• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology

Article

An Efficient Medical Image Retrieval and Classification using Deep Neural Network
  • VIEWS 1679
  • PDF 268

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v13i39.1621

Year: 2020, Volume: 13, Issue: 39, Pages: 4127-4141

Original Article

An Efficient Medical Image Retrieval and Classification using Deep Neural Network

K Chethan1*, Rekha Bhandarkar2

1Research Scholar, Department of Electronics and Communication Engineering, NMAM Institute of Technology, Nitte, 574110, India. Tel.: +91-8892410925
2Professor and Head, Department of Electronics and Communication Engineering, NMAM Institute of Technology Nitte, 574110, India

*Corresponding Author
Tel: +91-8892410925
Email: [email protected]
[email protected]

Received Date:08 September 2020, Accepted Date:18 October 2020, Published Date:07 November 2020

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Background/Objectives: The main objective of this work is to obtain an efficient brain tumor image retrieval and classification using Deep Neural Network (DNN). Methods/Statistical analysis: The features from the medical images are extracted by using tamura feature extraction, Local Ternary Pattern (LTP) and Histogram of Oriented Gradients (HOG). Subsequently, an Infinite Feature Selection (Inf-FS) technique is incorporated to select optimum features from feature vector, which leads to improve the classification process using sparse auto encoder based DNN. Furthermore, the retrieval performance of the proposed method is improved by Euclidean Distance technique. Findings: An Open Access Series of Imaging Studies (OASIS) and Contrast Enhanced- Magnetic Resonance Image (CE-MRI) datasets are utilized to analyze the proposed method. The sparse auto encoder based DNN classification scheme yields an overall accuracy of 95.34% in OASIS dataset and 99.87% in CEMRI dataset with improved sensitivity, specificity, error rate. The retrieval performance of proposed technique is assessed in terms of Average Retrieval Precision (ARP) and compared with two existing methods such as Local Mesh Vector Co-occurrence Pattern (LMVCoP) and Content Based Image Retrieval- Convolutional Neural Network (CBIR-CNN). The ARP of the proposed method for CE-MRI and OASIS dataset is 98.33% and 88.25% that is high when compared to the CBIR-CNN, LMVCoP method. Novelty/Applications: An appropriate feature selection using Inf-FS and DNN based nonlinear feature data classification are used in the applications of medical image retrieval.

Keywords: Average retrieval precision; deep neural network; Euclidean distance based image retrieval; feature extraction; image retrieval

