A Convolutional Neural Network for Lentigo Diagnosis

Sana Zorgui; Siwar Chaabene; Bassem Bouaziz; Hadj Batatia; Lotfi Chaari

doi:10.1007/978-3-030-51517-1_8

A Convolutional Neural Network for Lentigo Diagnosis

Sana Zorgui^*, Siwar Chaabene, Bassem Bouaziz, Hadj Batatia, Lotfi Chaari

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

14 Citations (Scopus)

Abstract

Using Reflectance Confocal Microscopy (RCM) for lentigo diagnosis is today considered essential. Indeed, RCM allows fast data acquisition with a high spatial resolution of the skin. In this paper, we use a deep convolutional neural network (CNN) to perform RCM image classification in order to detect lentigo. The proposed method relies on an InceptionV3 architecture combined with data augmentation and transfer learning. The method is validated on RCM data and shows very efficient detection performance with more than 98% of accuracy.

Original language	English
Title of host publication	The Impact of Digital Technologies on Public Health in Developed and Developing Countries. ICOST 2020
Editors	Mohamed Jmaiel, Mounir Mokhtari, Bessam Abdulrazak, Hamdi Aloulou, Slim Kallel
Publisher	Springer
Pages	89-99
Number of pages	11
ISBN (Electronic)	9783030515171
ISBN (Print)	9783030515164
DOIs	https://doi.org/10.1007/978-3-030-51517-1_8
Publication status	Published - 23 Jun 2020
Event	18th International Conference on Smart Homes and Health Telematics 2020 - Hammamet, Tunisia Duration: 24 Jun 2020 → 26 Jun 2020

Publication series

Name	Lecture Notes in Computer Science
Volume	12157
ISSN (Print)	0302-9743

Conference

Conference	18th International Conference on Smart Homes and Health Telematics 2020
Abbreviated title	ICOST 2020
Country/Territory	Tunisia
City	Hammamet
Period	24/06/20 → 26/06/20

Keywords

CNN classification
InceptionV3
Lentigo
Reflectance Confocal Microscopy

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-030-51517-1_8Licence: CC BY

Cite this

Zorgui, S., Chaabene, S., Bouaziz, B., Batatia, H., & Chaari, L. (2020). A Convolutional Neural Network for Lentigo Diagnosis. In M. Jmaiel, M. Mokhtari, B. Abdulrazak, H. Aloulou, & S. Kallel (Eds.), The Impact of Digital Technologies on Public Health in Developed and Developing Countries. ICOST 2020 (pp. 89-99). (Lecture Notes in Computer Science; Vol. 12157). Springer. https://doi.org/10.1007/978-3-030-51517-1_8

Zorgui, Sana ; Chaabene, Siwar ; Bouaziz, Bassem et al. / A Convolutional Neural Network for Lentigo Diagnosis. The Impact of Digital Technologies on Public Health in Developed and Developing Countries. ICOST 2020. editor / Mohamed Jmaiel ; Mounir Mokhtari ; Bessam Abdulrazak ; Hamdi Aloulou ; Slim Kallel. Springer, 2020. pp. 89-99 (Lecture Notes in Computer Science).

@inproceedings{1fed7b52f2cf45cb888b422b9d4d00bc,

title = "A Convolutional Neural Network for Lentigo Diagnosis",

abstract = "Using Reflectance Confocal Microscopy (RCM) for lentigo diagnosis is today considered essential. Indeed, RCM allows fast data acquisition with a high spatial resolution of the skin. In this paper, we use a deep convolutional neural network (CNN) to perform RCM image classification in order to detect lentigo. The proposed method relies on an InceptionV3 architecture combined with data augmentation and transfer learning. The method is validated on RCM data and shows very efficient detection performance with more than 98% of accuracy.",

keywords = "CNN classification, InceptionV3, Lentigo, Reflectance Confocal Microscopy",

author = "Sana Zorgui and Siwar Chaabene and Bassem Bouaziz and Hadj Batatia and Lotfi Chaari",

year = "2020",

month = jun,

day = "23",

doi = "10.1007/978-3-030-51517-1_8",

language = "English",

isbn = "9783030515164",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "89--99",

editor = "Mohamed Jmaiel and Mounir Mokhtari and Bessam Abdulrazak and Hamdi Aloulou and Slim Kallel",

booktitle = "The Impact of Digital Technologies on Public Health in Developed and Developing Countries. ICOST 2020",

address = "United States",

note = "18th International Conference on Smart Homes and Health Telematics 2020, ICOST 2020 ; Conference date: 24-06-2020 Through 26-06-2020",

