Artificial intelligence for the objective evaluation of Acne investigator global assessment

Antonella Melina, Nhan Ngo Dinh, Benedetta Tafuri, Giusy Schipani, Steven Nisticò, Carlo Cosentino, Francesco Amato, Diane Thiboutot, Andrea Cherubini

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Introduction: The evaluation of Acne using ordinal scales reflects the clinical perception of severity but has shown low reproducibility both intra- and inter-rater. In this study, we investigated if Artificial Intelligence trained on images of Acne patients could perform acne grading with high accuracy and reliabilities superior to those of expert physicians. Methods: 479 patients with acne grading ranging from clear to severe and sampled from three ethnic groups participated in this study. Multi-polarization images of facial skin of each patient were acquired from five different angles using the visible spectrum. An Artificial Intelligence was trained using the acquired images to output automatically a measure of Acne severity in the 0-4 numerical range of the Investigator Global Assessment (IGA). Results: The Artificial Intelligence recognized the IGA of a patient with an accuracy of 0.854 and a correlation between manual and automatized evaluation of r=0.958 (P<.001). Discussion: This is the first work where an Artificial Intelligence was able to directly classify acne patients according to an IGA ordinal scale with high accuracy, no human intervention and no need to count lesions.

Original languageEnglish (US)
Pages (from-to)1006-1009
Number of pages4
JournalJournal of Drugs in Dermatology
Volume17
Issue number9
StatePublished - Jan 1 2018

Fingerprint

Artificial Intelligence
Acne Vulgaris
Research Personnel
Ethnic Groups
Physicians
Skin

All Science Journal Classification (ASJC) codes

  • Dermatology

Cite this

Melina, A., Dinh, N. N., Tafuri, B., Schipani, G., Nisticò, S., Cosentino, C., ... Cherubini, A. (2018). Artificial intelligence for the objective evaluation of Acne investigator global assessment. Journal of Drugs in Dermatology, 17(9), 1006-1009.
Melina, Antonella ; Dinh, Nhan Ngo ; Tafuri, Benedetta ; Schipani, Giusy ; Nisticò, Steven ; Cosentino, Carlo ; Amato, Francesco ; Thiboutot, Diane ; Cherubini, Andrea. / Artificial intelligence for the objective evaluation of Acne investigator global assessment. In: Journal of Drugs in Dermatology. 2018 ; Vol. 17, No. 9. pp. 1006-1009.
@article{d5cb823453bf4d43bffd36302d9f68fb,
title = "Artificial intelligence for the objective evaluation of Acne investigator global assessment",
abstract = "Introduction: The evaluation of Acne using ordinal scales reflects the clinical perception of severity but has shown low reproducibility both intra- and inter-rater. In this study, we investigated if Artificial Intelligence trained on images of Acne patients could perform acne grading with high accuracy and reliabilities superior to those of expert physicians. Methods: 479 patients with acne grading ranging from clear to severe and sampled from three ethnic groups participated in this study. Multi-polarization images of facial skin of each patient were acquired from five different angles using the visible spectrum. An Artificial Intelligence was trained using the acquired images to output automatically a measure of Acne severity in the 0-4 numerical range of the Investigator Global Assessment (IGA). Results: The Artificial Intelligence recognized the IGA of a patient with an accuracy of 0.854 and a correlation between manual and automatized evaluation of r=0.958 (P<.001). Discussion: This is the first work where an Artificial Intelligence was able to directly classify acne patients according to an IGA ordinal scale with high accuracy, no human intervention and no need to count lesions.",
author = "Antonella Melina and Dinh, {Nhan Ngo} and Benedetta Tafuri and Giusy Schipani and Steven Nistic{\`o} and Carlo Cosentino and Francesco Amato and Diane Thiboutot and Andrea Cherubini",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "17",
pages = "1006--1009",
journal = "Journal of Drugs in Dermatology",
issn = "1545-9616",
publisher = "Journal of Drugs in Dermatology",
number = "9",

}

Melina, A, Dinh, NN, Tafuri, B, Schipani, G, Nisticò, S, Cosentino, C, Amato, F, Thiboutot, D & Cherubini, A 2018, 'Artificial intelligence for the objective evaluation of Acne investigator global assessment', Journal of Drugs in Dermatology, vol. 17, no. 9, pp. 1006-1009.

Artificial intelligence for the objective evaluation of Acne investigator global assessment. / Melina, Antonella; Dinh, Nhan Ngo; Tafuri, Benedetta; Schipani, Giusy; Nisticò, Steven; Cosentino, Carlo; Amato, Francesco; Thiboutot, Diane; Cherubini, Andrea.

In: Journal of Drugs in Dermatology, Vol. 17, No. 9, 01.01.2018, p. 1006-1009.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Artificial intelligence for the objective evaluation of Acne investigator global assessment

AU - Melina, Antonella

AU - Dinh, Nhan Ngo

AU - Tafuri, Benedetta

AU - Schipani, Giusy

AU - Nisticò, Steven

AU - Cosentino, Carlo

AU - Amato, Francesco

AU - Thiboutot, Diane

AU - Cherubini, Andrea

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Introduction: The evaluation of Acne using ordinal scales reflects the clinical perception of severity but has shown low reproducibility both intra- and inter-rater. In this study, we investigated if Artificial Intelligence trained on images of Acne patients could perform acne grading with high accuracy and reliabilities superior to those of expert physicians. Methods: 479 patients with acne grading ranging from clear to severe and sampled from three ethnic groups participated in this study. Multi-polarization images of facial skin of each patient were acquired from five different angles using the visible spectrum. An Artificial Intelligence was trained using the acquired images to output automatically a measure of Acne severity in the 0-4 numerical range of the Investigator Global Assessment (IGA). Results: The Artificial Intelligence recognized the IGA of a patient with an accuracy of 0.854 and a correlation between manual and automatized evaluation of r=0.958 (P<.001). Discussion: This is the first work where an Artificial Intelligence was able to directly classify acne patients according to an IGA ordinal scale with high accuracy, no human intervention and no need to count lesions.

AB - Introduction: The evaluation of Acne using ordinal scales reflects the clinical perception of severity but has shown low reproducibility both intra- and inter-rater. In this study, we investigated if Artificial Intelligence trained on images of Acne patients could perform acne grading with high accuracy and reliabilities superior to those of expert physicians. Methods: 479 patients with acne grading ranging from clear to severe and sampled from three ethnic groups participated in this study. Multi-polarization images of facial skin of each patient were acquired from five different angles using the visible spectrum. An Artificial Intelligence was trained using the acquired images to output automatically a measure of Acne severity in the 0-4 numerical range of the Investigator Global Assessment (IGA). Results: The Artificial Intelligence recognized the IGA of a patient with an accuracy of 0.854 and a correlation between manual and automatized evaluation of r=0.958 (P<.001). Discussion: This is the first work where an Artificial Intelligence was able to directly classify acne patients according to an IGA ordinal scale with high accuracy, no human intervention and no need to count lesions.

UR - http://www.scopus.com/inward/record.url?scp=85060694461&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060694461&partnerID=8YFLogxK

M3 - Article

C2 - 30235389

AN - SCOPUS:85060694461

VL - 17

SP - 1006

EP - 1009

JO - Journal of Drugs in Dermatology

JF - Journal of Drugs in Dermatology

SN - 1545-9616

IS - 9

ER -

Melina A, Dinh NN, Tafuri B, Schipani G, Nisticò S, Cosentino C et al. Artificial intelligence for the objective evaluation of Acne investigator global assessment. Journal of Drugs in Dermatology. 2018 Jan 1;17(9):1006-1009.