Comparing Pixel N-grams and Bag of Visual Word Features for the Classification of Diabetic Retinopathy
Article No.: 22, Pages 1 - 7
Abstract
The extraction of Bag of Visual Words (BoVW) features from retinal images for automated classification has been shown to be effective but computationally expensive. Histogram and co-variance matrix features do not generally result in models that have the same predictive accuracy as BoVW and are still computationally expensive. The discovery of features that result in accurate image classification on computationally constrained devices such as smartphones would enable new and promising applications for image classification. For example, smartphone retinal cameras can conceivably make diabetic retinopathy widely available and potentially reduce undiagnosed retinopathy if it could be achieved with computationally simple classification algorithms.
A novel image feature extraction technique inspired by N-grams in text mining, called 'Pixel N-grams' is described that can serve this purpose. Results on mammogram and texture classification have shown high accuracy despite the reduced computational complexity. However retinal scan classification results using Pixel N-grams lag behind BoVW approaches. An explanation for the relative poor performance of Pixel N-grams with diabetic retinopathy that draws on concepts associated with the No Free Lunch theorem are presented.
References
[1]
Smeulders, A.W., et al., Content-based image retrieval at the end of the early years. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2000(12): p. 1349--1380.
[2]
Chen, Y., J.Z. Wang, and R. Krovetz. Content-based image retrieval by clustering. in Proceedings of the 5th ACM SIGMM international workshop on Multimedia information retrieval. 2003. ACM.
[3]
Sivic and Zisserman. Video Google: a text retrieval approach to object matching in videos. in Proceedings Ninth IEEE International Conference on Computer Vision. 2003.
[4]
Cruz-Roa, A., J.C. Caicedo, and FA. González, Visual pattern mining in histology image collections using bag of features. Artificial intelligence in medicine, 2011. 52(2): p. 91--106.
[5]
Jiang, M., et al., Computer-aided diagnosis of mammographic masses using scalable image retrieval. IEEE Transactions on Biomedical Engineering, 2015. 62(2): p. 783--792.
[6]
Pires, R., et al., Advancing bag-of-visual-words representations for lesion classification in retinal images. PloS one, 2014. 9(6): p. e96814.
[7]
van de Sande, K.E., T. Gevers, and C.G. Snoek, Empowering visual categorization with the GPU. IEEE Transactions on Multimedia, 2011. 13(1): p. 60--70.
[8]
Kulkarni, P., et al., Visual Character n-grams for Classification and Retrieval of Radiological Images. The International Journal of Multimedia & Its Applications, 2014. 6(2): p. 35.
[9]
Suen, C.Y., N-gram statistics for natural language understanding and text processing. IEEE transactions on pattern analysis and machine intelligence, 1979(2): p. 164--172.
[10]
Kanaris, I., et al., Words versus character n-grams for anti-spam filtering. International Journal on Artificial Intelligence Tools, 2007. 16(06): p. 1047--1067.
[11]
Kulkarni, P., S. Kulkarni, and A. Stranieri, A Novel Architecture and Analysis of Challenges for Combining Text and Image for Medical Image Retrieval. 2014.
[12]
Kulkarni, P., A. Stranieri, and J. Ugon, Pixel N-grams: Size, Location and Resolution. Invariance for Shape Classification International Journal of Science, Engineering and Management, 2016. 1(8): p. 6.
[13]
Kulkarni, P., Pixel N-grams for Mammographic Image Classification. 2017, Federation University: Ballarat.
[14]
Pedrosa, G.V. and A.J. Traina. From bag-of-visual-words to bag-of-visual-phrases using n-grams. in Graphics, Patterns and Images (SIBGRAPI), 2013 26th SIBGRAPI-Conference on. 2013. IEEE.
[15]
Kempen, J.H., et al., The prevalence of diabetic retinopathy among adults in the United States. Archives of ophthalmology (Chicago, Ill.: 1960), 2004. 122(4): p. 552--563.
[16]
Kovarik, J.J., et al., Prevalence of undiagnosed diabetic retinopathy among inpatients with diabetes: the diabetic retinopathy inpatient study (DRIPS). BMJ Open Diabetes Research and Care, 2016. 4(1): p. e000164.
[17]
Kumar, S., et al., Teleophthalmology assessment of diabetic retinopathy fundus images: smartphone versus standard office computer workstation. TELEMEDICINE and e-HEALTH, 2012. 18(2): p. 158--162.
[18]
Wolpert, D.H., The existence of a priori distinctions between learning algorithms. Neural Computation, 1996. 8(7): p. 1391--1420.
