Update README.md

README.md

@@ -52,17 +52,16 @@ This model is a Vision Transformer adapted for neuropathology tasks, developed u
 ## Model Details
 
 * **Model Type:** Vision Transformer (ViT) for neuropathology.
-* **Developed by:** [https://caai.ai.uky.edu], [Optional: in collaboration with the University of Kentucky [Specific Department/Center, e.g., Sanders-Brown Center on Aging]]
-* **Model Date:** [PLACEHOLDER: YYYY-MM-DD of model training completion or publication]
-* **Base Model Architecture (if applicable):** [PLACEHOLDER: e.g., DINOv2 ViT-S/14, ViT-B/14. Specify if registers are used, e.g., "Based on ViT-B/14 with 4 register tokens."]
-* **Input:** Image (e.g., patches from whole slide images).
-* **Output:** Class token and patch tokens [Optional: and register tokens]. These can be used for various downstream tasks (e.g., classification, segmentation, similarity search).
-* **Embedding Dimension:** [PLACEHOLDER: Specify for your ViT variant, e.g., 384 for ViT-S, 768 for ViT-B]
-* **Patch Size:** [PLACEHOLDER: e.g., 14 or 16. Confirm based on your model, e.g., "14 for a ViT with patch size 14."]
+* **Developed by:** Center for Applied Artificial Intelligence (CAAI)
+* **Model Date:** 05/05/2025
+* **Base Model Architecture:** Dinov2-giant (https://huggingface.co/facebook/dinov2-giant)
+* **Input:** Image (224x224).
+* **Output:** Class token and patch tokens. These can be used for various downstream tasks (e.g., classification, segmentation, similarity search).
+* **Embedding Dimension:** 1536
+* **Patch Size:** 14
 * **Image Size Compatibility:**
-    * The model was trained on images/patches of size [PLACEHOLDER: e.g., 224x224].
-    * For an input of [PLACEHOLDER: e.g., 224x224] with a patch size of [PLACEHOLDER: e.g., 14], this results in 1 class token + ([PLACEHOLDER: e.g., 224]/[PLACEHOLDER: e.g., 14])^2 = [PLACEHOLDER: e.g., 256] patch tokens [Optional: + X register tokens].
-    * The model can accept larger images provided the image dimensions are multiples of the patch size. If not, cropping to the closest smaller multiple may occur.
+    * The model was trained on images/patches of size 224x224.
+    * The model can accept images of any size, not just the 224x224 dimensions used in training.
 * **License:** [PLACEHOLDER: Reiterate license chosen in YAML, e.g., Apache 2.0. Add link to full license if custom or 'other'.]
 * **Repository:** [PLACEHOLDER: Link to your model repository (e.g., GitHub, Hugging Face Hub)]
 * **Paper(s)/Reference(s):**
@@ -77,115 +76,138 @@ This model is a Vision Transformer adapted for neuropathology tasks, developed u
 This model is intended for research purposes in the field of neuropathology.
 
 * **Primary Intended Uses:**
-    * [PLACEHOLDER: e.g., Automated detection of specific neuropathological features (e.g., amyloid plaques, neurofibrillary tangles, Lewy bodies) in digitized histopathological slides.]
-    * [PLACEHOLDER: e.g., Classification of tissue samples based on the presence/severity of neuropathological changes.]
-    * [PLACEHOLDER: e.g., Feature extraction for quantitative analysis of neuropathology.]
-    * [PLACEHOLDER: e.g., A research tool to explore correlations between image features and disease states/progression.]
-* **Primary Intended Users:**
-    * [PLACEHOLDER: e.g., Neuropathology researchers]
-    * [PLACEHOLDER: e.g., Computational pathology scientists]
-    * [PLACEHOLDER: e.g., AI developers working on medical imaging solutions for neurodegenerative diseases]
-* **Out-of-Scope Uses:**
-    * [PLACEHOLDER: e.g., Direct clinical diagnosis or patient management decisions without expert human neuropathologist review and confirmation.]
-    * [PLACEHOLDER: e.g., Use on staining methods, tissue types, or species significantly different from the training data without thorough validation.]
-    * [PLACEHOLDER: e.g., Any application with legal or primary diagnostic implications without regulatory clearance.]
-
+    * Classification of tissue samples based on the presence/severity of neuropathological changes.
+    * Feature extraction for quantitative analysis of neuropathology.  
 ## How to Get Started with the Model
 
 [PLACEHOLDER: Provide code snippets for loading and using your model. If available on Hugging Face, show an example using `transformers` or `torch.hub.load`.]
 
