Skip to main content
Erschienen in: Journal of Digital Imaging 3/2019

10.10.2018

Applying Densely Connected Convolutional Neural Networks for Staging Osteoarthritis Severity from Plain Radiographs

verfasst von: Berk Norman, Valentina Pedoia, Adam Noworolski, Thomas M. Link, Sharmila Majumdar

Erschienen in: Journal of Imaging Informatics in Medicine | Ausgabe 3/2019

Einloggen, um Zugang zu erhalten

Abstract

Osteoarthritis (OA) classification in the knee is most commonly done with radiographs using the 0–4 Kellgren Lawrence (KL) grading system where 0 is normal, 1 shows doubtful signs of OA, 2 is mild OA, 3 is moderate OA, and 4 is severe OA. KL grading is widely used for clinical assessment and diagnosis of OA, usually on a high volume of radiographs, making its automation highly relevant. We propose a fully automated algorithm for the detection of OA using KL gradings with a state-of-the-art neural network. Four thousand four hundred ninety bilateral PA fixed-flexion knee radiographs were collected from the Osteoarthritis Initiative dataset (age = 61.2 ± 9.2 years, BMI = 32.8 ± 15.9 kg/m2, 42/58 male/female split) for six different time points. The left and right knee joints were localized using a U-net model. These localized images were used to train an ensemble of DenseNet neural network architectures for the prediction of OA severity. This ensemble of DenseNets’ testing sensitivity rates of no OA, mild, moderate, and severe OA were 83.7, 70.2, 68.9, and 86.0% respectively. The corresponding specificity rates were 86.1, 83.8, 97.1, and 99.1%. Using saliency maps, we confirmed that the neural networks producing these results were in fact selecting the correct osteoarthritic features used in detection. These results suggest the use of our automatic classifier to assist radiologists in making more accurate and precise diagnosis with the increasing volume of radiographic image being taken in clinic.
Literatur
1.
Zurück zum Zitat Roos EM, Roos HP, Lohmander LS, Ekdahl C, Beynnon BD: Knee Injury and osteoarthritis outcome score (KOOS)—development of a self-administered outcome measure. J Orthop Sports Phys Ther 28(2):88–96, 1998CrossRefPubMed Roos EM, Roos HP, Lohmander LS, Ekdahl C, Beynnon BD: Knee Injury and osteoarthritis outcome score (KOOS)—development of a self-administered outcome measure. J Orthop Sports Phys Ther 28(2):88–96, 1998CrossRefPubMed
2.
Zurück zum Zitat Ackerman I: Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). Aust J Physiother 55(3):213, 2009CrossRefPubMed Ackerman I: Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). Aust J Physiother 55(3):213, 2009CrossRefPubMed
3.
Zurück zum Zitat Pelletier JP, Cooper C, Peterfy C, Reginster JY, Brandi ML, Bruyère O, Chapurlat R, Cicuttini F, Conaghan PG, Doherty M, Genant H, Giacovelli G, Hochberg MC, Hunter DJ, Kanis JA, Kloppenburg M, Laredo JD, McAlindon T, Nevitt M, Raynauld JP, Rizzoli R, Zilkens C, Roemer FW, Martel-Pelletier J, Guermazi A: What is the predictive value of MRI for the occurrence of knee replacement surgery in knee osteoarthritis? Ann Rheum Dis 72(10):1594–1604, 2013CrossRefPubMed Pelletier JP, Cooper C, Peterfy C, Reginster JY, Brandi ML, Bruyère O, Chapurlat R, Cicuttini F, Conaghan PG, Doherty M, Genant H, Giacovelli G, Hochberg MC, Hunter DJ, Kanis JA, Kloppenburg M, Laredo JD, McAlindon T, Nevitt M, Raynauld JP, Rizzoli R, Zilkens C, Roemer FW, Martel-Pelletier J, Guermazi A: What is the predictive value of MRI for the occurrence of knee replacement surgery in knee osteoarthritis? Ann Rheum Dis 72(10):1594–1604, 2013CrossRefPubMed
4.
