Abstract
Akciğer nodülleri kanser vakalarında sıkça
gözlenmektedir. Günümüzde nodüller, tomografi veya MRI gibi teknolojiler
kullanılarak görüntülenebilmektedir. Ancak, x-ray görüntüleme yaygın
kullanımının yanı sıra düşük maliyetli bir yöntemdir. Bu bağlamda, nodüllerin
gelişimlerinin sık aralıklarla takip edilmesinde x-ray görüntülerinin
kullanılması birçok yönden fayda sağlamaktadır. Bu çalışmada akciğer x-ray
görüntülerinden nodüllerin gelişimlerini otomatik olarak takip edebilen üç
aşamalı yenilikçi bir yaklaşım önerilmiştir. İlk aşamada; bir hastaya ait nodül
gelişiminin değerlendirilebilmesi için farklı zamanlarda çekilen görüntülerin
üst üste bindirilmesi gerçekleştirilmiştir. Üst üste bindirme yapabilmek için
öz nitelik çıkarma ve eşleştirme yöntemleri kullanılarak homografi matrisi elde
edilmiş ve sonrasında görüntü çakıştırma işlemi gerçekleştirilmiştir. İkinci
aşamada; çakıştırılmış görüntüler üzerindeki nodüllerin daha önceden bilinen
konum bilgilerine göre her iki görüntüde eşleşen nodüller tespit edilmiştir.
İlk görüntüde eşleşmeyen nodüllerin kaybolduğu, sadece ikinci görüntüde yer
alan nodüllerin yeni ortaya çıktığı değerlendirilmiştir. Son aşamada; nodüller,
görüntü üzerinde piksel kümesinden oluşan kapalı alan olarak değerlendirilmiş
olup eşleşmeden sonra kapalı alanların oluşturduğu alan bilgileri
hesaplanmıştır. Bu şekilde büyüme ya da küçülme durumları sayısal olarak ortaya
konulmuştur. Geliştirilen yaklaşımın test edilmesi için Başkent Üniversitesi
Radyoloji Bölümü tarafından temin edilen hasta veri kümesi kullanılmıştır. Test
sonuçlarının doğrulanması uzman bir radyolog desteği ile gerçekleştirilmiştir.
Bu çalışmada sunulan nodül gelişim takip sisteminde umut verici sonuçlara
ulaşılmıştır.
Keywords
X-ray görüntüleri Akciğer nodülleri Görüntü çakıştırma Nodül eşleştirme Nodül gelişim takibi
References
- Işık Z, Selçuk H, Albayram S. “Bilgisayarlı tomografi ve radyasyon”. Klinik Gelişim, 23(2), 16-18, 2010.
- Sotiras A, Davatzikos C, Paragios N. “Deformable Medical Image Registration: A Survey”. IEEE Transactions on Medical Imaging, 32(7), 1153-1190, 2013.
- Mani VRS, Arivazgahan S. “Survey on Medical Image Registration”. Journal of Biomedical Engineering and Technology, 1(2), 8-25, 2013.
- Zitova B, Flusser J. “Image registration methods: A survey”. Image and Vision Computing, 21(11), 977-1000, 2003.
- Cheung W, Hamarneh G. “n-SIFT: N-dimensional scale invariant feature transform”. IEEE Transactions on Image Processing, 18(9), 2012-2021, 2009.
- Allaire S, Kim JJ, Breen SL, Jaffray DA, Pekar V. “Full orientation invariance and improved feature selectivity of 3D sift with application to medical image analysis”. Computer Vision and Pattern Recognition Workshops (CVPRW’08), Anchorage, Alaska, USA, 23-28 June 2008.
- Niemeijer M, Garvin MK, Lee K, VanGinneken B, Abrámoff MD, Sonka M. “Registration of 3D spectral OCT volumes using 3D sift feature point matching”. SPIE Medical Imaging: Image Processing, 7259, 2009.