References

  1. Shamna P, Govindan VK, Nazeer KAA. Content-based medical image retrieval by spatial matching of visual words. Journal of King Saud University - Computer and Information Sciences. 2018. Available from: https://dx.doi.org/10.1016/j.jksuci.2018.10.002
  2. Cai Y, Li Y, Qiu C, Ma J, Gao X. Medical Image Retrieval Based on Convolutional Neural Network and Supervised Hashing. IEEE Access. 2019;7:51877–51885. Available from: https://dx.doi.org/10.1109/access.2019.2911630
  3. Lundervold AS, Lundervold A. An overview of deep learning in medical imaging focusing on MRI. Zeitschrift für Medizinische Physik. 2019;29(2):102–127. Available from: https://dx.doi.org/10.1016/j.zemedi.2018.11.002
  4. Shamna P, Govindan VK, Nazeer KAA. Content based medical image retrieval using topic and location model. Journal of Biomedical Informatics. 2019;91. Available from: https://dx.doi.org/10.1016/j.jbi.2019.103112
  5. Biswas R, Roy S, Purkayastha D. An efficient content-based medical image indexing and retrieval using local texture feature descriptors. International Journal of Multimedia Information Retrieval. 2019;8(4):217–231. Available from: https://dx.doi.org/10.1007/s13735-019-00176-9
  6. Mishra S, Panda M. Medical image retrieval using self-organising map on texture features. Future Computing and Informatics Journal. 2018;3(2):359–370. Available from: https://dx.doi.org/10.1016/j.fcij.2018.10.006
  7. Rao TYS, Reddy PC. Content and context based image retrieval classification based on firefly-neural network. Multimedia Tools and Applications. 2018;77:32041–32062. Available from: https://dx.doi.org/10.1007/s11042-018-6224-x
  9. Zeineldin RA, Karar ME, Coburger J, Wirtz CR, Burgert O. DeepSeg: deep neural network framework for automatic brain tumor segmentation using magnetic resonance FLAIR images. International Journal of Computer Assisted Radiology and Surgery. 2020;15(6):909–920. Available from: https://dx.doi.org/10.1007/s11548-020-02186-z
  10. Badža MM, Barjaktarović MČ. Classification of Brain Tumors from MRI Images Using a Convolutional Neural Network. Applied Sciences. 2020;10(6). Available from: https://dx.doi.org/10.3390/app10061999
  11. Estienne T, Lerousseau M, Vakalopoulou M, Andres EA, Battistella E, Carré A, et al. Deep Learning-Based Concurrent Brain Registration and Tumor Segmentation. Frontiers in Computational Neuroscience. 2020;14:17. Available from: https://dx.doi.org/10.3389/fncom.2020.00017
  12. Sundararajan SK, Sankaragomathi B, Priya DS. Deep Belief CNN Feature Representation Based Content Based Image Retrieval for Medical Images. Journal of Medical Systems. 2019;43(6):174. doi: 10.1007/s10916-019-1305-6
  13. Behnam M, Pourghassem H. Optimal Query-Based Relevance Feedback in Medical Image Retrieval Using Score Fusion-Based Classification. Journal of Digital Imaging. 2015;28(2):160–178. doi: 10.1007/s10278-014-9730-z
  14. Zhang X, Liu W, Dundar M, Badve S, Zhang S. Towards Large-Scale Histopathological Image Analysis: Hashing-Based Image Retrieval. IEEE Transactions on Medical Imaging. 2015;34(2):496–506. doi: 10.1109/tmi.2014.2361481
  15. Tang Q, Yang J, Xia X. Medical Image Retrieval Using Multi-Texton Assignment. Journal of Digital Imaging. 2018;31(1):107–116. doi: 10.1007/s10278-017-0017-z
  16. Wei G, Cao H, Ma H, Qi S, Qian W, Ma Z. Content-based image retrieval for Lung Nodule Classification Using Texture Features and Learned Distance Metric. Journal of Medical Systems. 2018;42(1):13. doi: 10.1007/s10916-017-0874-5
  17. Kitanovski I, Strezoski G, Dimitrovski I, Madjarov G, Loskovska S. Multimodal medical image retrieval system. Springer Science and Business Media LLC. 2017. doi: 10.1007/s11042-016-3261-1 Available from: https://dx.doi.org/10.1007/s11042-016-3261-1
  18. Ko BC, Lee J, Nam JY. Automatic medical image annotation and keyword-based image retrieval using relevance feedback. Journal of Digital Imaging. 2012;25(4):454–465. doi: 10.1007/s10278-011-9443-5
  19. Somasundaram S, Gobinath R. Current Trends on Deep Learning Models for Brain Tumor Segmentation and Detection-A Review. 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon). 2019;p. 217–221.
  20. Khan MA, Ashraf I, Alhaisoni M, Damaševičius R, Scherer R, Rehman A, et al. Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists. Diagnostics. 2020;10(8):565. doi: 10.3390/diagnostics10080565
  21. Wu W, Li D, Du J, Gao X, Gu W, Zhao F, et al. An Intelligent Diagnosis Method of Brain MRI Tumor Segmentation Using Deep Convolutional Neural Network and SVM Algorithm. Computational and Mathematical Methods in Medicine. 2020.
  22. Bhandari A, Koppen J, Agzarian M. Convolutional neural networks for brain tumour segmentation. Insights into Imaging. 2020;11(1):1–9. doi: 10.1186/s13244-020-00869-4
