AN ENSEMBLE TEMPLATE MATCHING AND CONTENT-BASED IMAGE RETRIEVAL SCHEME TOWARDS EARLY STAGE DETECTION OF MELANOMA

Authors

  • Spiros Kostopoulos Medical Image and Signal Processing Laboratory (MEDISP), Department of Biomedical Engineering, Technological Educational Institute of Athens
  • Dimitris Glotsos Medical Image and Signal Processing Laboratory (MEDISP), Department of Biomedical Engineering, Technological Educational Institute of Athens
  • Pantelis Asvestas Medical Image and Signal Processing Laboratory (MEDISP), Department of Biomedical Engineering, Technological Educational Institute of Athens
  • Christos Konstandinou Department of Medical Physics, University of Patras, Rio, Patras
  • George Xenogiannopoulos Medical Image and Signal Processing Laboratory (MEDISP), Department of Biomedical Engineering, Technological Educational Institute of Athens
  • Konstantinos Sidiropoulos European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Welcome Trust Genome Campus, Hinxton, Cambridge
  • Eirini-Konstantina Nikolatou Medical Image and Signal Processing Laboratory (MEDISP), Department of Biomedical Engineering, Technological Educational Institute of Athens
  • Konstantinos Perakis UBITECH Research Department, UBITECH Ltd., Athens, Greece;
  • Spyros Mantzouratos UBITECH Research Department, UBITECH Ltd., Athens, Greece;
  • Theophilos Sakkis Dermatology Center, Aegion
  • George Sakellaropoulos Department of Medical Physics, University of Patras, Rio, Patras
  • George Nikiforidis Department of Medical Physics, University of Patras, Rio, Patras
  • Dionisis Cavouras Medical Image and Signal Processing Laboratory (MEDISP), Department of Biomedical Engineering, Technological Educational Institute of Athens

DOI:

https://doi.org/10.5566/ias.1446

Keywords:

template matching, content-based image retrieval, decision support system, melanoma diagnosis, self-skin examination

Abstract

Malignant melanoma represents the most dangerous type of skin cancer. In this study we present an ensemble classification scheme, employing the mutual information, the cross-correlation and the clustering based on proximity of image features methods, for early stage assessment of melanomas on plain photography images. The proposed scheme performs two main operations. First, it retrieves the most similar, to the unknown case, image samples from an available image database with verified benign moles and malignant melanoma cases. Second, it provides an automated estimation regarding the nature of the unknown image sample based on the majority of the most similar images retrieved from the available database. Clinical material comprised 75 melanoma and 75 benign plain photography images collected from publicly available dermatological atlases. Results showed that the ensemble scheme outperformed all other methods tested in terms of accuracy with 94.9±1.5%, following an external cross-validation evaluation methodology. The proposed scheme may benefit patients by providing a second opinion consultation during the self-skin examination process and the physician by providing a second opinion estimation regarding the nature of suspicious moles that may assist towards decision making especially for ambiguous cases, safeguarding, in this way from potential diagnostic misinterpretations.

References

Abbasi N R, Shaw H M, Rigel D S, Friedman R J, McCarthy W H, Osman I, Kopf A W, Polsky D (2004). Early diagnosis of cutaneous melanoma: Revisiting the ABCD criteria. JAMA 292: 2771-6.

Abikhair M R, Mahar P D, Cachia A R, Kelly J W (2014). Liability in the context of misdiagnosis of melanoma in australia. MED J Australia 200: 119-21.

Ambroise C, McLachlan G J (2002). Selection bias in gene extraction on the basis of microarray gene-expression data. PNAS 99: 6562-6.

Asgarizadeh M, Pourghassem H, Shahgholian G, Robust object tracking using regional mutual information and normalized cross correlation, (2012), Proceedings - 4th International Conference on Computational Intelligence and Communication Networks, CICN 2012, Mathura, Uttar Pradesh, India, 411-5.

Balch C M, et al. (2001). Long-term results of a prospective surgical trial comparing 2 cm vs. 4 cm excision margins for 740 patients with 1-4 mm melanomas. Ann Surg Oncol 8: 101-8.

Ballerini L, Fisher R B, Aldridge B, Rees J (2013). A color and texture based hierarchical k-nn approach to the classification of non-melanoma skin lesions. In: E. M. Celebi, G. Schaefer, eds. Color medical image analysis, Dordrecht: Springer Netherlands, 63-86.

