=Paper=
{{Paper
|id=Vol-1984/Mediaeval_2017_paper_7
|storemode=property
|title=HKBU at MediaEval 2017 - Medico: Medical Multimedia Task
|pdfUrl=https://ceur-ws.org/Vol-1984/Mediaeval_2017_paper_7.pdf
|volume=Vol-1984
|authors=Yang Liu,Zhonglei Gu,William K. Cheung
|dblpUrl=https://dblp.org/rec/conf/mediaeval/LiuGC17
}}
==HKBU at MediaEval 2017 - Medico: Medical Multimedia Task==
https://ceur-ws.org/Vol-1984/Mediaeval_2017_paper_7.pdf
HKBU at MediaEval 2017
Medico: Medical Multimedia Task
Yang Liu1,2 , Zhonglei Gu1 , William K. Cheung1
1
Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China
2
Institute of Research and Continuing Education, Hong Kong Baptist University, Shenzhen, China
csygliu@comp.hkbu.edu.hk,cszlgu@comp.hkbu.edu.hk,william@comp.hkbu.edu.hk
ABSTRACT 2 METHOD
In this paper, we describe our model designed for automat- 2.1 Bidirectional Marginal Fisher Analysis
ic detection of diseases based on multimedia data collected
Given the data matrix X = [x1 , x2 , ..., xπ ], where π denotes
in hospitals. Specifically, a two-stage learning strategy is
the number of data points in the training set, xπ β Rπ·
designed to predict the diseases. In the first stage, a di-
the high-dimensional feature vector of the π-th data point,
mensionality reduction method called bidirectional marginal
ππ β {1, 2, ..., 8} the set of possible labels, and l = [π1 , π2 , ..., ππ ]
Fisher analysis (BMFA) is proposed to project the original
the set of true labels corresponding to each data point xπ .
data to the low-dimensional space, with the key discriminant
The proposed bidirectional marginal fisher analysis (BMFA)
information being well preserved. In the second stage, the
aims to learn the subspace of original features, in which the
multi-class support vector machine (SVM) is utilized on the
marginal discriminant information is well preserved.
low-dimensional space for detection. Experimental results
A manifold learning algorithm typically involves the def-
demonstrate the efficiency of designed model.
inition of a neighborhood graph. The effectiveness of the
algorithm very often depends on how well the defined neigh-
1 INTRODUCTION borhood graph can preserve the local topological properties of
the data manifold. To achieve a robust neighborhood graph,
We have evidenced an increasing trend of applying multi-
we use the following two-way connection criterion to con-
media processing and analysis methods, such as computer
struct the graph [4]: we connect xπ and xπ only if xπ is one
vision and medical image processing, to assisting diagnosis,
of the πΎ-nearest neighbors of xπ , and, xπ is also one of the
detection and interpretation of medical abnormalities [7].
πΎ-nearest neighbors of xπ . The above criterion adopts the
While there exist a number of successful applications related
βand β hypothesis, which means it agrees to connect two data
to healthcare decision support, predictive analytics are still
points if and only if both of them are neighbors of each other.
considered challenging for some specific medical multimedia
The within-class adjacency matrix and between-class adja-
data like endoscopy and ultrasound images, due to the high
cency matrix are then defined as follows:
complexity of these medical tasks [8]. Moreover, most of the {οΈ
existing methods make use of a limited amount of information, ||x βx ||2
π€
Aππ = exp(β π 2ππ πΉ ), if π β π©π and π β π©π and ππ = ππ ,
where possibly useful information sources such as sensory and 0, otherwise
temporal information were mostly not considered [5, 10, 11]. (1)
The 2017 MediaEval Medico Task aims to improve de- {οΈ
||xπ βxπ ||2
tection and location of abnormalities through designing an Aπππ = exp(β 2π
πΉ
), if π β π©π and π β π©π and ππ ΜΈ= ππ ,
integrated approach combining information from both video 0, otherwise
and image information, as well as other sensory information (2)
and assistance of medical experts. The dataset used in this where π©π denotes the index set of the βοΈ πΎ nearest neighbors
task consists of 8,000 GI tract images that are annotated of xπ , and π is empirically set by π = π 2
π=1 ||xπ β xππΎ ||πΉ /π
and verified by medical doctors for the ground truth. More where xππΎ is the πΎth nearest neighbor of xπ .
