Multi-scale dyadic filter modulation based enhancement and classification of medical images


For the last many decades, the research is towards the classification of medical images in the early phase of its detection. But, the task becomes challenging due to the absence of the color information, like in natural scene images, and low illumination. In this paper, a multi-scale spectral approach is proposed for the classification of medical images. The proposed approach uses a dyadic filter bank extended to six scales for simultaneous modulation of the frequency and amplitude signal of the medical image. The modulated signal strength is used for enhancing the contrast of the image as a preprocessing step. The 32 bin spectral histogram is used to fetch the features using different modulation components at each scale of the dyadic filter bank. The proposed method has experimented with two medical imaging databases - one is malignant Brain tumor MRI scans collected from SMS medical college Jaipur. The second database is from the TCIA data repository having three datasets of Lung-CT and Brain MRI. These datasets have experimented with SVM using a quadratic kernel function. The experimental results show that the proposed approach fetches better textural information as compared with traditional texture analysis methods. Based on the analysis of the experimentation results, it is recommended that the use of the spectral features gives better early detection of the abnormalities for medical imaging datasets.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8


  1. 1.

    Amira S, Sourav S, Nilanjan D et al (2015) Computed tomography image enhancement using cuckoo search: a log transform based approach. Sig and Info Proc 6:244–257

    Google Scholar 

  2. 2.

    Cancer Imaging Archive,, accessed on 15 May 2018.

  3. 3.

    Chu J, Guo Z, Leng L (2018) Object detection based on multi-layer convolution feature fusion and online hard example mining. Access 6:19959–19967

    Article  Google Scholar 

  4. 4.

    Cristianini N, Taylor J.S (2000). An introduction to support vector machines and other kernel-based learning methods, 1st ed. Cambridge, MA: Cambridge Univ. Press

  5. 5.

    Fesharaki N.J, Pourghassem H (2012). Medical x-ray images classification based on shape features and bayesian rule, Int. Conf. on Comp. Intel. and Comm. Net., pp. 369–373

  6. 6.

    Fesharaki NJ, Pourghassem H (2013) Medical X-Ray Image Hierarchical Classification Using a Merging and Splitting Scheme in Feature Space. Jour. Med Sig. and Sens. 3(3):150–163

    Article  Google Scholar 

  7. 7.

    Guo W, Xia X, Xiaofei W (2014) A remote sensing ship recognition method based on dynamic probability generative model. Expert Syst Appl 41:6446–6458

    Article  Google Scholar 

  8. 8.

    Hong L, Wan Y, Jain A (1998) Fingerprint image enhancement: algorithm and performance evaluation, trans. Pat Anal & Mach Intel 20(8):777–789

    Article  Google Scholar 

  9. 9.

    Jiang G, Wong CY, Lin SCF, Rahman MA, Ren TR, Kwok N, Shi H, Yu YH, Wu T (2015) Image contrast enhancement with brightness preservation using an optimal gamma correction and weighted sum approach. J Mod Opt 62(7):536–547

    Article  Google Scholar 

  10. 10.

    Jianning C, Walia E, Babyn P et al (2017) Thyroid nodule classification in ultrasound images by fine-tuning deep convolution neural network. Jour of Dig Imag 30(4):477–486

    Article  Google Scholar 

  11. 11.

    Jindal K, Gupta K, Jain M et al. (2014). Bio-medical image enhancement based on spatial domain technique, Int. Conf. on Adv. Eng. & Tech. Res. (ICAETR), pp. 1–5

  12. 12.

    Jing-Jing W, Zhen-Hong J, Xi-Zhong Q et al (2015) Medical image enhancement algorithm based on NSCT and improved fuzzy contrast, Imag. Sys And Tech 25(1):7–14

    Google Scholar 

  13. 13.

    Khatkar K, Kumar D (2015) Biomedical image enhancement using wavelets. Proc Comp Sci 48:513–517

    Article  Google Scholar 

  14. 14.

