Skip to main content
main-content

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

Erschienen in: Health and Technology 3/2021

18.03.2021 | Original Paper

Comparison of different machine learning approaches to detect femoral neck fractures in x-ray images

verfasst von: Koray Açıcı, Emre Sümer, Salih Beyaz

Erschienen in: Health and Technology | Ausgabe 3/2021

Einloggen, um Zugang zu erhalten
share
TEILEN

Abstract

Femoral neck fractures are a serious health problem, especially in the elderly population. Misdiagnosis leads to improper treatment and adversely affects the quality of life of the patients. On the other hand, when looking from the perspective of orthopedic surgeons, their workload increases during the pandemic, and the rates of correct diagnosis may decrease with fatigue. Therefore, it becomes essential to help healthcare professionals diagnose correctly and facilitate treatment planning. The main purpose of this study is to develop a framework to detect fractured femoral necks in PXRs (Pelvic X-ray, Pelvic Radiographs) while also researching how different machine learning approaches affect different data distributions. Conventional, LBP (Local Binary Patterns), and HOG (Histogram of Gradients) features were extracted manually from gray-level images to feed the canonical machine learning classifiers. Gray-level and three-channel images were used as inputs to extract the features automatically by CNNs (Convolutional Neural Network). LSTMs (Long Short-Term Memory) and BILSTMs (Bidirectional Long Short-Term Memory) were fed by automatically extracted features. Metaheuristic optimization algorithms, GA (Genetic Algorithm) and PSO (Particle Swarm Optimization), were utilized to optimize hyper-parameters such as the number of the feature maps and the size of the filters in the convolutional layers of the CNN architecture. The majority voting was applied to the results of the different classifiers. For the imbalanced dataset, the best performance was achieved by the 2-layer LSTM architecture that used features extracted from the fifth max-pooling layer of the CNN architecture optimized by GA. For the balanced dataset, the best performance was obtained by the CNN architecture optimized by PSO in terms of the Kappa evaluation metric. Although metaheuristic optimization algorithms such as GA and PSO do not guarantee the optimal solution, they can improve the performance on a not extremely imbalanced dataset especially in terms of sensitivity and Kappa evaluation metrics. On the other hand, for a balanced dataset, more reliable results can be obtained without using metaheuristic optimization algorithms but including them can result in an acceptable agreement in terms of the Kappa metric.

Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 69.000 Bücher
  • über 500 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Testen Sie jetzt 15 Tage kostenlos.

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 58.000 Bücher
  • über 300 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Testen Sie jetzt 15 Tage kostenlos.

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 50.000 Bücher
  • über 380 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




Testen Sie jetzt 15 Tage kostenlos.

