def scad_propseg_validation(folder_input, contrast): from sct_get_centerline import ind2sub import time import math import numpy import sct_convert as cnv t0 = time.time() current_folder = os.getcwd() os.chdir(folder_input) try: patients = next(os.walk('.'))[1] for i in patients: directory = i + "/" + str(contrast) try: os.chdir(directory) except Exception, e: print str(i)+" : "+contrast+" directory not found" try: if os.path.isfile(i+"_"+contrast+".nii.gz"): raw_image = Image(i+"_"+contrast+".nii.gz") elif os.path.isfile(contrast+".nii.gz"): raw_image = Image(contrast+".nii.gz") else: raise Exception("Patient scan not found") if os.path.isfile(i+"_"+contrast+"_manual_segmentation.nii.gz"): manual_segmentation = i+"_"+contrast+"_manual_segmentation.nii.gz" # Using propseg default sct.run("sct_propseg -i "+raw_image.absolutepath+" -t "+contrast) cnv.convert(raw_image.file_name+"_seg.nii.gz", "propseg_default.nii.gz") # Using scad scad = SCAD(raw_image, contrast=contrast, rm_tmp_file=1, verbose=1) scad.execute() # Using propseg with scad sct.run("sct_propseg -i "+raw_image.absolutepath+" -t "+contrast+" -init-centerline "+scad.output_filename) cnv.convert(raw_image.file_name+"_seg.nii.gz", "propseg_scad.nii.gz") # Calculate dice of propseg_default sct.run("sct_dice_coefficient propseg_default.nii.gz "+manual_segmentation+" -o propseg_default_result.txt") # Calculate dice of propseg_scad sct.run("sct_dice_coefficient propseg_scad.nii.gz "+manual_segmentation+" -o propseg_scad_result.txt") else: printv("Cannot find the manual segmentation", type="warning") except Exception, e: print e.message os.chdir(folder_input)
def validate_scad(folder_input, contrast): """ Expecting folder to have the following structure : errsm_01: - t2 -- errsm_01.nii.gz or t2.nii.gz -- :param folder_input: :return: """ from sct_get_centerline import ind2sub import time import math import numpy t0 = time.time() current_folder = os.getcwd() os.chdir(folder_input) try: patients = next(os.walk('.'))[1] overall_distance = {} max_distance = {} standard_deviation = 0 overall_std = {} rmse = {} for i in patients: directory = i + "/" + str(contrast) try: os.chdir(directory) except Exception, e: print str(i)+" : "+contrast+" directory not found" try: if os.path.isfile(i+"_"+contrast+".nii.gz"): raw_image = Image(i+"_"+contrast+".nii.gz") elif os.path.isfile(contrast+".nii.gz"): raw_image = Image(contrast+".nii.gz") else: raise Exception("Patient scan not found") if os.path.isfile(i+"_"+contrast+"_manual_segmentation.nii.gz"): raw_orientation = raw_image.change_orientation() scad = SCAD(raw_image, contrast=contrast, rm_tmp_file=1, verbose=1) scad.execute() manual_seg = Image(i+"_"+contrast+"_manual_segmentation.nii.gz") manual_orientation = manual_seg.change_orientation() from scipy.ndimage.measurements import center_of_mass # find COM iterator = range(manual_seg.data.shape[2]) com_x = [0 for ix in iterator] com_y = [0 for iy in iterator] for iz in iterator: com_x[iz], com_y[iz] = center_of_mass(manual_seg.data[:, :, iz]) centerline_scad = Image(i+"_"+contrast+"_centerline.nii.gz") # os.remove(i+"_"+contrast+"_centerline.nii.gz") centerline_scad.change_orientation() distance = {} for iz in range(1, centerline_scad.data.shape[2]-1): ind1 = np.argmax(centerline_scad.data[:, :, iz]) X,Y = ind2sub(centerline_scad.data[:, :, iz].shape,ind1) com_phys = np.array(manual_seg.transfo_pix2phys([[com_x[iz], com_y[iz], iz]])) scad_phys = np.array(centerline_scad.transfo_pix2phys([[X, Y, iz]])) distance_magnitude = np.linalg.norm([com_phys[0][0]-scad_phys[0][0], com_phys[0][1]-scad_phys[0][1], 0]) if math.isnan(distance_magnitude): print "Value is nan" else: distance[iz] = distance_magnitude f = open(i+"_"+contrast+"_results.txt", 'w+') f.write("Patient,Slice,Distance") for key, value in distance.items(): f.write(i+","+str(key)+","+str(value)) standard_deviation = np.std(np.array(distance.values())) average = sum(distance.values())/len(distance) root_mean_square = np.sqrt(np.mean(np.square(distance.values()))) f.write("\nAverage : "+str(average)) f.write("\nStandard Deviation : "+str(standard_deviation)) f.close() overall_distance[i] = average max_distance[i] = max(distance.values()) overall_std[i] = standard_deviation rmse[i] = root_mean_square else: printv("Cannot find the manual segmentation", type="warning") except Exception, e: print e.message os.chdir(folder_input)