Digital X-ray imaging is essential for diagnosing osteoporosis, but distinguishing affected patients from healthy individuals using these images remains challenging.
OBJECTIVE:
This study introduces a novel method using deep learning to improve osteoporosis diagnosis from bone X-ray images.
METHODS:
A dataset of bone X-ray images was analyzed using a newly proposed procedure. This procedure involves segregating the images into regions of interest (ROI) and non-ROI, thereby reducing data redundancy. The images were then processed to enhance both spatial and statistical features. For classification, a Support Vector Machine (SVM) classifier was employed to distinguish between osteoporotic and non-osteoporotic cases.
RESULTS:
The proposed method demonstrated a promising Area under the Curve (AUC) of 90.8% in diagnosing osteoporosis, benchmarking favorably against existing techniques. This signifies a high level of accuracy in distinguishing osteoporosis patients from healthy controls.
CONCLUSIONS:
The proposed method effectively distinguishes between osteoporotic and non-osteoporotic cases using bone X-ray images. By enhancing image features and employing SVM classification, the technique offers a promising tool for efficient and accurate osteoporosis diagnosis.
ChenS., MulgrewB., GrantP.M., A clustering technique for digital communications channel equalization using radial basis function networks, IEEE Trans Neural Netw4 (1993), 570–590.
KanisJ.A., Diagnosis of osteoporosis and assessment of fracture risk, Lancet359 (2002), 1929–1936.
4.
HassouniM.E., TafraoutiA., ToumiH., LespessaillesE., JennaneR., Fractional Brownian motion and rao geodesic distance for bone X-ray image characterization, IEEE J Biomed Health Inform21 (2016), 1347–1359.
5.
PothuaudL., LespessaillesE., HarbaR., JennaneR., RoyantV., EynardE., BenhamouC.L., Fractal analysis of trabecular bone texture on radiographs: discriminant value in postmenopausal osteoporosis, Osteoporos Int8 (1998), 618–626.
6.
BenhamouC.L., PouponS., LespessaillesE., LoiseauS., JennaneR., SirouxV., OhleyW., PothuaudL., Fractal analysis of radiographic trabecular bone texture and bone mineral density: two complementary parameters related to osteoporotic fractures, J Bone Miner Res16 (2001), 697–704.
7.
LundahlT., OhleyW.J., KayS.M., SiffertR., Fractional Brownian motion: a maximum likelihood estimator and its application to image texture, IEEE Trans Med Imaging5 (1986), 152–161.
8.
TafraoutiA., HassouniM.E., ToumiH., LespessaillesE., JennaneR.Osteoporosis diagnosis using steerable pyramid decomposition and fractional Brownian motion. In: 2015 International Conference on Image Processing Theory, Tools and Applications (IPTA). IEEE, Orleans, France (2015), pp. 309–312.
9.
JanvierT., ToumiH., HarrarK., LespessaillesE., JennaneR.ROI impact on the characterization of knee osteoarthritis using fractal analysis. In: 2015 International Conference on Image Processing Theory, Tools and Applications (IPTA). IEEE, Orleans, France, 2015, pp. 304–308.
HouamL., HafianeA., BoukroucheA., LespessaillesE., JennaneR., One dimensional local binary pattern for bone texture characterization, Pattern Anal Appl17 (2014), 179–193.
12.
OulhajH., RzizaM., AmineA., ToumiH., LespessaillesE., JennaneR., ElM., Hassouni, Trabecular bone characterization using circular parametric models, Biomed Signal Process Control33 (2016), 411–421.
13.
NamK.H., SeoI., KimD.H., LeeJ.I., ChoiB.K., HanI.H., Machine learning model to predict osteoporotic spine with hounsfield units on lumbar computed tomography, J Korean Neurosurg Soc62 (2019), 442–449.
14.
YasakaK., AkaiH., KunimatsuA., KiryuS., AbeO., Prediction of bone mineral density from computed tomography: application of deep learning with a convolutional neural network, Eur Radiol30 (2020), 3549–3557.
15.
