Medical diagnostic support systems are important tools in the field of radiology. However, the precision obtained, during the exploitation of high homogeneity image datasets, needs to be improved.
OBJECTIVE:
To develop a new learning system dedicated to public health practitioners. This study presents an upgraded version dedicated to radiology experts for better clinical decision-making when diagnosing and treating the patient (CAD approach).
METHODS:
Our system is a hybrid approach based on a matching of semantic and visual attributes of images. It is a combination of two complementary subsystems to form the intermodal system. The first one named α based on semantic attributes. Indexing and image retrieval based on specific keywords. The second system named β based on low-level attributes. Vectors characterizing the digital content of the image (color, texture and shape) represent images. Our image database consists of 930 X-ray images including 320 mammograms acquired from the mini-MIAS database of mammograms and 610 X-rays acquired from the Public Hospital Establishment (EPH-Rouiba Algeria). The combination of two subsystems gives rise to the intermodal system: α-subsystem offers an overall result (based on visual descriptors), then β-subsystem (low level descriptors) refines the result and increases relevance.
RESULTS:
Our system can perform a specific image search (in a database of images with very high homogeneity) with an accuracy of around 90% for a recall of 25%. The average (overall) accuracy of the system exceeds 70%.
CONCLUSION:
The results obtained are very encouraging, and demonstrate efficiency of our approach, particularly for the intermodal system.
SivakamasundariJ., KavithaG., NatarajanV., RamakrishnanS. Proposal of a Content Based retinal Image Retrieval system using Kirsch template-based edge detection, Int Conference on Informatics Electronics and Visio n (ICIEV) (2014), 1–5.
2.
CandemirS., JaegerS., PalaniappanK.et al., Lung segmentation in chest radiographs using anatomical atlases with non-rigid registration, IEEE Trans Med Imaging33(2) (2014), 577–590.
3.
OussalahA., LaclotteC., ChevauxJ.B.et al., Long-term outcome of adalimumab therapy for ulcerative colitis with intolerance or lost response to infliximab: a single-center experience, Aliment Pharmacol Ther28(8) (2014), 966–972.
4.
RuofeiZ., ZhongfeiZ., MingjingL.et al., A probabilistic semantic model for image annotation and multimodal image retrieval, Tenth IEEE Int Conference on Computer Vision (ICCV’05)1 (2005), 846–851.
5.
AkgulC.B., RubinD.L., NapelS.et al., Content-Based Image Retrieval in Radiology: Current Status and Future Directions, Int J of Digital Imaging24(2) (2011), 208–222.
6.
FloreaF., RogozanA., BensrhairA.et al., Modality Categorization by Textual Annotations Interpretation in Medical Imaging, Connecting Medical Informatics and Bio-Informatics R. Engelbrecht et al. (Eds.) ENMI (2005).
7.
OliveiraJ.E., MachadoA., ChavezG.C.et al., A content-based image retrieval system using breast density patterns, Computer Methods and Programs in Biomedicine99(3) (2010), 289–97.
8.
RamosJ., KockelkornT.T.J.P., RamosI.et al., Content-based image retrieval by metric learning from radiology reports: Application to interstitial lung diseases, IEEE J of Biomedical and Health Informatics20(1) (2016), 281–292.
9.
RajalakshmiT., MinuR.I. improving relevance feedback for content based medical image retrieval, Int Conference on Information Communication and Embedded Systems (ICICES2014) (2014), 1–5.
10.
SidhomS., DavidA. Automatic indexing of multimedia documents as a starting point to annotation process, 9th Int Conference ISKO, Vienna, Austria (2006).
11.
RangayyanR.M., MudigondaN.R., DesautelsJ.E.L.Boundary modelling and shape analysis methods for classification of mammographic masses, Med Biol Eng Comput38 (2000), 487–496.
12.
TangG.Y.A management system for an integrated database of pictures and alphanumerical data, Computer Graphics and Image Processing16(3) (1981), 270–286.
13.
PrasadB.E., GuptaA., TongH.D.et al., A microcomputer-based image database management system, in IEEE Trans on Industrial Electronics34(1) (1987), 83–88.
14.
KuntM., IkonomopoulosA., KocherM.Second-generation image-coding techniques, Proceedings of the IEEE73(4) (1985), 549–574.
15.
BaxterG., AndersonD.Image indexing and retrieval: some problems and proposed solutions, New Library World96(6) (1995), 4–13.
16.
NASA CR-189791, Digital document imaging systems: an overview and guide, Nasa scientific and technical information facility. RMS Associates. N92-18254, (1990).
17.
WangY., MitraS.K.Image representation using block pattern models and its image processing applications, IEEE Trans on Pattern Analysis and Machine Intelligence15(4) (1993), 321–336.
18.
MakandarA.Content based image retrieval using image preprocessing techniques, NOVYI MIR Research Journal5(11) (2020), 44–50.
19.
AkrourL., AmeurS., LahdirM.et al., Fast hyperspectral image encoder based on supervised multimodal scheme, Int J Image Graph21(1) (2021).
20.
