Top

European Radiology

Published in:

01-09-2020 | Imaging Informatics and Artificial Intelligence

Development of automatic measurement for patellar height based on deep learning and knee radiographs

Authors: Qin Ye, Qiang Shen, Wei Yang, Shuai Huang, Zhiqiang Jiang, Linyang He, Xiangyang Gong

Published in: European Radiology | Issue 9/2020

Abstract

Objectives

To develop and evaluate the performance of a deep learning–based system for automatic patellar height measurements using knee radiographs.

Methods

The deep learning–based algorithm was developed with a data set consisting of 1018 left knee radiographs for the prediction of patellar height parameters, specifically the Insall-Salvati index (ISI), Caton-Deschamps index (CDI), modified Caton-Deschamps index (MCDI), and Keerati index (KI). The performance and generalizability of the algorithm were tested with 200 left knee and 200 right knee radiographs, respectively. The intra-class correlation coefficient (ICC), Pearson correlation coefficient, mean absolute difference (MAD), root mean square (RMS), and Bland-Altman plots for predictions by the system were evaluated in comparison with manual measurements as the reference standard.

Results

Compared with the reference standard, the deep learning–based algorithm showed high accuracy in predicting the ISI, CDI, and KI (left knee ICC = 0.91–0.95, r = 0.84–0.91, MAD = 0.02–0.05, RMS = 0.02–0.07; right knee ICC = 0.87–0.96, r = 0.78–0.92, MAD = 0.02–0.06, RMS = 0.02–0.10), but not the MCDI (left knee ICC = 0.65, r = 0.50, MAD = 0.14, RMS = 0.18; right knee ICC = 0.62, r = 0.47, MAD = 0.15, RMS = 0.20). The performance of the algorithm met or exceeded that of manual determination of ISI, CDI, and KI by radiologists.

Conclusions

In its current state, the developed system can predict the ISI, CDI, and KI for both left and right knee radiographs as accurately as radiologists. Training the system further with more data would increase its utility in helping radiologists measure patellar height in clinical practice.

Key Points

• Objective and reliable measurement of patellar height parameters is important for clinical diagnosis and the development of a treatment strategy.

• Deep learning can be used to create an automatic patellar height measurement system based on knee radiographs.

• The deep learning–based patellar height measurement system achieves comparable performance to radiologists in measuring ISI, CDI, and KI.

Available only for authorised users

Chareancholvanich K, Narkbunnam R (2012) Novel method of measuring patellar height ratio using a distal femoral reference point. Int Orthop 36:749–753PubMedCrossRef

Caton J, Deschamps G, Chambat P, Lerat JL, Dejour H (1982) Patella infera. apropos of 128 cases. Rev Chir Orthop Reparatrice Appar Mot 68:317–325PubMed

Caton JH, Prudhon JL, Aslanian T, Verdier R (2016) Patellar height assessment in total knee arthroplasty: a new method. Int Orthop 40:2527–2531PubMedCrossRef

Biedert RM, Tscholl PM (2017) Patella alta: a comprehensive review of current knowledge. Am J Orthop (Belle Mead NJ) 46:290–300

Portner O, Pakzad H (2011) The evaluation of patellar height: a simple method. J Bone Joint Surg Am 93:73–80PubMedCrossRef

Saltzman BM, Rao A, Erickson BJ et al (2017) A systematic review of 21 tibial tubercle osteotomy studies and more than 1000 knees: indications, clinical outcomes, complications, and reoperations. Am J Orthop (Belle Mead NJ) 46:E396–E407

Smith TO, Davies L, Toms AP, Hing CB, Donell ST (2011) The reliability and validity of radiological assessment for patellar instability. A systematic review and meta-analysis. Skeletal Radiol 40:399–414PubMedCrossRef

Chen HC, Lin CJ, Wu CH, Wang CK, Sun YN (2010) Automatic Insall-Salvati ratio measurement on lateral knee X-ray images using model-guided landmark localization. Phys Med Biol 55:6785–6800PubMedCrossRef

Chen HC, Wu CH, Lin CJ, Liu YH, Sun YN (2009) Automated segmentation for patella from lateral knee X-ray images. Conf Proc IEEE Eng Med Biol Soc 2009:3553–3556

10.

Balakrishnan G, Zhao A, Sabuncu MR, Guttag J, Dalca AV (2019) VoxelMorph: a learning framework for deformable medical image registration. IEEE Trans Med Imaging. https://doi.org/10.1109/TMI.2019.2897538

11.

LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444PubMedCrossRef

12.

Olczak J, Fahlberg N, Maki A et al (2017) Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop 88:581–586PubMedPubMedCentralCrossRef

13.

Norman B, Pedoia V, Majumdar S (2018) 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 288:177–185PubMedCrossRef

14.

Chee CG, Kim Y, Kang Y et al (2019) Performance of a deep learning algorithm in detecting osteonecrosis of the femoral head on digital radiography: a comparison with assessments by radiologists. AJR Am J Roentgenol 27:1–8

15.

Larson DB, Chen MC, Lungren MP, Halabi SS, Stence NV, Langlotz CP (2018) Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology 287:313–322PubMedCrossRef

16.

Li Y, Huang Z, Dong X et al (2019) Forensic age estimation for pelvic X-ray images using deep learning. Eur Radiol 29:2322–2329PubMedCrossRef

17.