details about the task requirements and the dataset can be BMFA aims to learn a transformation matrix W β Rπ·Γπ
found in [8]. where the following objective function is maximized:
In order to perform efficient detection of diseases, we design βοΈπ π π π 2
a two-stage learning strategy. In the first stage, a manifold π,π=1 Aππ ||W xπ β W xπ ||πΉ
W = arg max βοΈπ π€ 2
. (3)
π,π=1 Aππ ||W xπ β W xπ ||πΉ
π π
learning method called bidirectional marginal Fisher analysis W
(BMFA) is proposed to learn the compact representation The above optimization problem can be relaxed to the
of the original data, with the key discriminant information following ratio trace problem:
being well preserved. In the second stage, the multi-class
support vector machine (SVM) is applied to the compact Wπ Sπ W
W = arg max π‘π( ), (4)
representation of each data point for detection. W Wπ Sπ€ W
where Sπ = XLπ Xπ and Sπ€ = XLπ€ Xπ , in which Lπ = Dπ β
Copyright held by the owner/author(s).
MediaEvalβ17, 13-15 September 2017, Dublin, Ireland Aπ and Lπ€ = Dπ€ β Aπ€ are the Laplacian matrices βοΈ[1, 3], and
Dπ and Dπ€ are diagonal matrices defined as Dπππ = π π=1 Aππ
π
MediaEvalβ17, 13-15 September 2017, Dublin, Ireland Y. Liu, Z. Gu, W. K. Cheung
Table 1: Official evaluation results (provided by the organizers) of the proposed model on the Kvasir dataset.
Recall Specificity Precision Accuracy F1 MCC π
π statistic
Run 1 for both subtasks 0.6975 0.9568 0.6975 0.9244 0.6975 0.6543 0.6571
Run 2 for both subtasks 0.7028 0.9575 0.7028 0.9257 0.7028 0.6603 0.6626
Run 3 for both subtasks 0.6890 0.9556 0.6890 0.9223 0.6890 0.6446 0.6453
Run 4 for both subtasks 0.6988 0.9570 0.6988 0.9247 0.6988 0.6557 0.6585
Run 5 for both subtasks 0.6918 0.9560 0.6918 0.9229 0.6918 0.6477 0.6483
βοΈπ
and Dπ€ ππ =
π€
π=1 Aππ (π = 1, ..., π). The optimization problem
in Eq. (4) could be solved by generalized eigen-decomposition.
For each high-dimensional data point xπ , we can obtain
its low-dimensional representation by yπ = Wπ xπ .
2.2 Support Vector Classification
To predict diseases, we apply the multi-class support vector
machine (SVM) to the low-dimensional representation of
each data point. Specifically, we employ the one-against-all
strategy for the multi-class classification and use the π-SVM
[9] on each class.
3 RESULTS
Figure 1: Contribution of each individual feature.
In this section, we report the experimental settings and the
evaluation results. The Kvasir Dataset is used to evaluate
the performance of the proposed model [6]. The size of the
training set is 4, 000 (500 for each of the eight classes) and with only a portion of the available data being utilized for
the dimension of the original feature space is 1, 185. We em- training. This indicates that the learned subspace is able to
ploy the same setting on both the detection subtask and capture the discriminant information of the dataset. More-
the efficient detection subtask (i.e., the 5 runs of the detec- over, by reducing the original data to a very low-dimensional
tion subtask and those of the efficient detection subtask are subspace, the learning process becomes more efficient.
identical). Specifically: In addition to the overall performance, we analyze the
contribution of each dimension in the original feature s-
β For Run 1 of both subtasks, we randomly select
pace. The contribution of the π-th dimension is defined as
1, 000 data samples (125 for each class) for training, βοΈ
πΆπππ‘ππππ’π‘ππππ = π ππ |π€ππ |, where ππ denotes the π-th eigen-
and project the original data to the 8-dimensional
value, π€ππ denotes the (π, π)-th element of W, and | Β· | de-
subspace via BMFA;
notes the absolute value operator. From Figure 1 we can
β For Run 2 of both subtasks, we randomly select 1, 000
see that the edge histogram and auto color correlogram fea-
data samples for training, and project the original
tures contribute more than the others, which indicates their
data to the 9-dimensional subspace via BMFA;
importance in medical image classification.
β For Run 3 of both subtasks, we randomly select
800 data samples (100 for each class) for training,
and project the original data to the 9-dimensional 4 CONCLUSION
subspace via BMFA; This paper described the model designed for disease detection
β For Run 4 of both subtasks, we randomly select 1, 000 based on multimedia data. A novel dimensionality reduction
data samples for training, and project the original algorithm dubbed bidirectional marginal Fisher analysis (BM-
data to the 7-dimensional subspace via BMFA; FA) was presented to extract the discriminant information
β For Run 5 of both subtasks, we randomly select 800 from the original feature space. After that, SVM was applied
data samples for training, and project the original to the low-dimensional subspace for multi-class classification.
data to the 7-dimensional subspace via BMFA. Experimental results on the Kvasir dataset validated the
effectiveness and efficiency of the proposed model.