 Example using Hugging Face `transformers` (adjust based on your actual model and task):
 ```python
-# Ensure you have the necessary libraries installed:
-# pip install transformers torch Pillow
 
-from transformers import AutoImageProcessor, AutoModel # Or AutoModelForImageClassification
 import torch
 from PIL import Image
-import requests # For fetching image from URL if needed
-
-# Make sure to replace with your actual model identifier on the Hugging Face Hub
-# For example: model_id = "your-username/your-model-name"
-model_id = "[PLACEHOLDER: your-hf-hub-username/your-model-name]"
-
-# Load the processor and model
-try:
-    image_processor = AutoImageProcessor.from_pretrained(model_id)
-    # If your model is for a specific task like classification, use the appropriate AutoModel class
-    # model = AutoModelForImageClassification.from_pretrained(model_id)
-    model = AutoModel.from_pretrained(model_id) # For feature extraction
-    model.eval() # Set model to evaluation mode
-except Exception as e:
-    print(f"Error loading model or processor from Hugging Face Hub: {e}")
-    print(f"Please ensure '{model_id}' is a valid model identifier and you have an internet connection.")
-    # Fallback for placeholder if model_id is not set for demonstration
-    if model_id == "[PLACEHOLDER: your-hf-hub-username/your-model-name]":
-        print("Using a dummy model structure for demonstration as placeholder ID is used.")
-        # This is a dummy structure, not a functional model
-        from transformers import ViTConfig, ViTModel
-        config = ViTConfig(image_size=224, patch_size=14, num_labels=3, hidden_size=192, num_hidden_layers=12, num_attention_heads=3) # Minimal ViT-Tiny like
-        model = ViTModel(config) # Or ViTForImageClassification(config)
-        # A dummy processor
-        class DummyProcessor:
-            def __init__(self):
-                self.size = {"height": 224, "width": 224}
-            def __call__(self, images, return_tensors=None):
-                # Simplified dummy preprocessing
-                return {"pixel_values": torch.randn(1, 3, self.size['height'], self.size['width'])}
-        image_processor = DummyProcessor()
-
-
-# Example: Load an image
-# Option 1: From a local path
-image_path = "[PLACEHOLDER: path/to/your/neuropathology_image.png]"
-# Option 2: From a URL (example)
-# image_url = "[https://placehold.co/224x224/E6E6FA/800080?text=Sample](https://placehold.co/224x224/E6E6FA/800080?text=Sample)\nImage" # Lilac background, purple text
-image_url = "[https://placehold.co/224x224/cccccc/333333?text=Sample+Patch](https://placehold.co/224x224/cccccc/333333?text=Sample+Patch)"
-
-
-try:
-    # image = Image.open(image_path).convert("RGB")
-    # Uncomment above line and comment below if using local path
-    image = Image.open(requests.get(image_url, stream=True).raw).convert("RGB")
-except FileNotFoundError:
-    print(f"Image file not found at: {image_path}. Using a dummy image.")
-    image = Image.new('RGB', (image_processor.size['height'], image_processor.size['width']), color = 'skyblue')
-except Exception as e:
-    print(f"Error loading image: {e}. Using a dummy image.")
-    image = Image.new('RGB', (224, 224), color = 'skyblue') # Fallback size
-
-# Preprocess the image
-try:
-    inputs = image_processor(images=image, return_tensors="pt")
-except Exception as e:
-    print(f"Error during image processing: {e}")
-    inputs = {"pixel_values": torch.randn(1, 3, 224, 224)} # Fallback input
-
-# Perform inference
-with torch.no_grad():
-    try:
+from transformers import AutoModel, AutoImageProcessor
+from torchvision import transforms
+
+def get_embeddings_with_processor(image_path, model_path):
+    """
+    Extract embeddings using a HuggingFace image processor.
+    This approach handles normalization and resizing automatically.
+    
+    Args:
+        image_path: Path to the image file
+        model_path: Path to the model directory
+        processor_path: Path to the processor config directory
+    
+    Returns:
+        Image embeddings from the model
+    """
+    # Load model
+    model = AutoModel.from_pretrained(model_path)
+    model.eval()
+    
+    # Load processor from config
+    image_processor = AutoImageProcessor.from_pretrained(model_path)
+    
+    # Process the image
+    with torch.no_grad():
+        image = Image.open(image_path).convert('RGB')
+        inputs = image_processor(images=image, return_tensors="pt")
         outputs = model(**inputs)
-        # For feature extraction (AutoModel):
