Hybrid Ontology-Deep Learning Integrated CBMIR System for CT Lung Diseases

Hybrid Ontology-Deep Learning Integrated CBMIR System for CT Lung Diseases

© 2021 by IJETT Journal
Volume-69 Issue-9
Year of Publication : 2021
Authors : Nora yahia Ibrahim, Amira samy Talaat, Hany M. Harb
DOI :  10.14445/22315381/IJETT-V69I9P223

How to Cite?

Nora yahia Ibrahim, Amira samy Talaat, Hany M. Harb, "Hybrid Ontology-Deep Learning Integrated CBMIR System for CT Lung Diseases," International Journal of Engineering Trends and Technology, vol. 69, no. 9, pp. 193-202, 2021. Crossref, https://doi.org/10.14445/22315381/IJETT-V69I9P223

Recently, radiologists and general practitioners diagnose abnormal CT (Computed Tomography) lung images based on the CBMIR (Content-Based Medical Image Retrieval) system. This system idea is to extract the image feature and retrieve the relevant CT lung images that match a query image. The semantic gap between low-level visual content images and conceptual high-level semantic knowledge is a challenge in the CBMIR system. Most of the conventional CBMIR system works on the details of the images and doesn`t exploit the metadata, for example, tags, image description, etc. This paper tackles this problem by using the metadata that describes the contents of images. This paper utilizes the high-level knowledge representation structure called ontology that represents the semantic annotations extracted from metadata to improve the classification accuracy of the CBMIR. Two stages are proposed to retrieve medical images: the classification and the retrieval stages. In the classification stage, the images are trained using a Deep Convolutional Neural Network (DCNN), and then the trained model is used to classify the CT lung images. However, the images are retrieved from the predicted class according to a query image in the retrieval stage. In addition, it retrieves similar images from the whole database without incorporating class prediction. The proposed method is evaluated in retrieving common CT Imaging Signs (CISs), which are vital for diagnosing lung diseases. The proposed method achieved an accuracy of 95.2 for the classification task and a mean average precision (mAP) of 0.742 for the retrieval task.

ontology, deep learning, semantic, image retrieval, lung diseases.

[1] Liu X., Ma L., Song L., Zhao Y., Zhao X., Zhou C.: Recognizing common ct imaging signs of lung diseases through a new feature selection method based on fisher criterion and genetic optimization, IEEE journal of biomedical and health informatics, 19(2) (2014) 635–647.
[2] Han G., Liu X., Han F., Santika I. N. T., Zhao Y., Zhao X., Zhou C.: The liss —a public database of common imaging signs of lung diseases for computer-aided detection and diagnosis research and medical education, IEEE Transactions on Biomedical Engineering, 62(2) (2014) 648–656.
[3] Aigrain, P., Zhang, H., Petkovic, D. Content-based representation and retrieval of visual media: a state-of-the-art review,”.Multimedia Tools Appl. 3 (1996) 179–202.
[4] Suresh M B, Dr.B Mohankumar Naik. An Efficient Approach of Content-Based Image Retrieval using Texture, Color and Shape Features of an Image, International Journal of Engineering Trends and Technology (IJETT) – 48(2017) 316-320.
[5] Raicu DS, Varutbangkul E, Furst JD, Armato III, SG: Modeling semantics from image data: opportunities from LIDC. IJBET 2 (2008) 1–22.
[6] M.M. Rahman, S.K. Antani, G.R. Thoma, A medical image retrieval framework in correlation enhanced visual concept feature space, in 22nd IEEE International Symposium on Computer-Based Medical Systems, (2009) 1–4.
[7] Johannes Hofmanninger, Georg Langs, Mapping Visual Features to Semantic Profiles for Retrieval in Medical Imaging, Proceedings of the IEEE, – open access. The cvf.com, (2015) 457-465.
[8] Camille Kurtz, Adrien Depeursinge, Sandy Napel, Christopher F. Beaulieu, Daniel L. Rubin. On combining image-based and ontological semantic dissimilarities for medical image retrieval applications, Medical Image Analysis, 18(7) (2014) 1082-1100.
[9] Yang Chen, Xiaofeng Ren, Guo-Qiang Zhang, Rong X, Ontology-guided organ detection to retrieve web images of disease manifestation: towards the construction of a consumer-based health image library, Med Inform Assoc (2013) 1076–1081.
[10] Filali J, Zghal HB, Martinet J. Ontology and HMAX features-based image classification using merged classifiers. In: Proceedings of the 14th international joint conference on computer vision, imaging and computer graphics theory and applications, VISIGRAPP 5 (2019). SciTePress, (2019) 124–134.VISAPP, Prague, Czech Republic, February 25-27.
[11] Filali, J., Zghal, H. B., and Martinet, J.. Towards Visual Vocabulary and Ontology-based Image Retrieval System. In Proceedings of the 8th International Conference on Agents and Artificial Intelligence (ICAART 2016) – 2 (2016) 560-565.
[12] Umar Manzoor, Mohammed A., Bassam Zafar, Hafsa Umar, M. Shoaib Khan, Semantic Image Retrieval: An Ontology-Based Approach, (IJARAI) International Journal of Advanced Research in Artificial Intelligence, 4(4) (2015).
[13] R. Biswas, S. Roy Content-Based CT Image Sign Retrieval using Fast Discrete Curvelet Transform and Deep Learning, International Journal of Advanced Trends in Computer Science and Engineering 8(3) (2019).
[14] M. Kashif, Gulistan Raj.,f. Shaukat, An Efficient Content-Based Image Retrieval System for the Diagnosis of Lung Diseases, Journal of Digital Imaging (2020) 971–987.
[15] 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, 66 (2017) 148–158.
[16] Ranjit Biswas, Sudipta Roy, Abhijit Biswas, Triplet Contents based Medical Image Retrieval System for Lung Nodules CT Images Retrieval and Recognition Application, International Journal of Engineering and Advanced Technology (IJEAT)ISSN: 2249 –8958, 8(6) (2019).
[17] Luhn, H. P. A statistical approach to the mechanized encoding and searching of literary information. IBM Journal of Research and Development 1(4), (1957) 309–317.
[18] D. B. Lenat, Cyc: A Large-scale investment in Knowledge Infrastructure, Communications of the ACM, 38(11) (1995) 33-38.
[19] G. A. Miller, Wordnet: a lexical database for English, Communications of the ACM, 38(11) (1995) 39–41.
[20] G. Miller, Nouns in WordNet: a Lexical Inheritance System, International Journal of Lexicography, 3(4) (1994) 245-264.
[21] Maillot N, Thonnat M, Boucher A. Towards ontology-based cognitive vision, Machine Vision and Applications. Springer. 16(1) (2004) 33–40.