1940 NM FİBER LAZER KAYNAĞININ KARACİĞER DOKUSUNDAKİ ISIL HASARININ YAPAY SİNİR AĞLARI İLE TAHMİNİ

Abstract

Bu çalışmada Yapay Sinir Ağları (YSA) yöntemi kullanılarak 1940 nm dalgaboyuna sahip lazer kaynağının karaciğer dokusu üzerinde oluşturduğu ısıl hasarların güç ve uygulama süreleri ile arasındaki ilişkisi incelenmiştir. Farklı güç değerlerine sahip lazer kaynağı koagülasyon ve karbonizasyon gözlenene kadar dokuya farklı sürelerde uygulanmıştır. Buna bağlı olarak radyal ve düşey yönde oluşan ısıl hasarlar deneysel olarak ölçülmüş ve kayıt altına alınmıştır. Bu kayıtların %70’i Matlab ortamında geliştirilen YSA modellerini eğitmek için kullanılmıştır. Lazer gücü ve uygulama süreleri model için giriş verileri, koagülasyon/karbonizasyon oluşma durumu ve oluşan ısıl hasarlar ise (çap, derinlik) modelin çıkış değerleri olarak kabul edilmiştir. Giriş verileri kullanılarak beş farklı öğrenme (LM, GDA, GDX, CGP ve BFG) algoritmasının en küçük kareler değeri (MSE) hesaplanmıştır ve karşılaştırılmıştır. Gizli katmanında 14 tane nörona sahip GDX, 2-14-3 yapısı, en iyi MSE (7.58E-2) sonucunu vermiştir ve eğitimde kullanılmayan veriler ile bu algoritmanın tahmin etme performansını test etmek için kullanılmıştır. Geliştirilen modelin ne kadar iyi çalıştığını anlamak için YSA tarafından tahmin edilen sonuçlar, deneysel sonuçlar ile karşılaştırılmıştır. Minimum %2.7 ve  % 3.6 hata oranı ile dokuda oluşan ısıl çap ve derinliklerinin tahmin edilebileceği gösterilmiştir. Bu sonuçlara göre, medikal uygulamalarda YSA yönteminin lazere yardımcı bir araç olarak kullanılması, çevre dokuların korunarak istenilen hedef bölgenin daha kontrollü ve daha yüksek doğrulukla tedavisini mümkün kılabilir.

Keywords

• Yapay Sinir Ağları (YSA),Koagülasyon,Karbonizasyon

Prediction of 1940 nm Fiber Laser Induced Thermal Damage Using Artificial Neural Networks

Abstract

These study presents relation between power and application time of 1940 nm laser source and thermal damage occurred on liver tissue using artificial neural networks (ANNs) method. Laser source with different powers and application times implemented on liver tissue until onset of coagulation and carbonization. Thermal damages occurred in horizontal and vertical direction have been experimentally measured and recorded. 70 % of this data was used to training ANN model, which was built in Matlab environment. Power and application time were defined as input parameters of model. Coagulation /carbonization occurrence, diameter and depth of thermal damages were used as output of model. This data was used to calculate and compare MSE value of five different learning algorithm (LM, GDA, GDX, CGP ve BFG). GDX algorithm with a 14 neuron in hidden layer, 2-14-3, was resulted in minimum MSE value (7.58E-2) and remaining untrained data was used to show prediction performance of GDX algorithm. ANN model outputs were compared with experimental results. It was shown that diameter and depth of coagulation and carbonization can be predicted using using ANN method with a minimum 2.7% and 3.6% success rate, respectively. According to these results, ANN assisted laser thermal therapies can provide more accurate treatment of undesired target tissue (tumor) with a minimal damage of surrounding healthy tissues. 

