Abstract

Machine learning is a powerful tool that can be applied to pattern search and mathematical optimization for making predictions on new data with unknown labels. In the field of medical imaging, one challenge with applying machine learning techniques is the limited size and relative expense of obtaining labeled data. For example, in glenoid labral tears, current imaging diagnosis is best achieved by imaging through magnetic resonance (MR) arthrography, a method of injecting contrast-enhancing material into the joint that can potentially cause discomfort to the patient, and adds expense compared to a standard magnetic resonance image (MRI). This work proposes limiting the use of MR arthrography through a medical diagnostic approach, based on convolutional neural networks (CNNs) and transfer learning from a separate medical imaging dataset to improve the efficiency and effectiveness. The results indicate an effective method applied to a small dataset of unenhanced shoulder MRI in order to diagnose labral tear severity while potentially significantly reducing cost and reducing unnecessary invasive imaging techniques. The proposed method ultimately can reduce physician workload while ensuring that the least number of patients as possible need to be subjected to an additional invasive contrast-enhanced imaging procedure.

References

References
1.
Whiting
,
M.
,
Cagan
,
J.
, and
LeDuc
,
P.
,
2016
, “Efficient Probabilistic Grammar Induction for Design,” AI EDAM,
32
(2), pp.
177
188
.
2.
Szegedy
,
C.
,
Liu
,
W.
,
Jia
,
Y.
,
Sermanet
,
P.
,
Reed
,
S.
,
Anguelov
,
D.
,
Erhan
,
D.
,
Vanhoucke
,
V.
, and
Rabinovich
,
A.
,
2015
, “
Going Deeper With Convolutions
,”
IEEE Computer Society Conference on Computer Vision and Pattern Recognition
(
CVPR
),
Boston, MA
,
June 7–12
, pp.
1
9
.10.1109/CVPR.2015.7298594
3.
Szegedy
,
C.
,
Vanhoucke
,
V.
,
Ioffe
,
S.
,
Shlens
,
J.
, and
Wojna
,
Z.
,
2016
, “
Rethinking the Inception Architecture for Computer Vision
,” Conference on Computer Vision and Pattern Recognition (
CVPR
), June 27–30, Las Vegas, NV, pp.
2818
2826
.10.1109/CVPR.2016.308
4.
Fleuret
,
F.
,
Li
,
T.
,
Dubout
,
C.
,
Wampler
,
E. K.
,
Yantis
,
S.
, and
Geman
,
D.
,
2011
, “
Comparing Machines and Humans on a Visual Categorization Test
,”
Proc. Natl. Acad. Sci.
,
108
(
43
), pp.
17621
17625
.10.1073/pnas.1109168108
5.
Lo
,
S.-C. B.
,
Lou
,
S.-L. A.
,
Lin
,
J.-S.
,
Freedman
,
M. T.
,
Chien
,
M. V.
, and
Mun
,
S. K.
,
1995
, “
Artificial Convolution Neural Network Techniques and Applications for Lung Nodule Detection
,”
IEEE Trans. Med. Imaging
,
14
(
4
), pp.
711
718
.10.1109/42.476112
6.
Alkabawi
,
E. M.
,
Hilal
,
A. R.
, and
Basir
,
O. A.
,
2017
, “
Computer-Aided Classification of Multi-Types of Dementia Via Convolutional Neural Networks
,”
IEEE International Symposium on Medical Measurements and Applications
(
MeMeA
),
Rochester, MN
,
May 7–10
, pp.
45
50
.10.1109/MeMeA.2017.7985847
7.
Roth
,
H. R.
,
Le Lu
,
A. S.
,
Cherry
,
K. M.
,
Hoffman
,
J.
,
Wang
,
S.
,
Liu
,
J.
,
Turkbey
,
E.
, and
Summers
,
R. M.
,
2014
, “
A New 2.5D Representation for Lymph Node Detection Using Random Sets of Deep Convolutional Neural Network Observations
,”
International Conference on Medical Image Computing and Computer-Assisted Intervention
, Boston, MA, Sept. 14–18, pp.
520
527
.10.1007/978-3-319-10404-1_65
8.
Zheng
,
Y.
,
Liu
,
D.
,
Georgescu
,
B.
,
Nguyen
,
H.
, and
Comaniciu
,
D.
,
2015
, “
3D Deep Learning for Efficient and Robust Landmark Detection in Volumetric Data BT—Medical Image Computing and Computer-Assisted Intervention
,”
International Conference on Medical Image Computing and Computer-Assisted Intervention
,
Cham, Switzerland, Munich, Germany
,
Oct. 5–9
, pp.
