459 add camelyon16 slide level task

configs/vision/dino_vit/offline/camelyon16.yaml

@@ -0,0 +1,135 @@
+---
+trainer:
+  class_path: eva.Trainer
+  init_args:
+    n_runs: &N_RUNS ${oc.env:N_RUNS, 3}
+    default_root_dir: &OUTPUT_ROOT ${oc.env:OUTPUT_ROOT, logs/${oc.env:DINO_BACKBONE, owkin/phikon}/offline/camelyon16}
+    max_steps: &MAX_STEPS ${oc.env:MAX_STEPS, 12500}
+    callbacks:
+      - class_path: lightning.pytorch.callbacks.LearningRateMonitor
+        init_args:
+          logging_interval: epoch
+      - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+        init_args:
+          filename: best
+          save_last: true
+          save_top_k: 1
+          monitor: &MONITOR_METRIC ${oc.env:MONITOR_METRIC, val/BinaryAccuracy}
+          mode: &MONITOR_METRIC_MODE ${oc.env:MONITOR_METRIC_MODE, max}
+      - class_path: lightning.pytorch.callbacks.EarlyStopping
+        init_args:
+          min_delta: 0
+          patience: 74
+          monitor: *MONITOR_METRIC
+          mode: *MONITOR_METRIC_MODE
+      - class_path: eva.callbacks.EmbeddingsWriter
+        init_args:
+          output_dir: &DATASET_EMBEDDINGS_ROOT ${oc.env:EMBEDDINGS_ROOT, ./data/embeddings}/${oc.env:DINO_BACKBONE, dino_vits16}/camelyon16
+          dataloader_idx_map:
+            0: train
+            1: val
+            2: test
+          metadata_keys: ["wsi_id"]
+          backbone:
+            class_path: eva.models.ModelFromFunction
+            init_args:
+              path: torch.hub.load
+              arguments:
+                repo_or_dir: ${oc.env:REPO_OR_DIR, facebookresearch/dino:main}
+                model: ${oc.env:DINO_BACKBONE, dino_vits16}
+                pretrained: ${oc.env:PRETRAINED, true}
+                force_reload: ${oc.env:FORCE_RELOAD, false}
+              checkpoint_path: ${oc.env:CHECKPOINT_PATH, null}
+    logger:
+      - class_path: lightning.pytorch.loggers.TensorBoardLogger
+        init_args:
+          save_dir: *OUTPUT_ROOT
+          name: ""
+model:
+  class_path: eva.HeadModule
+  init_args:
+    head:
+      class_path: eva.vision.models.networks.ABMIL
+      init_args:
+        input_size: ${oc.env:IN_FEATURES, 768}
+        output_size: &NUM_CLASSES 1
+        projected_input_size: 128
+    criterion: torch.nn.BCEWithLogitsLoss
+    optimizer:
+      class_path: torch.optim.AdamW
+      init_args:
+        lr: &LR_VALUE 0.000039
+        betas: [0.9, 0.999]
+    lr_scheduler:
+      class_path: torch.optim.lr_scheduler.CosineAnnealingLR
+      init_args:
+        T_max: *MAX_STEPS
+        eta_min: 0.0
+    metrics:
+      common:
+        - class_path: eva.metrics.AverageLoss
+        - class_path: eva.metrics.BinaryClassificationMetrics
+data:
+  class_path: eva.DataModule
+  init_args:
+    datasets:
+      train:
+        class_path: eva.datasets.MultiEmbeddingsClassificationDataset
+        init_args: &DATASET_ARGS
+          root: *DATASET_EMBEDDINGS_ROOT
+          manifest_file: manifest.csv
+          split: train
+          embeddings_transforms:
+            class_path: eva.core.data.transforms.Pad2DTensor
+            init_args:
+              pad_size: 10_000
+          target_transforms:
+            class_path: eva.core.data.transforms.dtype.ArrayToFloatTensor
+      val:
+        class_path: eva.datasets.MultiEmbeddingsClassificationDataset
+        init_args:
+          <<: *DATASET_ARGS
+          split: val
+      test:
+        class_path: eva.datasets.MultiEmbeddingsClassificationDataset
+        init_args:
+          <<: *DATASET_ARGS
+          split: test
+      predict:
+        - class_path: eva.vision.datasets.Camelyon16
+          init_args: &PREDICT_DATASET_ARGS
+            root: ${oc.env:DATA_ROOT, ./data}/camelyon16
+            sampler:
+              class_path: eva.vision.data.wsi.patching.samplers.ForegroundGridSampler
+              init_args:
+                max_samples: 10_000
+            width: 224
+            height: 224
+            target_mpp: 0.25
+            split: train
+            image_transforms:
+              class_path: eva.vision.data.transforms.common.ResizeAndCrop
+              init_args:
+                size: ${oc.env:RESIZE_DIM, 224} 
+                mean: ${oc.env:NORMALIZE_MEAN, [0.485, 0.456, 0.406]} 
+                std: ${oc.env:NORMALIZE_STD, [0.229, 0.224, 0.225]}
+        - class_path: eva.vision.datasets.Camelyon16
+          init_args:
+            <<: *PREDICT_DATASET_ARGS
+            split: val
+        - class_path: eva.vision.datasets.Camelyon16
+          init_args:
+            <<: *PREDICT_DATASET_ARGS
+            split: test
+    dataloaders:
+      train:
+        batch_size: &BATCH_SIZE ${oc.env:BATCH_SIZE, 16}
+        shuffle: true
+      val:
+        batch_size: *BATCH_SIZE
+      test:
+        batch_size: *BATCH_SIZE
+      predict:
+        batch_size: &PREDICT_BATCH_SIZE ${oc.env:PREDICT_BATCH_SIZE, 64}
+        num_workers: 12 #multiprocessing.cpu_count
+        prefetch_factor: 2

