improve support for tissue seg

README.md

@@ -39,9 +39,12 @@ pip install slide2vec
 
 2. Create a configuration file
 
-   A good starting point is the default configuration file `slide2vec/configs/default.yaml` where parameters are documented.<br>
+   A good starting point are the default configuration files where parameters are documented:<br>
+   - for preprocessing options: `slide2vec/configs/default_tiling.yaml`
+   - for model options: `slide2vec/configs/default_model_.yaml`
+
    We've also added default configuration files for each of the foundation models currently supported:
-   - tile-level: `uni`, `uni2`, `virchow`, `virchow2`, `prov-gigapath`, `h-optimus-0`, `h-optimus-1`, `h0-mini`, `conch`, `musk`, `phikonv2`, `hibou-b`, `hibou-L`, [`kaiko`](https://github.com/kaiko-ai/towards_large_pathology_fms)
+   - tile-level: `uni`, `uni2`, `virchow`, `virchow2`, `prov-gigapath`, `h-optimus-0`, `h-optimus-1`, `h0-mini`, `conch`, `musk`, `phikonv2`, `hibou-b`, `hibou-L`, `MidNight12k`, [`kaiko`](https://github.com/kaiko-ai/towards_large_pathology_fms)
    - slide-level: `prov-gigapath`, `titan`, `prism`
 
 

slide2vec/configs/__init__.py

@@ -8,10 +8,13 @@ def load_config(config_name: str):
     return OmegaConf.load(pathlib.Path(__file__).parent.resolve() / config_filename)
 
 
-default_config = load_config("default")
+default_tiling_config = load_config("default_tiling")
+default_model_config = load_config("default_model")
 
 
 def load_and_merge_config(config_name: str):
-    default_config = OmegaConf.create(default_config)
+    default_tiling_config = OmegaConf.create(default_tiling_config)
+    default_model_config = OmegaConf.create(default_model_config)
+    default_config = OmegaConf.merge(default_tiling_config, default_model_config)
     loaded_config = load_config(config_name)
-    return OmegaConf.merge(default_config, loaded_config)
+    return OmegaConf.merge(default_config, loaded_config)

slide2vec/configs/default_model.yaml

@@ -0,0 +1,34 @@
+csv: # path to csv containing slide paths
+
+output_dir: "output" # output directory
+resume: false # resume from a previous run
+resume_dirname: # directory name to resume from
+
+seed: 0 # seed for reproducibility
+
+model:
+  level: "tile" # level at which to extract the features ("tile", "region" or "slide")
+  name: # foundation model name ["uni", "uni2", "virchow", "virchow2", "prov-gigapath", "h-optimus-0", "h-optimus-1", "titan", "prism"] (leave empty when using a custom model)
+  mode: "cls" # embedding mode ["cls", "full"]
+  arch: # architecture of custom model
+  pretrained_weights: # path to the pretrained weights when using a custom model
+  batch_size: 256
+  tile_size: ${tiling.params.tile_size}
+  restrict_to_tissue: false # whether to restrict tile content to tissue pixels only when feeding tile through encoder
+  patch_size: 256 # if level is "region", size used to unroll the region into patches
+  save_tile_embeddings: false # whether to save tile embeddings alongside the pooled slide embedding when level is "slide"
+  save_latents: false # whether to save the latent representations from the model alongside the slide embedding (only supported for 'prism')
+
+speed:
+  fp16: false # use mixed precision during model inference
+  num_workers_embedding: 8 # number of workers for data loading when embedding slides
+
+wandb:
+  enable: false
+  project: "" # wandb project name
+  username: "" # wandb username
+  exp_name: "" # wandb experiment name
+  tags: ["features", "${model.level}", "${tiling.params.tile_size}"] # wandb tags
+  dir: "/home/user/"
+  group:
+  resume_id: "${resume_dirname}"

slide2vec/configs/default_tiling.yaml

@@ -0,0 +1 @@
+../hs2p/hs2p/configs/default.yaml

slide2vec/data/dataset.py

@@ -41,6 +41,7 @@ def __init__(
                 path=self.path,
                 mask_path=self.mask_path,
                 backend=self.backend,
+                segment=self.mask_path is None,
                 segment_params=segment_params,
                 sampling_params=sampling_params,
             )

slide2vec/embed.py

@@ -173,10 +173,13 @@ def main(args):
         process_list.is_file()
     ), "Process list CSV not found. Ensure tiling has been run."
     process_df = pd.read_csv(process_list)
+    cols = ["wsi_name", "wsi_path", "tiling_status", "error", "traceback"]
     if "feature_status" not in process_df.columns:
         process_df["feature_status"] = ["tbp"] * len(process_df)
-        cols = ["wsi_name", "wsi_path", "mask_path", "tiling_status", "feature_status", "error", "traceback"]
-        process_df = process_df[cols]
+    if "mask_path" not in process_df.columns:
+        process_df["mask_path"] = [None] * len(process_df)
+    cols = ["wsi_name", "wsi_path", "mask_path", "tiling_status", "feature_status", "error", "traceback"]
+    process_df = process_df[cols]
 
     skip_feature_extraction = process_df["feature_status"].str.contains("success").all()
 
@@ -217,7 +220,7 @@ def main(args):
         total = len(process_stack)
 
         wsi_paths_to_process = [Path(x) for x in process_stack.wsi_path.values.tolist()]
-        mask_paths_to_process = [Path(x) for x in process_stack.mask_path.values.tolist()]
+        mask_paths_to_process = [Path(x) if x is not None and not pd.isna(x) else None  for x in process_stack.mask_path.values.tolist()]
         combined_paths = zip(wsi_paths_to_process, mask_paths_to_process)
 
         features_dir = Path(cfg.output_dir, "features")

slide2vec/utils/config.py

@@ -11,7 +11,7 @@
 
 import slide2vec.distributed as distributed
 from slide2vec.utils import initialize_wandb, fix_random_seeds, get_sha, setup_logging
-from slide2vec.configs import default_config
+from slide2vec.configs import default_tiling_config, default_model_config
 
 logger = logging.getLogger("slide2vec")
 
@@ -25,7 +25,9 @@ def write_config(cfg, output_dir, name="config.yaml"):
 
 
 def get_cfg_from_file(config_file):
-    default_cfg = OmegaConf.create(default_config)
+    default_tiling_cfg = OmegaConf.create(default_tiling_config)
+    default_embedding_cfg = OmegaConf.create(default_model_config)
+    default_cfg = OmegaConf.merge(default_tiling_cfg, default_embedding_cfg)
     cfg = OmegaConf.load(config_file)
     cfg = OmegaConf.merge(default_cfg, cfg)
     OmegaConf.resolve(cfg)
@@ -36,7 +38,9 @@ def get_cfg_from_args(args):
     if args.output_dir is not None:
         args.output_dir = os.path.abspath(args.output_dir)
         args.opts += [f"output_dir={args.output_dir}"]
-    default_cfg = OmegaConf.create(default_config)
+    default_tiling_cfg = OmegaConf.create(default_tiling_config)
+    default_embedding_cfg = OmegaConf.create(default_model_config)
+    default_cfg = OmegaConf.merge(default_tiling_cfg, default_embedding_cfg)
     cfg = OmegaConf.load(args.config_file)
     cfg = OmegaConf.merge(default_cfg, cfg, OmegaConf.from_cli(args.opts))
     OmegaConf.resolve(cfg)

test/input/config.yaml

@@ -19,7 +19,7 @@ model:
 
 speed:
   fp16: true
-  num_workers_tiling: 4
+  num_workers: 4
   num_workers_embedding: 4
 
 wandb: