臺灣博碩士論文加值系統

脈絡膜新生血管是異常的血管發育在視網膜下，它是導致失明的主要原因。醫生要從螢光眼底攝影影像來找出脈絡膜新生血管是一件非常費時的事情。因此，我們開發出一套半自動的系統，可以偵測出脈絡膜新生血管的區域，並且擷取有用的量化資訊。
我們分析影像的拍攝，來了解影像衰退發生的原因。接著我們利用一個演算法來恢復衰退的影像。我們利用計算視網膜影像的背景來達成亮度修正。影像中的血管、視覺圓盤與小窩我們事先已將之切割。利用滲出的螢光素來找出脈絡膜新生血管，我們先使用形態學操作來找出其輪廓。接著利用snake來找出脈絡膜新生血管正確的區域。
演算法在23組影像序列被測試，並且與專家描繪的結果相比較。我們演算法正確偵測脈絡膜新生血管的準確性為77.8%。平均的敏感度為85.9%、明確性為99.8%，與89.8%的預測值。並且我們量化了脈絡膜新生血管的嚴重程度。

Choroidal neovascularization means abnormal blood vessels are developing under the retina, and it is a leading cause of blindness. It is time-consuming for the physician looking for CNV from fluorescein angiographic images. Therefore, we developed a semi-automated system which can segment the area of CNV and extract information which is useful for quantification.
We analyzed image capture to know how image degradation happened, and then we adopted an algorithm to restore image degradation. Illumination correction was achieved by estimating the background of the retinal image. It exploited extractive segmentations of the retinal vasculature, optic disk, and fovea. We use fluorescent leakage to find CNV, and we use morphological operators to determine its contour. Then we use the snake to circle the correct area of choroidal neovascularization.
The algorithm has been tested on 23 image sequences and compared with the performance of a retina specialist. Our algorithm has 74.5% success rate to detect choroidal neovascularization. The average sensitivity was 84.4%, the average specificity was 99.8%, and the average predictive value was 86.9%. The seriousness of the choroidal neovascularization has been quantified.

Chapter 1 Introduction 1
1.1. Motivation 1
1.2. Challenges 3
1.3. Problem Definition 4
1.4. Summary of our Approach 4
1.5. Contributions 5
1.6. Overview of this thesis 5
Chapter 2 Study of related approaches 6
Chapter 3 Methods 8
3.1. Image Capture 9
3.2. Vasculature Extraction 10
3.3. Optic Disk Detection 11
3.4. Fovea Detection 13
3.5. Illumination Correction 14
3.6. Calculating the Camera Function 15
3.7. CNV Detection of Single Late Image 19
3.8. Snakes 21
3.9. Registration 23
3.10. CNV Detection of a Time Series of Images 24
3.11. Quantification 28
Chapter 4 Experimental Evaluation 33
4.1. Evaluation for CNV Detection 33
4.2. Quantitative Analysis 38
Chapter 5 Discussion and Conclusion 43
References 45

[1]M.J. Cree, J.A. Olson, K.C. McHardy, P.F. Sharp, and J.V. Forrester, “The preprocessing of retinal images for the detection of fluorescein leakage,” Phys. Med. Biol., vol. 44, pp. 296-308, 1999.
[2]M.J. Cree, J.A. Olson, K.C. McHardy, P.F. Sharp, and J.V. Forrester, “A fully automated comparative microaneurysm digital detection system, ” Eye, vol. 11, pp. 622-628, 1998.
[3]Z.B. Sbeh, L.D. Cohen, G. Mimoun and G. Coscas, “A new approach of geodesic reconstruction for drusen segmentation in eye fundus images,” IEEE Transactions on Medical Imaging, vol. 20, no. 12, pp. 1321-1333, Dec. 2001.
[4]T. Spencer, J. A. Olson, K. C. McHardy, P. F. Sharp, and J. V. Forrester, “An image-processing strategy for the segmentation of microaneurysms in fluorescein angiograms of the ocular fundus,” Computers and Biomedical Research , vol. 29, no. 4, pp. 284-302, Aug. 1996.
[5]J. H. Hipwell, F. Strachan, J. A. Olson, K. C. McHardy, P. F. Sharp, and J. V. Forrester, “Automated detection of microaneurysms in digital red-free photographs: a diabetic retinopathy screening tool,” Diabetic Medicine, vol. 17, no. 8, pp. 588-594, Aug. 2000.
[6]K.A. Goatman, M.J. Cree, J.A. Olson, J.V. Forrester, and P.F. Sharp, “Automated measurement of microaneurysm turnover,” Investigative ophthalmology and Visual Science, vol. 44, pp. 5335-5341, 2003.
[7]R.T. Smith, T.Nagasaki, J.R. Sparrow, I. Barbazetto, C.C.W. Klaver, and J.K. Chan, “A method of drusen measurement based on the geometry of fundus reflectance,” Biomedical Engineering Online, 2(1):10, 2003.
