Spaces:
Sleeping
Sleeping
Download src/models/medsam_wrapper.py from amitaddi/btxrd-workstation: direct link, hf CLI and curl.
- Browser
- Download file 5.78 kB
-
https://huggingface.co/spaces/amitaddi/btxrd-workstation/resolve/main/src/models/medsam_wrapper.py
- Command line
-
hf download hf://spaces/amitaddi/btxrd-workstation/src/models/medsam_wrapper.py
-
curl -L -o medsam_wrapper.py https://huggingface.co/spaces/amitaddi/btxrd-workstation/resolve/main/src/models/medsam_wrapper.py
5.78 kB
| """ | |
| MedSAM Wrapper for Bone Tumor Segmentation. | |
| MedSAM is a SAM variant fine-tuned on 1.5M medical image-mask pairs, | |
| providing a strong medical imaging prior compared to vanilla SAM/SAM2. | |
| Supports: | |
| - Zero-shot inference with bounding box prompts | |
| - Fine-tuning on BTXRD | |
| """ | |
| import os | |
| import numpy as np | |
| import torch | |
| from typing import Optional, List, Dict, Tuple | |
| # MedSAM imports | |
| try: | |
| from segment_anything import sam_model_registry, SamPredictor | |
| MEDSAM_AVAILABLE = True | |
| except ImportError: | |
| try: | |
| # Alternative import path | |
| from segment_anything import sam_model_registry, SamPredictor | |
| MEDSAM_AVAILABLE = True | |
| except ImportError: | |
| MEDSAM_AVAILABLE = False | |
| print("WARNING: MedSAM/segment_anything not installed.") | |
| print("Install with: pip install git+https://github.com/bowang-lab/MedSAM.git") | |
| MEDSAM_CHECKPOINT_URL = "https://zenodo.org/records/10689643/files/medsam_vit_b.pth" | |
| class MedSAMWrapper: | |
| """ | |
| Wrapper around MedSAM for bone tumor segmentation. | |
| MedSAM uses SAM's ViT-B architecture, fine-tuned on medical images. | |
| It only supports bounding box prompts (no point prompts). | |
| """ | |
| def __init__(self, | |
| checkpoint_path: Optional[str] = None, | |
| device: str = 'cuda'): | |
| """ | |
| Args: | |
| checkpoint_path: Path to medsam_vit_b.pth | |
| device: 'cuda' or 'cpu' | |
| """ | |
| if not MEDSAM_AVAILABLE: | |
| raise RuntimeError("segment_anything not installed for MedSAM") | |
| self.device = device | |
| if checkpoint_path is None: | |
| checkpoint_path = self._get_or_download_checkpoint() | |
| # Build MedSAM (uses SAM's ViT-B architecture) | |
| self.model = sam_model_registry['vit_b'](checkpoint=checkpoint_path) | |
| self.model = self.model.to(device) | |
| self.model.eval() | |
| self.predictor = SamPredictor(self.model) | |
| print(f"MedSAM (ViT-B) loaded on {device}") | |
| def _get_or_download_checkpoint(self) -> str: | |
| """Download MedSAM checkpoint if not present.""" | |
| cache_dir = os.path.join(os.path.expanduser('~'), '.cache', 'medsam') | |
| os.makedirs(cache_dir, exist_ok=True) | |
| filepath = os.path.join(cache_dir, 'medsam_vit_b.pth') | |
| if not os.path.exists(filepath): | |
| print(f"Downloading MedSAM checkpoint...") | |
| print(f" URL: {MEDSAM_CHECKPOINT_URL}") | |
| print(f" Saving to: {filepath}") | |
| import urllib.request | |
| urllib.request.urlretrieve(MEDSAM_CHECKPOINT_URL, filepath) | |
| print(" Download complete!") | |
| return filepath | |
| def set_image(self, image: np.ndarray): | |
| """ | |
| Set image for prediction. | |
| Args: | |
| image: (H, W, 3) RGB numpy array | |
| """ | |
| self.predictor.set_image(image) | |
| def predict_with_box(self, | |
| box: np.ndarray, | |
| multimask_output: bool = False) -> Tuple[np.ndarray, float]: | |
| """ | |
| Predict segmentation using bounding box prompt. | |
| Args: | |
| box: (4,) [x1, y1, x2, y2] in pixel coordinates | |
| multimask_output: Return multiple mask candidates | |
| Returns: | |
| mask: (H, W) binary mask | |
| score: Predicted IoU | |
| """ | |
| # MedSAM expects box as (1, 4) tensor | |
| box_torch = torch.tensor(box, dtype=torch.float32, device=self.device) | |
| box_transformed = self.predictor.transform.apply_boxes_torch( | |
| box_torch.unsqueeze(0), | |
| self.predictor.original_size | |
| ) | |
| masks, scores, logits = self.predictor.predict_torch( | |
| point_coords=None, | |
| point_labels=None, | |
| boxes=box_transformed, | |
| multimask_output=multimask_output, | |
| ) | |
| # Move to CPU and take best | |
| masks = masks.cpu().numpy() | |
| scores = scores.cpu().numpy() | |
| best_idx = scores[0].argmax() | |
| mask = masks[0, best_idx] | |
| score = float(scores[0, best_idx]) | |
| return mask.astype(np.uint8), score | |
| def predict_all_objects(self, | |
| image: np.ndarray, | |
| prompts: List[Dict]) -> List[Dict]: | |
| """ | |
| Predict masks for all objects using box prompts. | |
| Args: | |
| image: (H, W, 3) RGB | |
| prompts: List of prompt dicts with 'box', 'class_id' | |
| Returns: | |
| List of result dicts | |
| """ | |
| self.set_image(image) | |
| results = [] | |
| for prompt in prompts: | |
| mask, score = self.predict_with_box(prompt['box']) | |
| results.append({ | |
| 'mask': mask, | |
| 'score': score, | |
| 'class_id': prompt['class_id'], | |
| 'prompt_type': 'box', | |
| }) | |
| return results | |
| def combine_masks(self, results: List[Dict], shape: Tuple[int, int]) -> np.ndarray: | |
| """Combine per-object masks into single binary mask.""" | |
| import cv2 | |
| combined = np.zeros(shape, dtype=np.uint8) | |
| for r in results: | |
| mask = r['mask'] | |
| if mask.shape != shape: | |
| mask = cv2.resize(mask, (shape[1], shape[0]), | |
| interpolation=cv2.INTER_NEAREST) | |
| combined = np.maximum(combined, mask) | |
| return combined | |
| if __name__ == '__main__': | |
| if MEDSAM_AVAILABLE: | |
| print("MedSAM dependencies available!") | |
| else: | |
| print("MedSAM not installed. Run:") | |
| print(" pip install git+https://github.com/bowang-lab/MedSAM.git") | |