Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Evaluation of Levenberg–Marquardt neural networks and stacked autoencoders clustering for skin lesion analysis, screening and follow-up

© The Institution of Engineering and Technology
Received 09/04/2018, Accepted 18/07/2018, Published 03/08/2018

Traditional methods for early detection of melanoma rely on the visual analysis of the skin lesions performed by a dermatologist. The analysis is based on the so-called ABCDE (Asymmetry, Border irregularity, Colour variegation, Diameter, Evolution) criteria, although confirmation is obtained through biopsy performed by a pathologist. The proposed method exploits an automatic pipeline based on morphological analysis and evaluation of skin lesion dermoscopy images. Preliminary segmentation and pre-processing of dermoscopy image by SC-cellular neural networks is performed, in order to obtain ad-hoc grey-level skin lesion image that is further exploited to extract analytic innovative hand-crafted image features for oncological risks assessment. In the end, a pre-trained Levenberg–Marquardt neural network is used to perform ad-hoc clustering of such features in order to achieve an efficient nevus discrimination (benign against melanoma), as well as a numerical array to be used for follow-up rate definition and assessment. Moreover, the authors further evaluated a combination of stacked autoencoders in lieu of the Levenberg–Marquardt neural network for the clustering step.

Inspec keywords: biomedical optical imaging; skin; image segmentation; cancer; feature extraction; medical image processing; neural nets; image classification

Other keywords: visual analysis; stacked autoencoders; ad-hoc grey-level skin lesion image; skin lesion dermoscopy images; Levenberg–Marquardt neural network; hand-crafted image features; benign against melanoma; dermoscopy image; skin lesion analysis; ad-hoc clustering; SC-cellular neural networks; morphological analysis

Subjects: Patient diagnostic methods and instrumentation; Optical and laser radiation (biomedical imaging/measurement); Computer vision and image processing techniques; Biology and medical computing; Optical and laser radiation (medical uses); Image recognition; Neural computing techniques

References

    1. 1)
      • 19. Titsias, M.K.: ‘Variational learning of inducing variables in sparse Gaussian processes’. Int. Conf. Artificial Intelligence and Statistics, 2009a, vol. 12, pp. 567–574.
    2. 2)
      • 14. Fukushima, K.: ‘Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position’, Biol. Cybern., 1980, 36, (4), pp. 93–202.
    3. 3)
      • 15. Fridan, U., Sarı, İ., Kumrular, R.K.: ‘Classification of skin lesions using ANN’ Medical Technologies National Congress (TIPTEKNO), Antalya, Turkey, 2016.
    4. 4)
      • 6. Rashad, M.W., Takruri, M.: ‘Automatic non-invasive recognition of melanoma using support vector machines’. BioSMART Conf., 2016.
    5. 5)
      • 20. Barata, C., Ruela, M., Francisco, M., et al: ‘Two systems for the detection of melanomas in dermoscopy images using texture and color features’, IEEE Syst. J., 2013, 99, pp. 1–15.
    6. 6)
      • 21. STM32 32-bit ARM Cortex MCUs: Available at http://www.st.com/en/microcontrollers/stm32-32-bit-arm-cortex-mcus.html?querycriteria=productId=SC1169, accessed August 2018.
    7. 7)
      • 13. Hagan, M.T., Menhaj, M.: ‘Training feed-forward networks with Marquardt algorithm’, IEEE Trans. Neural Netw., 1994, 5, (6), pp. 989–993.
    8. 8)
      • 10. Battiato, S., Rundo, F., Stanco, F.: ‘ALZ: adaptive learning for zooming digital image’. IEEE Proc. of Int. Conf. Consumer and Electronics, Las Vegas, NV, USA, 2007, pp. 1–2.
    9. 9)
      • 7. Gonzalez, R.C., Woods, R.E.: ‘Digital image processing’ (Prentice-Hall, New York, NY, USA, 2018, 4th edn.).
    10. 10)
      • 9. Arena, P., Baglio, S., Fortuna, L., et al: ‘Dynamics of state controlled CNNs’. IEEE Proc. of Int. Symp. Circuits and Systems, ISCAS'96, Atlanta, GA, USA, 1996.
    11. 11)
      • 8. Chua, L.O., Yang, L.: ‘Cellular neural networks: theory’, IEEE Trans. Circuits Syst., 1988, 35, (10), pp. 1257–1272.
    12. 12)
      • 17. Battiato, S., Gallo, G., Stanco, F.: ‘A new edge-adaptive zooming algorithm for digital images’. Proc. Signal Processing and Communications SPC, 2000, pp. 144–149.
    13. 13)
      • 1. Mendonça, T., Ferreira, P.M., Marques, J.S., et al: ‘PH2 – a dermoscopic image database for research and benchmarking’. 35th Int. Conf. the IEEE Engineering in Medicine and Biology Society, 3–7 July 2013, Osaka, Japan.
    14. 14)
      • 5. Jamil, U., Khalid, S., Usman Akram, M.: ‘Dermoscopic feature analysis for melanoma recognition and prevention’. Sixth Int. Conf. Innovative Computing Technology (INTECH), 2016.
    15. 15)
      • 12. Rundo, F., Banna, G.L.: ‘A Method of analyzing skin lesions, corresponding system, instrument and computer program product’. EU Registered Patent App. N. 102016000121060, 29 November, 2016.
    16. 16)
      • 4. Majtner, T., Yildirim-Yayilgan, S., Hardeberg, J.Y.: ‘Combining deep learning and hand-crafted features for skin lesion classification’. Sixth Int. Conf. Image Processing Theory, Tools and Applications (IPTA), 2016.
    17. 17)
      • 3. Conoci, S., Rundo, F, Petralia, S., et al: ‘Advanced skin lesion discrimination pipeline for early melanoma cancer diagnosis towards PoC devices’. IEEE Proc. the Circuit Theory and Design European Conf. (ECCTD), 4–6 September 2017, Catania.
    18. 18)
      • 18. Bengio, Y.: ‘Learning deep architectures for AI’, Found. Trends Mach. Learn., 2009, 2, (1), pp. 1–127.
    19. 19)
      • 16. Xie, F., Fan, H, Li, Y., et al: ‘Melanoma classification on dermoscopy images using a neural network ensemble model’, IEEE Trans. Med. Imaging, 2017, 36, (3), pp. 849–858.
    20. 20)
      • 2. Binu Sathiya, S., Kumar, S.S., Prabin, A.: ‘A survey on recent computer-aided diagnosis of melanoma’. 2014 Int. Conf. Control, Instrumentation, Communication and Computational Technologies (ICCICCT).
    21. 21)
      • 11. Lee, H., Ekanadham, C., Ng, A.Y.: ‘Sparse deep belief net model for visual area V2’, Adv. Neural. Inf. Process. Syst., 2007, 7, pp. 873–880.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2018.5195
Loading

Related content

content/journals/10.1049/iet-cvi.2018.5195
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address