Literatur
1.
Zurück zum Zitat Beyaz S. A brief history of artificial intelligence and robotic surgery in orthopedics & traumatology and future expectations. Jt Dis Relat Surg. 2020;31(3):653–5. MathSciNetCrossRef Beyaz S. A brief history of artificial intelligence and robotic surgery in orthopedics & traumatology and future expectations. Jt Dis Relat Surg. 2020;31(3):653–5. MathSciNetCrossRef
2.
Zurück zum Zitat Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist level classification of skin cancer with deep neural networks. Nature. 2017;542:115–8. CrossRef Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist level classification of skin cancer with deep neural networks. Nature. 2017;542:115–8. CrossRef
4.
Zurück zum Zitat Lee J-G, Jun S, Cho Y-W, Lee H, Kim GB, Seo JB, Kim N. Deep learning in medical imaging: general overview. Korean J Radiol. 2017;18(4):570–84. CrossRef Lee J-G, Jun S, Cho Y-W, Lee H, Kim GB, Seo JB, Kim N. Deep learning in medical imaging: general overview. Korean J Radiol. 2017;18(4):570–84. CrossRef
5.
Zurück zum Zitat Olczak J, Fahlberg N, Maki A, Razavian AS, Jilert A, Stark A, Sköldenberg O, Gordon M. Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop. 2017;88(6):581–6. CrossRef Olczak J, Fahlberg N, Maki A, Razavian AS, Jilert A, Stark A, Sköldenberg O, Gordon M. Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop. 2017;88(6):581–6. CrossRef
6.
Zurück zum Zitat Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, Venugopalan S, Widner K, Madams T, Juadros J, Kim R, Raman R, Nelson PC, Mega JL, Webster DR. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402–10. CrossRef Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, Venugopalan S, Widner K, Madams T, Juadros J, Kim R, Raman R, Nelson PC, Mega JL, Webster DR. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402–10. CrossRef
7.
Zurück zum Zitat Tang A, Tam R, Cadrin-Chenevert A, Guest W, Chong J, Barfett J, Chepelev L, Cairns R, Mitchell JR, Cicero MD, Poudrette MG, Jaremko JL, Reinhold C, Gallix B, Gray B, Geis R. Canadian association of radiologists white paper on artificial intelligence in radiology. Can Assoc Radiol J. 2018;69(2):120–35. CrossRef Tang A, Tam R, Cadrin-Chenevert A, Guest W, Chong J, Barfett J, Chepelev L, Cairns R, Mitchell JR, Cicero MD, Poudrette MG, Jaremko JL, Reinhold C, Gallix B, Gray B, Geis R. Canadian association of radiologists white paper on artificial intelligence in radiology. Can Assoc Radiol J. 2018;69(2):120–35. CrossRef
8.
Zurück zum Zitat Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017;284:574–82. CrossRef Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017;284:574–82. CrossRef
9.
Zurück zum Zitat Atik OŞ. There is an association between sarcopenia, osteoporosis, and the risk of hip fracture. Eklem Hastalik Cerrahisi. 2019;30:1. CrossRef Atik OŞ. There is an association between sarcopenia, osteoporosis, and the risk of hip fracture. Eklem Hastalik Cerrahisi. 2019;30:1. CrossRef
10.
Zurück zum Zitat Bozkurt HH, Tokgöz MA, Yapar A, Atik OŞ. What is the importance of canal-to-diaphysis ratio on osteoporosisrelated hip fractures? Eklem Hastalik Cerrahisi. 2019;30(3):296–300. CrossRef Bozkurt HH, Tokgöz MA, Yapar A, Atik OŞ. What is the importance of canal-to-diaphysis ratio on osteoporosisrelated hip fractures? Eklem Hastalik Cerrahisi. 2019;30(3):296–300. CrossRef
11.
Zurück zum Zitat Leslie WD, O’Donnell S, Jean S, Lagacé C, Walsh P, Bancej C, Morin S, Hanley DA, Papaioannou A. Trends in hip fracture rates in Canada. JAMA. 2009;302(8):883–9. CrossRef Leslie WD, O’Donnell S, Jean S, Lagacé C, Walsh P, Bancej C, Morin S, Hanley DA, Papaioannou A. Trends in hip fracture rates in Canada. JAMA. 2009;302(8):883–9. CrossRef
12.
Zurück zum Zitat Lewiecki EM, Wright NC, Curtis JR, Siris E, Gagel RF, Saag KG, Singer AJ, Steven PM, Adler RA. Hip fracture trends in the United States, 2002 to 2015. Osteoporos Int. 2018;29(3):717–22. CrossRef Lewiecki EM, Wright NC, Curtis JR, Siris E, Gagel RF, Saag KG, Singer AJ, Steven PM, Adler RA. Hip fracture trends in the United States, 2002 to 2015. Osteoporos Int. 2018;29(3):717–22. CrossRef
13.
Zurück zum Zitat Bozkurt HH, Atik OŞ, Tokgöz MA. Can distal radius or vertebra fractures due to low-energy trauma be a harbinger of a hip fracture? Eklem Hastalik Cerrahisi. 2018;29(2):100–3. CrossRef Bozkurt HH, Atik OŞ, Tokgöz MA. Can distal radius or vertebra fractures due to low-energy trauma be a harbinger of a hip fracture? Eklem Hastalik Cerrahisi. 2018;29(2):100–3. CrossRef
