Abstract
Medical images are growing dramatically both in quantity and application in the data era and the emerging Big Data problem. Searching and finding the proper medical image among such a huge number of medical images is not possible unless using a proper medical search engine. Indexing is the backend process in information retrieval systems in which documents are annotated with the index entry to be retrieved more accurately and efficiently. Most of the indexing techniques for medical images are content-based that are more complex and time consuming than the text-based ones. In this paper, a text-based medical image indexing technique is proposed that use medical images’ attributes and fragments them with the hybrid fragmentation approach (that are used in distributed database design) and re-form each of such attribute fragments into a hierarchy, constructing a multidimensional index. Hybrid fragmentation approach uses both Horizontal and vertical fragmentation of medical images’ attributes provided in header of medical image standard formats (such as the DICOM). Horizontal fragmentation uses values of image attributes (i.e., image content and properties dependent), whilst the vertical fragmentation uses pairwise affinity and correlation of the attributes in the application domain (i.e., application dependent). So, the proposed hybrid fragmentation approach based indexing of medical images aim to consider both the image properties and application statistics together to provide a better functionality. As the experimental performance evaluation results illustrate, the proposed multidimensional indexing can provide better precision of information retrieval rather that a single index or a set of multiple indexes, since that considers semantic relationship of the medical image’s attributes via the hybrid (horizontal and vertical) fragmentation. Moreover, the hybrid fragmentations approach based indexing also outperforms the vertical fragmentation-based multidimensional medical image indexing technique in terms of precision, recall and response time.
Similar content being viewed by others
References
Hwang, K.H., Lee, H., Choi, D.: Medical image retrieval: past and present. Healthc Inform Res 18(1), 3–9 (2012)
Schütze, H., Manning, C.D., Raghavan, P.: Introduction to Information Retrieval, vol. 39. Cambridge University Press (2008)
Ceri, S., Bozzon, A., Brambilla, M., Della Valle, E., Fraternali, P., Quarteroni, S.: Web Information Retrieval. Springer, Berlin (2013)
Mosteghanemi, H., Drias, H.: Towards a multidimensional information retrieval. In: New Contributions in Information Systems and Technologies, pp. 91–100. Springer, Berlin (2015)
Renita, D.B., Christopher, C.S.: Novel real time content based medical image retrieval scheme with GWO-SVM. Multimedia Tools Appl. 14, 1–7 (2020)
Srinivas, M.: Medical image indexing and retrieval using multiple features. pp. 365–369 (2013).
Habibi Asl, S., Safaei, A.A.: Medical image retrieval approaches, methods and systems: a systematic review. Pajoohandeh J. 21(2), 61–73 (2016)
Cai, T. W., Kim, J., Feng, D. D.: Content-based medical image retrieval. In: Biomedical information technology. Academic Press, New York, pp. 83–113 (2008)
Sudhamani, M.V., Venugopal, C.R.: Multidimensional indexing structures for content-based image retrieval: a survey. Int. J. Innov. Comput. Inf. Control 4(4), 867–882 (2008)
Kumar, A., Kim, J., Cai, W., Fulham, M., Feng, D.: Content-based medical image retrieval: a survey of applications to multidimensional and multimodality data. J. Digit. Imaging 26(6), 1025–1039 (2013)
Das, P., Neelima, A.: An overview of approaches for content-based medical image retrieval. Int. J. Multimedia Inf. Retr. 6(4), 271–280 (2017)
Owais, M., Arsalan, M., Choi, J., Park, K.R.: Effective diagnosis and treatment through content-based medical image retrieval (CBMIR) by using artificial intelligence. J. Clin. Med. 8(4), 462 (2019)
Malviya, N., Choudhary, N., Jain, K.: Content based medical image retrieval and clustering based segmentation to diagnose lung cancer. Adv. Comput. Sci. Technol. 10(6), 1577–1594 (2017)
Kumar, M., Singh, K.M.: Retrieval of head–neck medical images using Gabor filter based on power-law transformation method and rank BHMT. SIViP 12(5), 827–833 (2018)
Mezzoudj, S., Behloul, A., Seghir, R., Saadna, Y.: A parallel content-based image retrieval system using spark and tachyon frameworks. J. King Saud University-Computer Inf. Sci. 33(2), 141–149 (2019)
Siddiqa, A., Karim, A., Chang, V.: SmallClient for big data: an indexing framework towards fast data retrieval. Clust. Comput. 20(2), 1193–1208 (2017)
Lan, R., Zhong, S., Liu, Z., Shi, Z., Luo, X.: A simple texture feature for retrieval of medical images. Multimedia Tools Appl. 77(9), 10853–10866 (2018)
Özsu, M.T., Valduriez, P.: Distributed and Parallel Database Design. In Principles of Distributed Database Systems 2020 (pp. 33–89). Springer, Cham.
