Arch Index ile Pes Planus ve Pes Kavus'un Uzaktan Ön Tanısı

Öz

Literatüre göre nüfusun yaklaşık üçte birinin bir tür ayak deformitesine sahip olduğu ve bunun kişilerin yaşam kalitesinin düşürdüğü bilinmektedir. Tüm deformiteler içinde ayağın medial longitudinal arkının kaybından kaynaklanan Pes Planus ve anormal derecede yüksek plantar longitudinal arkın neden olduğu pes cavus toplum verimliliğini en çok olumsuz etkileyen deformitelerdendir. Yukarıdakiler ışığında, bu çalışmada pes planus ve pes cavus için literatürde kabul gören geleneksel deformite tanımlama yöntemlerini kullanan, görüntü işleme ve derin sinir ağları yardımıyla bir cep telefonu uygulaması konsepti geliştirilmesiyle birlikte yeni bir mobil ön tanı sistemi sunulmuştur. Çalışma kapsamında, yaş ortalaması 24,06 olan ve bunların 22’si (%64,71) erkek ve 12’si (%35,29) kadın olmak üzere toplamda 34 katılımcı üzerinde bir prototip mobil çözüm uygulanmış ve test edilmiştir. Çalışma boyunca, çalışmaya katılan katılımcılardan ayak görüntüleri toplanmış ve bir ortopedi uzmanından deformite tiplerini hesaplamak için kullanılan kilit karar verme noktalarının belirlenmesi istenmiştir. Daha sonra aynı görüntüler, görüntü işleme ve derin öğrenme algoritmaları yardımıyla kilit noktaları belirlemek ve deformite tipini hesaplamak amacıyla prototipe beslenmiştir. Sonuçların karşılaştırılması, uzman ve prototip bulgularının %91.80 oranında uyum içinde olduğunu göstermiş ve bu da genel bir başarıya işaret etmiştir

Anahtar Kelimeler

• Pes Planus
• Pes Cavus
• Görüntü İşleme
• Ortopedi
• Derin Öğrenme

Remote Pre-Diagnosis of Pes Planus and Pes Cavus Using Arch Index

Abstract

According to the literature, people with foot deformities report poor quality of life and nearly one-third of the population has some type of foot deformity. Of all the deformities, Pes Planus, caused by the loss of the medial longitudinal arch of the foot, and pes cavus, caused by having an abnormally high plantar longitudinal arch, are the ones that negatively influence the productivity of society most. In the light of the above, this study proposes a novel mobile pre-diagnosis system for pes planus and pes cavus that is utilizing conventional deformity identification methods accepted in the literature through a mobile phone app by harnesing image processing and deep neural networks. As part of the study, a prototype is implemented and tested using 34 participants - 22 (64.71%) males and 12 (35.29%) females - with an average age of 24.06. In order to benchmark our prototype, an orthopedic specialist was asked to identify the key decision making points, which was then used to calculate the deformity type, on a set of foot images collected from participants. Then the same images were fed to the prototype with the objective of identifying the key points and calculating the deformity type via the help of image processing and deep learning algorithms. The comparison of the results showed that specialist’s and prototypes findings were in 91.80% match, which indicated an overall success

Keywords

• Pes Planus
• Pes Cavus
• Vision
• Image Processing
• Orthopedics
• Deep Learning

References

1. Michaudet, C., Edenfield, K. M., Nicolette, G. W., & Carek, P. J. (2018). Foot and Ankle Conditions: Pes Planus. FP essentials, 465, 18-23.
2. Franco, A. H. (1987). Pes cavus and pes planus: analyses and treatment. Physical therapy, 67(5), 688-694.
3. Kelly, L. A., Cresswell, A. G., & Farris, D. J. (2018). The energetic behaviour of the human foot across a range of running speeds. Scientific reports, 8(1), 1-6.
4. Aenumulapalli, A., Kulkarni, M. M., & Gandotra, A. R. (2017). Prevalence of flexible flat foot in adults: a cross-sectional study. Journal of clinical and diagnostic research: JCDR, 11(6), AC17.
5. Mickle, K. J., Steele, J. R., & Munro, B. J. (2006). The feet of overweight and obese young children: are they flat or fat?. Obesity, 14(11), 1949-1953.
6. Woźniacka, R., Bac, A., Matusik, S., Szczygieł, E., & Ciszek, E. (2013). Body weight and the medial longitudinal foot arch: high-arched foot, a hidden problem?. European journal of pediatrics, 172(5), 683-691.
7. Kohls-Gatzoulis, J., Woods, B., Angel, J. C., & Singh, D. (2009). The prevalence of symptomatic posterior tibialis tendon dysfunction in women over the age of 40 in England. Foot and Ankle Surgery, 15(2), 75-81.
8. DA, B., & DR, S. (1963). " IDIOPATHIC" PES CAVUS: AN INVESTIGATION INTO ITS AETIOLOGY. British Medical Journal, 2(5358), 659-661.

