How to segment Lung tissue from CT Image?
1 Ansicht (letzte 30 Tage)
Ältere Kommentare anzeigen
Louise Giansante
am 14 Okt. 2015
Beantwortet: Image Analyst
am 30 Dez. 2015
Hello,
I've been looking for a good algorithm to segment lungs from CT images. I have a serie of CT images (DICOM) from a phantom and I only want to segment the lung tissue. So far I've tried the "activecontour" function with the Chan-Vese algorithm (which is the default of the function), but it doesn't work really well: this function segments structures that aren't related to the lungs. When I've applied the function to a JPEG image, though, it worked. I don't know what to do; I'm new on MatLab and it's supposed to be a simple problem because I don't want to segment any structure, only the contour of the lungs.
Please, contact me if you can help me. I've tried many different algorithms and could not find a good one.
1 Kommentar
Akzeptierte Antwort
Image Analyst
am 30 Dez. 2015
I'd try thresholding. Then call imclearborder() to get rid of any light stuff that touches the border. Then take the largest blob with bwareafilt(). If the area is not big enough, then take the biggest two blobs.
Also check the literature for better algorithms: http://www.visionbib.com/bibliography/contentsmedical.html#Medical%20Applications,%20CAT,%20MRI,%20Ultrasound,%20Heart%20Models,%20Brain%20Models
0 Kommentare
Weitere Antworten (0)
Siehe auch
Kategorien
Mehr zu Image Segmentation and Analysis finden Sie in Help Center und File Exchange
Produkte
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!