Shahin SHAFEI, Hamid VAHDATI, Asghar CHARMIN, Tohid SEDGHI

CBMIR System Based on Matrix Weighting Framework and Linear Transformation with KNN

Biomedical images are utilized by radiologists and physicians in cases where diagnosis and recognition would be more efficient. Therefore, it is recommended to propose novel methods that can retrieve medical images with a high percentage of accuracy. A comprehensive feature selection and weighting combination method with novel learning of k-nearest neighbor artificial neural network (KNN-ANN) was introduced for retrieval of biomedical MR images. Modified Radon, and modified Hu moments operators with weighting combinational methods were proposed for achieving a higher percentage of retrieval. Moreover, these characteristics are re-composed for presenting outstanding statistic specification and spatial signals. This spatial and frequency information is obtained for all MR image datasets. The composition of shape and textural features presents robust vectors for retrieval of the biomedical database. In addition, a KNN-ANN framework is proposed and applied to measure the similarity between the query and biomedical database. The presented system achieves 90% retrieval for all types of classes. For matching features, the most similar highest priority principle with KNN is used. The image retrieved from the databases is the image which has less distance and less most-similar highest priority at KNN. The proposed algorithm is evaluated on two different databases. This novel scheme illustrates higher and better specialty in the MRI datasets. The results were compared and understood to be remarkable.

PDF

___

1. M. Fakheri, T. Sedghi, M. G. Shayesteh, and M. C. Chehel Amirani, “Framework for image retrieval using machine learning and statistical similarity matching techniques,” IET Image Process., vol. 7, no. 1, pp. 1–11, Feb. 2013.
2. G. Takacs, V. Chandrasekhar, S. S. Tsai, D. Chen, R.Grzeszczuk, and B.Girod, “Fast computation of rotation-invariant image features by an approximate radial gradient transform,” IEEE Trans. Image Process., vol. 22, no. 8, pp.2970–2982, Apr. 2013.
3. G. Shan, W. Minghua, W. Lei, and Y. Cihui, “Reduced quaternion matrix for color texture classification,” Neural Comput. Appl., vol. 25, no. 3, pp. 945–954, Jun. 2014.
4. S. P. Chen, “W.single-shot imaging without reference wave using binary intensity pattern for optically-secured-based correlation,” IEEE Photonics J., vol. 8, no. 1, pp. 8–13, Aug. 2016.
5. S. Medina, and I. Biomed, “Normalization and Query Abstraction Based on SNOMED-CT and HL7: Supporting Multicentric Clinical Trials,” IEEE J. Biomed. Health. Inform., vol. 19, pp. 10–16, Jul. 2014.
6. T. Sedghi, “A fast and effective model for cyclic analysis and its application in classification,” Arab. J. Sci. Eng., vol. 38, no. 4, pp. 927–935, Sep. 2013.
7. P. Wu, S. C. H. Hoi, P. Zhao, C. Miao, and Z.-Y. Liu, “Onlinemulti-modal distance metric learning with application to imageretrieval,” IEEE Trans. Knowl. Data Eng., vol. 28, no. 2, pp. 454–467, Feb. 2016.
8. H. C. Shin et al., “Deep convolutional neural networks for computeraideddetection CNN architectures, dataset characteristics and transfer learning,” IEEE Trans. Med. Imag., vol. 35, no. 5, pp. 1285–1298, May. 2016.
9. S.Shafei, H.Vahdati, T. Sedghi, and A. Charmin, “Novel high level retrieval system based on mathematic algorithm & technique for MRI medical imaging and classification,” J. Instrum., vol. 16, no. 7, pp. 1–14, Jul. 2021.
10. J. Li, J. Wang, and J. Z. Wiederhold, “Integrated region matching for image retrieval in proceedings,” The 8th ACM International Conference on Multimedia, pp. 147–156, Oct, 2015.
11. F. Baig et al., “Boosting the Performance of the BoVW Model Using SURF– CoHOG-Based Sparse Features with Relevance Feedback for CBIR” Iran. J. Sci. Technol. Trans. Electr. Eng., vol. 44, no. 1, pp. 99–118, Aug 2020.
12. M. h.Hajigholam, A. A.Raie, and K. Faez, “Using sparse representation classifier (SRC) to calculate dynamic coefficients for multitask joint spatial pyramid Matching, ” Iran. J. Sci. Technol. Trans. Electr. Eng., vol. 45, no. 1, pp. 295–307, 2021.
13. F.Rahdari, E.Rashedi, and M.Eftekhari, “ A multimodal emotion recognition system using facial landmark analysis,” Iran. J. Sci. Technol. Trans. Electr. Eng., vol. 43, no. S1, pp. 171–189, Sep. 2019.
14. N. Hor, and S. Fekri-Ershad, “Image retrieval approach based on local texture information derived from predefined patterns and spatial domain information,” Int. J. Comput. Sci. Eng., vol. 8, no. 6, pp. 246–254, Dec 2019.
15. K. M. Hosny, R. M. Farouk, A. M. Alzohairy, and G. Hassan, “Efficient quaternion moments for representation and retrieval of biomedical color images,” Biomed. Eng. Appl. Basis Commun., vol. 32, pp. 1–16, Oct. 2020.
16. G. Hassan, K. M. Hosny, R. M. Farouk, and A. M. Alzohairy, “An efficient retrieval system for biomedical images based on Radial Associated Laguerre Moments,” IEEE Access, vol. 8, pp. 175669–175687, Sep. 2020.