prob_data[..., j + 1] += temp
prob_data = prob_data / num
prob_data[prob_data < thres] = 0
mpm = np.argmax(prob_data, axis=3)
for j in range(len(cls_list)):
mpm[mpm == j + 1] = cls_list[j]
## save MPM file
#mybase.save2nifti(mpm, header, os.path.join(data_dir, 'mpm.nii.gz'))
pred_label = mpm * mask_data * test_data
# compute Dice
for label_idx in cls_list:
P = pred_label == label_idx
T = test_label == label_idx
dice_val = mymath.dice_coef(T, P)
print 'Dice for label %s: %f' % (label_idx, dice_val)
if label_idx == 4:
temp_ffa_dice.append(dice_val)
else:
temp_ofa_dice.append(dice_val)
# compute consistency of peak location
for label_idx in cls_list:
P = pred_label == label_idx
T = test_label == label_idx
pred_zstat = P * zstat_data[..., i]
true_zstat = T * zstat_data[..., i]
if P.sum() and T.sum():
if np.argmax(pred_zstat) == np.argmax(true_zstat):
c = 1
prob_data[..., j+1] += temp
prob_data = prob_data / num
prob_data[prob_data<thres] = 0
mpm = np.argmax(prob_data, axis=3)
for j in range(len(cls_list)):
mpm[mpm==j+1] = cls_list[j]
## save MPM file
#mybase.save2nifti(mpm, header, os.path.join(data_dir, 'mpm.nii.gz'))
pred_label = mpm * mask_data * test_data
# compute Dice
for label_idx in cls_list:
P = pred_label == label_idx
T = test_label == label_idx
dice_val = mymath.dice_coef(T, P)
print 'Dice for label %s: %f'%(label_idx, dice_val)
if label_idx == 4:
temp_ffa_dice.append(dice_val)
else:
temp_ofa_dice.append(dice_val)
# compute consistency of peak location
for label_idx in cls_list:
P = pred_label == label_idx
T = test_label == label_idx
pred_zstat = P * zstat_data[..., i]
true_zstat = T * zstat_data[..., i]
if P.sum() and T.sum():
if np.argmax(pred_zstat) == np.argmax(true_zstat):
c = 1
pred_data = np.around(pred_data)
roi_label = [8, 10, 12]
for roi in roi_label:
out_file = os.path.join(pred_dir, 'perf_' + str(roi) + '.txt')
f = open(out_file, 'w')
f.write('SID, peak, dice\n')
for i in range(len(sessid)):
tmp_pred = pred_data[..., i].copy()
tmp_pred[tmp_pred!=roi] = 0
tmp_pred[tmp_pred==roi] = 1
tmp_label = label_data[..., i].copy()
tmp_label[tmp_label!=roi] = 0
tmp_label[tmp_label==roi] = 1
pred_zstat = tmp_pred * zstat_data[..., i]
true_zstat = tmp_label * zstat_data[..., i]
if tmp_pred.sum() and tmp_label.sum():
if np.argmax(pred_zstat) == np.argmax(true_zstat):
c = 1
else:
c = 0
elif tmp_pred.sum() or tmp_label.sum():
c = 0
else:
c = 1
dice = mymath.dice_coef(tmp_pred, tmp_label)
f.write(','.join([sessid[i], str(c), str(dice)]) + '\n')
pred_data = nib.load(pred_file).get_data()
pred_data = np.around(pred_data)
roi_label = [8, 10, 12]
for roi in roi_label:
out_file = os.path.join(pred_dir, 'perf_' + str(roi) + '.txt')
f = open(out_file, 'w')
f.write('SID, peak, dice\n')
for i in range(len(sessid)):
tmp_pred = pred_data[..., i].copy()
tmp_pred[tmp_pred != roi] = 0
tmp_pred[tmp_pred == roi] = 1
tmp_label = label_data[..., i].copy()
tmp_label[tmp_label != roi] = 0
tmp_label[tmp_label == roi] = 1
pred_zstat = tmp_pred * zstat_data[..., i]
true_zstat = tmp_label * zstat_data[..., i]
if tmp_pred.sum() and tmp_label.sum():
if np.argmax(pred_zstat) == np.argmax(true_zstat):
c = 1
else:
c = 0
elif tmp_pred.sum() or tmp_label.sum():
c = 0
else:
c = 1
dice = mymath.dice_coef(tmp_pred, tmp_label)
f.write(','.join([sessid[i], str(c), str(dice)]) + '\n')
'lffa': 4,
'rpcsts': 7,
'lpcsts': 8,
'rpsts': 9,
'lpsts': 10,
'rasts': 11,
'lasts': 12}
for roi in roi_dict:
roi_idx = roi_dict[roi]
roi_dice = []
roi_mask = parcel_data.copy()
roi_mask[roi_mask!=roi_idx] = 0
roi_mask[roi_mask==roi_idx] = 1
label = label_data.copy()
label[label!=roi_idx] = 0
label[label==roi_idx] = 1
for i in range(act_data.shape[3]):
pred_roi = act_data[..., i] * roi_mask
dice = mymath.dice_coef(pred_roi, label[..., i])
roi_dice.append(dice)
print 'Mean Dice - %s: %s'%(roi, np.array(roi_dice).mean())
out_file = os.path.join(roi + '_dice_output.txt')
f = open(out_file, 'w')
for line in roi_dice:
f.write(str(line) + '\n')
def leave_one_out_test(sid_list,
atlas_num,
data_dir,
class_label,
forest_list,
classes_list,
spatial_ptn,
save_nifti=False,
sorted=True,
single_atlas=False):
"""
Evaluate classifier performance with leave-one-out scheme.