  23. Ma L, Liu X, Gao Y, Zhao Y, Zhao X, Zhou C. A new method of content based medical image retrieval and its applications to CT imaging sign retrieval. Journal of Biomedical Informatics. 2017;66:148–158. doi: 10.1016/j.jbi.2017.01.002
  24. Rahman MM, You D, Simpson MS, Antani SK, Demner-Fushman D, Thoma GR. Interactive cross and multimodal biomedical image retrieval based on automatic region-of-interest (ROI) identification and classification. International Journal of Multimedia Information Retrieval. 2014;3(3):131–146. doi: 10.1007/s13735-014-0057-9
  25. Kasban H, Salama DH. A robust medical image retrieval system based on wavelet optimization and adaptive block truncation coding. Multimedia Tools and Applications. 2019;78(24):35211–35236. doi: 10.1007/s11042-019-08100-3
  26. Majid A, Khan MA, Yasmin M, Rehman A, Yousafzai A, Tariq U. Classification of stomach infections: A paradigm of convolutional neural network along with classical features fusion and selection. Microscopy Research and Technique. 2020;83(5):562–576. doi: 10.1002/jemt.23447
  27. Khan MA, Qasim M, Lodhi HMJ, Nazir M, Javed K, Rubab S, et al. 2020.
  28. Khan MA, Kadry S, Alhaisoni M, Nam Y, Zhang Y, Rajinikanth V, et al. Computer-Aided Gastrointestinal Diseases Analysis From Wireless Capsule Endoscopy: A Framework of Best Features Selection. IEEE Access. 2020;8:132850–132859. doi: 10.1109/access.2020.3010448
  29. Muhammad K, Khan S, Kumar N, Del Ser J, Mirjalili S. Vision-based personalized Wireless Capsule Endoscopy for smart healthcare: Taxonomy, literature review, opportunities and challenges. Future Generation Computer Systems. 2020;113:266–280. doi: 10.1016/j.future.2020.06.048
  30. Liaqat A, Khan MA, Sharif M, Mittal M, Saba T, Manic KS, et al. Gastric Tract Infections Detection and Classification from Wireless Capsule Endoscopy using Computer Vision Techniques: A Review. Current Medical Imaging Formerly Current Medical Imaging Reviews. 2020;16. doi: 10.2174/1573405616666200425220513
  31. Faria AV, Oishi K, Yoshida S, Hillis A, Miller MI, Mori S. Content-based image retrieval for brain MRI: An image-searching engine and population-based analysis to utilize past clinical data for future diagnosis. NeuroImage: Clinical. 2015;7:367–376. doi: 10.1016/j.nicl.2015.01.008
  32. Anbarasa Pandian A, Balasubramanian R. Fusion of Contourlet Transform and Zernike Moments using Content based Image Retrieval for MRI Brain Tumor Images. Indian Journal of Science and Technology. 2016;9(29):29. doi: 10.17485/ijst/2016/v9i29/93837
  34. Sivakumar P, Ganeshkumar P. CANFIS based glioma brain tumor classification and retrieval system for tumor diagnosis. International Journal of Imaging Systems and Technology. 2017;27(2):109–117. doi: 10.1002/ima.22215
  35. Swati ZNK, Zhao Q, Kabir M, Ali F, Ali Z, Ahmed S, et al. Content-Based Brain Tumor Retrieval for MR Images Using Transfer Learning. IEEE Access. 2019;7:17809–17822. doi: 10.1109/access.2019.2892455
  36. Rehman A, Khan MA, Saba T, Mehmood Z, Tariq U, Ayesha N. Microscopic brain tumor detection and classification using 3D CNN and feature selection architecture. Microscopy Research and Technique. 2020. doi: 10.1002/jemt.23597
  37. Hussain UN, Khan MA, Lali IU, Javed K, Ashraf I, Tariq J, et al. A Unified Design of ACO and Skewness based Brain Tumor Segmentation and Classification from MRI Scans. Journal of Control Engineering and Applied Informatics. 2020;22(2):43–55.
  38. Chen F, Muhammad K, Wang SH. Three-dimensional reconstruction of CT image features based on multi-threaded deep learning calculation. Pattern Recognition Letters. 2020;136:309–315. doi: 10.1016/j.patrec.2020.04.033
  39. Khan SA, Khan MA, Song OY, Nazir M. Medical Imaging Fusion Techniques: A Survey Benchmark Analysis, Open Challenges and Recommendations. Journal of Medical Imaging and Health Informatics. 2020;10(11):2523–2531.
  40. Muhammad K, Khan S, Ser JD, de Albuquerque VHC. Deep Learning for Multigrade Brain Tumor Classification in Smart Healthcare Systems: A Prospective Survey. IEEE Transactions on Neural Networks and Learning Systems. 2020;p. 1–16. doi: 10.1109/tnnls.2020.2995800
  41. Naheed N, Shaheen M, Ali Khan S, Alawairdhi M, Attique Khan M. Importance of Features Selection, Attributes Selection, Challenges and Future Directions for Medical Imaging Data: A Review. Computer Modeling in Engineering & Sciences. 2020;125(1):315–344. doi: 10.32604/cmes.2020.011380
  42. Marcus DS, Wang TH, Parker J, Csernansky JG, Morris JC, Buckner RL. Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults. Journal of Cognitive Neuroscience. 2007;19(9):1498–1507. doi: 10.1162/jocn.2007.19.9.1498

Copyright

© 2020 Chethan & Bhandarkar.This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee).

  • 09 November 2020

Year: 2020, Volume: 13, Issue: 39

Article Metrics


Post Graduate Fellowship in Research Communication

More articles

DON'T MISS OUT!

Subscribe now for latest articles and news.