Research Article
BibTex RIS Cite

A K-nearest neighbors-based classification approach for automated detection of knee osteoarthritis

Year 2023, Volume: 48 Issue: 2, 715 - 722, 02.07.2023
https://doi.org/10.17826/cumj.1281955

Abstract

Purpose: Osteoarthritis is a serious condition that can significantly reduce a person’s quality of life, causing pain and stiffness in the knees and limiting their mobility. The condition progressively worsens over time, emphasizing the importance of early diagnosis. This study implemented a computer-aided classification approach to reduce the time and effort required for diagnosing knee osteoarthritis while minimizing human errors.
Materials and Methods: Data analyzed in this study was obtained from the Osteoarthritis Initiative. A total of 165 samples were used in the study. All abnormal samples were graded as severe osteoarthritis. While 78 samples were used to test the implemented algorithm, the training process of the algorithm was completed with 87 samples. The proposed approach involves three main stages: segmenting the cartilage region through a series of image-processing operations, extracting morphological features from the defined region, and classifying samples based on these features. In the classification stage, morphological features characterizing the cartilage region were classified in the observation space, and the k-nearest neighbors algorithm was applied for automated discrimination. Accordingly, the computer utilizes the previously classified sample features to estimate the presence of pathology.
Results: Test classifications were completed with 78 samples; 28 were previously diagnosed with osteoarthritis. Morphological measures of the training samples were accepted as a reference for abnormality. The applied classification scheme can distinguish severed cartilage regions with a 0.95% accuracy.
Conclusion: This study demonstrates the potential effectiveness of a computer-aided approach in diagnosing knee osteoarthritis with high accuracy. The developed approach offers a promising solution for early and efficient diagnosis, enabling more timely and effective treatment strategies for osteoarthritis patients. The progressive nature of the disease makes these advancements in diagnostic methods invaluable. Future studies may focus on expanding the sample size and further refining the model for enhanced precision and broad applicability in clinical settings.