}

Zorgui, S, Chaabene, S, Bouaziz, B, Batatia, H & Chaari, L 2020, A Convolutional Neural Network for Lentigo Diagnosis. in M Jmaiel, M Mokhtari, B Abdulrazak, H Aloulou & S Kallel (eds), The Impact of Digital Technologies on Public Health in Developed and Developing Countries. ICOST 2020. Lecture Notes in Computer Science, vol. 12157, Springer, pp. 89-99, 18th International Conference on Smart Homes and Health Telematics 2020, Hammamet, Tunisia, 24/06/20. https://doi.org/10.1007/978-3-030-51517-1_8

A Convolutional Neural Network for Lentigo Diagnosis. / Zorgui, Sana; Chaabene, Siwar; Bouaziz, Bassem et al.
The Impact of Digital Technologies on Public Health in Developed and Developing Countries. ICOST 2020. ed. / Mohamed Jmaiel; Mounir Mokhtari; Bessam Abdulrazak; Hamdi Aloulou; Slim Kallel. Springer, 2020. p. 89-99 (Lecture Notes in Computer Science; Vol. 12157).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A Convolutional Neural Network for Lentigo Diagnosis

AU - Zorgui, Sana

AU - Chaabene, Siwar

AU - Bouaziz, Bassem

AU - Batatia, Hadj

AU - Chaari, Lotfi

PY - 2020/6/23

Y1 - 2020/6/23

N2 - Using Reflectance Confocal Microscopy (RCM) for lentigo diagnosis is today considered essential. Indeed, RCM allows fast data acquisition with a high spatial resolution of the skin. In this paper, we use a deep convolutional neural network (CNN) to perform RCM image classification in order to detect lentigo. The proposed method relies on an InceptionV3 architecture combined with data augmentation and transfer learning. The method is validated on RCM data and shows very efficient detection performance with more than 98% of accuracy.

AB - Using Reflectance Confocal Microscopy (RCM) for lentigo diagnosis is today considered essential. Indeed, RCM allows fast data acquisition with a high spatial resolution of the skin. In this paper, we use a deep convolutional neural network (CNN) to perform RCM image classification in order to detect lentigo. The proposed method relies on an InceptionV3 architecture combined with data augmentation and transfer learning. The method is validated on RCM data and shows very efficient detection performance with more than 98% of accuracy.

KW - CNN classification

KW - InceptionV3

KW - Lentigo

KW - Reflectance Confocal Microscopy

UR - http://www.scopus.com/inward/record.url?scp=85087790431&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-51517-1_8

DO - 10.1007/978-3-030-51517-1_8

M3 - Conference contribution

AN - SCOPUS:85087790431

SN - 9783030515164

T3 - Lecture Notes in Computer Science

SP - 89

EP - 99

BT - The Impact of Digital Technologies on Public Health in Developed and Developing Countries. ICOST 2020

A2 - Jmaiel, Mohamed

A2 - Mokhtari, Mounir

A2 - Abdulrazak, Bessam

A2 - Aloulou, Hamdi

A2 - Kallel, Slim

PB - Springer

T2 - 18th International Conference on Smart Homes and Health Telematics 2020

Y2 - 24 June 2020 through 26 June 2020

ER -

Zorgui S, Chaabene S, Bouaziz B, Batatia H, Chaari L. A Convolutional Neural Network for Lentigo Diagnosis. In Jmaiel M, Mokhtari M, Abdulrazak B, Aloulou H, Kallel S, editors, The Impact of Digital Technologies on Public Health in Developed and Developing Countries. ICOST 2020. Springer. 2020. p. 89-99. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-51517-1_8

A Convolutional Neural Network for Lentigo Diagnosis

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this