[8]T. Walter, J.-C. Klein, P. Massin, and A. Erginay, “A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina,” IEEE Transactions on Medical Imaging, vol. 21, no. 10, pp. 1236-1243, Oct. 2002.
[9]W. Hsu, P. M. D. S. Pallawala, M. L. Lee and K. A. Eong, “The role of domain knowledge in the detection of retinal hard exudates,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246-251 , 2001.
[10]R. Phillips, J.V. Forrester, and P. F. Sharp, “Automated detection and quantification of retinal exudates,” Graefe''s Archives of Clinical and Experimental Ophthalmology, vol. 231, pp. 90-94, 1993.
[11]S. Chaudhuri, S. Chatterjee, N. Katz, M. Nelson, M. Goldbaum, “Detection of blood vessels in retinal images using two-dimensional matched filters,” IEEE Transactions on Medical Imaging, vol. 8, no. 3, pp. 263-269, Sep. 1989.
[12]A. Hoover, V. Kouznetsova, and M. Goldbaum, “Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response,” IEEE Transactions on Medical Imaging, vol. 19, no. 3, pp. 203-210, Mar. 2000.
[13]X. Jiang and D. Mojon, “Adaptive local thresholding by verification-based multithreshold probing with application to vessel detection in retinal images,” IEEE Pattern Analysis and Machine Intelligence, vol. 25, no. 1, pp. 131-137, Jan. 2003.
[14]L. Zhou, M.S. Rzeszotarski, L. J. Singerman and J.M. Chokreff, “The detection and quantification of retinopathy using digital angiograms,” IEEE Transactions on Medical Imaging, vol. 13, no. 4, pp. 619-626, Dec. 1994.
[15]F. Zana and J.C. Klein, “Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation,” IEEE Transactions on Image Processing, vol. 10, no. 7, pp. 1010-1019, July 2001.
[16]T. Walter, J. C. Klein, P. Massin and A. Erginay, “A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina,” IEEE Transactions on Medical Imaging, vol. 21, no. 10, pp. 1236-1244, Oct. 2002.
[17]L. Gagnon, M. Lalonde, M. Beaulieu and M.C. Boucher, “Procedure to detect anatomical structures in optical fundus images,” Proc of Conference Medical Imaging, SPIE Proc. Vol. 4322, pp. 1218-1225, 2001.
[18]A. Can, H. Shen, J.N. Turner, H.L. Tanenbaum, and B. Roysam, “Rapid automated tracing and feature extraction from live high-resolution retinal fundus images using direct exploratory algorithms,” IEEE Transactions on Information Technology in Biomedicine, vol. 3, no. 2, pp. 125-138, June 1999.
[19]K. Fritzsche, A. Can, H. Shen, C. Tsai, J. Turner, H.L. Tanenbuam, C.V. Stewart and B. Roysam, “Automated model based segmentation, tracing and analysis of retinal vasculature from digital fundus images,” Angiography and Plaque Imaging: Advanced Segmentation Techniques, J.S. Suri and S. Laxminarayan, Ed, CRC Press, 2002.
[20]S.R. Aylward and E. Bullitt, “Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction,” IEEE Transactions on Medical Imaging, vol. 21, no. 2, pp. 61-75, Feb. 2002.
[21]M. Fontaine, L. Macaire, J. G. Postaire, M. Valette and P. Labalette, “Fundus images segmentation by unsupervised classification,” Vision Interface, Trois-Rivieres, Canada, May 1999.
[22]J. Staal,, M.D. Abramoff, M. Niemeijer, M.A. Viergever, B. van Ginneken, “Ridge-based vessel segmentation in color images of the retina,” IEEE Transactions on Medical Imaging, vol. 23, no. 4, pp. 501-509, Apr 2004.
[23]V. Mahadevan, H. Narasimha-Iyer, B. Roysam, and H. L. Tanenbaum, “Robust model-based vasculature detection in noisy biomedical images,” IEEE Transactions on Information Technology in Biomedicine, vol. 8, no. 3, pp. 360-376, Sep. 2004.
[24]K. Fritzsche, “Computer Vision Algorithms for Retinal Vessel Width Change Detection and Quantification,” PhD thesis, Rensselaer Polytechnic Institute, Troy, NY, 2003.
[25]M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contour models,” International Journal of Computer Vision, vol. 4, no .321–331, Jan. 1988.
[26]C. Sinthanayothin, J. F. Boyce, H. L. Cook and T. H. Williamson, “Automated localisation of the optic disc, fovea, and retinal blood vessels from digital color fundus images,” British Journal of Ophthalmology, vol. 83, no. 8, pp. 902-910, Aug. 1999.
[27]T. Walter, J.C. Klein, P. Massin, A. Erginay, “A contribution of image processing to the diagnosis of diabetic retinopathy detection of exudates in color fundus images of the human retina,” IEEE Transactions on Medical Imaging, vol. 21, no. 10, pp. 1236-1243, Oct. 2002.
