Detection of foot bone anomaly using medical photogrammetry

Abstract

Photogrammetry has been used for medical diagnostic and treatment. Mostly used medical photogrammetric techniques are Ultrasound, Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) images. CT and MRI are the most effective method for the early detection of foot and ankle anomaly. Researchers have been developing various methods to detect anomaly. Many image segmentation techniques are available in the literature. Computer Aided Diagnosing (CAD) system has been proposed in this study for detection of foot bone anomaly by the analysis of CT images. In this study, a segmentation based on edge detection method is proposed for the classification of anomaly in foot CT images. Edge detection algorithms are the most commonly used techniques in image processing for edge detection. Canny edge detector is evaluated in this study. In this study, “.dicom” medical image standard format and ten male patient's foot CT images (245 images and 50 test data) are used. The used parameters are detector collimation of 64 mm, scanning thickness of 1-5 mm, and pixel sizes of 512x512 in radiometric resolution of 16 bits’ gray levels. The proposed method consists of five major steps: (i) calculating the horizontal & vertical gradient, (ii) determining gradient magnitude and gradient direction, (iii) applying non-maximal suppression, (iv) computing high and low thresholds, (v) hysteresis thresholding are applied to the multi-detector computed tomography to detect the bone anomaly. In this study, automatic edge-based digital image processing techniques are applied to detect of foot bone anomaly. The proposed canny segmentation method enables users segment anomaly in MDCT of foot very quickly and efficiently. The results demonstrate that the proposed segmentation method is effective for segmenting anomaly. The proposed method obtains satisfactory performances in terms of accuracy and F-measure the area under Receiver Operating Characteristic curve (ROC curve (AUC)). The proposed segmentation method achieves an accuracy of 0.86 and F- measure of 0.92, respectively. The purpose of our study is to detect the anomaly of the foot and it was the simplest and less time consuming process.

Keywords

• Medical Photogrammetry
• Medical Image Processing
• Segmentation, Anomaly
• CT

References

1. Bakotic, B. and Huvos, A.G., 2001. Tumors of the Bones of the Feet: The Clinicopathologic Features of 150 Cases, Journal of Foot & Ankle Surgery, 40(5), pp. 277 -286.
2. Biswas, R. and Sil, J., 2012. An Improved Canny Edge Detection Algorithm Based on Type-2 Fuzzy Sets, Procedia Technology, 4, pp. 820 – 824.
3. Canny, J.F., 1983. Finding Edges and Lines in Images, Technical Report AI-TR-720, MIT, Artificial Intelligence Laboratory, Cambridge, MA.
4. Canny, J.F., 1986. A Computational Approach to Edge Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), pp. 679-698.
5. Catal Reis, H., Bayram, B. and Seker, D.Z., 2016. Bone Tumor Segmentation by Gradient Operators from CT Images, Selcuk International Scientific Conference on Applied Sciences (The Selçuk ISCAS 2016), 27-30 September, Antalya, Turkey
6. Doi, K., 2007. Computer-Aided Diagnosis in Medical Imaging: Historical Review, Current Status and Future Potential, Comput Med Imaging Graph., 31(4-5), pp. 198–211.
7. Foo, L.F. and Raby, N., 2005. Tumors and Tumor-like Lesions in the Foot and Ankle, Clinical Radiology, 60, pp. 308–332.
8. Giger, M.L., Huo, Z., Kupinski, M.A., Vyborny, C.J., 2000. Computer-Aided Diagnosis in Mammography. In: Fitzpatrick JM, Sonka M, editors. The Handbook of Medical Imaging, volume 2 Medical Imaging Processing and Analysis, SPIE, pp. 915–1004.

9. Gonzalez, R.C. and Woods, R.E., 2007. Digital Image Processing”, 2nd ed., Beijing: Publishing House of Electronics Industry.
10. Hasbek Z., Salk I.., Yucel B., Akgul Babacan, N., 2013. Which Imaging Method to Choose for Detection of Bone Metastases? Bone Scintigraphy, CT, 18F-FDG PET/CT or MR? Bozok Med J, 3(3), pp. 44-50.
11. Jepson, A.D. and Fleet, D.J., Edge Detection, 2009, http://www.cs.toronto.edu/~jepson/csc2503/edgeDetecti on.pdf, 1 Nov 2015.
12. Kabade, A.L. and Sangam, V.G., 2016. Canny Edge Detection Algorithm, International Journal of Advanced Research in Electronics and Communication Engineering (IJARECE), 5(5), pp. 1292-1296.
13. Kizilkaya, A., 2008. Department of Electrical Engineering, Lecture Note, Pamukkale University, Denizli- Turkey.
14. Lodwick, G.S., Haun, C.L., Smith, W.E., Keller, R.F. and Robertson, E.D., 1963. Computer Diagnosis of Primary Bone Tumors. A prelim. Report, 80, pp. 273-5.
15. Maini, R. and Aggarwa, H., 2009. Study and Comparison of Various Image Edge Detection Techniques, International Journal of Image Processing (IJIP), 3(1), pp. 1-11.
16. Mascard, E., Gaspar, N., Brugières, L., Glorion, C., Pannier, S. and Gomez-Brouchet, A., 2017. Malignant Tumours of the Foot and Ankle, EFORT Open Rev., 2(5), pp. 261–271.
17. Obuchowski, N.A., 2005. ROC Analysis, Fundamentals of Clinical Research for Radiologists, American College of Radiology (ACR), 184, pp. 364-372.
18. Ozer, D., Er, T., Aycan O.E., Oke, R., Coskun, M. and Kabukcuoglu, Y.S., 2014. May Bone Cement Be Used To Treat Benign Aggressive Bone Tumors of the Feet with Confidence? The Foot, 24, pp. 1–5.
19. Rice, B.M., Todd, N.W., Jensen, R., Rush, S.M. and William Rogers, W., 2014. Metastatic Calcaneal Lesion Associated with Uterine Carcinosarcoma, The Journal of Foot & Ankle Surgery, 53, pp. 364–368.
20. Rong, W., Li, Z., Zhang, W. and Sun, L., 2014. An Improved Canny Edge Detection Algorithm, Mechatronics and Automation (ICMA), IEEE International Conference, 3-6 Aug. 2014, Tianjin, China.
21. Toriwaki, J., Suenaga, Y., Negoro, T, et al., 1973. Pattern Recognition of Chest X-Ray Images, Computer Graphics and Image Processing, 2, pp. 252–271.
22. Yogamangalam, R. and Karthikeyan, B., 2013. Segmentation Techniques Comparison in Image Processing, International Journal of Engineering and Technology (IJET), 5(1) (Feb-Mar).