Zurück zum Zitat Kohn MD, Sassoon AA, Fernando ND: Classifications in brief: Kellgren-Lawrence classification of osteoarthritis. Clin Orthop Relat Res 474(8):1886–1893, 2016CrossRefPubMedPubMedCentral Kohn MD, Sassoon AA, Fernando ND: Classifications in brief: Kellgren-Lawrence classification of osteoarthritis. Clin Orthop Relat Res 474(8):1886–1893, 2016CrossRefPubMedPubMedCentral
6.
Zurück zum Zitat Gunther KP, Sun Y: Reliability of radiographic assessment in hip and knee osteoarthritis. Osteoarthr Cartil 7(2):239–246, 1999CrossRef Gunther KP, Sun Y: Reliability of radiographic assessment in hip and knee osteoarthritis. Osteoarthr Cartil 7(2):239–246, 1999CrossRef
7.
Zurück zum Zitat Kallenberg M, Petersen K, Nielsen M, Ng AY, Diao P, Igel C, Vachon CM, Holland K, Winkel RR, Karssemeijer N, Lillholm M: Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring. IEEE Trans Med Imaging 35(5):1322–1331, 2016CrossRefPubMed Kallenberg M, Petersen K, Nielsen M, Ng AY, Diao P, Igel C, Vachon CM, Holland K, Winkel RR, Karssemeijer N, Lillholm M: Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring. IEEE Trans Med Imaging 35(5):1322–1331, 2016CrossRefPubMed
8.
Zurück zum Zitat Lee H, Grosse R, Ranganath R, Ng AY: Unsupervised learning of hierarchical representations with convolutional deep belief networks. Commun ACM 54(10):95–103, 2011CrossRef Lee H, Grosse R, Ranganath R, Ng AY: Unsupervised learning of hierarchical representations with convolutional deep belief networks. Commun ACM 54(10):95–103, 2011CrossRef
9.
Zurück zum Zitat Li XG, Hong CF, Yang YN, Wu XH: Deep neural networks for syllable based acoustic modeling in Chinese speech recognition. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (Apsipa), 2013 Li XG, Hong CF, Yang YN, Wu XH: Deep neural networks for syllable based acoustic modeling in Chinese speech recognition. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (Apsipa), 2013
10.
Zurück zum Zitat Hinton G, Deng L, Yu D, Dahl G, Mohamed AR, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath T, Kingsbury B: Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process Mag 29(6):82–97, 2012CrossRef Hinton G, Deng L, Yu D, Dahl G, Mohamed AR, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath T, Kingsbury B: Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process Mag 29(6):82–97, 2012CrossRef
11.
Zurück zum Zitat Pan J, Liu C, Wang ZG, Hu Y, Jiang H: Investigation of Deep Neural Networks (Dnn) for Large Vocabulary Continuous Speech Recognition: Why Dnn Surpasses Gmms in Acoustic Modeling. 2012 8th International Symposium on Chinese Spoken Language Processing, 2012, pp 301–305 Pan J, Liu C, Wang ZG, Hu Y, Jiang H: Investigation of Deep Neural Networks (Dnn) for Large Vocabulary Continuous Speech Recognition: Why Dnn Surpasses Gmms in Acoustic Modeling. 2012 8th International Symposium on Chinese Spoken Language Processing, 2012, pp 301–305
12.
Zurück zum Zitat Leung MKK, Delong A, Alipanahi B, Frey BJ: Machine learning in genomic medicine: a review of computational problems and data sets. Proc IEEE 104(1):176–197, 2016CrossRef Leung MKK, Delong A, Alipanahi B, Frey BJ: Machine learning in genomic medicine: a review of computational problems and data sets. Proc IEEE 104(1):176–197, 2016CrossRef
14.
Zurück zum Zitat Bengio Y, Lee H: Editorial introduction to the neural networks special issue on deep learning of representations. Neural Netw 64:1–3, 2015CrossRefPubMed Bengio Y, Lee H: Editorial introduction to the neural networks special issue on deep learning of representations. Neural Netw 64:1–3, 2015CrossRefPubMed
15.
