Automated segmentation of pigmented skin lesions in multispectral imaging

Mauro Carrara, Stefano Tomatis, Aldo Bono, Cesare Bartoli, Daniele Moglia, Manuela Lualdi, Ambrogio Colombo, Mario Santinami, Renato Marchesini

Research output: Contribution to journalArticle

Abstract

The aim of this study was to develop an algorithm for the automatic segmentation of multispectral images of pigmented skin lesions. The study involved 1700 patients with 1856 cutaneous pigmented lesions, which were analysed in vivo by a novel spectrophotometric system, before excision. The system is able to acquire a set of 15 different multispectral images at equally spaced wavelengths between 483 and 951 nm. An original segmentation algorithm was developed and applied to the whole set of lesions and was able to automatically contour them all. The obtained lesion boundaries were shown to two expert clinicians, who, independently, rejected 54 of them. The 97.1% contour accuracy indicates that the developed algorithm could be a helpful and effective instrument for the automatic segmentation of skin pigmented lesions.

Original languageEnglish
JournalPhysics in Medicine and Biology
Volume50
Issue number22
DOIs
Publication statusPublished - Nov 21 2005

Fingerprint

lesions
Skin
Imaging techniques
Wavelength
wavelengths

ASJC Scopus subject areas

  • Biomedical Engineering
  • Physics and Astronomy (miscellaneous)
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology

Cite this

Automated segmentation of pigmented skin lesions in multispectral imaging. / Carrara, Mauro; Tomatis, Stefano; Bono, Aldo; Bartoli, Cesare; Moglia, Daniele; Lualdi, Manuela; Colombo, Ambrogio; Santinami, Mario; Marchesini, Renato.

In: Physics in Medicine and Biology, Vol. 50, No. 22, 21.11.2005.

Research output: Contribution to journalArticle

Carrara, Mauro ; Tomatis, Stefano ; Bono, Aldo ; Bartoli, Cesare ; Moglia, Daniele ; Lualdi, Manuela ; Colombo, Ambrogio ; Santinami, Mario ; Marchesini, Renato. / Automated segmentation of pigmented skin lesions in multispectral imaging. In: Physics in Medicine and Biology. 2005 ; Vol. 50, No. 22.
@article{69e3796d84bf454081158c2d17823503,
title = "Automated segmentation of pigmented skin lesions in multispectral imaging",
abstract = "The aim of this study was to develop an algorithm for the automatic segmentation of multispectral images of pigmented skin lesions. The study involved 1700 patients with 1856 cutaneous pigmented lesions, which were analysed in vivo by a novel spectrophotometric system, before excision. The system is able to acquire a set of 15 different multispectral images at equally spaced wavelengths between 483 and 951 nm. An original segmentation algorithm was developed and applied to the whole set of lesions and was able to automatically contour them all. The obtained lesion boundaries were shown to two expert clinicians, who, independently, rejected 54 of them. The 97.1{\%} contour accuracy indicates that the developed algorithm could be a helpful and effective instrument for the automatic segmentation of skin pigmented lesions.",
author = "Mauro Carrara and Stefano Tomatis and Aldo Bono and Cesare Bartoli and Daniele Moglia and Manuela Lualdi and Ambrogio Colombo and Mario Santinami and Renato Marchesini",
year = "2005",
month = "11",
day = "21",
doi = "10.1088/0031-9155/50/22/N01",
language = "English",
volume = "50",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "22",

}

TY - JOUR

T1 - Automated segmentation of pigmented skin lesions in multispectral imaging

AU - Carrara, Mauro

AU - Tomatis, Stefano

AU - Bono, Aldo

AU - Bartoli, Cesare

AU - Moglia, Daniele

AU - Lualdi, Manuela

AU - Colombo, Ambrogio

AU - Santinami, Mario

AU - Marchesini, Renato

PY - 2005/11/21

Y1 - 2005/11/21

N2 - The aim of this study was to develop an algorithm for the automatic segmentation of multispectral images of pigmented skin lesions. The study involved 1700 patients with 1856 cutaneous pigmented lesions, which were analysed in vivo by a novel spectrophotometric system, before excision. The system is able to acquire a set of 15 different multispectral images at equally spaced wavelengths between 483 and 951 nm. An original segmentation algorithm was developed and applied to the whole set of lesions and was able to automatically contour them all. The obtained lesion boundaries were shown to two expert clinicians, who, independently, rejected 54 of them. The 97.1% contour accuracy indicates that the developed algorithm could be a helpful and effective instrument for the automatic segmentation of skin pigmented lesions.

AB - The aim of this study was to develop an algorithm for the automatic segmentation of multispectral images of pigmented skin lesions. The study involved 1700 patients with 1856 cutaneous pigmented lesions, which were analysed in vivo by a novel spectrophotometric system, before excision. The system is able to acquire a set of 15 different multispectral images at equally spaced wavelengths between 483 and 951 nm. An original segmentation algorithm was developed and applied to the whole set of lesions and was able to automatically contour them all. The obtained lesion boundaries were shown to two expert clinicians, who, independently, rejected 54 of them. The 97.1% contour accuracy indicates that the developed algorithm could be a helpful and effective instrument for the automatic segmentation of skin pigmented lesions.

UR - http://www.scopus.com/inward/record.url?scp=27644508802&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27644508802&partnerID=8YFLogxK

U2 - 10.1088/0031-9155/50/22/N01

DO - 10.1088/0031-9155/50/22/N01

M3 - Article

C2 - 16264245

AN - SCOPUS:27644508802

VL - 50

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 22

ER -