[19]
Gómez, D. and A. Rojas, An empirical overview of the no free lunch theorem and its effect on real-world machine learning classification. Neural computation, 2016. 28(1): p. 216--228.
[20]
Vinyals, O., et al. Show and tell: A neural image caption generator. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
[21]
Lowe, D.G., Distinctive image features from scale-invariant keypoints. International journal of computer vision, 2004. 60(2): p. 91--110.
[22]
Bay, H., T. Tuytelaars, and L. Van Gool. Surf: Speeded up robust features. in European conference on computer vision. 2006. Springer.
[23]
Dalal, N. and B. Triggs. Histograms of oriented gradients for human detection. in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. 2005. IEEE.
[24]
Tan, X. and B. Triggs. Enhanced local texture feature sets for face recognition under difficult lighting conditions. in International Workshop on Analysis and Modeling of Faces and Gestures. 2007. Springer.
[25]
Tsai, C.-F., Bag-of-words representation in image annotation: A review. ISRN Artificial Intelligence, 2012. 2012.
[26]
Tirilly, P., V. Claveau, and P. Gros. Language modeling for bag-of-visual words image categorization. in Proceedings of the 2008 international conference on Content-based image and video retrieval. 2008. ACM.
[27]
Kulkarni, P., et al. HYBRID TECHNIQUE BASED ON NGram AND NEURAL NETWORKS FOR CLASSIFICATION OF MAMMOGRAPHIC IMAGES. in Second International Conference on Signal, Image Processing and Pattern Recognition. 2014.
[28]
Kulkarni, S., et al., Framework for Integration of Medical Image and Text-Based Report Retrieval to Support Radiological Diagnosis. Biomedical Signal and Image Processing in Patient Care, 2017: p. 86.
[29]
Suhaila, Z., et al., Bag of Visual Words Approach for Classification of Benign and Malignant Masses in Mammograms Using Voting Based Feature Encoding.
[30]
Lazebnik, S., C. Schmid, and J. Ponce, A sparse texture representation using local affine regions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005. 27(8): p. 1265--1278.
[31]
Jelinek, H.F., C. Wilding, and P. Tinely, An innovative multi-disciplinary diabetes complications screening program in a rural community: A description and preliminary results of the screening. Australian Journal of Primary Health, 2006. 12(1): p. 14--20.
[32]
Pires, R., et al. Automatic diabetic retinopathy detection using BossaNova representation. in Intl. Conference of the IEEE Engineering in Medicine and Biology Society. 2014.
[33]
Orlando, J.I., et al., An ensemble deep learning based approach for red lesion detection in fundus images. Computer methods and programs in biomedicine, 2018. 153: p. 115--127.
[34]
Rittel, H.W. and M.M. Webber, Wicked problems. Man-made Futures, 1974. 26(1): p. 272--280.
[35]
Kunz, W. and H.W. Rittel, Issues as elements of information systems. Vol. 131. 1970
Index Terms
- Comparing Pixel N-grams and Bag of Visual Word Features for the Classification of Diabetic Retinopathy
Recommendations
GLCM-based detection and classification of microaneurysm in diabetic retinopathy fundus images
Diabetic retinopathy is a major cause of blindness and it includes the lesions like microaneurysms, haemorrhages, and exudates. Microaneurysms are the first clinical sign of diabetic retinopathy and it is a small red dot on the retinopathy fundus images. ...
Retinal Vessel Segmentation of Non-Proliferative Diabetic Retinopathy
Diabetic retinopathy is a disease in diabetic patients that affects the eye. It happens due to damage in the blood vessels of the light-sensitive tissues at the retina. In non-proliferative diabetic retinopathy, tiny changes occur in the blood vessels ...
Algorithms for the Automated Detection of Diabetic Retinopathy Using Digital Fundus Images: A Review
Diabetes is a chronic end organ disease that occurs when the pancreas does not secrete enough insulin or the body is unable to process it properly. Over time, diabetes affects the circulatory system, including that of the retina. Diabetic retinopathy is ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
January 2019
486 pages
ISBN:9781450366038
DOI:10.1145/3290688
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
In-Cooperation
- CORE - Computing Research and Education
- Macquarie University-Sydney
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 29 January 2019
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ACSW 2019
Acceptance Rates
ACSW '19 Paper Acceptance Rate 61 of 141 submissions, 43%;
Overall Acceptance Rate 61 of 141 submissions, 43%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 70Total Downloads
- Downloads (Last 12 months)1
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in