565
572
.
9.
Havaei
,
M.
,
Davy
,
A.
,
Warde-Farley
,
D.
,
Biard
,
A.
,
Courville
,
A.
,
Bengio
,
Y.
,
Pal
,
C.
,
Jodoin
,
P.-M.
, and
Larochelle
,
H.
,
2017
, “
Brain Tumor Segmentation With Deep Neural Networks
,”
Med. Image Anal.
,
35
(
Suppl. C
), pp.
18
31
.10.1016/j.media.2016.05.004
10.
Azizpour
,
H.
,
Razavian
,
A. S.
,
Sullivan
,
J.
,
Maki
,
A.
, and
Carlsson
,
S.
,
2015
, “
From Generic to Specific Deep Representations for Visual Recognition
,”
IEEE Conference on Computer Vision and Pattern Recognition Workshops
(
CVPRW
),
Boston, MA
,
June 7–12
, pp.
36
45
.10.1109/CVPRW.2015.7301270
11.
Razavian
,
A.
,
Azizpour
,
H.
,
Sullivan
,
J.
, and
Carlsson
,
S.
,
2014
, “
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
,”
IEEE Conference on Computer Vision and Pattern Recognition Workshops
(
CVPRW
),
Columbus, OH
,
June 23–28
, pp.
806
813
.10.1109/CVPRW.2014.131
12.
Penatti
,
O. A. B.
,
Nogueira
,
K.
, and
Santos
,
J. A. D.
,
2015
, “
Do Deep Features Generalize From Everyday Objects to Remote Sensing and Aerial Scenes Domains?
,”
IEEE Conference on Computer Vision and Pattern Recognition Workshops
(
CVPRW
),
Boston, MA
,
June 7–12
, pp.
44
51
.10.1109/CVPRW.2015.7301382
13.
Olah
,
C.
,
Mordvintsev
,
A.
, and
Schubert
,
L.
,
2017
, “
Feature Visualization
,”
Distill
,
2
(
11
), p. 1.10.23915/distill.00007
14.
Tajbakhsh
,
N.
,
Shin
,
J. Y.
,
Gurudu
,
S. R.
,
Hurst
,
R. T.
,
Kendall
,
C. B.
,
Gotway
,
M. B.
, and
Liang
,
J.
,
2016
, “
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
,”
IEEE Trans. Med. Imaging
,
35
(
5
), pp.
1299
1312
.10.1109/TMI.2016.2535302
15.
Magee
,
T.
,
2015
, “
Usefulness of Unenhanced MRI and MR Arthrography of the Shoulder in Detection of Unstable Labral Tears
,”
Am. J. Roentgenol.
,
205
(
5
), pp.
1056
1060
.10.2214/AJR.14.14262
16.
Chang
,
D.
,
Mohana-Borges
,
A.
,
Borso
,
M.
, and
Chung
,
C. B.
,
2008
, “
SLAP Lesions: Anatomy, Clinical Presentation, MR Imaging Diagnosis and Characterization
,”
Eur. J. Radiol.
,
68
(
1
), pp.
72
87
.10.1016/j.ejrad.2008.02.026
17.
Bencardino
,
J. T.
,
Beltran
,
J.
,
Rosenberg
,
Z. S.
,
Rokito
,
A.
,
Schmahmann
,
S.
,
Mota
,
J.
,
Mellado
,
J. M.
,
Zuckerman
,
J.
,
Cuomo
,
F.
, and
Rose
,
D.
,
2000
, “
Superior Labrum Anterior- Posterior Lesions: Diagnosis With MR Arthrography of the Shoulder
,”
Radiology
,
214
(
1
), pp.
267
271
.10.1148/radiology.214.1.r00ja22267
18.
Herold
,
T.
,
Hente
,
R.
,
Zorger
,
N.
,
Finkenzeller
,
T.
,
Feuerbach
,
S.
,
Lenhart
,
M.
, and
Paetzel
,
C.
,
2003
, “
Indirect MR-Arthrography of the Shoulder-Value in the Detection of SLAP-Lesions
,”
Rofo
,
175
(
11
), pp.
1508
1514
.10.1055/s-2003-43408
19.
Dinauer
,
P. A.
,
Flemming
,
D. J.
,
Murphy
,
K. P.
, and
Doukas
,
W. C.
,
2007
, “
Diagnosis of Superior Labral Lesions: Comparison of Noncontrast MRI With Indirect MR Arthrography in Unexercised Shoulders
,”
Skeletal Radiol.
,
36
(
3
), pp.
