Diagnostic techniques for improved segmentation, feature extraction, and classification of malignant melanoma
Tóm tắt
A typical diagnosis of malignant melanoma involves three major steps: segmentation of a lesion from the input color image, feature extraction from the separated lesion, and classification to distinguish malignant from benign melanomas based on features obtained. We suggest new methods for segmentation, feature extraction, and classification compared. We replaced edge-imfill method with U-Otsu method for segmentation, the previous features with new features for the criteria ABCD (asymmetry, border irregularity, color variegation, diameter) criteria, and the median thresholding with weighted receiver operating characteristic thresholding for classification. We used 88 melanoma images and expert’s segmentation. All the three steps in the suggested method were compared with the steps in the previous method, with respect to sensitivity, specificity, and accuracy of the 88 samples. For segmentation, the previous and the suggested segmentations were also compared assuming the skin cancer expert’s segmentation as a ground truth. All three steps resulted in remarkable improvement in the suggested method.
Tài liệu tham khảo
Cancer Facts & Figures 2018. Atlanta: The American Cancer Society; 2018.
Celebi ME, Codella N, Halpern A. Dermoscopy image analysis: overview and future directions. IEEE J Biomed Health Inform. 2019;23(2):474–8.
Barata C, Celebi ME, Marques JS. A survey of feature extraction in dermoscopy image analysis of skin caner. IEEE J Biomed Health Inform. 2019;23(3):1096–109.
Celebi ME, Wen Q, Iyatomi H, Shimizu K, Zhou H, Schaefer G. A state-of-the-art survey on lesion border detection in dermoscopy images. In: Celebi ME, Mendonca T, Marques JS, editors. Dermoscoy image analysis. CRC Press: London; 2015. p. 97–129.
Celebi ME, Iyatomi H, Schaefer G, Stoecker WV. Lesion border detection in dermoscopy images. Comput Med Imaging Graph. 2009;33(2):148–53.
Perch F, Bogo F, Bonazza M, Capelleri VM, Peserico E. Simpler, faster, more accurate melanocytic lesion segmentation through MEDS. IEEE Trans Biomed Eng. 2014;61(2):557–65.
Celebi ME, Wen Q, Hwang S, Iyatomi H, Schaefer G. Lesion border detection in dermoscopy images using ensembles of thresholding methods. Skin Res Technol. 2013;19(1):e252–258.
Garnavi R, Aldeen M, Celebi ME, Varigos G, Finch S. Border detection in dermoscopy images using hybrid thresholding on optimize color channels. Comput Med Imaging Graph. 2011;35(2):105–15.
Mete M, Kockara S, Aydin K. Fast density-based lesion detection in dermoscopy images. Comput Med Imaging Graph. 2011;35(2):128–36.
Silveira M, Nascimento JC, Marques JS, Marcal ARS, Mendoca T, Yamauchi S, Maeda J, Rozeira J. Comparison of segmentation methods for melanoma diagnosis in dermascopy images. IEEE J Sel Top Signal Process. 2009;3(1):35–45.
Iyatomi H, Oka H, Celebi ME, Hashimoto M, Hagiwara M, Tanaka M, Ogawa K. An improved internet-based melanoma screening system with dermatologist-like Tumor area extraction algorithm. Comput Med Imaging Graph. 2008;32(7):566–79.
Otsu N. A threshold selection method from gray level histograms. IEEE Trans Syst. 1979;9(1):62–6.
Friedman RJ, Rigel DS, Kopf AW. Early detection of malignant melanoma: the role of physician examination and self-examination of the skin. A Cancer J Clin. 1985;35:130–51.
Menzies Method. https://dermoscopedia.org/w/index.php?title=Menzies_Method&oldid=9988. Accessed 5 Sept. 2019.
Healsmith MF, Bourke JF, Osborne JE, Graham-Brown RAC. An evaluation of the revised seven-point checklist for the early diagnosis of cutaneous malignant melanoma. Br J Dermatol. 1994;130(1):48–50.
Lee H, Kwon K. A mathematical analysis of the ABCD criteria for diagnosing malignant melanoma. Phys Med Biol. 2017;62:1865–84.
Ercal F, Chawla A, Stoecker WV, Lee H-C, Moss RH. Neural network diagnosis of malignant melanoma from color images. IEEE Trans Biomed Eng. 1994;14(9):837–45.
Ercal F, Maganti M, Stoecker WV, Moss RH. Boundary detection and color segmentation in skin tumor images. IEEE Trans Med Imaging. 1993;12(3):624–7.
Abbadi NKE, Faisal Z. Detection and analysis of skin cancer from skin lesions. Int J Appl Eng Res. 2017;12(19):9046–52.
Dalila F, Zohra A, Reda K, Hocine C. Segmentation and classification of melanoma and benign skin lesions. Opt Int J Light Electron. 2017;140:749–61.
Jaworek-Korjakowska J. Computer-aided diagnosis of micromalignant melanoma lesions applying support vector machines. Biomed Res Int. 2016;2016:4381972.
In: The International Skin Imaging Collaboration Website. 2019. https://www.isic-archive.com.
In: DermNet New Zealand Trust. 2016. https://dermnetnz.org.
In: National Cancer Institute. 2015. https://health.wikinut.com/Malignant-Melanoma-A-Cancerous-Mole-in-the-Skin%21/28o6uojq/ which is permitted by National Cancer Institute 2015 https://cancer.gov.
Gutman D, Codella NCF, Celebi E, Helba B, Marchetti M, Mishra N, Halpern A, Skin lesion analysis toward melanoma detection: a challenge at the International symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC); 2016. https://arxiv.org/abs/1605.01739.
Fawcett T. An introduction to ROC analysis. Pattern Recogn Lett. 2006;27:861–74.
Usted LB. Decision-making studies in patient management. N Engl J Med. 1971;284(8):416–24.
Metz CE. Basic principles of ROC analysis. Semin Nuclear Med. 1978;8:283–98.