Keywords

• Artificial Neural Network (ANN),coagulation,carbonization

References

1. Amato, F., López, A., Peña-Méndez, E. M., Vaňhara, P., Hampl, A., Havel, J. (2013) Artificial neural networks in medical diagnosis. Journal of Applied Biomedicine, 11(2):, 47–58. https://doi.org/10.2478/v10136-012-0031-x
2. Carleo, G. and Troyer, M. (2016) Solving the Quantum Many-Body Problem with Artificial Neural Networks. arXiv e-prints, 127383. https://doi.org/10.1126/science.aag2302
3. Cömert, Z. and Kocamaz, A. (2017) A Study of Artificial Neural Network Training Algorithms for Classification of Cardiotocography Signals. Bitlis Eren University Journal of Science and Technology, 7(2):93–103. https://doi.org/10.17678/beuscitech.338085
4. Cubero, S., Aleixos, N., Moltó, E., Gómez-Sanchis, J., Blasco, J. (2011) Advances in Machine Vision Applications for Automatic Inspection and Quality Evaluation of Fruits and Vegetables. Food and Bioprocess Technology, 4(4):, 487–504. https://doi.org/10.1007/s11947-010-0411-8
5. Dick, E. A., Taylor-Robinson, S. D., Thomas, H. C., Gedroyc, W. M. W. (2002) Ablative therapy for liver tumours. Gut, 50(5):, 733–739. https://doi.org/10.1136/gut.50.5.733
6. Er, O., Yumusak, N., Temurtas, F. (2010). Chest diseases diagnosis using artificial neural networks. Expert Systems with Applications, 37(12):, 7648–7655. https://doi.org/10.1016/j.eswa.2010.04.078
7. Fast, M. and Palmé, T. (2010) Application of artificial neural networks to the condition monitoring and diagnosis of a combined heat and power plant. Energy, 35(2):, 1114–1120. https://doi.org/10.1016/j.energy.2009.06.005
8. Faust, O., Acharya U., R., Ng, E. Y. K., Ng, K.-H., Suri, J. S. (2012) Algorithms for the Automated Detection of Diabetic Retinopathy Using Digital Fundus Images: A Review. Journal of Medical Systems, 36(1):, 145–157. https://doi.org/10.1007/s10916-010-9454-7