LeeS.H., KimJ.Y.Classification of the era emotion reflected on the image using characteristics of color and color-based classification method, Int J of Software Engineering and Knowledge Engineering29(8) (2019), 1103–1123.
21.
ChinnasamyV.A., ShashikumarD.R.Breast cancer detection in mammogram image with segmentation of tumor region, Int J Medical Engineering and Informatics12(1) (2020), 77–94.
22.
ParkerJ.R., BehmB.Composite algorithms in image content searches, Int J of Software Engineering and Knowledge Engineering17(4) (2007), 451–463.
23.
ArunlalS.L., SanthiN., RamarK.Design and implementation of content-based natural image retrieval approach using feature distance, Int J Image Graph20(2) (2020).
24.
RodrigoD.C.S., ThomasR.J.Classification of mammogram abnormalities using Legendre moments, Int J Image Graph20(1) (2020).
25.
WangL., ShiC., LinS.et al., Convolutional sparse representation and local density peak clustering for medical image fusion, Int J of Pattern Recognition and Artificial Intelligence34(7) (2020).
26.
RajendiranN., GurunathanT., PalanivelM.Wavelet packet transform-based medical image multiple watermarking with independent component analysis extraction, Int J Medical Engineering and Informatics12(4) (2020), 322–335.
27.
SinghV.P., SrivastavaS., SrivastavaR.Automated and effective content-based image retrieval for digital mammography, Journal of X-ray Science and Technology26(1) (2018), 29–49.
28.
ShatnawiM.Q., Al-RousanM.A., AmareenS.A new approach for content-based image retrieval for medical applications using low-level image descriptors, Int J of Electrical and Computer Engineering10 (2020), 4363–4371.
29.
NatarajanM., SathiamoorthyS.Heterogeneous medical image retrieval using multi-trend structure descriptor and fuzzy SVM classifier, Int J of Recent Technology and Engineering (IJRTE)8(3) (2019), 3958–3963.
30.
FadaeiS., AmirfattahiR., AhmadzadehM.R.New content-based image retrieval system based on optimized integration of DCD, wavelet and curvelet features, IET Image Processing11(2) (2017), 89–98.
31.
CruzT.N., CruzT.M., SantosW.P.Detection and classification of mammary lesions using artificial neural networks and morphological wavelets, IEEE Latin America Transactions16(3) (2018), 926–932.
32.
AdamsW.H., IyengarG., LinC.Y.et al., Semantic indexing of multimedia content using visual, audio and text cues, EURASIP J on Applied Signal Processing2 (2003), 170–185.
33.
DashJ.K., MukhopadhyayS.Similarity learning for texture image retrieval using multiple classifier system, Multimedia Tools and Applications77 (2018), 459–483.
34.
BourkacheN., LaghroucheM., SidhomS. Gabor filter algorithm for medical image processing: evolution in big data context, Int Multi-Conference on Organization of Knowledge and Advanced Technologies (OCTA) (2020), 1–4.
35.
AdegbolaO.A., AborisadeD.O., PopoolaS.I., AtayeroA.A.Performance evaluation of visual descriptors for image indexing in content based image retrieval systems, Gervasi O. et al. (eds) Computational Science and Its Applications (ICCSA, Lecture Notes in Computer Science10963 (2018).
36.
SidhomS., BourkacheN., LaghroucheM. Multimodal indexing and information retrieval system based on mammographic image analysis: Gabor model in digital learning, Dey, Nilanjan, and Amira Ashour, eds. Classification and Clustering in Biomedical Signal Processing (2016), 170–197.
37.
BarnardK., DuyguluP., FreitasN.et al., Matching words and pictures, J of Machine Learning Research3 (2003), 1107–1135.
38.
OmhoverJ.F., DetynieckiM. Combining text and image retrieval, EUROFUSEWorkshop on Data and Knowledge Engineering (2004), 388–398.
39.
RodneyL., AntaniS., DesemoT.M.et al., Content-based image retrieval in medicine: retrospective assessment, state of the art, and future directions, Int Journal of Healthcare Information Systems and Informatics, (IJHISI)4(1) (2009), 1–16.
40.
CsillaghyA., HinterbergerH., BenzA.O.Content-based image retrieval in astronomy information retrieval, Manufactured in The Netherlands3(3) (2000), 229–241.
41.
RuiL., YongshengZ., YonghongF., DengX.Research on content-based remote sensing image retrieval: the strategy for visual feature selection, extraction, description and similarity measurement, Int Conferences on Info-Tech and Info-Net Proceedings (Cat. No.01EX479)1 (2001), 321–325.
42.
AnupamM. Retrieval of multimedia information using content-based image retrieval (CBIR) techniques, intelligent analysis of multimedia information, edited by Siddhartha Bhattacharyya, et al., IGI Global (2017), 143–180.
43.
KoreV.S., ChandreP., AbhyankarP.P. Integrated algorithm (S-CBIR) for image retrieval in image-rich information networks, Int Conference on Communications and Signal Processing (ICCSP) (2015), 1337–1342.
44.
HuM.K.Visual pattern recognition by moment invariants, IRE Transactions on Information Theory8(2) (1962), 179–187.