Alsinan AZ, Patel VM, Hacihaliloglu I (2019) Automatic segmentation of bone surfaces from ultrasound using a filter-layer-guided CNN. Int J Comput Assist Radiol Surg 14:775–783PubMedCrossRef

18.

Al Arif SMMR, Knapp K, Slabaugh G (2018) Fully automatic cervical vertebrae segmentation framework for X-ray images. Comput Methods Programs Biomed 157:95–111PubMedCrossRef

19.

Klein A, Warszawski J, Hillengaß J, Maier-Hein KH (2019) Automatic bone segmentation in whole-body CT images. Int J Comput Assist Radiol Surg 14:21–29PubMedCrossRef

20.

Li X, Dou Q, Chen H et al (2018) 3D multi-scale FCN with random modality voxel dropout learning for intervertebral disc localization and segmentation from multi-modality MR images. Med Image Anal 45:41–54PubMedCrossRef

21.

Galbusera F, Niemeyer F, Wilke HJ et al (2019) Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach. Eur Spine J 28:951–960PubMedCrossRef

22.

Liao S, Zhan Y, Dong Z et al (2016) Automatic lumbar spondylolisthesis measurement in CT images. IEEE Trans Med Imaging 35:1658–1669

23.

Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: arXiv e-prints. Available via https://arxiv.org/abs/1505.04597. Accessed 18 May 2019

24.

Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: arXiv e-prints. Available via https://arXiv.org/abs/1409.1556. Accessed 24 May 2019

25.

Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10). pp 807-814

26.

Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: arXiv e-prints. Available via http://arxiv.org/abs/1502.03167. Accessed 18 May 2019

27.

Simonyan K, Vedaldi A, Zisserman A (2013) Deep inside convolutional networks: Visualising image classification models and saliency maps. In: arXiv e-prints. Available via https://arxiv.org/abs/1312.6034. Accessed 24 May 2019

28.

Russakovsky O, Deng J, Su H, et al (2014) ImageNet large scale visual recognition challenge. In: arXiv e-prints. Available via http://arxiv.org/abs/1409.0575. Accessed 24 May 2019

29.

Shin HC, Roth HR, Gao M et al (2016) Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35:1285–1298PubMedCrossRef

30.

Tajbakhsh N, Shin JY, Gurudu SR et al (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 35:1299–1312PubMedCrossRef

31.

Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. In: arXiv e-prints. Available via https://arxiv.org/abs/1412.6980. Accessed 24 May 2019

32.

Chen Y, Wang Z, Peng Y, Zhang Z, Yu G, Sun J (2017) Cascaded pyramid network for multi-person pose estimation. In: arXiv e-prints. Available via https://arxiv.org/abs/1711.07319. Accessed 18 May 2019

33.

Li W, Wang Z, Yin B et al (2019) Rethinking on multi-stage networks for human pose estimation. In: arXiv e-prints. Available via https://arxiv.org/abs/1901.00148. Accessed 27 May 2019

34.

Payer C, Štern D, Bischof H, Urschler M (2019) Integrating spatial configuration into heatmap regression based CNNs for landmark localization. Med Image Anal 54:207–219PubMedCrossRef

35.

Tiulpin A, Melekhov I, Saarakkala S (2019) KNEEL: knee anatomical landmark localization using hourglass networks. In: arXiv e-prints. Available via https://arxiv.org/abs/1907.12237. Accessed 25 Nov 2019

36.

Koo TK, Li MY (2016) A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med 15:155–163PubMedPubMedCentralCrossRef

37.

Bland JM, Altman DG (1986) Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 1:307–310PubMedCrossRef

38.

Lindner C, Bromiley PA, Ionita MC, Cootes TF (2015) Robust and accurate shape model matching using random forest regression-voting. IEEE Trans Pattern Anal Mach Intell 37:1862–1874PubMedCrossRef

Title: Development of automatic measurement for patellar height based on deep learning and knee radiographs
Authors: Qin Ye
Qiang Shen
Wei Yang
Shuai Huang
Zhiqiang Jiang
Linyang He
Xiangyang Gong
Publication date: 01-09-2020
Publisher: Springer Berlin Heidelberg
Published in: European Radiology / Issue 9/2020
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-020-06856-z

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Development of automatic measurement for patellar height based on deep learning and knee radiographs

Abstract

Objectives

Methods

Results

Conclusions

Key Points

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Please log in to get access to this content

Other articles of this Issue 9/2020

Research progress on mechanism and dosimetry of brainstem injury induced by intensity-modulated radiotherapy, proton therapy, and heavy ion radiotherapy

Magnetic resonance imaging features in 283 patients with primary biliary cholangitis

Prospective comparison of longitudinal change in hepatic proton density fat fraction (PDFF) estimated by magnitude-based MRI (MRI-M) and complex-based MRI (MRI-C)

Outcome prediction in resectable lung adenocarcinoma patients: value of CT radiomics

High spatiotemporal resolution dynamic contrast-enhanced MRI improves the image-based discrimination of histopathology risk groups of peripheral zone prostate cancer: a supervised machine learning approach

Intraoperative imaging findings in transcranial MR imaging-guided focused ultrasound treatment at 1.5T may accurately detect typical lesional findings correlated with sonication parameters