: 15 laparoscopic cholecystectomy videos recorded at the University Hospital of Strasbourg.
The dataset is characterized by its high-quality annotations and diverse visual content derived from laparoscopic cholecystectomies (gallbladder removals). This procedure is a standard choice for surgical datasets due to its high volume and relatively consistent workflow, though the visual conditions can vary drastically. m2cai16-tool-locations
# Parse annotations: list of [x1, y1, x2, y2, class_id] boxes = [] labels = [] for obj in ann.get('objects', []): x1, y1, x2, y2 = obj['bbox'] # absolute pixel coords label = self.CLASSES.index(obj['class_name']) boxes.append([x1, y1, x2, y2]) labels.append(label) : 15 laparoscopic cholecystectomy videos recorded at the
: 15 laparoscopic cholecystectomy videos recorded at the University Hospital of Strasbourg.
The dataset is characterized by its high-quality annotations and diverse visual content derived from laparoscopic cholecystectomies (gallbladder removals). This procedure is a standard choice for surgical datasets due to its high volume and relatively consistent workflow, though the visual conditions can vary drastically.
# Parse annotations: list of [x1, y1, x2, y2, class_id] boxes = [] labels = [] for obj in ann.get('objects', []): x1, y1, x2, y2 = obj['bbox'] # absolute pixel coords label = self.CLASSES.index(obj['class_name']) boxes.append([x1, y1, x2, y2]) labels.append(label)
