.18.0; extra == "fm"
@@ -143,8 +145,8 @@ from slide2vec import ExecutionOptions, Pipeline, PreprocessingConfig
 pipeline = Pipeline(
     model=model,
     preprocessing=PreprocessingConfig(
-        target_spacing_um=0.5,
-        target_tile_size_px=224,
+        requested_spacing_um=0.5,
+        requested_tile_size_px=224,
         tissue_threshold=0.1,
     ),
     execution=ExecutionOptions(output_dir="outputs/demo"),
@@ -160,8 +162,8 @@ Tile embeddings can be spatially grouped into regions for downstream models that
 
 ```python
 preprocessing = PreprocessingConfig(
-    target_spacing_um=0.5,
-    target_tile_size_px=224,
+    requested_spacing_um=0.5,
+    requested_tile_size_px=224,
     region_tile_multiple=6,  # 6x6 tiles per region
 )
 embedded = model.embed_slide("/path/to/slide.svs", preprocessing=preprocessing)
@@ -210,7 +212,7 @@ The CLI is a thin wrapper over the package API.
 Bundled configs live under `slide2vec/configs/preprocessing/` and `slide2vec/configs/models/`.
 
 ```shell
-python -m slide2vec --config-file /path/to/config.yaml
+slide2vec /path/to/config.yaml
 ```
 
 By default, manifest-driven CLI runs use all available GPUs. Set `speed.num_gpus=4` when you want to cap the sharding explicitly.

{slide2vec-4.1.0 → slide2vec-4.2.0}/README.md

@@ -45,8 +45,8 @@ from slide2vec import ExecutionOptions, Pipeline, PreprocessingConfig
 pipeline = Pipeline(
     model=model,
     preprocessing=PreprocessingConfig(
-        target_spacing_um=0.5,
-        target_tile_size_px=224,
+        requested_spacing_um=0.5,
+        requested_tile_size_px=224,
         tissue_threshold=0.1,
     ),
     execution=ExecutionOptions(output_dir="outputs/demo"),
@@ -62,8 +62,8 @@ Tile embeddings can be spatially grouped into regions for downstream models that
 
 ```python
 preprocessing = PreprocessingConfig(
-    target_spacing_um=0.5,
-    target_tile_size_px=224,
+    requested_spacing_um=0.5,
+    requested_tile_size_px=224,
     region_tile_multiple=6,  # 6x6 tiles per region
 )
 embedded = model.embed_slide("/path/to/slide.svs", preprocessing=preprocessing)
@@ -112,7 +112,7 @@ The CLI is a thin wrapper over the package API.
 Bundled configs live under `slide2vec/configs/preprocessing/` and `slide2vec/configs/models/`.
 
 ```shell
-python -m slide2vec --config-file /path/to/config.yaml
+slide2vec /path/to/config.yaml
 ```
 
 By default, manifest-driven CLI runs use all available GPUs. Set `speed.num_gpus=4` when you want to cap the sharding explicitly.

{slide2vec-4.1.0 → slide2vec-4.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "slide2vec"
-version = "4.1.0"
+version = "4.2.0"
 description = "Embedding of whole slide images with Foundation Models"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -21,7 +21,7 @@ classifiers = [
     "Programming Language :: Python :: 3.13",
 ]
 dependencies = [
-    "hs2p[asap,cucim,openslide,vips]>=3.1.4",
+    "hs2p[asap,cucim,openslide,vips]>=3.2.1",
     "omegaconf",
     "matplotlib",
     "numpy<2",
@@ -42,7 +42,7 @@ Homepage = "https://github.com/clemsgrs/slide2vec"
 "Bug Tracker" = "https://github.com/clemsgrs/slide2vec/issues"
 
 [project.scripts]
-slide2vec = "slide2vec.cli:main"
+slide2vec = "slide2vec.cli:entrypoint"
 
