def evaluate(self):
"""
Evaluate the detection performance of a model based on the model probability map output,
the ground truth tumor mask, and their associated metadata (e.g., pixel_spacing, level)
"""
# compute false positive (FP) and true positive (TP) probabilities for all images
fp_probs, tp_probs, num_targets, num_images = self.compute_fp_tp()
# compute FROC curve given the evaluation of all images
fps_per_image, total_sensitivity = compute_froc_curve_data(
fp_probs=fp_probs, tp_probs=tp_probs, num_targets=num_targets, num_images=num_images
)
# compute FROC score give specific evaluation threshold
froc_score = compute_froc_score(
fps_per_image=fps_per_image, total_sensitivity=total_sensitivity, eval_thresholds=self.eval_thresholds
)
return froc_score
def test_value(self, input_data, thresholds, expected_score):
fps_per_image, total_sensitivity = compute_froc_curve_data(
**input_data)
score = compute_froc_score(fps_per_image, total_sensitivity,
thresholds)
np.testing.assert_allclose(score, expected_score, rtol=1e-5)