-        last_hidden_states = outputs.last_hidden_state
-        class_token_embedding = last_hidden_states[:, 0] # CLS token embedding
-        patch_embeddings = last_hidden_states[:, 1:]    # Patch token embeddings (excluding CLS)
-        print("Class token embedding shape:", class_token_embedding.shape)
-        print("Patch embeddings shape:", patch_embeddings.shape)
-
-        # For classification (AutoModelForImageClassification):
-        # if hasattr(outputs, 'logits'):
-        #     logits = outputs.logits
-        #     predicted_class_idx = logits.argmax(-1).item()
-        #     # Assuming your model config has id2label mapping
-        #     if hasattr(model.config, 'id2label') and model.config.id2label:
-        #         print("Predicted class:", model.config.id2label[predicted_class_idx])
-        #     else:
-        #         print("Predicted class index:", predicted_class_idx)
-        # else:
-        #     print("Model output does not contain logits. Check if you are using the correct AutoModel class for your task.")
-
-    except Exception as e:
-        print(f"Error during model inference: {e}")
+        embeddings = outputs.last_hidden_state[:, 0, :]
+    
+    return embeddings
+
+def get_embeddings_direct(image_path, model_path, mean=[0.83800817, 0.6516568, 0.78056043], std=[0.08324149, 0.09973671, 0.07153901]):
+    """
+    Extract embeddings directly without an image processor.
+    This approach works with various image resolutions since transformers handle
+    different input sizes by design.
+    
+    Args:
+        image_path: Path to the image file
+        model_path: Path to the model directory
+        mean: Normalization mean values
+        std: Normalization standard deviation values
+    
+    Returns:
+        Image embeddings from the model
+    """
+    # Load model
+    model = AutoModel.from_pretrained(model_path)
+    model.eval()
+    
+    # Define transformation - just converting to tensor and normalizing
+    transform = transforms.Compose([
+        transforms.ToTensor(),
+        transforms.Normalize(mean=mean, std=std)
+    ])
+    
+    # Process the image
+    with torch.no_grad():
+        # Open image and convert to RGB
+        image = Image.open(image_path).convert('RGB')
+        # Convert image to tensor
+        image_tensor = transform(image).unsqueeze(0)  # Add batch dimension
+        # Feed to model
+        outputs = model(pixel_values=image_tensor)
+        # Get embeddings
+        embeddings = outputs.last_hidden_state[:, 0, :]
+    
+    return embeddings
+
+def get_embeddings_resized(image_path, model_path, size=(224, 224), mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]):
+    """
+    Extract embeddings with explicit resizing to 224x224.
+    This approach ensures consistent input size regardless of original image dimensions.
+    
+    Args:
+        image_path: Path to the image file
+        model_path: Path to the model directory
+        size: Target size for resizing (default: 224x224)
+        mean: Normalization mean values
+        std: Normalization standard deviation values
+    
+    Returns:
+        Image embeddings from the model
+    """
+    # Load model
+    model = AutoModel.from_pretrained(model_path)
+    model.eval()
+    
+    # Define transformation with explicit resize
+    transform = transforms.Compose([
+        transforms.Resize(size, interpolation=transforms.InterpolationMode.BICUBIC),
+        transforms.ToTensor(),
+        transforms.Normalize(mean=mean, std=std)
+    ])
+    
+    # Process the image
+    with torch.no_grad():
+        image = Image.open(image_path).convert('RGB')
+        image_tensor = transform(image).unsqueeze(0)  # Add batch dimension
+        outputs = model(pixel_values=image_tensor)
+        embeddings = outputs.last_hidden_state[:, 0, :]
+    
+    return embeddings
+
+# Example usage
+if __name__ == "__main__":
+    image_path = "test.jpg"
+    model_path = "IBI-CAAI/NP-TEST-0" 
+    
+    # Method 1: Using image processor (recommended for consistency)
+    embeddings1 = get_embeddings_with_processor(image_path, model_path)
+    print('Embedding shape (with processor):', embeddings1.shape)
+     
+    # Method 2: Direct approach without resizing (works with various resolutions)
+    embeddings2 = get_embeddings_direct(image_path, model_path)
+    print('Embedding shape (direct):', embeddings2.shape)
+    
+    # Method 3: With explicit resize to 224x224
+    embeddings3 = get_embeddings_resized(image_path, model_path)
+    print('Embedding shape (resized):', embeddings3.shape)
 