docs/datasets/camelyon16.md

@@ -0,0 +1,68 @@
+# Camelyon16
+
+The Camelyon16 dataset consists of 400 WSIs of lymph nodes for breast cancer metastasis classification. The dataset is a combination of two independent datasets, collected from two separate medical centers in the Netherlands (Radboud University Medical Center and University Medical Center Utrecht). The dataset contains the slides from which [PatchCamelyon](patch_camelyon.md)-patches were extracted.
+
+The dataset is divided in a train set (270 slides) and test set (130 slides), both containing images from both centers.
+
+The task was part of [Grand Challenge](https://grand-challenge.org/) in 2016 and has later been replaced by Camelyon17.
+
+Source: https://camelyon16.grand-challenge.org
+
+## Raw data
+
+### Key stats
+
+|                           |                                                          |
+|---------------------------|----------------------------------------------------------|
+| **Modality**              | Vision (Slide-level)                                     |
+| **Task**                  | Binary classification                                    |
+| **Cancer type**           | Breast                                                   |
+| **Data size**             | ~700 GB                                                  |
+| **Image dimension**       | ~100-250k x ~100-250k x 3                                |
+| **Magnification (μm/px)** | 40x (0.25) - Level 0                                     |
+| **Files format**          | `.tif`                                                   |
+| **Number of images**      | 400 (270 train, 130 test)                                |
+
+
+### Organization
+
+The data `CAMELYON16` (download links [here](https://camelyon17.grand-challenge.org/Data/)) is organized as follows:
+
+```
+CAMELYON16
+├── training
+│   ├── normal
+|   │   ├── normal_001.tif
+|   │   └── ...
+│   ├── tumor
+|   │   ├── tumor_001.tif
+|   │   └── ...
+│   └── lesion_annotations.zip
+├── testing
+│   ├── images
+|   │   ├── test_001.tif
+|   │   └── ...
+│   ├── evaluation     # masks not in use
+│   ├── reference.csv  # targets
+│   └── lesion_annotations.zip
+```
+
+## Download and preprocessing
+
+The `Camelyon16` dataset class doesn't download the data during runtime and must be downloaded manually from links provided [here](https://camelyon17.grand-challenge.org/Data/).
+
+The dataset is split into train / test. Additionally, we split the train set into train/val using the same splits as [PatchCamelyon](patch_camelyon.md) (see metadata CSV files on [Zenodo](https://zenodo.org/records/2546921)).
+
+| Splits   | Train       | Validation  | Test       |  
+|----------|-------------|-------------|------------|
+| #Samples | 216 (54%)  | 54 (13.5%)  | 130 (32.5%) |
+
+
+## Relevant links
+
+* [Grand Challenge dataset description](https://camelyon16.grand-challenge.org/Data/)
+* [Download links](https://camelyon17.grand-challenge.org/Data/)
+
+
+## References
+1 : [A General-Purpose Self-Supervised Model for Computational Pathology](https://arxiv.org/abs/2308.15474)