 [project.optional-dependencies]
 hoptimus = [
@@ -71,6 +71,9 @@ hibou = [
     "scipy~=1.8.1",
     "scikit-image~=0.19.3",
 ]
+moozy = [
+    "huggingface_hub>=0.30.0,<1.0",
+]
 titan = [
     "torch==2.0.1",
     "timm==1.0.3",
@@ -85,7 +88,7 @@ fm = [
     "pandas",
     "pillow",
     "rich",
-    "hs2p[asap,cucim,openslide,vips]>=3.1.4",
+    "hs2p[asap,cucim,openslide,vips]>=3.2.1",
     "wandb",
     "torch>=2.3,<2.8",
     "torchvision>=0.18.0",
@@ -154,7 +157,7 @@ no_implicit_reexport = true
 max-line-length = 160
 
 [tool.bumpver]
-current_version = "4.1.0"
+current_version = "4.2.0"
 version_pattern = "MAJOR.MINOR.PATCH"
 commit = false       # We do version bumping in CI, not as a commit
 tag = false          # Git tag already exists — we don't auto-tag

{slide2vec-4.1.0 → slide2vec-4.2.0}/slide2vec/__init__.py

@@ -2,7 +2,7 @@ from slide2vec.api import EmbeddedSlide, ExecutionOptions, Model, Pipeline, Prep
 from slide2vec.artifacts import HierarchicalEmbeddingArtifact, SlideEmbeddingArtifact, TileEmbeddingArtifact
 
 
-__version__ = "4.1.0"
+__version__ = "4.2.0"
 
 __all__ = [
     "Model",

{slide2vec-4.1.0 → slide2vec-4.2.0}/slide2vec/api.py

@@ -11,6 +11,7 @@ from hs2p import SlideSpec
 
 from slide2vec.artifacts import (
     HierarchicalEmbeddingArtifact,
+    PatientEmbeddingArtifact,
     SlideEmbeddingArtifact,
     TileEmbeddingArtifact,
 )
@@ -42,9 +43,9 @@ TilingResultsInput = Sequence[Any] | Mapping[str, Any]
 @dataclass(frozen=True, kw_only=True)
 class PreprocessingConfig:
     backend: str = "auto"
-    target_spacing_um: float | None = None
-    target_tile_size_px: int | None = None
-    target_region_size_px: int | None = None
+    requested_spacing_um: float | None = None
+    requested_tile_size_px: int | None = None
+    requested_region_size_px: int | None = None
     region_tile_multiple: int | None = None
     tolerance: float = 0.05
     overlap: float = 0.0
@@ -75,11 +76,11 @@ class PreprocessingConfig:
         preview_downsample = int(preview_cfg.downsample)
         return cls(
             backend=tiling.backend,
-            target_spacing_um=float(tiling.params.target_spacing_um),
-            target_tile_size_px=int(tiling.params.target_tile_size_px),
-            target_region_size_px=(
+            requested_spacing_um=float(tiling.params.requested_spacing_um),
+            requested_tile_size_px=int(tiling.params.requested_tile_size_px),
+            requested_region_size_px=(
                 int(v)
-                if (v := getattr(tiling.params, "target_region_size_px", None)) is not None
+                if (v := getattr(tiling.params, "requested_region_size_px", None)) is not None
                 else None
             ),
             region_tile_multiple=(
@@ -127,6 +128,7 @@ class ExecutionOptions:
     prefetch_factor: int = 4
     persistent_workers: bool = True
     save_tile_embeddings: bool = False
+    save_slide_embeddings: bool = False
     save_latents: bool = False
 
     @classmethod
@@ -151,6 +153,7 @@ class ExecutionOptions:
             prefetch_factor=prefetch_factor,
             persistent_workers=persistent_workers,
             save_tile_embeddings=bool(cfg.model.save_tile_embeddings),
+            save_slide_embeddings=bool(cfg.model.save_slide_embeddings),
             save_latents=bool(cfg.model.save_latents),
         )
 
@@ -200,9 +203,17 @@ class RunResult:
     tile_artifacts: list[TileEmbeddingArtifact]
     hierarchical_artifacts: list[HierarchicalEmbeddingArtifact]
     slide_artifacts: list[SlideEmbeddingArtifact]
+    patient_artifacts: list[PatientEmbeddingArtifact] = field(default_factory=list)
     process_list_path: Path | None = None
 