    Kwok NM, Shi HY, Ha QP, Fang G, Chen SY, Jia X (2013) Simultaneous image color correction and enhancement using particle swarm optimization, Eng. Appl Artif Intell 26(10):2356–2371

    Article  Google Scholar 

  15. 15.

    Leng L, Li M, Kim C, Bi X (2017) Dual-source discrimination power analysis for multi-instance contactless Palmprint recognition. Multimed Tools Appl 76:333–354

    Article  Google Scholar 

  16. 16.

    Leng L, Yang Z, Kim C et al (2020) A Light-Weight Practical Framework for Feces Detection and Trait Recognition. Sens 20(9):2644

    Article  Google Scholar 

  17. 17.

    Leng L, Zhang J, Khan MK et al (2010) Dynamic weighted discrimination power analysis: a novel approach for face and Palmprint recognition in DCT domain. Jour of Phy Sci 5(17):2543–2554

    Google Scholar 

  18. 18.

    Leng L, Zhang J, Khan MK et al. (2011). Two-directional two-dimensional random projection and its variations for face and palmprint recognition, Int. Conf. on Comp. sci. and app., pp. 458–470

  19. 19.

    Loizou P, Murray V, Pattichis MS et al (2011) Multiscale amplitude-modulation frequency- modulation (AM–FM) texture analysis of multiple sclerosis in brain MRI images. Trans on Info Tech Biomed 15(1):119–129

    Article  Google Scholar 

  20. 20.

    Miranda E, Aryuni M, Irwansyah E (2017). A survey of medical image classification techniques, Int. Conf. on Info. Mgmt and Tech., pp. 56–61

  21. 21.

    Mohsen H, El-Dahshan EA, El-Horbaty EM et al (2018) Classification using deep learning neural networks for brain tumors, Fut. Comp and Info J 3(1):68–71

    Google Scholar 

  22. 22.

    Murray V, Rodriquez P, Pattichis M (2010) Multi-scale AM-FM demodulation and reconstruction methods with improved accuracy, trans. Imag Process 19(5):1138–1152

    MATH  Article  Google Scholar 

  23. 23.

    Ngaiming K, Shi H, Fang G et al (2015) Color image enhancement using correlated intensity and saturation adjustments. J Mod Opt 62(13):1037–1047

    Article  Google Scholar 

  24. 24.

    Pei S-C, Chiu Y-M (2006) Background adjustment and saturation enhancement in ancient Chinese paintings. Trans Imag Process 15:3230–3234

    Article  Google Scholar 

  25. 25.

    Purushothaman J, Kamiyama M, Taguchi A (2016). Color image enhancement based on hue differential histogram equalization, Int. Sym. on Intelli. Sig. Proc. and Comm. Sys. (ISPACS), pp. 1–5

  26. 26.

    Qinli Z, Shuting S, Xiaoyun S et al (2017) A novel method of medical image enhancement based on wavelet decomposition, autom. Cont and Comp Sci 51(4):263–269

    Article  Google Scholar 

  27. 27.

    Silva S.D, Costa MF, Pereira WC et al. (2015). Breast tumor classification in ultrasound images using neural networks with improved generalization methods, Eng. in Med. and Bio. Soc., pp. 6321–6325

  28. 28.

    Sodanil M, Intarat C (2015). A development of image enhancement for CCTV images, 5th Int. Conf. on IT Conv. and Sec. (ICITCS), pp. 1–4

  29. 29.

    Strickland RN, Kim CS, McDonnell WF (1987) Digital color image enhancement based on the saturation component, opt. Eng. 26(7):26–34

    Google Scholar 

  30. 30.

    Thomas R (2015) Image enhancement of cancerous tissue in mammography images, dissertation for doctor of philosophy in computer science. Nova South eastern University

  31. 31.