"""
# initial output dice value
dice = {}
for idx in class_label:
dice[idx] = []
for i in range(len(sid_list)):
print 'Test subject %s' % (sid_list[i])
test_data = get_subj_sample(sid_list[i], data_dir)
# mask out voxels which are not activated significantly
smp_mask = test_data[..., 0] >= 2.3
#test_x = test_data[smp_mask, 0:4]
test_x = test_data[smp_mask, 1:4]
test_y = test_data[smp_mask, -1]
# define similarity index
similarity = []
atlas_idx = []
for j in range(len(sid_list)):
if i == j:
continue
atlas_idx.append(j)
#r = normalized_mutual_info_score(spatial_ptn[..., i],
# spatial_ptn[..., j])
#r = mymath.mutual_information(spatial_ptn[..., i],
# spatial_ptn[..., j])
r = np.corrcoef(spatial_ptn[..., i], spatial_ptn[..., j])[0, 1]
similarity.append(r)
# sort the similarity
sorted_sim_idx = np.argsort(similarity)[::-1]
#print similarity
#print sorted_sim_idx
# label the activation voxels with atlas forests (AFs)
tmp_dice = {}
for idx in class_label:
tmp_dice[idx] = []
for num in atlas_num:
print 'atlas number %s' % (num)
if sorted:
if not single_atlas:
selected_atlas = sorted_sim_idx[0:num]
else:
selected_atlas = sorted_sim_idx[(num - 1):num]
else:
selected_atlas = np.random.choice(len(sorted_sim_idx),
num,
replace=False)
pred_prob = None
for idx in selected_atlas:
clf = forest_list[atlas_idx[idx]]
prob = clf.predict_proba(test_x)
std_prob = np.zeros((prob.shape[0], len(class_label) + 1))
# TODO: construct a std prob table
for cls_idx in range(prob.shape[1]):
if classes_list[atlas_idx[idx]][cls_idx] == 0:
std_prob[..., 0] = prob[..., cls_idx]
else:
tmp_idx = class_label.index(
classes_list[atlas_idx[idx]][cls_idx])
std_prob[..., tmp_idx + 1] = prob[..., cls_idx]
new_prob = np.zeros(std_prob.shape)
new_prob[range(new_prob.shape[0]),
np.argmax(std_prob, axis=1)] = 1
# optional: modulate prediction probability with similarity
#new_prob = new_prob * similarity[clf_idx]
if not isinstance(pred_prob, np.ndarray):
pred_prob = new_prob
else:
pred_prob += new_prob
#print pred_prob.shape
tmp_pred_y = np.argmax(pred_prob, axis=1)
pred_y = np.zeros(tmp_pred_y.shape)
for k in range(1, pred_prob.shape[1]):
pred_y[tmp_pred_y == k] = class_label[k - 1]
for label_idx in class_label:
P = pred_y == label_idx
T = test_y == label_idx
dice_val = mymath.dice_coef(T, P)
print 'Dice for label %s: %f' % (label_idx, dice_val)
tmp_dice[label_idx].append(dice_val)
# save predicted label as a nifti file
if save_nifti:
# predicted nifti directory
pred_dir = os.path.join(data_dir, str(num) + '_atlas_pred')
if not os.path.exists(pred_dir):
os.system('mkdir ' + pred_dir)
fsl_dir = os.getenv('FSL_DIR')
img = nib.load(
os.path.join(fsl_dir, 'data', 'standard',
'MNI152_T1_2mm_brain.nii.gz'))
# save predicted label
header = img.get_header()
#coords = test_x[..., 1:4]
coords = test_x
pred_data = arlib.write2array(coords, pred_y)
pred_data = np.around(pred_data)
out_file = os.path.join(pred_dir, sid_list[i] + '_pred.nii.gz')
mybase.save2nifti(pred_data, header, out_file)
for idx in class_label:
dice[idx].append(tmp_dice[idx])
for idx in class_label:
print 'Mean Dice for label %s: %s' % (idx, np.mean(dice[idx],
axis=0)[0])
return dice