 
+@dataclass(frozen=True, kw_only=True)
+class EmbeddedPatient:
+    patient_id: str
+    patient_embedding: Any  # torch.Tensor [D]
+    slide_embeddings: dict[str, Any]  # {sample_id: torch.Tensor [D]}
+
+
 @dataclass(frozen=True, kw_only=True)
 class EmbeddedSlide:
     sample_id: str
@@ -343,6 +354,82 @@ class Model:
                 execution=resolved,
             )
 
+    def embed_patient(
+        self,
+        slides: SlideSequence,
+        patient_id: str | None = None,
+        *,
+        preprocessing: PreprocessingConfig | None = None,
+        execution: ExecutionOptions | None = None,
+    ) -> "EmbeddedPatient":
+        """Embed a single patient's slides and return one ``EmbeddedPatient``.
+
+        Convenience wrapper around :meth:`embed_patients` for the common case
+        where all *slides* belong to the same patient.
+
+        Args:
+            slides: All slides for this patient.
+            patient_id: Optional patient identifier applied to every slide.
+                When omitted, ``patient_id`` is read from slide dict keys or
+                object attributes; slides that carry no ``patient_id`` fall
+                back to ``sample_id``.
+        """
+        patient_id_map: dict | None = None
+        if patient_id is not None:
+            patient_id_map = {}
+            for s in slides:
+                if isinstance(s, (str, Path)):
+                    patient_id_map[Path(s).stem] = patient_id
+                elif isinstance(s, dict):
+                    patient_id_map[str(s["sample_id"])] = patient_id
+                else:
+                    patient_id_map[str(s.sample_id)] = patient_id
+        return self.embed_patients(
+            slides,
+            patient_id_map=patient_id_map,
+            preprocessing=preprocessing,
+            execution=execution,
+        )[0]
+
+    def embed_patients(
+        self,
+        slides: SlideSequence,
+        patient_id_map: dict | None = None,
+        *,
+        preprocessing: PreprocessingConfig | None = None,
+        execution: ExecutionOptions | None = None,
+    ) -> "list[EmbeddedPatient]":
+        """Embed slides and aggregate them into patient-level embeddings.
+
+        Requires a patient-level model (e.g. ``moozy``).  For each patient
+        all contributing slide embeddings are aggregated by the model's
+        ``encode_patient`` method.
+
+        Args:
+            slides: Slides to process.  Each entry may be a path, a
+                ``SlideSpec``, or a dict with ``sample_id`` / ``image_path``
+                keys.  When *patient_id_map* is ``None`` a ``patient_id``
+                key in each dict is used to group slides.
+            patient_id_map: Optional explicit ``{sample_id: patient_id}``
+                mapping.  When provided it takes precedence over any
+                ``patient_id`` key embedded in the slide dicts.  When
+                omitted and the slide dicts carry no ``patient_id``, each
+                slide is treated as its own patient.
+        """
+        from slide2vec.inference import embed_patients
+
+        resolved = _coerce_execution_options(execution, model=self)
+        resolved_preprocessing = _resolve_direct_api_preprocessing(self, preprocessing)
+        with _auto_progress_reporting(output_dir=resolved.output_dir):
+            _validate_model_config(self, resolved_preprocessing, resolved)
+            return embed_patients(
+                self,
+                slides,
+                patient_id_map=patient_id_map,
+                preprocessing=resolved_preprocessing,
+                execution=resolved,
+            )
+
     def _load_backend(self) -> LoadedModel:
         if self._backend is None:
             from slide2vec.inference import load_model
@@ -454,28 +541,28 @@ def _resolve_direct_api_preprocessing(
         return defaults
 
     if preprocessing is None:
-        target_tile_size_px, target_spacing_um = ensure_defaults()
+        requested_tile_size_px, requested_spacing_um = ensure_defaults()
         return _resolve_hierarchical_preprocessing(
             PreprocessingConfig(
                 backend="auto",
-                target_spacing_um=target_spacing_um,
-                target_tile_size_px=target_tile_size_px,
+                requested_spacing_um=requested_spacing_um,
+                requested_tile_size_px=requested_tile_size_px,
             )
         )
 
