Computer-aided diagnosis of melanocytic lesions

Ignazio Stanganelli, Aldo Brucale, Luigi Calori, Roberto Gori, Alberto Lovato, Serena Magi, Barbara Kopf, Roberto Bacchilega, Vincenzo Rapisarda, Alessandro Testori, Paolo Antonio Ascierto, Ester Simeone, Massimo Ferri

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

Background: The clinical diagnosis of melanoma could be difficult for a general practitioner and, in some cases, for dermatologists. To enhance and support the clinical evaluation of pigmented skin lesions a computer-aided diagnosis has been introduced. Materials and Methods: Images of melanocytic lesions (477 total, 42 melanomas and 435 melanocytic nevi) evaluated in epiluminescence microscopy and recorded with x16 magnification were selected. A training set of 22 melanomas and 218 nevi was randomized from the dataset. The test set was formed by the complement (the remaining 20 melanomas and 217 nevi). Furthermore, a set of images consisting of 31 melanomas and 103 nevi was selected to compare the discrimination capacity of three general practitioners and three dermatologists with experience in dermoscopy (2 years), and with the automatic data analysis for the melanoma early detection system (ADAM). Sensitivity and specificity were estimated for observer assessments and computer diagnosis. Results: The entire dataset used to test the implementation of the diagnostic algorithms ADAM showed a good sensitivity and specificity performance. Compared with the physicians, the ADAM system showed a slightly higher diagnostic performance in terms of sensitivity and a lower one in terms of specificity. Dermatologists showed higher levels of specificity, but lower levels in terms of sensitivity, when compared with the general practitioners. Conclusion: Image analysis has the potential to distinguish nevi and melanomas and to support the clinical diagnosis of melanocytic lesions by the general practitioner.

Original languageEnglish
Pages (from-to)4577-4582
Number of pages6
JournalAnticancer Research
Volume25
Issue number6 C
Publication statusPublished - Nov 2005

Fingerprint

Nevi and Melanomas
General Practitioners
Dermoscopy
Melanoma
Pigmented Nevus
Sensitivity and Specificity
Routine Diagnostic Tests
Physicians
Skin
Dermatologists
Datasets

Keywords

  • Automatic diagnosis
  • Computer-aided diagnosis
  • Dermoscopy
  • Digital epiluminescence microscopy
  • Melanocytic nevi
  • Melanoma

ASJC Scopus subject areas

  • Cancer Research
  • Oncology

Cite this

Stanganelli, I., Brucale, A., Calori, L., Gori, R., Lovato, A., Magi, S., ... Ferri, M. (2005). Computer-aided diagnosis of melanocytic lesions. Anticancer Research, 25(6 C), 4577-4582.

Computer-aided diagnosis of melanocytic lesions. / Stanganelli, Ignazio; Brucale, Aldo; Calori, Luigi; Gori, Roberto; Lovato, Alberto; Magi, Serena; Kopf, Barbara; Bacchilega, Roberto; Rapisarda, Vincenzo; Testori, Alessandro; Ascierto, Paolo Antonio; Simeone, Ester; Ferri, Massimo.

In: Anticancer Research, Vol. 25, No. 6 C, 11.2005, p. 4577-4582.

Research output: Contribution to journalArticle

Stanganelli, I, Brucale, A, Calori, L, Gori, R, Lovato, A, Magi, S, Kopf, B, Bacchilega, R, Rapisarda, V, Testori, A, Ascierto, PA, Simeone, E & Ferri, M 2005, 'Computer-aided diagnosis of melanocytic lesions', Anticancer Research, vol. 25, no. 6 C, pp. 4577-4582.
Stanganelli I, Brucale A, Calori L, Gori R, Lovato A, Magi S et al. Computer-aided diagnosis of melanocytic lesions. Anticancer Research. 2005 Nov;25(6 C):4577-4582.
Stanganelli, Ignazio ; Brucale, Aldo ; Calori, Luigi ; Gori, Roberto ; Lovato, Alberto ; Magi, Serena ; Kopf, Barbara ; Bacchilega, Roberto ; Rapisarda, Vincenzo ; Testori, Alessandro ; Ascierto, Paolo Antonio ; Simeone, Ester ; Ferri, Massimo. / Computer-aided diagnosis of melanocytic lesions. In: Anticancer Research. 2005 ; Vol. 25, No. 6 C. pp. 4577-4582.
@article{20811891a445430097e59461cfcbde9e,
title = "Computer-aided diagnosis of melanocytic lesions",
abstract = "Background: The clinical diagnosis of melanoma could be difficult for a general practitioner and, in some cases, for dermatologists. To enhance and support the clinical evaluation of pigmented skin lesions a computer-aided diagnosis has been introduced. Materials and Methods: Images of melanocytic lesions (477 total, 42 melanomas and 435 melanocytic nevi) evaluated in epiluminescence microscopy and recorded with x16 magnification were selected. A training set of 22 melanomas and 218 nevi was randomized from the dataset. The test set was formed by the complement (the remaining 20 melanomas and 217 nevi). Furthermore, a set of images consisting of 31 melanomas and 103 nevi was selected to compare the discrimination capacity of three general practitioners and three dermatologists with experience in dermoscopy (2 years), and with the automatic data analysis for the melanoma early detection system (ADAM). Sensitivity and specificity were estimated for observer assessments and computer diagnosis. Results: The entire dataset used to test the implementation of the diagnostic algorithms ADAM showed a good sensitivity and specificity performance. Compared with the physicians, the ADAM system showed a slightly higher diagnostic performance in terms of sensitivity and a lower one in terms of specificity. Dermatologists showed higher levels of specificity, but lower levels in terms of sensitivity, when compared with the general practitioners. Conclusion: Image analysis has the potential to distinguish nevi and melanomas and to support the clinical diagnosis of melanocytic lesions by the general practitioner.",
keywords = "Automatic diagnosis, Computer-aided diagnosis, Dermoscopy, Digital epiluminescence microscopy, Melanocytic nevi, Melanoma",
author = "Ignazio Stanganelli and Aldo Brucale and Luigi Calori and Roberto Gori and Alberto Lovato and Serena Magi and Barbara Kopf and Roberto Bacchilega and Vincenzo Rapisarda and Alessandro Testori and Ascierto, {Paolo Antonio} and Ester Simeone and Massimo Ferri",
year = "2005",
month = "11",
language = "English",
volume = "25",
pages = "4577--4582",
journal = "Anticancer Research",
issn = "0250-7005",
publisher = "International Institute of Anticancer Research",
number = "6 C",