9. Huang, Y., Kangas, L. J., Rasco, B. A. (2007)Applications of Artificial Neural Networks (ANNs) in food science. Critical Reviews in Food Science and Nutrition, 47(2):, 113–126. https://doi.org/10.1080/10408390600626453
10. Hung, O. N., Chan, C. K., Kan, C. W., Yuen, C. W. M., Song, L. J. (2014) Artificial neural network approach for predicting colour properties of laser-treated denim fabrics. Fibers and Polymers, 15(6):, 1330–1336. https://doi.org/10.1007/s12221-014-1330-5
11. Hung, O. N., Song, L. J., Chan, C. K., Kan, C. W., Yuen, C. W. M. (2011) Using artificial neural network to predict colour properties of laser-treated 100% cotton fabric. Fibers and Polymers, 12(8):, 1069–1076. https://doi.org/10.1007/s12221-011-1069-1
12. Jean, M. Der, Liu, C. Du, Wang, J. T. (2005) Design and development of artificial neural networks for depositing powders in coating treatment. Applied Surface Science, 245(1–4):290–303. https://doi.org/10.1016/j.apsusc.2004.10.041
13. Jiang, J., Trundle, P., Ren, J. (2010) Medical image analysis with artificial neural networks. Computerized Medical Imaging and Graphics, 34(8):, 617–631. https://doi.org/10.1016/j.compmedimag.2010.07.003
14. Kumar, K., Parida, M., Katiyar, V. K. (2013) Short Term Traffic Flow Prediction for a Non Urban Highway Using Artificial Neural Network. Procedia - Social and Behavioral Sciences, 104:, 755–764. https://doi.org/10.1016/j.sbspro.2013.11.170
15. Niemz, M. . H. (2007) Lasers-Tissue Interactions: Fundamentals and Applications, Springer. https://doi.org/10.1007/978-3-662-04717-0
16. Özdemir, A. T., Danisman, K. (2015) A comparative study of two different FPGA-based arrhythmia classifier architectures. Turkish Journal of Electrical Engineering and Computer Sciences, 23:, 2089–2106. https://doi.org/10.3906/elk-1305-41
17. Özdemir, A. T., Danişman, K. (2011) Fully parallel ann-based arrhythmia classifier on a single-chip fpga: Fpaac. Turkish Journal of Electrical Engineering and Computer Sciences, 19(4): 667–687. https://doi.org/10.3906/elk-1006-488
18. Rangraz, P., Behnam, H., Shakhssalim, N., Tavakkoli, J. (2012) A Feed-forward Neural Network Algorithm to Detect Thermal Lesions Induced by High Intensity Focused Ultrasound in Tissue. Journal of medical signals and sensors, 2(4):192–202.
19. Rao, S., Shrivastava, V., Dev, S., Seetharamu, K. N. (2012) Prediction of the Damage Coefficient in a Prostate Cancer Tissue during Laser Ablation Using Artificial Neural Networks, Proceedings of the World Congress on Engineering, 3:, 2–7.
20. Seera, M., Lim, C. P. (2014) A hybrid intelligent system for medical data classification. Expert Systems with Applications, 41(5): 2239–2249. https://doi.org/10.1016/j.eswa.2013.09.022
21. Shukur, O. B., Lee, M. H. (2015) Daily wind speed forecasting through hybrid KF-ANN model based on ARIMA. Renewable Energy, 76:, 637–647. https://doi.org/10.1016/j.renene.2014.11.084
22. Søreide, K., Thorsen, K., J. A. Søreide (2014) Predicting outcomes in patients with perforated gastroduodenal ulcers: artificial neural network modelling indicates a highly complex disease. European Journal of Trauma and Emergency Surgery, 41(1):, 91–98. https://doi.org/10.1007/s00068-014-0417-4
23. Su, B., Tang, J., Liao, H. (2015). Automatic laser ablation control algorithm for an novel endoscopic laser ablation end effector for precision neurosurgery. IEEE International Conference on Intelligent Robots and Systems, 4362–4367. https://doi.org/10.1109/IROS.2015.7353996
24. Theisen-Kunde, D., Danicke, V., Brinkmann, R. (2009) Comparison of two cw infrared laser systems emitting wavelengths at 1.92 µm and 2.01 µm for tissue dissection in liver surgery. IFMBE Proceedings, 25(6):, 132–135. https://doi.org/10.1007/978-3-642-03906-5-36
25. Tkáč, M. and Verner, R. (2015) Artificial neural networks in business: Two decades of research. Applied Soft Computing, 38:788–804. https://doi.org/10.1016/j.asoc.2015.09.040
26. Vogl, T J, Mack, M. G., Straub, R., Eichler, K., Engelmann, K., Zangos, S., Woitazek, D. (2001) MR guided laser-induced thermotherapy (LITT) of malignant liver and soft tissue tumours. Medical Laser Application, 16(2):91–102. https://doi.org/http://dx.doi.org/10.1078/1615-1615-00015
27. Vogl, Thomas J, Mack, M., Eichler, K., Lehnert, T., Nabil, M. (2006) Effect of laser-induced thermotherapy on liver metastases. Expert review of anticancer therapy, 6(5):, 769–774. https://doi.org/10.1586/14737140.6.5.769
28. Wang, C., Li, L., Wang, L., Ping, Z., Flory, M. T., Wang, G., Xi, Y., Li, W. (2013) Evaluating the risk of type 2 diabetes mellitus using artificial neural network: An effective classification approach. Diabetes Research and Clinical Practice, 100(1):, 111–118. https://doi.org/10.1016/j.diabres.2013.01.023
29. Wang, Y. C., Chan, T. C.-H., Sahakian, A. V. 2018. Real-time estimation of lesion depth and control of radiofrequency ablation within ex vivo animal tissues using a neural network. International journal of hyperthermia ,International Journal of Hyperthermia, 34(7):1104-1113. doi: 10.1080/02656736.2017.
30. Yildiz, F (2012) NIR-IR Lazerlerin Karaciğer Üzerindeki Etkilerinin In Vitro Ortamda Araştırılması ve Karşılaştırılması, Yüksek Lisans Tezi,İstanbul Teknik Üniversitesi Fen Bilimleri Enstitüsü,İstanbul
31. Yildiz, F., Gulsoy, M., Cilesiz, I. (2016) An experimental study on photothermal damage to tissue: The role of irradiance and wavelength. Laser Physics, 26(9):, 95601. https://doi.org/10.1088/1054-660x/26/9/095601
32. Yildiz, F. and Özdemir, A. T. (2019) Prediction of laser-induced thermal damage with artificial neural networks. Laser Physics, 29(7): 075205. https://doi.org/10.1088/1555-6611/ab183b
33. Zhang, Y., Wu, L., Wang, S. (2011) Magnetic Resonance Brain Image Classification By an Improved Artificial Bee Colony Algorithm. Progress In Electromagnetics Research, 116: 65–79. https://doi.org/10.2528/PIER11031709