In the following step, we use the LIBSVM toolbox for clas-
sification [2]. The π-SVC with linear kernel is selected, and
the parameters are set as π = 0.2 and πππ π‘ = 1. ACKNOWLEDGMENTS
Table 1 shows the official evaluation results (provided by This work was supported in part by the National Natural
the task organizers) of the proposed model on the Kvasir Science Foundation of China under Grant 61503317, and in
dataset. From the table, we can see that the proposed model part by the Faculty Research Grant of Hong Kong Baptist
performs well, given the task is a multi-class classification University (HKBU) under Project FRG2/16-17/032.
Medico: Medical Multimedia Task MediaEvalβ17, 13-15 September 2017, Dublin, Ireland
REFERENCES
[1] M. Belkin and P. Niyogi. 2001. Laplacian Eigenmaps and
Spectral Techniques for Embedding and Clustering. In Ad-
vances in Neural Information Processing Systems 14 (NIPS).
585β591.
[2] Chih-Chung Chang and Chih-Jen Lin. 2011. LIBSVM: A
library for support vector machines. ACM Transactions
on Intelligent Systems and Technology 2 (2011), 27:1β27:27.
Issue 3.
[3] X. He and P. Niyogi. 2003. Locality Preserving Projections.
In Advances in Neural Information Processing Systems 16
(NIPS). 153β160.
[4] Yang Liu, Yan Liu, and Keith C. C. Chan. 2011. Ordinal
regression via manifold learning. In Proceeding of the 25th
AAAI Conference on Artificial Intelligence (AAAI). 398β403.
[5] Konstantin Pogorelov, Sigrun Losada Eskeland, Thomas de
Lange, Carsten Griwodz, Kristin Ranheim Randel, HaΜkon K-
vale Stensland, Duc-Tien Dang-Nguyen, Concetto Spampina-
to, Dag Johansen, Michael Riegler, and PaΜl Halvorsen. 2017.
A Holistic Multimedia System for Gastrointestinal Tract Dis-
ease Detection. In Proceedings of the 8th ACM on Multimedia
Systems Conference (MMSYS). 112β123.
[6] Konstantin Pogorelov, Kristin Ranheim Randel, Carsten Gri-
wodz, Sigrun Losada Eskeland, Thomas de Lange, Dag Jo-
hansen, Concetto Spampinato, Duc-Tien Dang-Nguyen, Math-
ias Lux, Peter Thelin Schmidt, Michael Riegler, and PaΜl
Halvorsen. 2017. Kvasir: A Multi-Class Image Dataset for
Computer Aided Gastrointestinal Disease Detection. In Pro-
ceedings of the 8th ACM on Multimedia Systems Conference
(MMSYS). 164β169.
[7] Michael Riegler, Mathias Lux, Carsten Griwodz, Concetto
Spampinato, Thomas de Lange, Sigrun L. Eskeland, Kon-
stantin Pogorelov, Wallapak Tavanapong, Peter T. Schmidt,
Cathal Gurrin, Dag Johansen, HaΜvard Johansen, and PaΜl
Halvorsen. 2016. Multimedia and Medicine: Teammates for
Better Disease Detection and Survival. In Proceedings of the
2016 ACM on Multimedia Conference (ACMMM). 968β977.
[8] Michael Riegler, Konstantin Pogorelov, PaΜl Halvorsen,
Carsten Griwodz, Thomas de Lange, Kristin Ranheim Ran-
del, Sigrun Losada Eskeland, Duc-Tien Dang-Nguyen, Math-
ias Lux, and Concetto Spampinato. 2017. Multimedia for
Medicine: The Medico Task at MediaEval 2017. In Working
Notes Proceedings of the MediaEval 2017 Workshop.
[9] Bernhard SchoΜlkopf, Alex J. Smola, Robert C. Williamson,
and Peter L. Bartlett. 2000. New Support Vector Algorithms.
Neural Comput. 12, 5 (2000), 1207β1245.
[10] Y. Wang, W. Tavanapong, J. Wong, J. Oh, and P. C. de
Groen. 2011. Computer-aided detection of retroflexion in
colonoscopy. In Proceedings of 24th International Symposium
on Computer-Based Medical Systems (CBMS). 1β6.
[11] Yi Wang, Wallapak Tavanapong, Johnny Wong, Jung Hwan
Oh, and Piet C. de Groen. 2015. Polyp-Alert: Near real-
time feedback during colonoscopy. Computer Methods and
Programs in Biomedicine 120, 3 (2015), 164β179.