[28]A. Osareh, M. Mirmehdi, B. Thomas and R. Markham, “Classification and localisation of diabetic-related eye disease,” In 7th European Conference on Computer Vision (ECCV), A. Heyden, G. Sparr, M. Nielsen, and P. Johansen, editors, pp. 502-516, Springer LNCS 2353, May 2002.
[29]A. Hoover and M. Goldbaum, “Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels,” IEEE Transactions on Medical Imaging, vol. 22, no. 8, pp. 951-958, Aug. 2003.
[30]H. Narasimha-Iyer, A. Can, B. Roysam, V. Stewart, H.L. Tanenbaum, A. Majerovics, H. Singh, “Robust detection and classification of longitudinal changes in color retinal fundus images for monitoring diabetic retinopathy,” IEEE Transactions on Biomedical Engineering, vol. 53, no. 6, pp. 1084-1098, June 2006.
[31]A. Chopdar, “Fundus fluorescein angiography,” Oxford: Butterworth­Heinemann, 1996.
[32]E. Peli and M. Lahav, “Drusen measurements from fundus photographs using computer image analysis,” Ophthalmology, vol. 93, pp. 1575–1580, 1986.
[33]E. Peli and T. Peli, “Restoration of retinal images obtained through cataracts,” IEEE Transactions on Medical Imaging, vol. 8, no. 4, pp. 401-406, 1989.
[34]R.C. Gonzalez, R.E. Woods, “Digital Image Processing,” Reading, MA: Addison-Wesley, 1992.
[35]J.C. Russ, “The Image Processing Handbook,” Boca Raton, FL: CRC, 1993.
[36]A.A. Mahurkar, M.A. Vivino, B.L. Trus, E.M. Kuehl, M.B. Datiles 3rd, and M.I. Kaiser-Kupfer, “Constructing retinal fundus photomontages: a new computer-based method, ” Investigative Ophthalmology & Visual Science, vol. 37, pp. 1675-1683, 1996.
[37]W.H. Press, S.A. Teukolsky, W.T. Vetterling, and B.P. Flannery, “Numerical recipes in C: the art of scientific computing,” Cambridge: Cambridge University Press, 1992.
[38]J. Serra, “Introduction to mathematical morphology,” Computer Vision, Graphics, and Image Processing, vol. 35, no. 3, pp. 283-305, 1986.
[39]M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contour models,” International Journal of Computer Vision, vol. 1, no. 4, pp.321–331, Jan. 1988.
[40]J. Liang, T. McInerney, and D. Terzopoulos, “United Snakes,” The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999, vol. 2, pp. 933-940, 1999.
[41]G. K. Matsopoulos, N. A. Mouravliansky, K.K. Delibasis, and K.S. Nikita, “Automatic retinal image registration scheme using global optimization techniques,” IEEE Transactions on Information Technology in Biomedicine, vol. 3, no. 1, pp. 47-60, Mar.1999.
[42]N. Ritter, R. Owens, J. Cooper, R. Eikelboom, and P.P. van Saarloos, “Registration of stereo and temporal images of the retina,” IEEE Transactions on Medical Imaging, vol. 18, no. 5, pp. 404-418, May 1999.
[43]C. V. Stewart, C.-L. Tsai, and B. Roysam, “The dual-bootstrap iterative closest point algorithm with application to retinal image registration,” IEEE Transactions on Medical Imaging, vol. 22, no. 11, pp. 1379-1394, Nov. 2003.
[44]A. Can, C. V. Stewart, B. Roysam, and H. L. Tanenbaum, “A feature-based robust hierarchical algorithm for registration pairs of images of the curved human retina,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 3, pp. 347-364, Mar. 2002.
[45]G. Yang, C. V. Stewart, S. Michal, and C.-L. Tsai, “Registration of challenging image pairs: initialization, estimation, and decision”. IEEE Transactions on Pattern Analysis and Machine Intelligence, accepted, 2006.
[46]L. Zhou, M. Rzeszotarski, L.J. Singerman, and J.M Chokreff, “The detection and quantification of retinopathy using digital angiograms,” IEEE Transactions on Medical Imaging, vol.13, no. 4, pp. 619-626, 1994.
[47]L. Ballerini, “An automatic system for the analysis of vascular lesions in retinal images,” IEEE Medical Imaging Conference, Seattle, USA, Oct. 1999.
[48]A. Manivannant, P.F. Sharpt, R.P. Phillips, and J.V. Forrested, “Digital fundus imaging using a scanning laser ophthalmoscope,” Physiological Measurement, vol. 14, no. 1, pp. 43-56, 1993.
[49]E. Brankin, P. McCuIlagh, N. Black, W. Patton, and A. Muldrew, “The Optimisation of Thresholding Techniques for the Identification of Choroidal Neovascular Membranes in Exudative Age-Related Macular Degeneration,” 19th IEEE International Symposium on Computer-Based Medical Systems, 2006, pp. 430-435, 2006.