Supporting Institution

-

Project Number

-

Thanks

-

References

  • Xing D, Xu Y, Liu Q, Ke Y, Wang B, Li Z et al. Osteoarthritis and all-cause mortality in worldwide populations: grading the evidence from a meta-analysis. Sci Rep. 2016;6:24393.
  • Lespasio MJ, Piuzzi NS, Husni ME, Muschler GF, Guarino A, Mont MA. Knee osteoarthritis: a primer. Perm J. 2017;21.
  • Risberg MA, Oiestad BE, Gunderson R, Aune AK, Engebretsen L, Culvenor A et al. Changes in knee osteoarthritis, symptoms, and function after anterior cruciate ligament reconstruction: a 20-year prospective follow-up study. Am J Sports Med. 2016;44:1215-24.
  • Dulay GS, Cooper C, Dennison E. Knee pain knee injury knee osteoarthritis & work. Best Pract Res Clin Rheumatol. 2015;29:454-61.
  • Katz JN, Arant KR, Loeser RF. Diagnosis and treatment of hip and knee osteoarthritis: a review. JAMA. 2021;325:568-78.
  • Schock J, Truhn D, Abrar DB, Merhof D, Conrad S, Post M et al. Automated analysis of alignment in long-leg radiographs by using a fully automated support system based on artificial intelligence. Radiol Artif Intell. 2020;3:e200198.
  • Shamir L, Ling SM, Scott WW, Bos A, Orlov N, Macura TJ et al. Knee x-ray image analysis method for automated detection of osteoarthritis. IEEE Trans Biomed Eng. 2008;56:407-15.
  • Suresha S, Kidzin´ski L, Halilaj E, Gold G, Delp S. Automated staging of knee osteoarthritis severity using deep neural networks. Osteoarthritis Cartilage. 2018;26:S441.
  • Saleem M, Farid MS, Saleem S, Khan MH. X-ray image analysis for automated knee osteoarthritis detection. Signal Image Video Process. 2020;14:1079-87.
  • Chen P, Gao L, Shi X, Allen K, Yang L. Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss. Comput Med Imaging Graph. 2019;75:84-92.
  • Brahim A, Jennane R, Riad R, Janvier T, Khedher L, Toumi H et al. A decision support tool for early detection of knee osteoarthritis using X-ray imaging and machine learning: data from the osteoarthritis initiative. Comput Med Imaging Graph. 2019;73:11-8.
  • Shamir L, Ling SM, Scott W, Hochberg M, Ferrucci L, Goldberg IG. Early detection of radiographic knee osteoarthritis using computer-aided analysis. Osteoarthritis Cartilage. 2009;17:1307-12.
  • Alenazi AM, Alshehri MM, Alothman S, Alqahtani BA, Rucker J, Sharma N et al. The association of diabetes with knee pain severity and distribution in people with knee osteoarthritis using data from the osteoarthritis initiative. Sci Rep. 2020;10:3985.
  • Chen P. Knee Osteoarthritis Severity Grading Dataset. Mendeley Data. 2018.
  • Tolay P, Vajinepalli P, Bhattacharya P, Firtion C, Sisodia RS. Automated fetal spine detection in ultrasound images. Computer-Aided Diagnosis. vol. 7260. SPIE; 2009. p. 1054-63.
  • Davies-Tuck M, Wluka AE, Wang Y, Teichtahl A, Jones G, Ding C et al. The natural history of cartilage defects in people with knee osteoarthritis. Osteoarthritis and Cartilage. 2008;16:337-42.
  • Guo G, Wang H, Bell D, Bi Y, Greer K. KNN model-based approach in classification. In: On The Move to Meaningful Internet Syst 2003: CoopIS, DOA, and ODBASE: OTM Confed Int Conferences, CoopIS, DOA, and ODBASE 2003, Catania, Sicily, Italy, Nov 3-7, 2003. Proc. Springer; 2003.p. 986-96.
  • Zhang ML, Zhou ZH. ML-KNN: A lazy learning approach to multi-label learning. Pattern Recognit. 2007;40:2038-48.
  • Soucy P, Mineau GW. A simple KNN algorithm for text categorization. In: Proc 2001 IEEE Int Conf Data Min. IEEE; 2001:647-8.
  • Deng Z, Zhu X, Cheng D, Zong M, Zhang S. Efficient KNN classification algorithm for big data. Neurocomputing. 2016;195:143-8.
  • Xing W, Bei Y. Medical health big data classification based on KNN classification algorithm. IEEE Access. 2019;8:28808-19.
  • Bayramoglu N, Tiulpin A, Hirvasniemi J, Nieminen MT, Saarakkala S. Adaptive segmentation of knee radiographs for selecting the optimal ROI in texture analysis. Osteoarthritis Cartilage. 2020;28:941-52.
  • Olsson S, Akbarian E, Lind A, Razavian AS, Gordon M. Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population. BMC Musculoskelet Disord. 2021;22:1-8.
  • Thomson J, O’Neill T, Felson D, Cootes T. Automated shape and texture analysis for detection of osteoarthritis from radiographs of the knee. In: Med Image Comput Comput Assist Interv–MICCAI 2015: 18th Int Conf, Munich, Germany, October 5-9, 2015, Proceedings, Part II 18. Springer; 2015;127-34

Diz osteoartritinin otomatik tespiti için K-en yakın komşuluk algoritmasına dayalı bir sınıflandırma yaklaşımı

Year 2023, Volume: 48 Issue: 2, 715 - 722, 02.07.2023
https://doi.org/10.17826/cumj.1281955

