<div dir="ltr"><div><div>Dear All,<br><br></div>I have a dicom series having whole body image sequences, starting from head up to legs. <br><br>My aim is to write an algorithm to automatically identify the body parts (lungs, spines, head etc.) from the dicom sequence.<br>
<br></div>Although I am very new to the ITK world, I am following these steps in ITK (<b>I would appreciate if you comment whether I am following correct idea or not</b>):<br><ol><li>Read dicom series using 'DicomSeriesReadImageWrite2.cxx ' to create a 3D volume and save the result in mhd format.</li>
<li>Use 'ImageReadRegionOfInterestWrite.cxx' for separating various parts (like left lung, right lung, spines, head etc.) and save them in respective 3D volumes in mhd format.</li><li>Pick the various body parts prepared above, one by one and segment them using robust algorithm (say ThresholdSegmentationLevelSetImageFilter.cxx).</li>
<li>Use Mathematical Morphology to get better results.</li><li>Using the various results from above, form an algorithm for identifying the various body parts.<br></li></ol><p></p><p>Currently I am stuck in the second step because it is so hard to choose the co-ordinates for selecting proper region of interest. </p>
<p>For example, I chose these points for ROI of right lung (I checked the co-ordinates using 3D slicer visualizer) and it does not give me good results : <br></p><div>start[0] = 255; <br>start[1] =165; <br>start[2] = 0; <br>
<br><b>However I do not understand how to choose the points properly in ITK.</b><br><br><br></div><div>I would be really glad to have your response.<br><br></div><div>Thanking you in advance.<br></div><div>Kind Regards,<br>
</div><div>Bumpy.<br></div></div>