9. Gün, K., SaridoĞan, M., & Uysal, Ö. (2012). Pes Planus Tanısında Ayak İzi ve Radyografik Ölçüm Yöntemlerinin Korelasyonu. Turkish Journal of Physical Medicine & Rehabilitation/Turkiye Fiziksel Tip ve Rehabilitasyon Dergisi, 58(4).
10. Yalçın, N., Esen, E., Kanatlı, U., & Yetkin, H. (2010). Medial longitudinal arkın değerlendirilmesi: dinamik plantar basınç ölçüm sistemi ile radyografik yöntemlerin karşılaştırılması. Acta Orthop Traumatol Turc, 44(3), 241-5.
11. Smith, D. G., Barnes, B. C., Sands, A. K., Boyko, E. J., & Ahroni, J. H. (1997). Prevalence of radiographic foot abnormalities in patients with diabetes. Foot & ankle international, 18(6), 342-346.
12. Winfeld, M. J., & Winfeld, B. E. (2019). Management of pediatric foot deformities: an imaging review. Pediatric radiology, 49(12), 1678-1690.
13. Chen, K. C., Yeh, C. J., Kuo, J. F., Hsieh, C. L., Yang, S. F., & Wang, C. H. (2011). Footprint analysis of flatfoot in preschool-aged children. European journal of pediatrics, 170(5), 611-617.
14. Pauk, J., Ihnatouski, M., & Najafi, B. (2014). Assessing plantar pressure distribution in children with flatfoot arch: application of the Clarke angle. Journal of the American Podiatric Medical Association, 104(6), 622-632.
15. Kanatli, U., Yetkin, H., & Cila, E. (2001). Footprint and radiographic analysis of the feet. Journal of Pediatric Orthopaedics, 21(2), 225-228.
16. Yalçin, N., Esen, E., Kanatli, U., & Yetkin, H. (2010). Evaluation of the medial longitudinal arch: a comparison between the dynamic plantar pressure measurement system and radiographic analysis. Acta Orthop Traumatol Turc, 44(3), 241-5.
17. Menz, H. B., & Munteanu, S. E. (2005). Validity of 3 clinical techniques for the measurement of static foot posture in older people. Journal of Orthopaedic & Sports Physical Therapy, 35(8), 479-486.
18. Cavanagh, P. R., & Rodgers, M. M. (1987). The arch index: a useful measure from footprints. Journal of biomechanics, 20(5), 547-551.
19. Igbigbi, P. S., & Msamati, B. C. (2002). The footprint ratio as a predictor of pes planus: a study of indigenous Malawians. The Journal of foot and ankle surgery, 41(6), 394-397.
20. Didia, B. C., Omu, E. T., & Obuoforibo, A. A. (1987). The use of footprint contact index II for classification of flat feet in a Nigerian population. Foot & ankle, 7(5), 285-289.
21. Gun, K., Saridogan, M., & Uysal, O. (2012). The correlation between footprint and radiographic measurements in flatfoot.
22. Buldt, A. K., Levinger, P., Murley, G. S., Menz, H. B., Nester, C. J., & Landorf, K. B. (2015). Foot posture is associated with kinematics of the foot during gait: A comparison of normal, planus and cavus feet. Gait & posture, 42(1), 42-48.
23. Sennotech Co. Ltd. Gait Analysis Product. Retrieved August 16, 2021, from https://www.sennotech.com/en/index.php
24. alFOOTs Co. Ltd. 4ch PGO Gait Analysis Product. Retrieved August 20, 2021, from https://alfoots.com:5000/en/sub/02_sub/02_sub02.php
25. Vicon Motion Systems Ltd. Optical Motion Capture Cameras. Retrieved August 24, 2021, from https://www.vicon.com/hardware/cameras/
26. novel GmbH, emed Pressure Detection Device. Retrieved August 15, 2021, from https://www.novel.de/products/emed/
27. medilogic GmbH, emed Pressure Detection Device. Retrieved August 17, 2021, from https://medilogic.com/en/pressure-measuring-platform-nx/
28. Buldt, A. K., Forghany, S., Landorf, K. B., Levinger, P., Murley, G. S., & Menz, H. B. (2018). Foot posture is associated with plantar pressure during gait: A comparison of normal, planus and cavus feet. Gait & posture, 62, 235-240.
29. Keukenkamp, R., Busch‐Westbroek, T. E., Barn, R., Woodburn, J., & Bus, S. A. (2021). Foot ulcer recurrence, plantar pressure and footwear adherence in people with diabetes and Charcot midfoot deformity: A cohort analysis. Diabetic Medicine, 38(4), e14438.
30. Bosch, K., Gerß, J., & Rosenbaum, D. (2010). Development of healthy children's feet—nine-year results of a longitudinal investigation of plantar loading patterns. Gait & posture, 32(4), 564-571.