- Franz A, Carlsen IC, Renisch S. An Adaptive İrregular Grid Approach Using SIFT Features for Elastic Medical İmage Registration. Editors: Handels H, Ehrhardt J, Horsh A, Meinzer HP, Tolxdorff T. Bildverarbeitung für die Medizin, 201-205, Berlin, Heidelberg, Germany, Springer-Verlag, 2006.
- Lukashevich PV, Zalesky BA, Ablameyko SV. “Medical Image Registration Based on SURF Detector”. Pattern Recognition and Image Analysis, 21(3), 519-521, 2011.
- Engin M, Oğul H, Ağıldere M, Sümer E. “An evaluation of ımage registration methods for chest radiographs”. SAI Intelligent Systems Conference (IntelliSys 2015), London, UK, 10-11 November 2015.
- Pal R, Garg P, Chechi R, Kumar S, Kumar N. “Cancer growth prediction via artificial neural networks”. International Journal of Bio-Science and Bio-Technology, 2(2), 1-10, 2010.
- Scharcanski J, Da Silva LS, Koff D, Wong A. “Interactive modeling and evaluation of tumor growth”. Journal of Digital Imaging, 23(6), 755-768, 2010.
- Almasslawi DMS, Kabir E. “Using non-rigid image registration and Thin-Plate Spline warping for lung cancer progression assessment”. IEEE International Conference on Computer Science and Automation Engineering (CSAE), Shangai, China, 10-12 June 2011.
- Elamy AH, Hu M. “Mining brain tumors and tracking their growth rates”. Canadian Conference on Electrical and Computer Engineering, Vancouver, Canada, 22-26 April 2007.
- Sofka M, Stewart CV. “Location registration and recognition (LRR) for serial analysis of nodules in lung CT scans”. Medical Image Analysis, 14, 407-428, 2010.
- Reeves AP, Chan AB, Yankelevitz DF, Henschke CI, Kressler B, Kostis WJ. “On measuring the change in size of pulmonary nodules”. IEEE Transactions on Medical Imaging, 25(4), 435-450, 2006.
- El-Baz A, Gimel’farb G, Falk R, El-Ghar MA. “A new CAD system for early diagnosis of detected lung nodules”. IEEE International Conference on Image Processing,San Antonio, TX, USA, 16-19 September 2007.
- Jirapatnakul AC, Reeves AP, Biancardi AM, Yankelevitz DF, Henschke CI. “Semi-automated measurement of pulmonary nodule growth without explicit segmentation”. IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Boston, MA, USA, 28 June-01 July 2009.
- National Electrical Manufacturers Association (NEMA). “Digital Imaging and Communications in Medicine”. http://medical.nema.org/dicom (09.02.2017).
Abstract
Lung nodules are frequently observed in cases of
cancer. Nodules can be monitored with technologies such as computed tomography
(CT) or magnetic resonance imaging (MRI). However, x-ray imaging is a low-cost
method as well as its widespread usage. In this context, monitoring the nodules
in short intervals by x-ray imaging gives benefits in many aspects. In this
study, a three-stage novel approach is proposed to trace the nodule
progressions from the lung x-ray images, automatically. In the first stage,
x-ray images of a patient taken at different times must be registered to
evaluate the nodule progression. To perform the registration, feature
extraction and matching methods are employed, and then the homography matrix is
calculated. In the second stage, according to previously known nodule
positions, matched nodules are detected on registered images. Mismatched
nodules in the first image are considered as lost, while the nodules only found
in the second image are evaluated as newly appeared. In the last stage, nodules
are considered as closed contours consisting of pixel set where closed contour
area is calculated after nodule matching process. In this way, growth and
shrink states are determined numerically. To test the proposed approach, a
patient data set provided by Baskent University, Department of Radiology is
used. The validation of the test results is performed by an expert radiologist.
According to the results obtained, the presented nodule progression trace
system is found promising.
References
- Işık Z, Selçuk H, Albayram S. “Bilgisayarlı tomografi ve radyasyon”. Klinik Gelişim, 23(2), 16-18, 2010.
- Sotiras A, Davatzikos C, Paragios N. “Deformable Medical Image Registration: A Survey”. IEEE Transactions on Medical Imaging, 32(7), 1153-1190, 2013.
