def dsc_distribution(volumes):
dsc_dict = {}
for p in volumes:
y_pred = volumes[p][1]
y_true = volumes[p][2]
dsc_dict[p] = dsc(y_pred, y_true, lcc=False)
return dsc_dict
def dsc_per_volume(validation_pred, validation_true):
assert len(validation_pred) == len(validation_true)
dsc_list = []
for p in range(len(validation_pred)):
y_pred = np.array([validation_pred[p]])
y_true = np.array([validation_true[p]])
dsc_list.append(dsc(y_pred, y_true))
return dsc_list
def get_batch_dsc(y_pred_batch, mask):
batch_dsc = []
batch_size = mask.shape[0]
for case in range(batch_size):
y_pred = y_pred_batch[case, 0, :] # get a 3d volume for each case
y_true = mask[case, 0, :]
batch_dsc.append(dsc(y_pred, y_true))
return batch_dsc
def dsc_per_volume(validation_pred, validation_true, patient_slice_index):
dsc_list = []
num_slices = np.bincount([p[0] for p in patient_slice_index])
index = 0
for p in range(len(num_slices)):
y_pred = np.array(validation_pred[index : index + num_slices[p]])
y_true = np.array(validation_true[index : index + num_slices[p]])
dsc_list.append(dsc(y_pred, y_true))
index += num_slices[p]
return dsc_list
num_slices = np.bincount([p[0] for p in loader.dataset.patient_slice_index])
index = 0
for p in range(len(num_slices)):
volume_in = np.array(input_list[index : index + num_slices[p]])
volume_pred = np.round(np.array(pred_list[index : index + num_slices[p]])).astype(int)
volume_pred = largest_connected_component(volume_pred)
volume_true = np.array(true_list[index : index + num_slices[p]])
volumes[loader.dataset.patients[p]] = (volume_in, volume_pred, volume_true)
index += num_slices[p]
dsc_dict = {}
for p in volumes:
y_pred = volumes[p][1]
y_true = volumes[p][2]
dsc_dict[p] = dsc(y_pred, y_true, lcc=False)
y_positions = np.arange(len(dsc_dict))
dsc_dict = sorted(dsc_dict.items(), key=lambda x: x[1])
values = [x[1] for x in dsc_dict]
labels = [x[0] for x in dsc_dict]
labels = ["_".join(l.split("_")[1:-1]) for l in labels]
fig = plt.figure(figsize=(12, 8))
canvas = FigureCanvasAgg(fig)
plt.barh(y_positions, values, align="center", color="skyblue")
plt.yticks(y_positions, labels)
plt.xticks(np.arange(0.0, 1.0, 0.1))
plt.xlim([0.0, 1.0])
plt.gca().axvline(np.mean(values), color="tomato", linewidth=2)
plt.gca().axvline(np.median(values), color="forestgreen", linewidth=2)