31. DENİZ, G., KAVAKLI, A., ÖGETÜRK, M., ÖZTÜRK, D., TATAR, N., & PERİLİOĞLU, A. Z. (2014). Çocuklardaki Fleksibl Pes Planusun Yüklü ve Yüksüz Radyografilerle Değerlendirilmesi. Fırat Üniversitesi Sağlık Bilimleri Tıp Dergisi, 28(3), 129-132.
32. Flores, D. V., Mejía Gómez, C., Fernández Hernando, M., Davis, M. A., & Pathria, M. N. (2019). Adult acquired flatfoot deformity: anatomy, biomechanics, staging, and imaging findings. Radiographics, 39(5), 1437-1460.
33. Yates, B., & Merriman, L. M. (Eds.). (2009). Merriman's assessment of the lower limb. Elsevier Health Sciences.
34. Vanderwilde, R. U. S. S. E. L. L., Staheli, L. T., Chew, D. E., & Malagon, V. A. L. E. N. T. I. N. (1988). Measurements on radiographs of the foot in normal infants and children. The Journal of bone and joint surgery. American volume, 70(3), 407-415.
35. Banks, A. S. (2001). McGlamry's comprehensive textbook of foot and ankle surgery (Vol. 1). Lippincott Williams & Wilkins.
36. Almaawi, A., Alotaibi, N., Alsubaie, M., Altwaijri, N., Alduraibi, K., Awwad, W., & Algarni, A. (2019). Flatfoot Prevalence in Riyadh City Saudi Arabia And Its Association with Obesity, Using Three Footprint Indices; Clark’ s Angle, Chippaux-Smirak Index, and Staheli Index. Orthopedics and Rheumatology Open Access Journals, 15(2), 52-58.
37. Michie, D., Spiegelhalter, D. J., & Taylor, C. C. (1994). Machine learning, neural and statistical classification.
38. Ciregan, D., Meier, U., & Schmidhuber, J. (2012, June). Multi-column deep neural networks for image classification. In 2012 IEEE conference on computer vision and pattern recognition (pp. 3642-3649). IEEE.
39. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580-587).
40. Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 1440-1448).
41. Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28, 91-99.
42. Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
43. Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3431-3440).
44. Chen, L. C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587.
45. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
46. Razzak, M. I., Naz, S., & Zaib, A. (2018). Deep learning for medical image processing: Overview, challenges and the future. Classification in BioApps, 323-350.
47. Hemanth, D. J., & Estrela, V. V. (Eds.). (2017). Deep learning for image processing applications (Vol. 31). IOS Press.
48. Gonzalez, R. C., & Woods, R. E. (1992). Digital Image Processing Addison-Wesley. Reading, Ma.
49. Prewitt, J. M. (1970). Object enhancement and extraction. Picture processing and Psychopictorics, 10(1), 15-19.
50. Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on pattern analysis and machine intelligence, (6), 679-698.
51. Vinista, P., & Joe, M. M. (2019). A Novel Modified Sobel Algorithm for Better Edge Detection of Various Images. International journal of emerging technologies in engineering research (IJETER), 7(3), 26-31.
52. Yusoff, N. M., Halim, I. S. A., & Abdullah, N. E. (2018, August). Real-time hevea leaves diseases identification using Sobel edge algorithm on FPGA: A preliminary study. In 2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC) (pp. 168-171). IEEE.
53. Rezai-Rad, G., & Aghababaie, M. (2006, April). Comparison of SUSAN and sobel edge detection in MRI images for feature extraction. In 2006 2nd International Conference on Information & Communication Technologies (Vol. 1, pp. 1103-1107). IEEE.
54. Lee, M. S., Vanore, J. V., Thomas, J. L., Catanzariti, A. R., Kogler, G., Kravitz, S. R., ... & Gassen, S. C. (2005). Diagnosis and treatment of adult flatfoot. The Journal of Foot and Ankle Surgery, 44(2), 78-113.
55. Cheung, Z. B., Myerson, M. S., Tracey, J., & Vulcano, E. (2018). Weightbearing CT scan assessment of foot alignment in patients with hallux rigidus. Foot & ankle international, 39(1), 67-74.
56. Vaseenon, T., Wattanarojanaporn, T., Intharasompan, P., Theeraamphon, N., Auephanviriyakul, S., & Phisitkul, P. (2015). Foot and ankle problems in Thai monks. J Med Assoc Thai, 98(1), 71-6.