Onur Özdal MENGİ, Turgut GÖKBULUT, Burak ÜNAL, Burhan KAZİ

Vasküler Görüntüleyici Sistem

Günümüzde hızla gelişen kızılötesi görüntüleme teknolojisi tıp dünyasında yoğun olarak kullanılmaktadır. Kandaki alyuvarlarda bulunan hemoglobin kızılötesi ışınları emebilmektedir. Bu sayede damarlar diğer dokulara göre daha koyu ve belirgin bir şekilde görünür. Damar görüntüsü elde etmek için kullanılan cihazlar oldukça pahalıdır. Bunun sebebi bu cihazlarda yüksek hassasiyette ve yoğunlukta kızılötesi görüntü alan CCD sensörlü kameraların kullanılmasıdır. Bu sebeple maliyeti düşürmek için çok pahalı CCD sensör yerine fiyatı çok daha uygun olan CMOS sensörlü kızılötesi kameralar kullanılabilir. Ancak CMOS sensörü kullanan kameralardan elde edilen görüntü CCD sensörü kullanan kameralardan elde edilen görüntü kadar iyi değildir. Bu sebeple daha iyi görüntü elde etmek için gelişmiş görüntü işleme tekniklerine ihtiyaç vardır. 850nm kızılötesi ışık, CMOS sensörlü kamera ve 850nm dalga boyuna sahip bant geçiren fitre kullanılarak cildin 3mm derinliğindeki damar görüntüsü elde edilir. Elde edilen görüntü Raspberry Pi mikroişlemcisi kullanılarak OpenCV açık kaynak kodlu kütüphanesi yardımıyla Python dilinde sırasıyla; gri seviyeye dönüştürme, el maskesi için binari metot, damar maskeleme için ise medyan filtre ve canny metot kullanılmıştır. Ayrıca elde edilen görüntüyü iyileştirmek için çeşitli morfolojik işlemler (aşındırma ve genişletme) kullanılmıştır.

Anahtar Kelimeler:

CMOS, Python, Raspberry Pi, Medyan Filtre, Canny, Binari

Vascular Viewer System

Rapidly developing infrared imaging technology is used extensively in the medical world. The hemoglobin contained in the red blood cells in the blood can absorb infrared rays. In this way, the vessels appear darker and more pronounced than other tissues. The devices used to obtain a vascular image are quite expensive. The reason for this is the use of CCD sensor cameras with high sensitivity and intensity infrared images in these devices. For this reason, in order to reduce the cost, infrared cameras with CMOS sensors, which are much more affordable, can be used instead of the very expensive CCD sensor. However, the image obtained from cameras using CMOS sensors is not as good as the image obtained from cameras using CCD sensors. Therefore, advanced image processing techniques are needed to obtain better images. Using the 850nm infrared light, a camera with CMOS sensor and a bandpass filter with 850nm wavelength, a 3mm deep vein image of the skin is obtained. The obtained image is in Python language, respectively, with the help of OpenCV open source library using Raspberry Pi microprocessor; conversion to gray level, binary method for hand mask, median filter and canny method are used for vein masking. In addition, various morphological processes (erode and dilated) were used to improve the image obtained.

Keywords:

CMOS, Python, Raspberry Pi, Median filter, Canny, Binary,

PDF

___

Bath, J., Aziz, F. And Smeds, M. R. (2021, April). “Progression of Changes in VAscular Surgery Practices during tje Novel Corona Virus SARS-CoV-2 Pandemic, Annals of Vascular Surgery, In press. ( https://doi.org/10.1016/j.avsg.2021.03.002)
Bouzida, N., Bendada, A. H., & Maldague, X. P. (2010, October). "Near-infrared Image fFormation and Processing for the Extraction of Hand Veins", Journal of Modern Optics, Vol. 57, No. 18, pp. 1731-1737.
Canny, J. (1986, November). "A Computational Approach to Edge Detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-8, Issue: 6, pp. 679-698.
Delaune, S. C., & Ladner, P. K. (1997). "Process and Practice", in Fundamentals of Nursing 4e, pp. 949-958, Elsevier.
Erişti, E. (2010, Şubat 10-12). "Görüntü İşlemede Yeni Bir Soluk, OPENCV", Akademik Bilişim 2010 - XII. Akademik Bilişim Konferansı Bildirileri Muğla Üniversitesi, s. 223-229.
Fossum, E. R., & Hondongwa, D. B. (2014, May). "A Review of the Pinned Photodiode for CCD and CMOS Image Sensors", IEEE Journal of the Electron Devices Society, Vol. 2, No. 3, pp. 33-43.
Garrido, G., & Joshi, P. (2018). "Detecting and Tracking Different Body Parts", in OpenCV 3 with Python By Example 2e, pp. 74-95. Birmingham - Mumbai
Jain, C., Mishra, V., & Chugh, A. (2019). "Palm Vein Technology for Biometrics", International Journal of Innovative Technology and Exploring Engineering (IJITEE), Vol. 8, Issue 9S, pp. 598-602.
Lareyre, F., Chaudhuri, A., Adam, C., Carrier, M., Mialhe, C. and Raffort, J. (2021, April). “Applications of Head-Mounted Displays and smart Glasses in Vascular Surgery”, Annals of Vascular Surgery, In Press. (https://doi.org/10.1016/j.avsg.2021.02.033)
Mansoor, M., N., S. S., Naqvi, S. Z., Badshah, I., & Saleem, M. (2013). "Real-time Law Cast Infrared Vein Imaging System", International Conference on Signal Processing, Image Processing and Pattern Recognition (ICSIPRI), pp. 117-121.
Moss, J. P. (2008-2009, Dec-Jan). "100 Years of Infrared", The RPS Journal Royal Photographic Society, Vol. 148, No. 10, pp. 571.
Prasasti, A. L., Mengko, R. W., & Adiprawita, W. (2015). "Vein Tracking Using 880nm Near Infrared and CMOS Sensor with Maximum Curvature Points Segmentation", 7th World Congress on Bioengineering 2015 IFMBE Proceedings Vol. 52, pp. 206-209.
Sebastien, A., Chaib, I. D., Taillard, J., Chraibi, A., Delerue, D., Lernout, B. And Hertault, A. (2020)” Artificial Intelligence to Detect the Patients Eligible to Vasculer Surgery”, Annals of Vasculer Surgery, Vol. 68, pp.99.
Sezgin, M., & Sankur, B. (2004, January). "Survey over Image Thresholding Techniques and Quantitative Performance Evaluation", Journal of Electronic Imaging, Vol. 13, Issue 1, pp. 146-165.
Sontakke, B. M., Humbe, V. T., & Yannawar, P. L. (2018, March). "Automatic ROI Extraction and Vein Pattern Imaging of Dorsal Hand Vein Images", International Journal for Science and Advance Research In Technology(IJSART), Vol. 4, Issue 3, pp. 1678-1683.
Thanki, R. M., & Kothari, A. M. (2019). Digital Image Processing Using SCILAB. 6330 Cham, Switzerland: Springer.
Tran, L. T., & Pham, H. T.-T. (2020, January). "Designing and Building the Vein Finder System Utilizing Near-Infrared Technique", 7th International Conference on the Development of Biomedical Engineering in Vietnam (BME7). IFMBE Proceedings Vol. 69, pp. 383-387. Springer, Singapore.
Wang, L., & Leedham, G. (2005, August 22-25). "A Thermal Hand Vein Pattern Verification System", Pattern Recognition and Image Analysis: Third International Conference on Advances in Pattern Recognition, ICAPR 2005, Bath, UK, Proceedings, Part II, pp. 58-65.
Zhang, D., Guo, Z., Lu, G., Zhang, L., & Zuo, W. (2010, February). "An Online System of Multispectral Palmprint Verification", IEEE Transactions on Instrumentation and Measurement, Vol.59, no. 2, pp. 480-490.