- Mani VRS, Arivazgahan S. “Survey on Medical Image Registration”. Journal of Biomedical Engineering and Technology, 1(2), 8-25, 2013.
- Zitova B, Flusser J. “Image registration methods: A survey”. Image and Vision Computing, 21(11), 977-1000, 2003.
- Cheung W, Hamarneh G. “n-SIFT: N-dimensional scale invariant feature transform”. IEEE Transactions on Image Processing, 18(9), 2012-2021, 2009.
- Allaire S, Kim JJ, Breen SL, Jaffray DA, Pekar V. “Full orientation invariance and improved feature selectivity of 3D sift with application to medical image analysis”. Computer Vision and Pattern Recognition Workshops (CVPRW’08), Anchorage, Alaska, USA, 23-28 June 2008.
- Niemeijer M, Garvin MK, Lee K, VanGinneken B, Abrámoff MD, Sonka M. “Registration of 3D spectral OCT volumes using 3D sift feature point matching”. SPIE Medical Imaging: Image Processing, 7259, 2009.
- Franz A, Carlsen IC, Renisch S. An Adaptive İrregular Grid Approach Using SIFT Features for Elastic Medical İmage Registration. Editors: Handels H, Ehrhardt J, Horsh A, Meinzer HP, Tolxdorff T. Bildverarbeitung für die Medizin, 201-205, Berlin, Heidelberg, Germany, Springer-Verlag, 2006.
- Lukashevich PV, Zalesky BA, Ablameyko SV. “Medical Image Registration Based on SURF Detector”. Pattern Recognition and Image Analysis, 21(3), 519-521, 2011.
- Engin M, Oğul H, Ağıldere M, Sümer E. “An evaluation of ımage registration methods for chest radiographs”. SAI Intelligent Systems Conference (IntelliSys 2015), London, UK, 10-11 November 2015.
- Pal R, Garg P, Chechi R, Kumar S, Kumar N. “Cancer growth prediction via artificial neural networks”. International Journal of Bio-Science and Bio-Technology, 2(2), 1-10, 2010.
- Scharcanski J, Da Silva LS, Koff D, Wong A. “Interactive modeling and evaluation of tumor growth”. Journal of Digital Imaging, 23(6), 755-768, 2010.
- Almasslawi DMS, Kabir E. “Using non-rigid image registration and Thin-Plate Spline warping for lung cancer progression assessment”. IEEE International Conference on Computer Science and Automation Engineering (CSAE), Shangai, China, 10-12 June 2011.
- Elamy AH, Hu M. “Mining brain tumors and tracking their growth rates”. Canadian Conference on Electrical and Computer Engineering, Vancouver, Canada, 22-26 April 2007.
- Sofka M, Stewart CV. “Location registration and recognition (LRR) for serial analysis of nodules in lung CT scans”. Medical Image Analysis, 14, 407-428, 2010.
- Reeves AP, Chan AB, Yankelevitz DF, Henschke CI, Kressler B, Kostis WJ. “On measuring the change in size of pulmonary nodules”. IEEE Transactions on Medical Imaging, 25(4), 435-450, 2006.
- El-Baz A, Gimel’farb G, Falk R, El-Ghar MA. “A new CAD system for early diagnosis of detected lung nodules”. IEEE International Conference on Image Processing,San Antonio, TX, USA, 16-19 September 2007.
- Jirapatnakul AC, Reeves AP, Biancardi AM, Yankelevitz DF, Henschke CI. “Semi-automated measurement of pulmonary nodule growth without explicit segmentation”. IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Boston, MA, USA, 28 June-01 July 2009.
- National Electrical Manufacturers Association (NEMA). “Digital Imaging and Communications in Medicine”. http://medical.nema.org/dicom (09.02.2017).
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Engineering |
| Journal Section | Research Article |
| Authors | |
| Publication Date | October 12, 2018 |
| Published in Issue | Year 2018 Volume: 24 Issue: 5 |
Cite
