DICOM preprocessing

[python code] 

#      
# Loop over the image files and store everything into a list.
# 

def load_scan(path):
    slices = [dicom.read_file(path + '/' + s) for s in os.listdir(path)]
    slices.sort(key = lambda x: int(x.InstanceNumber))
    try:
        slice_thickness = np.abs(slices[0].ImagePositionPatient[2] - slices[1].ImagePositionPatient[2])
    except:
        slice_thickness = np.abs(slices[0].SliceLocation - slices[1].SliceLocation)
        
    for s in slices:
        s.SliceThickness = slice_thickness
        
    return slices

def get_pixels_hu(scans):
    image = np.stack([s.pixel_array for s in scans])
    # Convert to int16 (from sometimes int16), 
    # should be possible as values should always be low enough (<32k)
    image = image.astype(np.int16)

    # Set outside-of-scan pixels to 1
    # The intercept is usually -1024, so air is approximately 0
    image[image == -2000] = 0
    
    # Convert to Hounsfield units (HU)
    intercept = scans[0].RescaleIntercept
    slope = scans[0].RescaleSlope
    
    if slope != 1:
        image = slope * image.astype(np.float64)
        image = image.astype(np.int16)
        
    image += np.int16(intercept)
    
    return np.array(image, dtype=np.int16)

id=0
patient = load_scan(data_path)
imgs = get_pixels_hu(patient)

===========================================================================

 

HU's are useful because it is standardized across all CT scans regardless of the absolute number of photons the scanner detector captured.

Substance	HU
Air	−1000
Lung	−500
Fat	−100 to −50
Water	0
Blood	+30 to +70
Muscle	+10 to +40
Liver	+40 to +60
Bone	+700 (cancellous bone) to +3000 (cortical bone)

https://www.kaggle.com/akh64bit/full-preprocessing-tutorial

Full Preprocessing Tutorial

https://www.raddq.com/dicom-processing-segmentation-visualization-in-python/

DICOM Processing and Segmentation in Python