Abstract

For standard “off-the-shelf” knee replacement procedures, surgeons use X-ray images to aid implant selection from a limited number of models and sizes. This can lead to complications and the need for implant revision due to poor implant fit. Customized solutions have been shown to improve results but require increased preoperative assessment (Computed Tomography or Magnetic Resonance Imaging), longer lead times, and higher costs which have prevented widespread adoption. To attain the benefits of custom implants, whilst avoiding the limitations of currently available solutions, a fully automated mass-customization pipeline, capable of developing customized implant designs for fabrication via additive manufacturing from calibrated X-rays, is proposed. The proof-of-concept pipeline uses convolutional neural networks to extract information from biplanar X-ray images, point depth, and statistical shape models to reconstruct the anatomy, and application programming interface scripts to generate various customized implant designs. The pipeline was trained using data from the Korea Institute of Science and Technology Information. Thirty subjects were used to test the accuracy of the anatomical reconstruction, ten from this data set, and a further 20 independent subjects obtained from the Osteoarthritis Initiative. An average root-mean-squared error of 1.00 mm was found for the femur test cases and 1.07 mm for the tibia. Three-dimensional (3D) distance maps of the output components demonstrated these results corresponded to well-fitting components, verifying automatic customization of knee replacement implants is feasible from 2D medical imaging.

References

1.
Stewart
,
C.
,
2019
, Demand for Knee Replacement Grows 5 Percent Worldwide, https://orthospinenews.com/2019/06/04/demand-for-knee-replacement-grows-5-percent-worldwide/.
2.
Postler
,
A.
,
Lützner
,
C.
,
Beyer
,
F.
,
Tille
,
E.
, and
Lützner
,
J.
, “
Analysis of Total Knee Arthroplasty Revision Causes
,”
BMC Musculoskeletal Disorders
,
19
(
1
), pp.
1
6
.
3.
Tanzer
,
M.
, and
Makhdom
,
A. M.
,
2016
, “
Preoperative Planning in Primary Total Knee Arthroplasty
,”
J. Am. Acad. Orthopaedic Surgeons
,
24
(
4
), pp.
220
230
.
4.
O’Connor
,
M.
, and
Kransdorf
,
M.
,
2013
, “
Customized Knee Arthroplasty and the Role of Preoperative Imaging
,”
Musculoskeletal Imaging
,
201
(
3
), pp.
443
450
.
5.
Hernandez-Vaquero
,
D.
,
Abat
,
F.
,
Sarasquete
,
J.
, and
Monllau
,
J. C.
,
2013
, “
Reliability of Preoperative Measurement With Standardized Templating in Total Knee Arthroplasty
,”
World J. Orthopaedics
,
4
(
4
), pp.
287
290
.
6.
ConforMIS
,
2021
, Knee and Hip Replacements for Each Patient’s Unique Anatomy. https://www.conformis.com/.
7.
Schroeder
,
L.
, and
Martin
,
G.
,
2019
, “
In vivo Tibial Fit and Rotational Analysis of a Customized, Patient-Specific TKA Versus Off-the-Shelf TKA
,”
J. Knee Surgery
,
32
(
6
), pp.
499
505
.
8.
ConforMIS
,
2018
,
Implant Summary Report for the ITotal G2XE and ITotal G2 (Bicondylar Tray). Beyond Compliance Database
,
Northgate Public Services (UK) Ltd.
,
Cambridge, UK
.
9.
Evers
,
M.
,
2019
, Robotics, ASCs Will Continue to Drive Knee Replacement Market Trends. Orthoworld. https://www.orthoworld.com/robotics-ascs-will-continue-to-drive-knee-market-trends/.
10.
Seeking Alpha
,
2019
,
Conformis Is a Failed Market Experiment, No Justification for Its 400%+ Rally—$0.50 Price Target
,
Seeking Alpha
,
New York
.
11.
