Riccardo Di Palermo
ABSTRACT
A number of previous studies have shown that IIF image analysis requires complex and sometimes heterogeneous and diversified methods. Robust solutions can be proposed but they need to orchestrate several methods from low-level analysis up to more complex neural networks or SVM for data classification. The contribution intends to highlight the versatility of Wavelet Transform (WT) and their use in various levels of analysis for the classification of IIF images in order to develop a system capable of performing: image enhancement, ROI segmentation and object classification. Therefore, WT was adopted in the de-noise section, segmentation and classification. This analysis allows frequencies characterization (low/high) and with the statistical distributions of the wavelet coefficients will be able to support the medical diagnosis process. In particular, the robustness and the goodness of the segmentation phase must be highlighted and its validation was reported in the section 3.2.1. From the depicted data it is possible to assert that the validation with ground truths produced an accuracy of 90% and that the method, to the best of our knowledge, is superior to other methods, which do not support WT (see Table 1). The advantage of using WT in all levels of abstraction of IIF data analysis lies robustness of the method, and in the rapid understanding, by the end user, of a single method that shows good average results in all levels of analysis.
- AIDA. 2007. AIDA HEp-2 images dataset. http://www.aidaproject.net/index.php/it/component/users/?view=login.Google Scholar
- M. Alfano, B. Lenzitti, G. Lo Bosco, and V. Perticone. 2015. An automatic system for helping health consumers to understand medical texts. HEALTHINF 2015 - 8th International Conference on Health Informatics, Proceedings; Part of 8th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2015 (2015), 622--627. Google ScholarDigital Library
- A. Anzalone, G. Fusco, F. Isgró, E. Orlandi, R. Prevete, G. Sciortino, D. Tegolo, and C. Valenti. 2013. A system for the automatic measurement of the nuchal translucency thickness from ultrasound video stream of the foetus. In 26th IEEE International Symposium on Computer--Based Medical Systems. 239--244.Google Scholar
- V. Badrinarayanan, A. Kendall, and R. Cipolla. 2017. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 12 (2017), 2481--2495.Google ScholarCross Ref
- B. Ballaró, A.M. Florena, V. Franco, D. Tegolo, C. Tripodo, and C. Valenti. 2008. An automated image analysis methodology for classifying megakaryocytes in chronic myeloproliferative disorders. Medical Image Analysis 12, 6 (2008), 703-- 712.Google ScholarCross Ref
- N. Bayramoglu, J. Kannala, and J. Heikkilä. 2015. Human Epithelial Type 2 cell classification with convolutional neural networks. In IEEE 15th International Conference on Bioinformatics and Bioengineering. 1--6. Google ScholarDigital Library
- N. Bizzaro, I. Brusca, and et al. 2018. The association of solid-phase assays to immunofluorescence increases the diagnostic accuracy for ANA screening in patients with autoimmune rheumatic diseases. Autoimmunity Reviews 17, 6 (2018), 541--547.Google ScholarCross Ref
- A. Brunetti, L. Carnimeo, G.F. Trotta, and V. Bevilacqua. 2018. Computer-assisted frameworks for classification of liver, breast and blood neoplasias via neural networks: A survey based on medical images. Neurocomputing 335 (2018), 278-- 298.Google Scholar
- D. Cascio, V. Taormina, and G. Raso. 2019. An automatic HEp-2 specimen analysis system based on an active contours model and an SVM classification. Applied Sciences 9, 2 (2019).Google Scholar
- I. Dagher and S. Issa. 2012. Subband effect of the wavelet fuzzy C-means features in texture classification. Image and Vision Computing 30, 11 (2012), 896--905. Google ScholarDigital Library
- Lee R. Dice. 1945. Measures of the Amount of Ecologic Association Between Species. Ecology 26, 3 (1945), 297--302.Google ScholarCross Ref
- B. S. Divya, K. Subramaniam, and H. R. Nanjundaswamy. 2017. HEp-2 cell classification using artificial neural network approach. In International Conference on Pattern Recognition. 84--89.Google Scholar
- K. Doi. 2007. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential. Computerized Medical Imaging and Graphics 31, 4-5 (2007), 198--211.Google ScholarCross Ref
- S. Elakkiya and S. Audithan. 2014. Feature based object recognition using discrete wavelet transform. In Second International Conference on Current Trends In Engineering and Technology - ICCTET 2014. 393--396.Google ScholarCross Ref
- P. Foggia, G. Percannella, P. Soda, and M. Vento. 2013. Benchmarking HEp-2 cells classification methods. IEEE Trans Med Imaging 32, 10 (2013), 1878--1889.Google ScholarCross Ref
- G. J. Friou. 1962. Fluorescent spot test for anti-nuclear antibodies. Arthritis & Rheumatism 5, 4 (1962), 407--410.Google ScholarCross Ref
- R. Girshick, J. Donahue, T. Darrell, and J. Malik. 2016. Region-Based Convolutional Networks for Accurate Object Detection and Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 38, 1 (2016), 142--158. Google ScholarDigital Library
- D. Guastella and C. Valenti. 2016. Cartoon filter via adaptive abstraction. Journal of Visual Communication and Image Representation 36 (2016), 149--158. Google ScholarDigital Library
- K. Gupta, V. Gupta, A.K. Sao, A. Bhavsar, and A.D. Dileep. 2014. Class-specific hierarchical classification of hep-2 cell images: The case of two classes. In 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. 6--9. Google ScholarDigital Library
- H. Hamad, D. Tegolo, and C. Valenti. 2014. Automatic detection and classification of retinal vascular landmarks. Image Analysis and Stereology 33, 3 (2014), 189--200.Google ScholarCross Ref
- International Consensus on ANA Patterns. 2015. ANA-Patterns dataset. https://www.anapatterns.org/.Google Scholar
- X. Jiang, G. Percannella, and M. Vento. 2015. A verification-based multithreshold probing approach to HEp-2 cell segmentation. LNCS 9257 (2015), 266--276. Google ScholarDigital Library
- A. Kavanaugh, R. Tomar, J. Reveille, D.H. Solomon, and H.A. Homburger. 2000. Guidelines for clinical use of the antinuclear antibody test and tests for specific autoantibodies to nuclear antigens. Arch Pathol Lab Med 124, 1 (2000), 71--81.Google Scholar
- T. Liu, W. Zhang, and S. Yan. 2015. A novel image enhancement algorithm based on stationary wavelet transform for infrared thermography to the de-bonding defect in solid rocket motors. MSSP 62 (2015), 366--380.Google ScholarCross Ref
- M. Mafi, H. Martin, M. Cabrerizo, J. Andrian, A. Barreto, and M. Adjouadi. 2019. A comprehensive survey on impulse and Gaussian denoising filters for digital images. Signal Processing 157 (2019), 236--260.Google ScholarDigital Library
- A. Mencattini, M. Salmeri, R. Lojacono, M. Frigerio, and F. Caselli. 2008. Mammographic images enhancement and denoising for breast cancer detection using dyadic wavelet processing. IEEE Trans Instrum Meas 57, 7 (2008), 1422--1430.Google ScholarCross Ref
- M. Merone and P. Soda. 2016. On using active contour to segment HEp-2 cells. In IEEE Symposium on Computer-Based Medical Systems. 118--123.Google Scholar
- MIVIA LAB. 2010. HEp-2 images dataset. http://mivia.unisa.it/datasets/biomedical-image-datasets/hep2-image-dataset/.Google Scholar
- E. Pellegrini, G. Robertson, E. Trucco, T.J. MacGillivray, C. Lupascu, J. van Hemert, M.C. Williams, D.E. Newby, E.J.R. van Beek, and G. Houston. 2014. Blood vessel segmentation and width estimation in ultra-wide field scanning laser ophthalmoscopy. Biomedical Optics Express 5, 12 (2014), 4329--4337.Google ScholarCross Ref
- G. Percannella, P. Soda, and M. Vento. 2012. A classification-based approach to segment HEp-2 cells. In IEEE Symp. on Computer-Based Medical Systems. 1--5.Google Scholar
- Z. Qinli, S. Shuting, S. Xiaoyun, and G. Qi. 2017. A novel method of medical image enhancement based on wavelet decomposition. Automatic Control and Computer Sciences 51, 4 (2017), 263--269.Google ScholarCross Ref