14.
Zurück zum Zitat Dominguez S, Liu P, Roberts C, Mandell M, Richman PB. Prevalence of traumatic hip and pelvic fractures in patients with suspected hip fracture and negative initial standard radiographs–a study of emergency department patients. Acad Emerg Med. 2005;12(4):366–9. Dominguez S, Liu P, Roberts C, Mandell M, Richman PB. Prevalence of traumatic hip and pelvic fractures in patients with suspected hip fracture and negative initial standard radiographs–a study of emergency department patients. Acad Emerg Med. 2005;12(4):366–9.
15.
Zurück zum Zitat Perron AD, Miller MD, Brady WJ. Orthopedic pitfalls in the ED: radiographically occult hip fracture. Am J Emerg Med. 2002;20(3):234–7. CrossRef Perron AD, Miller MD, Brady WJ. Orthopedic pitfalls in the ED: radiographically occult hip fracture. Am J Emerg Med. 2002;20(3):234–7. CrossRef
16.
Zurück zum Zitat Al-Ayyoub M, Al-Zghool D. Determining the type of long bone fractures in X-ray images. WSEAS Trans Inf Sci Appl. 2013;10(8):261–70. Al-Ayyoub M, Al-Zghool D. Determining the type of long bone fractures in X-ray images. WSEAS Trans Inf Sci Appl. 2013;10(8):261–70.
17.
Zurück zum Zitat Lim SE, Xing Y, Chen Y, Leow WK, Howe TS, Png MA. Detection of femur and radius fractures in X-ray images. In: Proc. 2nd Int. Conf. on Advances in Medical Signal and Information Processing. 2004, pp. 249–56. Lim SE, Xing Y, Chen Y, Leow WK, Howe TS, Png MA. Detection of femur and radius fractures in X-ray images. In: Proc. 2nd Int. Conf. on Advances in Medical Signal and Information Processing. 2004, pp. 249–56.
18.
Zurück zum Zitat Lum VLF, Leow WK, Chen Y, Howe TS, Png MA. Combining classifiers for bone fracture detection in X-ray images. In: IEEE International Conference on Image Processing, Genova, 2005, pp. 1149–52. Lum VLF, Leow WK, Chen Y, Howe TS, Png MA. Combining classifiers for bone fracture detection in X-ray images. In: IEEE International Conference on Image Processing, Genova, 2005, pp. 1149–52.
19.
Zurück zum Zitat Mahendran SK, Baboo SS. An enhanced tibia fracture detection tool using image processing and classification fusion techniques in X-ray images. Global J Comput Sci Technol. 2011;11(14):22–8. Mahendran SK, Baboo SS. An enhanced tibia fracture detection tool using image processing and classification fusion techniques in X-ray images. Global J Comput Sci Technol. 2011;11(14):22–8.
20.
Zurück zum Zitat He JC, Leow WK, Howe TS. (2007) Hierarchical Classifiers for Detection of Fractures in X-ray Images. In: Kropatsch WG, Kampel M, Hanbury A, editors. Computer Analysis of Images and Patterns. CAIP 2007. Lecture Notes in Computer Science, vol 4673. Springer, Berlin, Heidelberg; 2007. pp. 962–9. https://​doi.​org/​10.​1007/​978-3-540-74272-2_​119. He JC, Leow WK, Howe TS. (2007) Hierarchical Classifiers for Detection of Fractures in X-ray Images. In: Kropatsch WG, Kampel M, Hanbury A, editors. Computer Analysis of Images and Patterns. CAIP 2007. Lecture Notes in Computer Science, vol 4673. Springer, Berlin, Heidelberg; 2007. pp. 962–9. https://​doi.​org/​10.​1007/​978-3-540-74272-2_​119.
21.
Zurück zum Zitat Cheng C-T, Ho T-Y, Lee T-Y, Chang C-C, Chou C-C, Chen C-C, Chung I-F, Liao C-H. Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs. Eur Radiol. 2019;29(10):5469–77. CrossRef Cheng C-T, Ho T-Y, Lee T-Y, Chang C-C, Chou C-C, Chen C-C, Chung I-F, Liao C-H. Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs. Eur Radiol. 2019;29(10):5469–77. CrossRef
23.
Zurück zum Zitat Adams M, Chen W, Holcdorf D, McCusker MW, Howe PDL, Gaillard F. Computer vs human: Deep learning versus perceptual training for the detection of neck of femur fractures. J Med Imaging Radiat Oncol. 2019;63(1):27–32. CrossRef Adams M, Chen W, Holcdorf D, McCusker MW, Howe PDL, Gaillard F. Computer vs human: Deep learning versus perceptual training for the detection of neck of femur fractures. J Med Imaging Radiat Oncol. 2019;63(1):27–32. CrossRef
24.
Zurück zum Zitat Chung SW, Han SS, Lee JW, Oh KS, Kim NR, Yoon JP, Kim JY, Moon SH, Kwon J, Lee HJ, Noh YM, Kim Y. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop. 2018;89(4):468–73. CrossRef Chung SW, Han SS, Lee JW, Oh KS, Kim NR, Yoon JP, Kim JY, Moon SH, Kwon J, Lee HJ, Noh YM, Kim Y. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop. 2018;89(4):468–73. CrossRef
25.