-    target_spacing_um = preprocessing.target_spacing_um
-    target_tile_size_px = preprocessing.target_tile_size_px
-    if target_spacing_um is None or target_tile_size_px is None:
+    requested_spacing_um = preprocessing.requested_spacing_um
+    requested_tile_size_px = preprocessing.requested_tile_size_px
+    if requested_spacing_um is None or requested_tile_size_px is None:
         default_tile_size_px, default_spacing_um = ensure_defaults()
-        if target_spacing_um is None:
-            target_spacing_um = default_spacing_um
-        if target_tile_size_px is None:
-            target_tile_size_px = default_tile_size_px
+        if requested_spacing_um is None:
+            requested_spacing_um = default_spacing_um
+        if requested_tile_size_px is None:
+            requested_tile_size_px = default_tile_size_px
     return _resolve_hierarchical_preprocessing(
         replace(
             preprocessing,
-            target_spacing_um=target_spacing_um,
-            target_tile_size_px=target_tile_size_px,
+            requested_spacing_um=requested_spacing_um,
+            requested_tile_size_px=requested_tile_size_px,
         )
     )
 
@@ -484,7 +571,7 @@ def _default_preprocessing_from_registry(name: str | None) -> tuple[int, float]:
     if not name or name not in encoder_registry:
         raise ValueError(
             "Cannot infer preprocessing defaults without a registered model. "
-            "Pass preprocessing.target_spacing_um and preprocessing.target_tile_size_px explicitly."
+            "Pass preprocessing.requested_spacing_um and preprocessing.requested_tile_size_px explicitly."
         )
 
     defaults = resolve_preprocessing_defaults(name)
@@ -499,7 +586,7 @@ def _validate_model_config(
     name = model.name
     if name not in encoder_registry:
         return
-    if preprocessing.region_tile_multiple is not None or preprocessing.target_region_size_px is not None:
+    if preprocessing.region_tile_multiple is not None or preprocessing.requested_region_size_px is not None:
         info = encoder_registry.info(name)
         if info["level"] != "tile":
             raise ValueError("Hierarchical preprocessing is only supported for tile encoders")
@@ -508,8 +595,8 @@ def _validate_model_config(
     precision = None if on_cpu or execution is None else execution.precision
     validate_encoder_config(
         name,
-        target_tile_size_px=preprocessing.target_tile_size_px,
-        target_spacing_um=preprocessing.target_spacing_um,
+        requested_tile_size_px=preprocessing.requested_tile_size_px,
+        requested_spacing_um=preprocessing.requested_spacing_um,
         precision=precision,
         output_variant=model._output_variant,
         allow_non_recommended=bool(model.allow_non_recommended_settings),
@@ -518,32 +605,32 @@ def _validate_model_config(
 