Abstract

Amaç: Osteoartrit, kişinin yaşam kalitesini düşüren, dizlerde hissedilen ağrı ve sertlik ile kişinin hareket kabiliyetini kısıtlayabilen ve zamanla şiddetini arttıran ciddi bir rahatsızlıktır. Hastalığın ilerleyici karakteri erken tanının önemini artırmaktadır. Röntgen görüntüleri bu hastalığım teşhisi için klinisyenler tarafından en çok tercih edilen araçlardan biridir. Çalışmada bilgisayar destekli sınıflandırma yaklaşımı ile diz osteoartritinin teşhisi için gereken zaman ve iş gücünün azaltılarak insan kaynaklı hataların minimize edilmesi hedeflenmiştir.
Gereç ve Yöntem: Bu çalışmada analiz edilen veriler, Osteoartrit Girişimi'nden elde edilmiştir. Çalışmada toplamda 165 örnek kullanılmıştır. Tüm anormal örneklerde şiddetli kıkırdak zararı gözlenmiştir. Uygulanan algoritmanın test safhasında 78, eğitim aşamasında ise 87 örnek kullanılmıştır. Önerilen yaklaşım üç ana aşama içermektedir: kıkırdak bölgesinin görüntü işleme yöntemleri ile bölütlenmesi, sınırları çizilen bölgeden morfolojik özelliklerin çıkarılması ve bu özelliklerin değerlendirilerek örneklerin sınıflandırılması. Sınıflandırma aşamasında, gözlem uzayı kıkırdak bölgesini karakterize eden morfolojik özellikler ile oluşturulmuş, otomatik sınıflandırma işlemi için k-en yakın komşu algoritması uygulanmıştır. Buna göre, bilgisayar önceden sınıflandırılmış örnek özelliklerini kullanarak patolojinin varlığını tahmin etmektedir.
Bulgular: Test sınıflandırmaları 28'ine osteoartrit teşhisi konmuş toplam 78 örnekle tamamlanmıştır. Eğitim örneklerinin sayısal özellikleri kıkırdak hasarının otomatik tespiti için referans olarak kabul edilmiştir. Uygulanan sınıflandırma mekanizması yıpranmış kıkırdak bölgelerini %0.95 doğrulukla ayırt edebilmiştir.
Sonuç: Hastalığın ilerleyici doğası, teşhis yöntemlerindeki ilerlemeleri oldukça değerli kılmaktadır. Sonraki çalışmalar örneklem büyüklüğünün genişletilerek ümit vadeden modelin klinik ortamlarda yüksek doğrulukla uygulanabilirlik kazanması için geliştirilmesine odaklanabilir.