Zurück zum Zitat Urakawa T, Tanaka Y, Goto S, Matsuzawa H, Watanabe K, Endo N. Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network. Skeletal Radiol. 2019;48(2):239–44. CrossRef Urakawa T, Tanaka Y, Goto S, Matsuzawa H, Watanabe K, Endo N. Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network. Skeletal Radiol. 2019;48(2):239–44. CrossRef
28.
Zurück zum Zitat Joshi MV. Learning classifier models for predicting rare phenomena. Ph.D. Thesis, University of Minnesota, Twin Cites, MN, USA, 2002. Joshi MV. Learning classifier models for predicting rare phenomena. Ph.D. Thesis, University of Minnesota, Twin Cites, MN, USA, 2002.
29.
Zurück zum Zitat Kubat M, Matwin S. Addressing the curse of imbalanced training sets: One-sided selection. In: Proceedings of the 14th International Conference on Machine Learning, ICML, Nashville, TN, 1997, pp. 179–186. Kubat M, Matwin S. Addressing the curse of imbalanced training sets: One-sided selection. In: Proceedings of the 14th International Conference on Machine Learning, ICML, Nashville, TN, 1997, pp. 179–186.
30.
Zurück zum Zitat Beyaz S, Açıcı K, Sümer E. Femoral neck fracture detection in X-ray images using deep learning and genetic algorithm approaches. Jt Dis Relat Surg. 2020;31(2):175–83. CrossRef Beyaz S, Açıcı K, Sümer E. Femoral neck fracture detection in X-ray images using deep learning and genetic algorithm approaches. Jt Dis Relat Surg. 2020;31(2):175–83. CrossRef
31.
Zurück zum Zitat Sharma N, Ray AK, Sharma S, Shukla KK, Pradhan S, Aggarwal LM. Segmentation and classification of medical images using texture-primitive features: Application of BAM-type artificial neural network. J Med Phys. 2008;33(3):119–26. CrossRef Sharma N, Ray AK, Sharma S, Shukla KK, Pradhan S, Aggarwal LM. Segmentation and classification of medical images using texture-primitive features: Application of BAM-type artificial neural network. J Med Phys. 2008;33(3):119–26. CrossRef
32.
Zurück zum Zitat Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA, USA, 2005, vol. 1, pp. 886–93. Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA, USA, 2005, vol. 1, pp. 886–93.
33.
Zurück zum Zitat Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell. 2002;24(7):971–87. CrossRef Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell. 2002;24(7):971–87. CrossRef
34.
Zurück zum Zitat Kubat M. An introduction to machine learning. Springer; 2016. Kubat M. An introduction to machine learning. Springer; 2016.
35.
Zurück zum Zitat Duda RO, Hart PE, Stork DG. Pattern classification. 2nd ed. New York: Wiley; 2001. MATH Duda RO, Hart PE, Stork DG. Pattern classification. 2nd ed. New York: Wiley; 2001. MATH
37.
38.
Zurück zum Zitat LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–44. CrossRef LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–44. CrossRef
39.
Zurück zum Zitat Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Networks. 1994;5:157–66. CrossRef Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Networks. 1994;5:157–66. CrossRef
40.
Zurück zum Zitat Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9:1735–80. CrossRef Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9:1735–80. CrossRef
41.
Zurück zum Zitat Karim AM, Güzel MS, Tolun MR, Kaya H, Çelebi FV. A new framework using deep auto-encoder and energy spectral density for medical waveform data classification and processing. Biocybern Biomed Eng. 2019;39(1):148–59. CrossRef Karim AM, Güzel MS, Tolun MR, Kaya H, Çelebi FV. A new framework using deep auto-encoder and energy spectral density for medical waveform data classification and processing. Biocybern Biomed Eng. 2019;39(1):148–59. CrossRef
42.
44.
Zurück zum Zitat Kennedy J, Eberhart R. Particle Swarm Optimization. In: Proceedings of IEEE International Conference on Neural Networks. 1995, vol. 4, pp. 1942–1948. Kennedy J, Eberhart R. Particle Swarm Optimization. In: Proceedings of IEEE International Conference on Neural Networks. 1995, vol. 4, pp. 1942–1948.
Metadaten
Titel
Comparison of different machine learning approaches to detect femoral neck fractures in x-ray images
verfasst von
Koray Açıcı
Emre Sümer
Salih Beyaz
Publikationsdatum
18.03.2021
Verlag
Springer Berlin Heidelberg
Erschienen in
Health and Technology / Ausgabe 3/2021
Print ISSN: 2190-7188
Elektronische ISSN: 2190-7196
DOI
https://doi.org/10.1007/s12553-021-00543-9

Weitere Artikel der Ausgabe 3/2021

Health and Technology 3/2021 Zur Ausgabe

Premium Partner