 ```
 
@@ -197,48 +219,46 @@ with torch.no_grad():
     * **Description:** [PLACEHOLDER: Describe the data. E.g., "Digitized whole slide images (WSIs) of human post-mortem brain tissue sections from [number] subjects. Sections were stained with [e.g., Hematoxylin and Eosin (H&E), and immunohistochemistry for Amyloid-beta (Aβ) and phosphorylated Tau (pTau)]. Images were acquired using [e.g., Aperio AT2 scanner at 20x magnification]."]
     * **Preprocessing:** [PLACEHOLDER: Describe significant preprocessing steps. E.g., "WSIs were tiled into non-overlapping [e.g., 224x224 pixel] patches. Tiles with excessive background or artifacts were excluded. Color normalization using [Method, e.g., Macenko method] was applied."]
     * **Annotation (if applicable for supervised fine-tuning or evaluation):** [PLACEHOLDER: Describe the annotation process. E.g., "Regions of interest (ROIs) for [pathologies] were annotated by board-certified neuropathologists. For classification tasks, slide-level or region-level labels for [disease/pathology presence/severity] were provided."]
-* **Data Collection and Bias:**
-    * **Demographics & Characteristics:** [PLACEHOLDER: Describe characteristics of the subjects providing data – e.g., age range, sex distribution, ethnicity distribution (if available and ethically appropriate to share), primary diagnoses, disease stages. Note any significant imbalances or selection criteria. E.g., "Data primarily from individuals over 65 years of age, with a representation of [X% female, Y% male]. The cohort includes cases spanning a spectrum of Alzheimer's Disease neuropathologic change (ADNC)."]
-    * **Known Biases in Data:** [PLACEHOLDER: Address any known or potential biases in the dataset. E.g., "The dataset is derived from a single academic medical center (University of Kentucky), potentially limiting geographic and scanner-type diversity.", "Underrepresentation of certain comorbid conditions or early disease stages.", "Potential for selection bias based on consent or case availability."]
 