RastegarS., VaziriM., QasempourY., AkhashM.R., AbdalvandN., ShiriI., AbdollahiH., ZaidiH., Radiomics for classification of bone mineral loss: a machine learning study, Diagn Interv Imaging101 (2020), 599–610.
16.
ZhangB., YuK., NingZ., WangK., DongY., et al. Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: a multicenter retrospective cohort study, Bone153 (2021), 116143.
17.
WaniI.M., AroraS., Computer-aided diagnosis systems for osteoporosis detection: a comprehensive survey, Med Biol Eng Comput58 (2020), 1873–1917.
18.
SmithA.D., Screening of bone density at CT: an overlooked opportunity, Radiology291 (2019), 368–369.
19.
SozenT., OzisikL., BasaranN.C., An overview and management of osteoporosis, Eur J Rheumatol4 (2017), 46–56.
20.
LoganathanR., KumaraswamyY.S.Animproved active contour medical image compression technique with lossless region of interest. In: 3rd International Conference on Trendz in Information Sciences & Computing (TISC2011). IEEE, Chennai, India, (2011), pp. 128–132.
21.
GonzalezR.C., WoodsR.E., EddinsS.L.Digital Image Processing Using MATLAB. Pearson Education India, India 2004.
22.
AdamsR., BischofL., Seeded region growing, IEEE Trans Pattern Anal Mach Intell16 (1994), 641–647.
23.
RufaiA.M., AnbarjafariG., DemirelH.Lossy medical image compression using Huffman coding and singular value decomposition. In: 2013 21st Signal Processing and Communications Applications Conference (SIU). IEEE, Haspolat, Turkey, (2013), pp. 1–4.
24.
SepehrbandF., MortazaviM., GhorshiS., ChoupanJ.Simple lossless and near-lossless medical image compression based on enhanced DPCM transformation. In: Proceedings of 2011 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing. IEEE, Victoria, BC, Canada 2011, pp. 66–72.
25.
Bartrina-RapestaJ., Serra-SagristaJ., Auli-LlinasF., GomezJ.M.JPEG2000 ROI coding method with perfect fine-grain accuracy and lossless recovery. In: 2009 Conference Record of the Forty-Third Asilomar Conference on Signals, Systems and Computers. IEEE, Pacific Grove, CA, USA 2009, pp. 558–562.
26.
OlshausenB.A., FieldD.J., Sparse coding with an overcomplete basis set: a strategy employed by V1?Vis Res37 (1997), 3311–3325.
27.
HintonG.E., A practical guide to training restricted boltzmann machines, Momentum9 (2012), 926.
28.
MøllerM.F., A scaled conjugate gradient algorithm for fast supervised learning, Neural Netw6 (1993), 525–533.
29.
LarochelleH., BengioY., LouradourJ., LamblinP., Exploring strategies for training deep neural networks, J Mach Learn Res10 (2009), 1–40.
30.
BengioY., LamblinP., PopoviciD., LarochelleH.Greedy layer-wise training of deep networks. In: B. Scholkopf, J. Platt, T. Hofmann (eds) Advances in Neural Information Processing Systems 19. The MIT Press, Cambridge, 2007, pp. 153–160.
31.
ZuiderveldK.Contrast limited adaptive histogram equalization. In: Graphic Gems IV. Academic Press Professional, San Diego, 1994, pp. 474–485.
BurrowsM., WheelerD.J.A Block-Sorting Lossless Data Compression Algorithm, Technical Report 124. Digital Systems Research Center, California, USA 1994.
34.
KarimiN., SamaviS., AmraeeS., ShiraniS., Use of symmetry in prediction-error field for lossless compression of 3D MRI images, Multimed Tools Appl74 (2014), 11007–11022.
35.
KarimiN., SamaviS., MahmoodzadehE., ShiraniS., Lossless compression of mammographic images with region-based predictor selection, IEEJ Trans Electr Electron Eng8 (2013), 478–482.
36.
SpeckD.Proposal for Next Generation Lossless Compression of Continuous-Tone Still Pictures: Activity Level Classification Model (ALCM), ISO Working Document ISO/IEC JTCI/SC29/WGl N198 1995.