docs/datasets/index.md

@@ -7,9 +7,10 @@
 ### Whole Slide (WSI) and microscopy image datasets
 
 #### Slide-level
-| Dataset                            | #Slides  | Slide Size        | Magnification (μm/px)  | Task                       | Cancer Type      |
-|------------------------------------|----------|------------|------------------------|----------------------------|------------------|
-| [PANDA](panda.md)                  | 3,152    | ~20k x 20k x 3    |  20x (0.5)             | Classification (6 classes) | Prostate         |
+| Dataset                            | #Slides  | Slide Size                | Magnification (μm/px)  | Task                       | Cancer Type      |
+|------------------------------------|----------|---------------------------|------------------------|----------------------------|------------------|
+| [Camelyon16](camelyon16.md)        | 400      | ~100-250k x ~100-250k x 3 |  40x (0.25)            | Classification (2 classes) | Breast           |
+| [PANDA](panda.md)                  | 10,616    | ~20k x 20k x 3            |  20x (0.5)             | Classification (6 classes) | Prostate         |
 
 
 #### Patch-level

src/eva/vision/data/datasets/__init__.py

@@ -5,6 +5,7 @@
     CRC,
     MHIST,
     PANDA,
+    Camelyon16,
     PatchCamelyon,
     TotalSegmentatorClassification,
     WsiClassificationDataset,
@@ -20,6 +21,7 @@
     "ImageSegmentation",
     "PatchCamelyon",
     "PANDA",
+    "Camelyon16",
     "TotalSegmentatorClassification",
     "TotalSegmentator2D",
     "VisionDataset",

src/eva/vision/data/datasets/_validators.py

@@ -57,3 +57,16 @@ def check_dataset_exists(dataset_dir: str, download_available: bool) -> None:
         if download_available:
             error_message += " You can set `download=True` to download the dataset automatically."
         raise FileNotFoundError(error_message)
+
+
+def check_number_of_files(file_paths: List[str], expected_length: int, split: str | None) -> None:
+    """Verifies the number of files in the dataset.
+
+    Raise:
+        ValueError: If the number of files in the dataset does not match the expected one.
+    """
+    if len(file_paths) != expected_length:
+        raise ValueError(
+            f"Expected {expected_length} files, for split '{split}' found {len(file_paths)}. "
+            f"{_SUFFIX_ERROR_MESSAGE}"
+        )

src/eva/vision/data/datasets/classification/__init__.py

@@ -1,6 +1,7 @@
 """Image classification datasets API."""
 
 from eva.vision.data.datasets.classification.bach import BACH
+from eva.vision.data.datasets.classification.camelyon16 import Camelyon16
 from eva.vision.data.datasets.classification.crc import CRC
 from eva.vision.data.datasets.classification.mhist import MHIST
 from eva.vision.data.datasets.classification.panda import PANDA
@@ -16,4 +17,5 @@
     "TotalSegmentatorClassification",
     "WsiClassificationDataset",
     "PANDA",
+    "Camelyon16",
 ]