 def _resolve_hierarchical_preprocessing(preprocessing: PreprocessingConfig) -> PreprocessingConfig:
     multiple = preprocessing.region_tile_multiple
-    target_region_size_px = preprocessing.target_region_size_px
+    requested_region_size_px = preprocessing.requested_region_size_px
     if multiple is not None:
         multiple = int(multiple)
         if multiple < 2:
             raise ValueError("region_tile_multiple must be at least 2")
-    if multiple is None and target_region_size_px is None:
+    if multiple is None and requested_region_size_px is None:
         return preprocessing
-    if preprocessing.target_tile_size_px is None:
+    if preprocessing.requested_tile_size_px is None:
         raise ValueError(
-            "target_tile_size_px must be resolved before deriving hierarchical region geometry"
+            "requested_tile_size_px must be resolved before deriving hierarchical region geometry"
         )
-    if target_region_size_px is None:
-        target_region_size_px = int(preprocessing.target_tile_size_px) * int(multiple)
+    if requested_region_size_px is None:
+        requested_region_size_px = int(preprocessing.requested_tile_size_px) * int(multiple)
     elif multiple is None:
-        if int(target_region_size_px) % int(preprocessing.target_tile_size_px) != 0:
+        if int(requested_region_size_px) % int(preprocessing.requested_tile_size_px) != 0:
             raise ValueError(
-                "target_region_size_px must be an exact multiple of target_tile_size_px"
+                "requested_region_size_px must be an exact multiple of requested_tile_size_px"
             )
-        multiple = int(target_region_size_px) // int(preprocessing.target_tile_size_px)
-    elif int(target_region_size_px) != int(preprocessing.target_tile_size_px) * int(multiple):
+        multiple = int(requested_region_size_px) // int(preprocessing.requested_tile_size_px)
+    elif int(requested_region_size_px) != int(preprocessing.requested_tile_size_px) * int(multiple):
         raise ValueError(
-            "target_region_size_px must match target_tile_size_px * region_tile_multiple"
+            "requested_region_size_px must match requested_tile_size_px * region_tile_multiple"
         )
     return replace(
         preprocessing,
-        target_region_size_px=int(target_region_size_px),
+        requested_region_size_px=int(requested_region_size_px),
         region_tile_multiple=int(multiple),
     )
 

{slide2vec-4.1.0 → slide2vec-4.2.0}/slide2vec/artifacts.py

@@ -35,6 +35,20 @@ class SlideEmbeddingArtifact:
         return load_metadata(self.metadata_path)
 
 
+@dataclass(frozen=True, kw_only=True)
+class PatientEmbeddingArtifact:
+    patient_id: str
+    path: Path
+    metadata_path: Path
+    format: str
+    feature_dim: int
+    num_slides: int
+
+    @property
+    def metadata(self) -> dict[str, Any]:
+        return load_metadata(self.metadata_path)
+
+
 @dataclass(frozen=True, kw_only=True)
 class HierarchicalEmbeddingArtifact:
     sample_id: str
@@ -223,6 +237,45 @@ def write_slide_embeddings(
     )
 
 
+def write_patient_embeddings(
+    patient_id: str,
+    embedding,
+    *,
+    output_dir: str | Path,
+    output_format: str = "pt",
+    metadata: dict[str, Any] | None = None,
+    num_slides: int = 0,
+) -> PatientEmbeddingArtifact:
+    output_format = _validate_output_format(output_format)
+    artifact_path, metadata_path = _setup_artifact_paths(
+        output_dir, "patient_embeddings", patient_id, output_format
+    )
+    embedding_array = _ensure_array(embedding)
+    if output_format == "pt":
+        torch.save(_ensure_tensor(embedding), artifact_path)
+    else:
+        np.savez_compressed(artifact_path, features=embedding_array)
+
+    patient_metadata = {
+        "patient_id": patient_id,
+        "artifact_type": "patient_embeddings",
+        "format": output_format,
+        "feature_dim": int(embedding_array.shape[-1]) if embedding_array.ndim else 1,
+        "num_slides": num_slides,
+    }
+    if metadata:
+        patient_metadata.update(metadata)
+    _write_metadata(metadata_path, patient_metadata)
+    return PatientEmbeddingArtifact(
+        patient_id=patient_id,
+        path=artifact_path,
+        metadata_path=metadata_path,
+        format=output_format,
+        feature_dim=patient_metadata["feature_dim"],
+        num_slides=num_slides,
+    )
+
+
 def write_hierarchical_embeddings(
     sample_id: str,
     features,

{slide2vec-4.1.0 → slide2vec-4.2.0}/slide2vec/cli.py

@@ -7,20 +7,21 @@ import slide2vec.progress as progress
 
 def get_args_parser(add_help: bool = True):
     parser = argparse.ArgumentParser("slide2vec", add_help=add_help)
-    parser.add_argument("--config-file", default="", metavar="FILE", help="path to config file")
+    parser.add_argument("config_file", metavar="CONFIG", help="path to config file")
     parser.add_argument("--skip-datetime", action="store_true", help="skip run id datetime prefix")
     parser.add_argument("--tiling-only", action="store_true", help="only run slide tiling")
     parser.add_argument("--run-on-cpu", action="store_true", help="run inference on cpu")
     parser.add_argument("--output-dir", type=str, default=None, help="output directory to save artifacts")
-    parser.add_argument(
-        "opts",
-        help='Modify config options at the end of the command using "path.key=value".',
-        default=None,
-        nargs=argparse.REMAINDER,
-    )
     return parser
 