Cernazanu-Glavan
,
C.
, and
Holban
,
S.
,
2013
, “
Segmentation of Bone Structure in X-ray Images Using Convolutional Neural Network
,”
Adv. Electr. Comput. Eng.
,
13
(
1
), pp.
87
94
.
12.
Liu
,
C.
,
Cao
,
Y.
,
Alcantara
,
M.
,
Liu
,
B.
,
Brunette
,
M.
,
Peinado
,
J.
, and
Curioso
,
W.
,
2018
, “
TX-CNN: Detecting Tuberculosis in Chest X-ray Images Using Convolutional Neural Network
,”
Proceedings—International Conference on Image Processing.
,
Beijing, China
,
Sept. 17–20
, pp.
2314
2318
.
13.
Kasten
,
Y.
,
Doktofsky
,
D.
, and
Kovler
,
I.
,
2020
, “
End-to-End Convolutional Neural Network for 3D Reconstruction of Knee Bones From Bi-planar X-Ray Images
,”
Machine Learning Med. Image Reconstr.
,
12450
, pp.
123
133
.
14.
Terzopoulos
,
D.
, and
Fleischer
,
K.
,
1988
, “
Deformable Models
,”
Visual Comput.
,
4
(
6
), pp.
306
331
.
15.
Zhu
,
Z.
, and
Li
,
G.
,
2011
, “
Construction of 3D Human Distal Femoral Surface Models Using a 3D Statistical Deformable Model
,”
J. Biomech.
,
44
(
13
), pp.
2362
2368
.
16.
Tsai
,
T. Y.
,
Li
,
J. S.
,
Wang
,
S.
,
Li
,
P.
, and
Kwon
,
Y.
,
2015
, “
Principal Component Analysis in Construction of 3D Human Knee Joint Models Using a Statistical Shape Model Method
,”
Comput. Meth. Biomech. Biomed. Eng.
,
18
(
7
), pp.
721
729
.
17.
Baka
,
N.
,
Kapteina
,
B. L.
,
Giphartb
,
J. E.
,
Staring
,
M.
,
de Bruijne
,
M.
,
Lelieveldt
,
B. P. F.
, and
Valstar
,
E.
,
2014
, “
Evaluation of Automated Statistical Shape Model Based Knee Kinematics From Biplane Fluoroscopy
,”
J. Biomech.
,
47
(
1
), pp.
122
129
.
18.
Tuck
,
C. R.
,
Hague
,
R. J. M.
,
Ruffo
,
M.
,
Ransley
,
M.
, and
Adams
,
P.
,
2008
, “
Rapid Manufacturing Facilitated Customization
,”
Int. J. Comput. Integr. Manuf.
,
21
(
3
), pp.
245
258
.
19.
Gandhi
,
A.
,
Magar
,
C.
, and
Roberts
,
R.
,
2013
, “
How Technology Can Drive the Next Wave of Mass Customization
,”
McKinsey on Business Technology
,
32
, pp.
1
9
.
20.
Javaid
,
M.
, and
Haleem
,
A.
,
2018
, “
Additive Manufacturing Applications in Medical Cases: A Literature Based Review
,”
Alexandria J. Med.
,
54
(
4
), pp.
411
422
.
21.
Jun
,
Y.
,
2011
, “
Morphological Analysis of the Human Knee Joint for Creating Custom-Made Implant Models
,”
Int. J. Adv. Manuf. Technol.
,
52
(
9–12
), pp.
841
853
.
22.
He
,
Y.
,
Ye
,
M.
, and
Wang
,
C.
,
2006
, “
A Method in the Design and Fabrication of Exact-Fit Customized Implant Based on Sectional Medical Images and Rapid Prototyping Technology
,”
Int. J. Adv. Manuf. Technol.
,
28
(
5–6
), pp.
504
508
.
23.
Cronskär
,
M.
,
Rännar
,
L. E.
,
Bäckström
,
M.
