Computational diagnostic methods on 2D photographs: A review of the literature - 01/05/21

Doi : 10.1016/j.jormas.2021.04.003

Quentin Hennocq ^a,^b,^⁎ , Roman Hossein Khonsari ^a,^b, Vincent Benoît ^a, Marlène Rio ^a,^c, Nicolas Garcelon ^a
^a Institut Imagine, Paris Descartes University-Sorbonne Paris Cité, Paris, France
^b Department of Maxillo-Facial Surgery and Plastic Surgery, Hôpital Universitaire Necker – Enfants Malades, Assistance Publique – Hôpitaux de Paris, Centre de Référence des Malformations Rares de la Face et de la Cavité Buccale MAFACE, Filière Maladies Rares TeteCou, Faculté de Médecine, Université de Paris, Paris, France
^c Department of Genetics, IHU Necker-Enfants Malades, University Paris Descartes, Paris, France

^⁎Corresponding author at: Institut Imagine; 24, boulevard du Montparnasse, 75015 Paris.Institut Imagine24, boulevard du MontparnasseParis75015

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Saturday 01 May 2021
Cet article a été publié dans un numéro de la revue, cliquez ici pour y accéder

Abstract

Here we provide a literature review of all the methods reported to date for analyzing 2D pictures for diagnostic purposes. Pubmed was used to screen the MEDLINE database using MeSH (Medical Subject Heading) terms and keyworks. The different recognition steps and the main results were reported. All human studies involving 2D facial photographs used to diagnose one or several conditions in healthy populations or in patients were included. We included 1515 articles and 27 publications were finally retained. 67% of the articles aimed at diagnosing one particular syndrome versus healthy controls and 33% aimed at performing multi-class syndrome recognition. Data volume varied from 15 to 17,106 patient pictures. Manual or automatic landmarks were one of the most commonly used tools in order to extract morphological information from images, in 22/27 (81%) publications. Geometrical features were extracted from landmarks based on Procrustes superimposition in 4/27 (15%). Textural features were extracted in 19/27 (70%) publications. Features were then classified using machine learning methods in 89% of publications, while deep learning methods were used in 11%. Facial recognition tools were generally successful in identifying rare conditions in dysmorphic patients, with comparable or higher recognition accuracy than clinical experts.

Le texte complet de cet article est disponible en PDF.

Keywords : Literature review, Machine learning, Deep learning, Photograph, Dysmorphology, Diagnosis