}

TY - JOUR

T1 - Computer-aided diagnosis of melanocytic lesions

AU - Stanganelli, Ignazio

AU - Brucale, Aldo

AU - Calori, Luigi

AU - Gori, Roberto

AU - Lovato, Alberto

AU - Magi, Serena

AU - Kopf, Barbara

AU - Bacchilega, Roberto

AU - Rapisarda, Vincenzo

AU - Testori, Alessandro

AU - Ascierto, Paolo Antonio

AU - Simeone, Ester

AU - Ferri, Massimo

PY - 2005/11

Y1 - 2005/11

N2 - Background: The clinical diagnosis of melanoma could be difficult for a general practitioner and, in some cases, for dermatologists. To enhance and support the clinical evaluation of pigmented skin lesions a computer-aided diagnosis has been introduced. Materials and Methods: Images of melanocytic lesions (477 total, 42 melanomas and 435 melanocytic nevi) evaluated in epiluminescence microscopy and recorded with x16 magnification were selected. A training set of 22 melanomas and 218 nevi was randomized from the dataset. The test set was formed by the complement (the remaining 20 melanomas and 217 nevi). Furthermore, a set of images consisting of 31 melanomas and 103 nevi was selected to compare the discrimination capacity of three general practitioners and three dermatologists with experience in dermoscopy (2 years), and with the automatic data analysis for the melanoma early detection system (ADAM). Sensitivity and specificity were estimated for observer assessments and computer diagnosis. Results: The entire dataset used to test the implementation of the diagnostic algorithms ADAM showed a good sensitivity and specificity performance. Compared with the physicians, the ADAM system showed a slightly higher diagnostic performance in terms of sensitivity and a lower one in terms of specificity. Dermatologists showed higher levels of specificity, but lower levels in terms of sensitivity, when compared with the general practitioners. Conclusion: Image analysis has the potential to distinguish nevi and melanomas and to support the clinical diagnosis of melanocytic lesions by the general practitioner.

AB - Background: The clinical diagnosis of melanoma could be difficult for a general practitioner and, in some cases, for dermatologists. To enhance and support the clinical evaluation of pigmented skin lesions a computer-aided diagnosis has been introduced. Materials and Methods: Images of melanocytic lesions (477 total, 42 melanomas and 435 melanocytic nevi) evaluated in epiluminescence microscopy and recorded with x16 magnification were selected. A training set of 22 melanomas and 218 nevi was randomized from the dataset. The test set was formed by the complement (the remaining 20 melanomas and 217 nevi). Furthermore, a set of images consisting of 31 melanomas and 103 nevi was selected to compare the discrimination capacity of three general practitioners and three dermatologists with experience in dermoscopy (2 years), and with the automatic data analysis for the melanoma early detection system (ADAM). Sensitivity and specificity were estimated for observer assessments and computer diagnosis. Results: The entire dataset used to test the implementation of the diagnostic algorithms ADAM showed a good sensitivity and specificity performance. Compared with the physicians, the ADAM system showed a slightly higher diagnostic performance in terms of sensitivity and a lower one in terms of specificity. Dermatologists showed higher levels of specificity, but lower levels in terms of sensitivity, when compared with the general practitioners. Conclusion: Image analysis has the potential to distinguish nevi and melanomas and to support the clinical diagnosis of melanocytic lesions by the general practitioner.

KW - Automatic diagnosis

KW - Computer-aided diagnosis

KW - Dermoscopy

KW - Digital epiluminescence microscopy

KW - Melanocytic nevi

KW - Melanoma

UR - http://www.scopus.com/inward/record.url?scp=28444456955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28444456955&partnerID=8YFLogxK

M3 - Article

C2 - 16334145

AN - SCOPUS:28444456955

VL - 25

SP - 4577

EP - 4582

JO - Anticancer Research

JF - Anticancer Research

SN - 0250-7005

IS - 6 C

ER -