195
202
.10.1007/s00256-006-0237-7
20.
Stone
,
M.
,
1974
, “
Cross-Validatory Choice and Assessment of Statistical Predictions (With Discussion)
,”
J. R. Stat. Soc., Ser. B
,
36
, pp.
111
147
.10.1111/j.2517-6161.1974.tb00994.x
21.
Mueller
,
S. G.
,
Weiner
,
M. W.
,
Thal
,
L. J.
,
Petersen
,
R. C.
,
Jack
,
C.
,
Jagust
,
W.
,
Trojanowski
,
J. Q.
,
Toga
,
A. W.
, and
Beckett
,
L.
,
2005
, “
The Alzheimer's Disease Neuroimaging Initiative
,”
Neuroimaging Clin. North Am.
,
15
(
4
), pp.
869
877
.10.1016/j.nic.2005.09.008
22.
Mueller
,
S. G.
,
Weiner
,
M. W.
,
Thal
,
L. J.
,
Petersen
,
R. C.
,
Jack
,
C. R.
,
Jagust
,
W.
,
Trojanowski
,
J. Q.
,
Toga
,
A. W.
, and
Beckett
,
L.
,
2005
, “
Ways Toward an Early Diagnosis in Alzheimer's Disease: The Alzheimer's Disease Neuroimaging Initiative (ADNI)
,”
Alzheimer's Dementia
,
1
(
1
), pp.
55
66
.10.1016/j.jalz.2005.06.003
23.
Whitwell
,
J. L.
,
Shiung
,
M. M.
,
Przybelski
,
S. A.
,
Weigand
,
S. D.
,
Knopman
,
D. S.
,
Boeve
,
B. F.
,
Petersen
,
R. C.
, and
Jack
,
C. R.
,
2008
, “
MRI Patterns of Atrophy Associated With Progression to AD in Amnestic Mild Cognitive Impairment
,”
Neurology
,
70
(
7
), pp.
512
520
.10.1212/01.wnl.0000280575.77437.a2
24.
C. R.
,
McDonald
,
L. K.
,
McEvoy
,
L.
,
Gharapetian
,
C.
,
Fennema-Notestine
,
D. J.
,
Hagler
, Jr.
,
D.
,
Holland
,
A.
,
Koyama
,
J. B.
,
Brewer
, and
A. M.
,
Dale
, and
A. D. N. I.
,
2009
, “
Regional Rates of Neocortical Atrophy From Normal Aging to Early Alzheimer Disease
,”
Neurology
,
73
(
6
), pp.
457
465
.10.1212/WNL.0b013e3181b16431
25.
Cuingnet
,
R.
,
Gerardin
,
E.
,
Tessieras
,
J.
,
Auzias
,
G.
,
Lehéricy
,
S.
,
Habert
,
M.-O.
,
Chupin
,
M.
,
Benali
,
H.
, and
Colliot
,
O.
,
2011
, “
Automatic Classification of Patients With Alzheimer's Disease From Structural MRI: A Comparison of Ten Methods Using the ADNI Database
,”
Neuroimage
,
56
(
2
), pp.
766
781
.10.1016/j.neuroimage.2010.06.013
26.
Jee
,
W.-H.
,
McCauley
,
T. R.
,
Katz
,
L. D.
,
Matheny
,
J. M.
,
Ruwe
,
P. A.
, and
Daigneault
,
J. P.
,
2001
, “
Superior Labral Anterior Posterior (SLAP) Lesions of the Glenoid Labrum: Reliability and Accuracy of MR Arthrography for Diagnosis
,”
Radiology
,
218
(
1
), pp.
127
132
.10.1148/radiology.218.1.r01ja44127
27.
Waldt
,
S.
,
Burkart
,
A.
,
Lange
,
P.
,
Imhoff
,
A. B.
,
Rummeny
,
E. J.
, and
Woertler
,
K.
,
2004
, “
Diagnostic Performance of MR Arthrography in the Assessment of Superior Labral Anteroposterior Lesions of the Shoulder
,”
Am. J. Roentgenol.
,
182
(
5
), pp.
1271
1278
.10.2214/ajr.182.5.1821271
28.
Fawcett
,
T.
,
2006
, “
An Introduction to ROC Analysis
,”
Pattern Recognit. Lett.
,
27
(
8
), pp.
861
874
.10.1016/j.patrec.2005.10.010
29.
Metz
,
C. E.
,
1978
, “
Basic Principles of ROC Analysis
,”
Semin. Nucl. Med.
,
8
(
4
), pp.