 
+def parse_args(argv=None):
+    parser = get_args_parser(add_help=True)
+    args, opts = parser.parse_known_args(argv)
+    args.opts = opts
+    return args
+
+
 def build_model_and_pipeline(args):
     cfg, _cfg_path = setup(args)
     hf_login()
@@ -39,8 +40,7 @@ def build_model_and_pipeline(args):
 
 
 def main(argv=None):
-    parser = get_args_parser(add_help=True)
-    args = parser.parse_args(argv)
+    args = parse_args(argv)
     pipeline, cfg = build_model_and_pipeline(args)
     reporter = progress.create_cli_progress_reporter(output_dir=getattr(cfg, "output_dir", None))
     with progress.activate_progress_reporter(reporter):
@@ -50,3 +50,6 @@ def main(argv=None):
         )
 
 
+def entrypoint(argv=None):
+    main(argv)
+    return 0

{slide2vec-4.1.0 → slide2vec-4.2.0}/slide2vec/configs/default.yaml

@@ -13,6 +13,7 @@ model:
   output_variant: # requested output variant for presets that expose multiple outputs
   batch_size: 32
   save_tile_embeddings: false # whether to save tile embeddings alongside the pooled slide embedding when level is "slide"
+  save_slide_embeddings: false # whether to save per-slide embeddings when level is "patient" (e.g. moozy); requires a 'patient_id' column in the input CSV
   save_latents: false # whether to save the latent representations from the model alongside the slide embedding (only supported for 'prism')
   allow_non_recommended_settings: false # when true, non-recommended spacing / tile size / precision combinations warn instead of erroring
 
@@ -26,10 +27,10 @@ tiling:
   read_tiles_from: # path to an existing directory containing pre-extracted `.tiles.tar` tile stores to reuse instead of starting tiling from scratch
   backend: "auto" # backend to use for slide reading; "auto" lets hs2p resolve the best backend per slide, preferring cuCIM when available
   params:
-    target_spacing_um: # spacing at which to tile the slide, in microns per pixel; filled from a preset model when available
+    requested_spacing_um: # spacing at which to tile the slide, in microns per pixel; filled from a preset model when available
     tolerance: 0.05 # tolerance for matching the spacing (float between 0 and 1, deciding how much the spacing can deviate from the one specified in the slide metadata)
-    target_tile_size_px: # size of the tiles to extract, in pixels; filled from a preset model when available
-    target_region_size_px: # size of hierarchical parent regions in pixels; when unset and region_tile_multiple is set, derived from target_tile_size_px * region_tile_multiple
+    requested_tile_size_px: # size of the tiles to extract, in pixels; filled from a preset model when available
+    requested_region_size_px: # size of hierarchical parent regions in pixels; when unset and region_tile_multiple is set, derived from requested_tile_size_px * region_tile_multiple
     region_tile_multiple: # hierarchical region grid width/height in tiles; e.g. 6 means 6x6 tiles per region
     overlap: 0.0 # percentage of overlap between two consecutive tiles (float between 0 and 1)
     tissue_threshold: 0.1 # minimum fraction of pixels that must be tissue to keep a tile (float between 0 and 1)
@@ -44,8 +45,8 @@ tiling:
     use_otsu: false # use otsu's method instead of simple binary thresholding
     use_hsv: true # use HSV thresholding instead of simple binary thresholding
   filter_params:
-    ref_tile_size: ${tiling.params.target_tile_size_px} # reference tile size at the target spacing
-    a_t: 4 # area filter threshold for tissue (positive integer, the minimum size of detected foreground contours to consider, relative to the reference tile size ref_tile_size, e.g. a value 10 means only detected foreground contours of size greater than 10 [ref_tile_size, ref_tile_size] tiles at spacing tiling.params.target_spacing_um will be kept)
+    ref_tile_size: ${tiling.params.requested_tile_size_px} # reference tile size at the target spacing
+    a_t: 4 # area filter threshold for tissue (positive integer, the minimum size of detected foreground contours to consider, relative to the reference tile size ref_tile_size, e.g. a value 10 means only detected foreground contours of size greater than 10 [ref_tile_size, ref_tile_size] tiles at spacing tiling.params.requested_spacing_um will be kept)
     a_h: 2 # area filter threshold for holes (positive integer, the minimum size of detected holes/cavities in foreground contours to avoid, once again relative to the reference tile size ref_tile_size)
     filter_white: false # whether to filter out mostly white tiles
     filter_black: false # whether to filter out mostly black tiles
@@ -78,7 +79,7 @@ wandb:
   project: "" # wandb project name
   username: "" # wandb username
   exp_name: "" # wandb experiment name
-  tags: ["features", "${model.name}", "${tiling.params.target_tile_size_px}"] # wandb tags
+  tags: ["features", "${model.name}", "${tiling.params.requested_tile_size_px}"] # wandb tags
   dir: "/home/user/"
   group:
   resume_id: "${resume_dirname}"