Ahmed, K.T., Iqbal, M.A.: Region and texture based effective image extraction. Clust. Comput. 21(1), 493–502 (2018)
Depeursinge, A., Miiller, H.: Medical visual information retrieval based on multi-dimensional texture modeling. Procedia Comput. Sci. 1(7), 127–129 (2011 Jan)
Silberschatz, A., Korth, H.F., Sudarshan, S.: Database System Concepts, 7th edn. McGraw-Hill, New York (2020)
Kumar, S., Madria, S., Linderman, M.: M-Grid: a distributed framework for multidimensional indexing and querying of location based data. Distributed and Parallel Databases. 35(1), 55–81 (2017)
Safaei, A.A., Habibi, A. S.: Multidimensional Indexing Technique for Medical Images Retrieval. J. Intell. Data Analysis (2021)
Safaei, A., HabibiAsl, S.: Diamond: multi-dimensional indexing technique for medical images retrieval using vertical fragmentation approach. J. Supercomput. 4, 1–60 (2021)
Wan, S., Zhao, Y., Wang, T., Gu, Z., Abbasi, Q.H., Choo, K.K.: Multi-dimensional data indexing and range query processing via Voronoi diagram for internet of things. Futur. Gener. Comput. Syst. 1(91), 382–391 (2019)
Elkariem, A.F., Bashir. M.B., Ahmed, T.H., Yousif, A.: Distributed medical image retrieval techniques: a review. In: IEEE 2017 Sudan Conference on Computer Science and Information Technology (SCCSIT), pp. 1–7 (2017)
Özsu, M.T., Valduriez, P.: Principles of Distributed Database Systems. Springer, Berlin (2011)
Valduriez, P., Jimenez-Peris, R., Özsu, M.T.: Distributed database systems: the case for NewSQL. In: Transactions on Large-Scale Data-and Knowledge-Centered Systems XLVIII 2021, pp. 1–15. Springer, Berlin (2021)
Nashat, D., Amer, A.A.: A comprehensive taxonomy of fragmentation and allocation techniques in distributed database design. ACM Comput. Surv. (CSUR) 51(1), 1–25 (2018)
Ubaidillah, S.H., Ahmad, N.: Fragmentation techniques for ideal performance in distributed database—a survey. Int. J. Softw. Eng. Comput.Syst. 6(1), 18–24 (2020)
Castro-Medina, F., Rodríguez-Mazahua, L., López-Chau, A., Cervantes, J., Alor-Hernández, G., Machorro-Cano, I.: Application of dynamic fragmentation methods in multimedia databases: a review. Entropy 22(12), 1352 (2020)
Rinaldi, A.M., Russo, C.: User-centered information retrieval using semantic multimedia big data. In: 2018 IEEE International Conference on Big Data (Big Data), pp. 2304–2313 (2018).
MÜLLERac, H., Kalpathy-Cramer, J., Hersh, W., Geissbuhler, A.: Using Medline queries to generate image retrieval tasks for benchmarking. eHealth Beyond the Horizon–Get IT There:523 (2007)
Tsikrika, T., Müller, H., Kahn Jr, C.E.: Log analysis to understand medical professionals’ image searching behaviour. In: Medical Informatics Europe (2012).
Funding
No funding or grant.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Author declares that he has no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Safaei, A.A. Hybrid fragmentation of medical images’ attributes for multidimensional indexing. Cluster Comput 25, 215–230 (2022). https://doi.org/10.1007/s10586-021-03356-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10586-021-03356-7