,
Nilsson
,
K. G.
, and
Samuelsson
,
B.
,
2015
, “
Patient-Specific Clavicle Reconstruction Using Digital Design and Additive Manufacturing
,”
ASME J. Mech. Des.
,
137
(
11
), p.
111418
.
24.
Pallari
,
J. H. P.
,
Dalgarno
,
K. W.
, and
Woodburn
,
J.
,
2010
, “
Mass Customization of Foot Orthoses for Rheumatoid Arthritis Using Selective Laser Mass Customization of Foot Orthoses for Rheumatoid Arthritis Using Selective Laser Sintering
,”
IEEE Trans. Biomed. Eng.
,
57
, pp.
1750
1756
.
25.
Yu
,
Z.
,
Shea
,
K.
, and
Stankovic
,
T.
,
2019
, “
A Computational Method for the Design of an Additively Manufactured Personalized Artificial Spinal Disc With Physiological Stiffness Under Multiple Loading Conditions
,”
ASME J. Mech. Des.
,
141
(
10
), p.
101406
.
26.
Li
,
S.
,
Ploumpis
,
S.
,
Zafeiriou
,
S.
, and
Myant
,
C.
,
2020
, “
Design Automation for Mass Customisation via Additive Manufacture: A Case Study on Continuous Positive Airway Pressure Mask
,”
Proceedings of the ASME 2020 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference.
,
Virtual, Online
,
Aug. 17–19
, pp.
1
7
.
27.
Cerveri
,
P.
,
Sacco
,
C.
,
Olgiati
,
G.
,
Manzotti
,
A.
, and
Baroni
,
G.
,
2017
, “
2D/3D Reconstruction of the Distal Femur Using Statistical Shape Models Addressing Personalized Surgical Instruments in Knee Arthroplasty: A Feasibility Analysis
,”
Int. J. Med. Robot. Comput. Assist. Surg.
,
13
(
4
), pp.
1
13
.
28.
Berg
,
S.
,
Kutra
,
D.
,
Kroeger
,
T.
,
Straehle
,
C.
, and
Kausler
,
B. X.
,
2019
, “
Ilastik: Interactive Machine Learning for (bio)Image Analysis
,”
Nat. Meth.
,
16
, pp.
1226
1232
.
29.
Nolte
,
D.
,
Ko
,
S.-T.
,
Bull
,
A. M. J.
, and
Kedgley
,
A. E.
,
2020
, “
Reconstruction of the Lower Limb Bones From Digitised Anatomical Landmarks Using Statistical Shape Modelling
,”
Gait Posture
,
77
, pp.
269
275
.
30.
Lee
,
S. H.
, and
Lee
,
S. B.
,
2010
, “
Production and Usage of Korean Human Information in KISTI
,”
J. Korea Contents Association
,
10
(
5
), pp.
416
421
.
31.
Nevitt
,
M.
,
Felson
,
D.
, and
Lester
,
G.
,
2006
,
The Osteoarthritis Initiative: Protocol for the Cohort Study
,
The Osteoarthritis Initiative
.
32.
Fedorov
,
A.
,
Beichel
,
R.
,
Kalpathy-Cramer
,
J.
, and
Finet
,
J.
,
2012
, “
3D Slicer as an Image Computing Platform for the Quantitative Imaging Network
,”
Magn. Reson. Imaging
,
30
(
9
), pp.
1323
1341
.
33.
Van den Broeck
,
J.
,
Vereecke
,
E.
,
Wirix-Speetjens
,
R.
, and
Sloten
,
J. V.
,
2014
, “
Segmentation Accuracy of Long Bones
,”
Med. Eng. Phys.
,
36
(
7
), pp.
949
953
.
34.
Wimsey
,
S.
,
Pickard
,
R.
, and
Shaw
,
G.