Zurück zum Zitat Norman B, Pedoia V, Majumdar S: Use of 2D U-net convolutional neural networks for automated cartilage and meniscus segmentation of knee MR imaging data to determine relaxometry and morphometry. Radiology:172322, 2018 Norman B, Pedoia V, Majumdar S: Use of 2D U-net convolutional neural networks for automated cartilage and meniscus segmentation of knee MR imaging data to determine relaxometry and morphometry. Radiology:172322, 2018
16.
Zurück zum Zitat Gao Huang ZL, Kilian Q: Weinberger, Laurens van der Maaten. Densely connected convolutional networks. ARXIV;eprint arXiv:1608.06993:12, 2016 Gao Huang ZL, Kilian Q: Weinberger, Laurens van der Maaten. Densely connected convolutional networks. ARXIV;eprint arXiv:1608.06993:12, 2016
17.
Zurück zum Zitat Cheng JAB, Mark JL: The relative performance of ensemble methods with deep convolutional neural networks for image classification. arXiv:170401664, 2017 Cheng JAB, Mark JL: The relative performance of ensemble methods with deep convolutional neural networks for image classification. arXiv:170401664, 2017
18.
Zurück zum Zitat Karen Simonyan AV, Zisserman A: Deep inside convolutional networks: visualising image classification models and saliency maps. ARXIV;1312.6034v2, 2014 Karen Simonyan AV, Zisserman A: Deep inside convolutional networks: visualising image classification models and saliency maps. ARXIV;1312.6034v2, 2014
19.
Zurück zum Zitat Joseph Antony KM, Connor NEO, Moran K: Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks. Pattern Recogn:1195–1200, 2016 Joseph Antony KM, Connor NEO, Moran K: Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks. Pattern Recogn:1195–1200, 2016
20.
Zurück zum Zitat UCSF. Multicenter Osteoarthritis Study (MOST) UCSF. Multicenter Osteoarthritis Study (MOST)
21.
Zurück zum Zitat Wright RW, Group M: Osteoarthritis classification scales: interobserver reliability and arthroscopic correlation. J Bone Joint Surg Am 96(14):1145–1151, 2014CrossRefPubMedPubMedCentral Wright RW, Group M: Osteoarthritis classification scales: interobserver reliability and arthroscopic correlation. J Bone Joint Surg Am 96(14):1145–1151, 2014CrossRefPubMedPubMedCentral
22.
Zurück zum Zitat Gossec L, Jordan JM, Mazzuca SA, Lam MA, Suarez-Almazor ME, Renner JB, Lopez-Olivo MA, Hawker G, Dougados M, Maillefert JF, OARSI-OMERACT task force "total articular replacement as outcome measure in OA": Comparative evaluation of three semi-quantitative radiographic grading techniques for knee osteoarthritis in terms of validity and reproducibility in 1759 X-rays: report of the OARSI-OMERACT task force. Osteoarthr Cartil 16(7):742–748, 2008CrossRef Gossec L, Jordan JM, Mazzuca SA, Lam MA, Suarez-Almazor ME, Renner JB, Lopez-Olivo MA, Hawker G, Dougados M, Maillefert JF, OARSI-OMERACT task force "total articular replacement as outcome measure in OA": Comparative evaluation of three semi-quantitative radiographic grading techniques for knee osteoarthritis in terms of validity and reproducibility in 1759 X-rays: report of the OARSI-OMERACT task force. Osteoarthr Cartil 16(7):742–748, 2008CrossRef
Metadaten
Titel
Applying Densely Connected Convolutional Neural Networks for Staging Osteoarthritis Severity from Plain Radiographs
verfasst von
Berk Norman
Valentina Pedoia
Adam Noworolski
Thomas M. Link
Sharmila Majumdar
Publikationsdatum
10.10.2018
Verlag
Springer International Publishing
Erschienen in
Journal of Imaging Informatics in Medicine / Ausgabe 3/2019
Print ISSN: 2948-2925
Elektronische ISSN: 2948-2933
DOI
https://doi.org/10.1007/s10278-018-0098-3

Weitere Artikel der Ausgabe 3/2019

Journal of Digital Imaging 3/2019 Zur Ausgabe

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.