- S. Roy and P. Maji. 2017. A modified rough-fuzzy clustering algorithm with spatial information for HEp-2 cell image segmentation. In IEEE International Conference on Bioinformatics and Biomedicine. 383--388.Google Scholar
- M. Satoh and et al. 2009. Clinical interpretation of antinuclear antibody tests in systemic rheumatic diseases. Mod Rheumatol 19, 3 (2009), 219--228.Google ScholarCross Ref
- G. Sciortino, E. Orlandi, C. Valenti, and D. Tegolo. 2016. Wavelet analysis and neural network classifiers to detect mid-sagittal sections for nuchal translucency measurement. Image Analysis and Stereology 35, 2 (2016), 105--115.Google ScholarCross Ref
- G. Sciortino, D. Tegolo, and C. Valenti. 2017. Automatic detection and measurement of nuchal translucency. Computers in Biology and Medicine 82 (2017), 12--20. Google ScholarDigital Library
- I.W. Selesnick, R.G. Baraniuk, and N.G. Kingsbury. 2005. The dual-tree complex wavelet transform. IEEE Signal Processing Magazine 22, 6 (2005), 123--151.Google ScholarCross Ref
- V. K. Sudarshan and et al. 2016. Application of wavelet techniques for cancer diagnosis using ultrasound images: A Review. Comput Biol Med 69 (2016), 97--111. Google ScholarDigital Library
- J. Tian and et al. 2018. Radiomics in medical imaging-detection, extraction and segmentation. Intelligent Systems Reference Library 140 (2018), 267--333.Google ScholarCross Ref
- S. Tonti and et al. 2015. An automated approach to the segmentation of HEp-2 cells for the indirect immunofluorescence ANA test. Comput Med Imaging Graph 40 (2015), 62--69.Google ScholarCross Ref
- C. Tripodo, C. Valenti, B. Ballaró, Z. Rudzki, D. Tegolo, V. Di Gesú, A.M. Florena, and V. Franco. 2006. Megakaryocytic features useful for the diagnosis of myeloproliferative disorders can be obtained by a novel unsupervised software analysis. Histology and Histopathology 21, 7-9 (2006), 813--821.Google Scholar
- D. Wormanns and et al. 2002. Automatic detection of pulmonary nodules at spiral CT: clinical application of a computer-aided diagnosis system. European Radiology 12, 5 (2002), 1052--1057.Google ScholarCross Ref
- P. Yang and G. Yang. 2018. Statistical model and local binary pattern based texture feature extraction in dual-tree complex wavelet transform domain. Multidimensional Systems and Signal Processing 29, 3 (2018), 851--865. Google ScholarDigital Library
- Y. Yang, Z. Su, and L. Sun. 2010. Medical image enhancement algorithm based on wavelet transform. Electronics Letters 46, 2 (2010), 120--121.Google ScholarCross Ref
- X. Zhou, Y. Li, and L. Shen. 2016. A novel adaptive local thresholding approach for segmentation of HEp-2 cell images. In IEEE International Conference on Signal and Image Processing. 174--178.Google Scholar
Index Terms
- A Wavelet approach to extract main features from indirect immunofluorescence images
Recommendations
New features for speech enhancement using bivariate shrinkage based on redundant wavelet filter-banks
There are some dependencies among wavelet coefficients.Bivariate shrinkage was proposed based on parent-child coefficients dependencies.Two-channel critically sampled filter-bank is not suitable for bivariate shrinkage.Multi-channel redundant wavelet ...
Application and numerical investigation of wavelet transform for traffic data denoising
Math'04: Proceedings of the 5th WSEAS International Conference on Applied MathematicsGood fitting of traffic data is important to traffic study because initial and boundary conditions of dynamic traffic models and relationships among traffic variables are dependent on the calibration of data. In this paper, a denoising method of traffic ...
Fusion of multimodal medical images using Daubechies complex wavelet transform - A multiresolution approach
Multimodal medical image fusion is an important task for the retrieval of complementary information from medical images. Shift sensitivity, lack of phase information and poor directionality of real valued wavelet transforms motivated us to use complex ...
Comments