,
2006
, “
Accurate Scaling of Digital Radiographs of the Pelvis. A Prospective Trial of Two Methods
,”
J. Bone Joint Surgery—Ser. B
,
88
(
11
), pp.
1508
1512
.
35.
Schumann
,
S.
,
Thelen
,
B.
,
Ballestra
,
S.
,
Nolte
,
L.
,
Büchler
,
P.
, and
Zheng
,
G.
,
2014
, “
X-Ray Image Calibration and Its Application to Clinical Orthopedics
,”
Med. Eng. Phys.
,
36
(
7
), pp.
968
974
.
36.
Rasband
,
W. S.
,
1997-2018
,
ImageJ. U. S
,
National Institutes of Health
,
Bethesda, MD
. https://imagej.nih.gov/ij/.
37.
Moturu
,
A.
, and
Chang
,
A.
,
2018
,
Creation of Synthetic X-Rays to Train a Neural Network to Detect Lung Cancer
,
Department of Computer Science, University of Toronto
,
Toronto, ON, Canada
. http://www.cs.toronto.edu/pub/reports/na/Project_Report_Moturu_Chang_1.pdf.
38.
Shubhangi
,
D. C.
,
Chinchansoor
,
R. S.
, and
Hiremath
,
P. S.
,
2012
, “
Edge Detection of Femur Bones in X-Ray Images a Comparative Study of Edge Detectors
,”
Int. J. Comput. Appl.
,
42
(
2
), pp.
13
16
.
39.
Machado
,
F.
,
Malpica
,
N.
, and
Borromeo
,
S.
,
2019
, “
Parametric CAD Modeling for Open Source Scientific Hardware: Comparing OpenSCAD and FreeCAD Python Scripts
,”
PLoS One
,
14
(
12
), pp.
1
30
.
40.
Buller
,
L. T.
,
Menken
,
L.
, and
Rodriguez
,
J. A.
,
2018
, “
The Custom Total Knee Replacement: A Bespoke Solution
,”
Seminars Arthroplasty
,
29
(
3
), pp.
209
213
.
41.
Ferguson
,
S. M.
,
Olewnik
,
A. T.
, and
Cormier
,
P.
,
2014
, “
A Review of Mass Customization Across Marketing, Engineering and Distribution Domains Toward Development of a Process Framework
,”
Res. Eng. Des.
,
25
(
1
), pp.
11
30
.
42.
Laureijs
,
R. E.
,
Fuchs
,
E. R. H.
, and
Whitefoot
,
K. S.
,
2019
, “
Is More Less? Benefits and Costs of High-Variety Production in Nonassembled Manufacturing
,”
ASME J. Mech. Des.
,
141
(
6
), p.
061703
.
43.
Mattheijer
,
J.
,
Herder
,
J. L.
,
Tuijthof
,
G. J. M.
,
Nelissen
,
R. G. H. H.
,
Dankelman
,
J.
, and
Valstar
,
E. R.
,
2013
, “
Shaping Patient Specific Surgical Guides for Arthroplasty to Obtain High Docking Robustness
,”
ASME J. Mech. Des.
,
135
(
7
), p.
071001
.
44.
Ghouse
,
S.
,
Reznikov
,
N.
,
Boughton
,
O. R.
,
Babu
,
S.
,
Ng
,
G.
,
Blunn
,
G.
,
Cobb
,
J. P.
,
Stevens
,
M. M.
, and
Jeffers
,
J.
,
2019
, “
The Design and In vivo Testing of a Locally Stiffness-Matched Porous Scaffold
,”
Appl. Mater. Today
,
15
, pp.
377
388
.
45.
Wang
,
Y.
,
Arabnejad
,
S.
,
Tanzer
,
M.
, and
Pasini
,
D.
,
2018
, “
Hip Implant Design With Three-Dimensional Porous Architecture of Optimized Graded Density
,”
ASME J. Mech. Des.
,
140
(
11
), pp.
111406
.
You do not currently have access to this content.