{slide2vec-4.1.0 → slide2vec-4.2.0}/slide2vec/data/tile_reader.py

@@ -89,7 +89,7 @@ class WSITileReader:
         self._num_cucim_workers = num_cucim_workers
         self._gpu_decode = gpu_decode
         self._read_level = int(tiling_result.read_level)
-        self._tile_size_px = int(tiling_result.effective_tile_size_px)
+        self._tile_size_px = int(tiling_result.read_tile_size_px)
         self._x = tiling_result.x
         self._y = tiling_result.y
         self._reader = None
@@ -215,7 +215,7 @@ class OnTheFlyBatchTileCollator:
         gpu_decode: bool = False,
         use_supertiles: bool = True,
     ):
-        self.tile_size = int(tiling_result.effective_tile_size_px)
+        self.tile_size = int(tiling_result.read_tile_size_px)
         self._reader = WSITileReader(
             image_path,
             tiling_result,
@@ -354,8 +354,8 @@ class OnTheFlyHierarchicalBatchCollator:
         tiling_result: TilingResult,
         region_index: np.ndarray,
         subtile_index_within_region: np.ndarray,
-        effective_region_size_px: int,
-        effective_tile_size_px: int,
+        read_region_size_px: int,
+        read_tile_size_px: int,
         backend: str = "cucim",
         num_cucim_workers: int = 4,
         gpu_decode: bool = False,
@@ -363,11 +363,11 @@ class OnTheFlyHierarchicalBatchCollator:
         self._region_index = np.asarray(region_index, dtype=np.int32)
         self._subtile_index_within_region = np.asarray(subtile_index_within_region, dtype=np.int32)
         self._tiles_per_region = int(self._subtile_index_within_region.max()) + 1 if len(self._subtile_index_within_region) else 0
-        self._tile_size = int(effective_tile_size_px)
+        self._tile_size = int(read_tile_size_px)
         self._reader = WSIRegionReader(
             image_path,
             read_level=int(tiling_result.read_level),
-            region_size_px=int(effective_region_size_px),
+            region_size_px=int(read_region_size_px),
             backend=backend,
             num_cucim_workers=num_cucim_workers,
             gpu_decode=gpu_decode,

{slide2vec-4.1.0 → slide2vec-4.2.0}/slide2vec/encoders/__init__.py

@@ -6,6 +6,7 @@ the ``models`` subpackage.
 
 from slide2vec.encoders.base import (
     Encoder,
+    PatientEncoder,
     SlideEncoder,
     TileEncoder,
     TimmTileEncoder,
@@ -24,6 +25,7 @@ from slide2vec.encoders import models as _models_pkg  # noqa: F401
 
 __all__ = [
     "Encoder",
+    "PatientEncoder",
     "TileEncoder",
     "SlideEncoder",
     "TimmTileEncoder",