    Thomas B, Strickland R, Rodriguez J (1997) Color image enhancement using spatially adaptive saturation feedback. Int Conf on Imag Proc 3:30–33

    Article  Google Scholar 

  32. 32.

    Tingting J, Guoyu W (2015) An approach to underwater image enhancement based on image structural decomposition, Ocea. Univ of Chi 14(2):255–260

    Google Scholar 

  33. 33.

    Vidyarthi A, Mittal N (2014). Comparative study for brain tumor classification on MR/CT Images, Int. Conf. on Soft Comp. for Prob. Solv., pp. 889–897

  34. 34.

    Wang L, Zhang K, Liu X et al (2017) Comparative Analysis of Image Classification Methods for Automatic Diagnosis of Ophthalmic Images. Sci. Rep. 7:41545.

    Article  Google Scholar 

  35. 35.

    Wei-Yen H, Ching-Yao C (2015) Medical image enhancement using modified color histogram equalization. Med and Bio Engg 35(5):580–584

    Article  Google Scholar 

  36. 36.

    Xiaohong WG, Rui H, Zengmin T (2017) Classification of CT brain images based on deep learning networks. Comput Methods Prog Biomed 138:49–56

    Article  Google Scholar 

  37. 37.

    Yang Z, Leng L, Kim BG (2019) StoolNet for color classification of stool medical images. Elect vol 8:1464

    Google Scholar 

  38. 38.

    Yu Y-H, Kwok NM, Ha QP (2011) Color tracking for multiple robot control using a system-on-programmable-Chip. Autom Constr 20:669–676

    Article  Google Scholar 

  39. 39.

    Zebin S, Wenquan F, Zhao Q et al (2015) Brightness preserving image enhancement based on a gradient and intensity histogram. Jour of Elect Imag 24(5):24–35

    Google Scholar 

  40. 40.

    Zhang Y, Chu J, Leng L et al (2020) Mask-Refined R-CNN: A Network for Refining Object Details in Instance Segmentation. Sens. 20(4):1010

    Article  Google Scholar 

  41. 41.

    Zhang J, Yong X, Yutong X et al. (2017). Classification of medical images in biomedical literature by jointly using deep and handcrafted visual features, Jour. of Biomed. and Heal. Infor., Early access, pp. 1–10

  42. 42.

    Zhang J, Yong X, Yutong X et al (2017). Classification of medical images and illustration in biomedical literature using synergic deep learning, arXiv: 1706.09092v1, pp. 1–8

  43. 43.

    Zhiwei Y, Mingwei W, Zhengbing H et al. (2015). An adaptive image enhancement technique by combining cuckoo search and particle swarm optimization algorithm, Comp.Intell. And Neuro., vol. 2015, Article ID 825398, pp. 1–12

  44. 44.

    Zhou W, Bovik AC, Sheikh HR et al (2004) Image quality assessment: from error visibility to structural similarity. Trans on Imag Proc 13(4):600–612

    Article  Google Scholar 

Download references


The authors would like to thank all the individuals who provide their guidance in the implementation of this work.

Author information



Corresponding author

Correspondence to Ankit Vidyarthi.

Ethics declarations

Conflicting interests

The author(s) declared no potential conflicts of interest concerning the research, authorship, and/or publication of this article.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study. Moreover, the prior patient consent has been taken by the respective authorities of the hospital for the participation of their images in the research study and for publications. As per the commitment all the annotations from the images where the details of the patients like their names, initials, and other related information were removed before its use. Also, the study has been approved by the Institutional ethics committee of SMS Medical College Jaipur with a grant IRB number 2182.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.




Listing 1 Free hand ROI extraction

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Vidyarthi, A. Multi-scale dyadic filter modulation based enhancement and classification of medical images. Multimed Tools Appl (2020).

Download citation


  • Filter bank
  • Image enhancement
  • Amplitude- Frequency modulation
  • Medical imaging
  • Classification