Function compute_froc_score

monai/metrics/froc.py:158–175

This function is modified from the official evaluation code of `CAMELYON 16 Challenge `_, and used to compute the challenge's second evaluation metric, which is defined as the average sensitivity at the predefined false positive rates per who

(
    fps_per_image: np.ndarray, total_sensitivity: np.ndarray, eval_thresholds: tuple = (0.25, 0.5, 1, 2, 4, 8)
)

def compute_froc_score(
    fps_per_image: np.ndarray, total_sensitivity: np.ndarray, eval_thresholds: tuple = (0.25, 0.5, 1, 2, 4, 8)
) -> Any:
    """
    This function is modified from the official evaluation code of
    `CAMELYON 16 Challenge <https://camelyon16.grand-challenge.org/>`_, and used to compute
    the challenge&#x27;s second evaluation metric, which is defined as the average sensitivity at
    the predefined false positive rates per whole slide image.

    Args:
        fps_per_image: the average number of false positives per image for different thresholds.
        total_sensitivity: sensitivities (true positive rates) for different thresholds.
        eval_thresholds: the false positive rates for calculating the average sensitivity. Defaults
            to (0.25, 0.5, 1, 2, 4, 8) which is the same as the CAMELYON 16 Challenge.

    """
    interp_sens = np.interp(eval_thresholds, fps_per_image[::-1], total_sensitivity[::-1])
    return np.mean(interp_sens)