 ## Training Procedure
 
-* **Training System/Framework:** [PLACEHOLDER: e.g., "PyTorch", "Hugging Face Transformers library". If custom or specific framework features were essential, mention them, e.g., "Custom training loop implementing DINOv2 self-distillation loss and iBOT masked image modeling."]
-* **Base Model (if fine-tuning):** [PLACEHOLDER: e.g., "Pretrained `facebook/dinov2-vitb14` loaded from Hugging Face Hub."]
-* **Training Objective(s):** [PLACEHOLDER: Describe the loss functions and training paradigm. E.g., "Self-supervised learning using DINO loss, iBOT masked-image modeling loss, and KoLeo regularization on [CLS] tokens.", or for fine-tuning: "Fine-tuned for [specific task, e.g., multi-class classification of neuropathological features] using a cross-entropy loss function."]
+* **Training System/Framework:** DINO-MX (Modular & Flexible Self-Supervised Training Framework)
+* **Base Model (if fine-tuning):** Pretrained `facebook/dinov2-giant` loaded from Hugging Face Hub.
+* **Training Objective(s):** Self-supervised learning using DINO loss, iBOT masked-image modeling loss.
 * **Key Hyperparameters (example):**
-    * Batch size: [PLACEHOLDER]
-    * Learning rate: [PLACEHOLDER] (and schedule if any)
-    * Epochs/Iterations: [PLACEHOLDER]
-    * Optimizer: [PLACEHOLDER: e.g., AdamW]
-    * Weight decay: [PLACEHOLDER]
-    * [Optional: Other important parameters like temperature for DINO, mask ratio for iBOT]
-* **Data Augmentation:** [PLACEHOLDER: List specific augmentations used. E.g., "Standard augmentations including random cropping, horizontal/vertical flipping, rotations. Color augmentations such as random brightness, contrast, and HED color jitter specifically for histopathology images. [Optional: Stain augmentation techniques if used.]"]
-* **Training Regime:** [PLACEHOLDER: e.g., "Trained with fp16 mixed-precision using PyTorch FSDP on [Number]x NVIDIA [Type, e.g., A100] GPUs."]
-* [Optional: Parameter-Efficient Fine-Tuning (PEFT): If used, describe e.g., "LoRA was applied to attention and feed-forward network layers with a rank of [r]."]
-* [Optional: Layer Freezing: If used, e.g., "The first N layers of the pretrained backbone were frozen during fine-tuning."]
-
+    * Batch size: 32
+    * Learning rate: 1.0e-4
+    * Epochs/Iterations: 5000 Iterations
+    * Optimizer: AdamW
+    * Weight decay: 0.04-0.4 
 ## Evaluation
 