Ballerini L, Li X, Fisher R B, Rees J (2010). A query-by-example content-based image retrieval system of non-melanoma skin lesions. In: B. Caputo, H. Müller, T. Syeda-Mahmood, J. S. Duncan, F. Wang, J. Kalpathy-Cramer, eds. Medical content-based retrieval for clinical decision support: First miccai international workshop, mcbr-cds 2009, london, uk, september 20, 2009, revised selected papers, Berlin, Heidelberg: Springer Berlin Heidelberg, 31-88.

Carli P, De Giorgi V, Nardini P, Mannone F, Palli D, Giannotti B (2002). Melanoma detection rate and concordance between self-skin examination and clinical evaluation in patients attending a pigmented lesion clinic in italy. Br J Dermatol 146: 261-6.

Cavalcanti P G, Scharcanski J, Baranoski G V G (2013). A two-stage approach for discriminating melanocytic skin lesions using standard cameras. Expert Sys Appl 40: 4054-64.

Chen R H, Snorrason M, Enger S M, Mostafa E, Ko J M, Aoki V, Bowling J (2016). Validation of a skin-lesion image-matching algorithm based on computer vision technology. Telemed J E Health 22: 45-50.

Cohn-Cedermark G, et al. (2000). Long term results of a randomized study by the swedish melanoma study group on 2-cm versus 5-cm resection margins for patients with cutaneous melanoma with a tumor thickness of 0.8-2.0 mm. Cancer 89: 1495-501.

El-Naqa I, Yang Y, Galatsanos N P, Nishikawa R M, Wernick M N (2004). A similarity learning approach to content-based image retrieval: Application to digital mammography. IEEE T Med Imaging 23: 1233-44.

Field L M (1994). Clinical misdiagnosis of melanoma as well as squamous cell carcinoma masquerading as seborrheic keratosis. J Dermatol Surg Oncol 20: 222.

Fukunaga K L D H (1975). The estimation of the gradient of a density function, with applications in pattern recognition. IEEE T Inform Theory 21: 32-40.

Gaidhane V H, Hote Y V, Singh V (2012). An efficient similarity measure technique for medical image registration. Sadhana - Academy Proceedings in Engineering Sciences 37: 709-21.

Gonzalez R C, Woods R E (2002). Digital image processing, NY: Addison-Wesley Pub, 518-528.

Grant-Kels J M, Bason E T, Grin C M (1999). The misdiagnosis of malignant melanoma. J Am Acad Dermatol 40: 539-48.

Jain A K, Dubes R C (1988). Algorithms for clustering data, Prentice-Hall Inc.

Jaleel J A, Salim S, Aswin R B (2012). Artificial neural network based detection of skin cancer. IJAREEIE 1: 200-05.

Kassianos A P, Emery J D, Murchie P, Walter F M (2015). Smartphone applications for melanoma detection by community, patient and generalist clinician users: A review. Br J Dermatol 172: 1507-18.

Kittler J, Hatef M, Duin R P W, Matas J (1998). On combining classifiers. IEEE T Pattern Anal 20: 226-39.

Leachman S A, et al. (2016). Methods of melanoma detection. Cancer Treat Res 167: 51-105.

Lee T, Ng V, Gallagher R, Coldman A, McLean D (1997). Dullrazor: A software approach to hair removal from images. Comput Biol Med 27: 533-43.

Li C H, Lee C K (1993). Minimum cross entropy thresholding. Pattern Recogn 26: 617-25.

Lorentzen H F, Weismann K, Grønhøj Larsen F (2001). Structural asymmetry as a dermatoscopic indicator of malignant melanoma - a latent class analysis of sensitivity and classification errors. Melanoma Res 11: 495-501.

Loukas C, Kostopoulos S, Tanoglidi A, Glotsos D, Sfikas C, Cavouras D (2013). Breast cancer characterization based on image classification of tissue sections visualized under low magnification. Comp Math Methods Med 2013: 7 pages.

Lucas R, McMichael T, Smith W, Armstrong B (2006). Solar ultraviolet radiation: Global burden of disease from solar ultraviolet radiation In: A. Prüss-Üstün, H. Zeeb, C. Mathers, M. Repacholi, eds. Environmental burden of disease series 13, Geneva: World Health Organization.

Maragoudakis M, Maglogiannis I (2011). A medical ontology for intelligent web-based skin lesions image retrieval. Health Informatics J 17: 140-57.

Mazurowski M A, Lo J Y, Harrawood B P, Tourassi G D (2011). Mutual information-based template matching scheme for detection of breast masses: From mammography to digital breast tomosynthesis. J Biomed Inform 44: 815-23.

Ming M E (2000). The histopathologic misdiagnosis of melanoma: Sources and consequences of "false positives" and "false negatives". J Am Acad Dermatol 43: 704-6.