Project Number

-

References

  • Xing D, Xu Y, Liu Q, Ke Y, Wang B, Li Z et al. Osteoarthritis and all-cause mortality in worldwide populations: grading the evidence from a meta-analysis. Sci Rep. 2016;6:24393.
  • Lespasio MJ, Piuzzi NS, Husni ME, Muschler GF, Guarino A, Mont MA. Knee osteoarthritis: a primer. Perm J. 2017;21.
  • Risberg MA, Oiestad BE, Gunderson R, Aune AK, Engebretsen L, Culvenor A et al. Changes in knee osteoarthritis, symptoms, and function after anterior cruciate ligament reconstruction: a 20-year prospective follow-up study. Am J Sports Med. 2016;44:1215-24.
  • Dulay GS, Cooper C, Dennison E. Knee pain knee injury knee osteoarthritis & work. Best Pract Res Clin Rheumatol. 2015;29:454-61.
  • Katz JN, Arant KR, Loeser RF. Diagnosis and treatment of hip and knee osteoarthritis: a review. JAMA. 2021;325:568-78.
  • Schock J, Truhn D, Abrar DB, Merhof D, Conrad S, Post M et al. Automated analysis of alignment in long-leg radiographs by using a fully automated support system based on artificial intelligence. Radiol Artif Intell. 2020;3:e200198.
  • Shamir L, Ling SM, Scott WW, Bos A, Orlov N, Macura TJ et al. Knee x-ray image analysis method for automated detection of osteoarthritis. IEEE Trans Biomed Eng. 2008;56:407-15.
  • Suresha S, Kidzin´ski L, Halilaj E, Gold G, Delp S. Automated staging of knee osteoarthritis severity using deep neural networks. Osteoarthritis Cartilage. 2018;26:S441.
  • Saleem M, Farid MS, Saleem S, Khan MH. X-ray image analysis for automated knee osteoarthritis detection. Signal Image Video Process. 2020;14:1079-87.
  • Chen P, Gao L, Shi X, Allen K, Yang L. Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss. Comput Med Imaging Graph. 2019;75:84-92.
  • Brahim A, Jennane R, Riad R, Janvier T, Khedher L, Toumi H et al. A decision support tool for early detection of knee osteoarthritis using X-ray imaging and machine learning: data from the osteoarthritis initiative. Comput Med Imaging Graph. 2019;73:11-8.
  • Shamir L, Ling SM, Scott W, Hochberg M, Ferrucci L, Goldberg IG. Early detection of radiographic knee osteoarthritis using computer-aided analysis. Osteoarthritis Cartilage. 2009;17:1307-12.
  • Alenazi AM, Alshehri MM, Alothman S, Alqahtani BA, Rucker J, Sharma N et al. The association of diabetes with knee pain severity and distribution in people with knee osteoarthritis using data from the osteoarthritis initiative. Sci Rep. 2020;10:3985.
  • Chen P. Knee Osteoarthritis Severity Grading Dataset. Mendeley Data. 2018.
  • Tolay P, Vajinepalli P, Bhattacharya P, Firtion C, Sisodia RS. Automated fetal spine detection in ultrasound images. Computer-Aided Diagnosis. vol. 7260. SPIE; 2009. p. 1054-63.
  • Davies-Tuck M, Wluka AE, Wang Y, Teichtahl A, Jones G, Ding C et al. The natural history of cartilage defects in people with knee osteoarthritis. Osteoarthritis and Cartilage. 2008;16:337-42.
  • Guo G, Wang H, Bell D, Bi Y, Greer K. KNN model-based approach in classification. In: On The Move to Meaningful Internet Syst 2003: CoopIS, DOA, and ODBASE: OTM Confed Int Conferences, CoopIS, DOA, and ODBASE 2003, Catania, Sicily, Italy, Nov 3-7, 2003. Proc. Springer; 2003.p. 986-96.
  • Zhang ML, Zhou ZH. ML-KNN: A lazy learning approach to multi-label learning. Pattern Recognit. 2007;40:2038-48.
  • Soucy P, Mineau GW. A simple KNN algorithm for text categorization. In: Proc 2001 IEEE Int Conf Data Min. IEEE; 2001:647-8.
  • Deng Z, Zhu X, Cheng D, Zong M, Zhang S. Efficient KNN classification algorithm for big data. Neurocomputing. 2016;195:143-8.
  • Xing W, Bei Y. Medical health big data classification based on KNN classification algorithm. IEEE Access. 2019;8:28808-19.
  • Bayramoglu N, Tiulpin A, Hirvasniemi J, Nieminen MT, Saarakkala S. Adaptive segmentation of knee radiographs for selecting the optimal ROI in texture analysis. Osteoarthritis Cartilage. 2020;28:941-52.
  • Olsson S, Akbarian E, Lind A, Razavian AS, Gordon M. Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population. BMC Musculoskelet Disord. 2021;22:1-8.
  • Thomson J, O’Neill T, Felson D, Cootes T. Automated shape and texture analysis for detection of osteoarthritis from radiographs of the knee. In: Med Image Comput Comput Assist Interv–MICCAI 2015: 18th Int Conf, Munich, Germany, October 5-9, 2015, Proceedings, Part II 18. Springer; 2015;127-34
There are 24 citations in total.

Details

Primary Language English
Subjects Clinical Sciences
Journal Section Research
Authors

Çağlar Cengizler 0000-0002-6699-5683

Ayşe Gül Kabakcı 0000-0001-7144-8759

Project Number -
Early Pub Date July 11, 2023
Publication Date July 2, 2023
Acceptance Date June 22, 2023
Published in Issue Year 2023 Volume: 48 Issue: 2

Cite

MLA Cengizler, Çağlar and Ayşe Gül Kabakcı. “A K-Nearest Neighbors-Based Classification Approach for Automated Detection of Knee Osteoarthritis”. Cukurova Medical Journal, vol. 48, no. 2, 2023, pp. 715-22, doi:10.17826/cumj.1281955.