283
298
.10.1016/S0001-2998(78)80014-2
30.
Obuchowski
,
N. A.
,
2003
, “
Receiver Operating Characteristic Curves and Their Use in Radiology
,”
Radiology
,
229
(
1
), pp.
3
8
.10.1148/radiol.2291010898
31.
De Coninck
,
T.
,
Ngai
,
S. S.
,
Tafur
,
M.
, and
Chung
,
C. B.
,
2016
, “
Imaging the Glenoid Labrum and Labral Tears
,”
RadioGraphics
,
36
(
6
), pp.
1628
1647
.10.1148/rg.2016160020
32.
Tanner
,
M. A.
, and
Wong
,
W. H.
,
2010
, “
From EM to Data Augmentation: The Emergence of MCMC Bayesian Computation in the 1980s
,”
Stat. Sci.
,
25
(
4
), pp.
506
516
.10.1214/10-STS341
33.
Kingma
,
D. P.
, and
Welling
,
M.
,
2014
, “
Auto-Encoding Variational Bayes
,”
The International Conference on Learning Representations
, Banff, Canada, Apr. 14–16.
34.
Goodfellow
,
I. J.
,
Pouget-Abadie
,
J.
,
Mirza
,
M.
,
Xu
,
B.
,
Warde-Farley
,
D.
,
Ozair
,
S.
,
Courville
,
A.
, and
Bengio
,
Y.
,
2014
, “
Generative Adversarial Networks
,” Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Canada, Dec. 8, pp. 2672–2680.
35.
Ha
,
T. M.
, and
Bunke
,
H.
,
1997
, “
Off-Line, Handwritten Numeral Recognition by Perturbation Method
,”
IEEE Trans. Pattern Anal. Mach. Intell.
,
19
(
5
), pp.
535
539
.10.1109/34.589216
36.
Dielman
,
S.
,
2015
, “
My Solution for the Galaxy Zoo Challenge
,” London, UK, accessed May 11, 2017, http://benanne.github.io/2014/04/05/galaxy-zoo.html
37.
Asperti
,
A.
, and
Mastronardo
,
C.
,
2017
, “
The Effectiveness of Data Augmentation for Detection of Gastrointestinal Diseases From Endoscopical Images
,” Bioimaging.,
11th International Joint Conference on Biomedical Engineering Systems and Technologies
, Vol. 2. Jan. 19–21, Funchal, Madeira, Portugal. pp. 199–205.10.5220/0006730901990205
38.
Glorot
,
X.
, and
Bengio
,
Y.
,
2010
, “
Understanding the Difficulty of Training Deep Feedforward Neural Networks
,”
13th International Conference on Artificial Intelligence and Statistics
, Vol.
9
,
Sardinia, Italy
,
May 13–15
, pp.
249
256
.
39.
Glorot
,
X.
,
Bordes
,
A.
, and
Bengio
,
Y.
,
2011
, “
Deep Sparse Rectifier Neural Networks
,”
14th International Conference on Artificial Intelligence and Statistics
,
Fort Lauderdale, FL
,
Apr. 11–13
, pp.
315
323
.
40.
Kingma
,
D. P.
, and
Ba
,
J.
,
2015
, “
Adam: A Method for Stochastic Optimization
,”
International Conference on Learning Representations (ICLR)
, San Diego, CA, May 7–9.
41.
Krawczyk
,
B.
,
2016
, “
Learning From Imbalanced Data: Open Challenges and Future Directions
,”
Prog. Artif. Intell.
,
5
(
4
), pp.
221
232
.10.1007/s13748-016-0094-0
42.
Buda
,
M.
,
Maki
,
A.
, and
Mazurowski
,
M. A.
,
2018
, “
A Systematic Study of the Class Imbalance Problem in Convolutional Neural Networks
,”
Neural Networks
,
106
, pp.
249
259
.10.1016/j.neunet.2018.07.011
43.
Srivastava
,
N.
,
Hinton
,
G.
,
Krizhevsky
,
A.
,
Sutskever
,
I.
, and
Salakhutdinov
,
R.
,
2014
, “
Dropout: A Simple Way to Prevent Neural Networks From Overfitting
,”
J. Mach. Learn. Res.
,
15
, pp.
1929
1958
.
44.
Tikhonov
,
N.
,
1943
, “
On the Stability of Inverse Problems
,”
Dokl. Akad. Nauk SSSR
,
39
(
5
), pp.
195
198
.
45.
Bishop
,
C. M.
,
2006
, Pattern Recognition and Machine Learning, New York, pp. 256–269.
You do not currently have access to this content.