Ninos K, et al. (2013). Computer-based image analysis system designed to differentiate between low-grade and high-grade laryngeal cancer cases. Anal Quant Cytol 35: 261-72.

Paddock L E, Lu S E, Bandera E V, Rhoads G G, Fine J, Paine S, Barnhill R, Berwick M (2016). Skin self-examination and long-term melanoma survival. Melanoma Res: in press.

Pfahlberg A B, Gefeller O (2008). Errors in assessing risk factors for melanoma: Lack of reproducibility is the minor problem. Melanoma Res 18: 300-1.

Rastrelli M, Tropea S, Rossi C R, Alaibac M (2014). Melanoma: Epidemiology, risk factors, pathogenesis, diagnosis and classification. In Vivo 28: 1005-11.

Ringborg U, et al. (1996). Resection margins of 2 versus 5 cm for cutaneous malignant melanoma with a tumor thickness of 0.8 to 2.0 mm: Randomized study by the swedish melanoma study group. Cancer 77: 1809-14.

Robson Y, Blackford S, Roberts D (2012). Caution in melanoma risk analysis with smartphone application technology. Br J Dermatol 167: 703-4.

Ruiz D, Berenguer V, Soriano A, Sanchez B (2011). A decision support system for the diagnosis of melanoma: A comparative approach. Expert Syst Appl 38: 15217-23.

Russakoff D B, Tomasi C, Rohlfing T, Maurer Jr C R (2004). Image similarity using mutual information of regions. 3023:596-607.

Schein O, Westreich M, Shalom A (2009). Effect of dermoscopy on diagnostic accuracy of pigmented skin lesions emphasizing malignant melanoma. Harefuah 148: 820-3.

Stoecker W V, Rader R K, Halpern A (2013). Diagnostic inaccuracy of smartphone applications for melanoma detection: Representative lesion sets and the role for adjunctive technologies. JAMA Dermatol 149: 884.

Stringa M (1988). Misdiagnosis of choroidal melanoma. Panminerva Med 30: 89-92.

Tenenhaus A, Nkengne A, Horn J F, Serruys C, Giron A, Fertil B (2010). Detection of melanoma from dermoscopic images of naevi acquired under uncontrolled conditions. Skin Res Technol 16: 85-97.

Theodoridis S, Koutroumbas K (2003). Pattern recognition, San Diego: Elsevier.

Vañó-Galván S, Paoli J, Ríos-Buceta L, Jaén P (2015). Skin self-examination using smartphone photography to improve the early diagnosis of melanoma. Actas Dermosifiliogr 106: 75-7.

Veierod M B, Parr C L, Lund E, Hjartaker A (2009). Response: Errors in assessing risk factors for melanoma. Melanoma Res 19: 61.

Veronesi U, Cascinelli N (1991). Narrow excision (1-cm margin). A safe procedure for thin cutaneous melanoma. Arch Surg 126: 438-41.

Wolf J A, Moreau J F, Akilov O, Patton T, English J C, 3rd, Ho J, Ferris L K (2013). Diagnostic inaccuracy of smartphone applications for melanoma detection. JAMA Dermatol 149: 422-6.

Yan Y, Huang X, Zheng Y, Xu W, An efficient template matching between rotated mono- or multi-sensor images, (2011), MIPPR 2011: Parallel Processing of Images and Optimization and Medical Imaging Processing, Guilin, China, 80050M-80050M-9.

Zagrouba E, Barhoumi W (2004). A prelimary approach for the automated recognition of malignant melanoma. Image Anal Stereol 23: 121-35.

Zhang S, Gao F, Wan D (2010). Effect of misdiagnosis on the prognosis of anorectal malignant melanoma. J Cancer Res Clin Oncol 136: 1401-5.

Downloads

Published

2016-12-08

Issue

Vol. 35 No. 3 (2016)

Section

Original Research Paper

How to Cite

Kostopoulos, S., Glotsos, D., Asvestas, P., Konstandinou, C., Xenogiannopoulos, G., Sidiropoulos, K., Nikolatou, E.-K., Perakis, K., Mantzouratos, S., Sakkis, T., Sakellaropoulos, G., Nikiforidis, G., & Cavouras, D. (2016). AN ENSEMBLE TEMPLATE MATCHING AND CONTENT-BASED IMAGE RETRIEVAL SCHEME TOWARDS EARLY STAGE DETECTION OF MELANOMA. Image Analysis and Stereology, 35(3), 137-148. https://doi.org/10.5566/ias.1446