-* **Task(s):** [PLACEHOLDER: Clearly define the task(s) the model was evaluated on. E.g., "Patch-level classification of [pathology A vs. B vs. healthy]", "Detection of [specific cellular feature]", "Slide-level prediction of [disease grade]"]
-* **Metrics:** [PLACEHOLDER: List the metrics used for evaluation. E.g., "For classification: Accuracy, Precision, Recall, F1-score (macro/micro/weighted), AUC-ROC, AUC-PR. For detection: mean Average Precision (mAP) at [IoU threshold(s)]."]
-* **Evaluation Data:**
-    * **Dataset(s):** [PLACEHOLDER: Describe the dataset(s) used for evaluation. E.g., "A held-out test set from the University of Kentucky dataset, comprising [N] images/slides from [M] subjects, ensuring no overlap with the training set.", "Optional: An external validation dataset from [Source Y] consisting of [details]."]
-    * **Demographics and Characteristics:** [PLACEHOLDER: Describe the evaluation set similarly to the training data, highlighting any differences.]
-* **Results:** [PLACEHOLDER: Present key quantitative results. Tables are good for multiple metrics/classes. Include confidence intervals or standard deviations if available. E.g., "The model achieved an accuracy of X% and an F1-score of Y for classifying [pathology Z] on the internal UKy test set. On the external validation set [Dataset Name], it achieved an accuracy of A%."]
-
-## Bias, Risks, and Limitations
-
-* **Model Biases:**
-    * [PLACEHOLDER: Reflect on potential biases. E.g., "Performance may be unequal across different demographic groups if these were imbalanced in the UKy training data and these characteristics correlate with image features.", "Model may exhibit bias towards features prevalent in the specific scanner or staining protocols used at the University of Kentucky.", "Bias may arise from class imbalance in the training data, leading to better performance on majority classes."]
-* **Risks:**
-    * [PLACEHOLDER: Identify potential risks. E.g., "Over-reliance on model predictions in a research setting without thorough critical assessment by domain experts could lead to erroneous scientific conclusions.", "Risk of algorithmic bias perpetuating or amplifying existing disparities if the model is naively applied to populations or data sources different from the training set without careful validation.", "Misinterpretation of model outputs as definitive diagnostic statements (model is for research/assistive use)."]
-* **Limitations:**
-    * [PLACEHOLDER: State known limitations. E.g., "The model was trained primarily on [specific stains/markers, e.g., H&E, Aβ, pTau] and its performance on other stains is not guaranteed.", "Generalization to images from different institutions, scanners, or significantly different tissue preparation protocols may be limited without further fine-tuning or validation.", "Performance on very rare neuropathological features or subtle morphological changes may be suboptimal due to limited representation in the training data.", "The model requires high-quality input images; performance may degrade with significant artifacts (e.g., blur, tissue folds, pen marks)."]
-* **Recommendations:**
-    * Users should critically evaluate model outputs, especially in novel contexts or with data from different sources.
-    * Extensive validation is recommended before use on datasets with different characteristics than the training data.
-    * [PLACEHOLDER: Add any other specific recommendations for users.]
+* **Task(s):** Classification, KNN, Clustering, Robustness
+* **Metrics:** Accuracy, Precision, Recall, F1 
+* **Dataset(s):** Neuro Path dataset  
+* **Results:** 
+  The model achieved strong performance across multiple evaluation methods using the Neuro Path dataset. The model architecture is based on facebook/dinov2-giant.
+
+  **Linear Probe Performance:**
+  - Accuracy: 80.17%
+  - Precision: 79.20%
+  - Recall: 79.60%
+  - F1 Score: 77.88%
+
+  **K-Nearest Neighbors Classification:**
+  - Accuracy: 83.76%
+  - Precision: 83.34%
+  - Recall: 83.76%
+  - F1 Score: 83.40%
+
+  **Clustering Quality:**
+  - Silhouette Score: 0.267
+  - Adjusted Mutual Information: 0.473
+
+  **Robustness Score:** 0.574
+
+  **Overall Performance Score:** 0.646
+  
 
 ## Ethical Considerations
 
@@ -250,15 +270,7 @@ with torch.no_grad():
     * This model is intended for research purposes to augment the capabilities of neuropathology researchers. It is not a medical device and should not be used for direct clinical decision-making, diagnosis, or treatment planning without comprehensive validation, regulatory approval (if applicable), and oversight by qualified medical professionals.
 * **Fairness and Bias Mitigation:**
     * [PLACEHOLDER: Describe any steps taken during development to assess or mitigate bias, or plans for future work in this area. E.g., "Ongoing work includes evaluating model performance across different demographic subgroups represented in the University of Kentucky dataset to identify and address potential disparities."]
-
-## Environmental Impact
-
-* **Hardware Type:** [PLACEHOLDER: e.g., NVIDIA A100 80GB, NVIDIA V100 32GB, or specific University of Kentucky HPC node types]
-* **Hours Used:** [PLACEHOLDER: Estimate total GPU/TPU hours for training/fine-tuning, e.g., "Approximately X GPU hours"]
-* **Cloud Provider:** [PLACEHOLDER: e.g., University of Kentucky Lipscomb Compute Cluster, AWS, GCP, Azure, Private Infrastructure]
-* **Compute Region:** [PLACEHOLDER: e.g., Lexington, KY (for UKy HPC); us-east-1 (if cloud); Not Applicable (if local HPC)]
-* **Carbon Emitted (CO2eq):** [PLACEHOLDER: e.g., "X kg". Estimate if possible using tools like CodeCarbon or ML CO2 Impact. If not measured, state "Not quantitatively measured." Consider adding: "We encourage users to be mindful of the computational cost of using and retraining deep learning models."]
-    * *Software:* [PLACEHOLDER: e.g., PyTorch X.Y, Transformers Z.A, CUDA B.C]
+ 
 
 ## Citation / BibTeX