1
|
Kong X, Wang Z, Sun J, Qi X, Qiu Q, Ding X. Facial recognition for disease diagnosis using a deep learning convolutional neural network: a systematic review and meta-analysis. Postgrad Med J 2024:qgae061. [PMID: 39102373 DOI: 10.1093/postmj/qgae061] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Revised: 03/20/2024] [Accepted: 04/24/2024] [Indexed: 08/07/2024]
Abstract
BACKGROUND With the rapid advancement of deep learning network technology, the application of facial recognition technology in the medical field has received increasing attention. OBJECTIVE This study aims to systematically review the literature of the past decade on facial recognition technology based on deep learning networks in the diagnosis of rare dysmorphic diseases and facial paralysis, among other conditions, to determine the effectiveness and applicability of this technology in disease identification. METHODS This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines for literature search and retrieved relevant literature from multiple databases, including PubMed, on 31 December 2023. The search keywords included deep learning convolutional neural networks, facial recognition, and disease recognition. A total of 208 articles on facial recognition technology based on deep learning networks in disease diagnosis over the past 10 years were screened, and 22 articles were selected for analysis. The meta-analysis was conducted using Stata 14.0 software. RESULTS The study collected 22 articles with a total sample size of 57 539 cases, of which 43 301 were samples with various diseases. The meta-analysis results indicated that the accuracy of deep learning in facial recognition for disease diagnosis was 91.0% [95% CI (87.0%, 95.0%)]. CONCLUSION The study results suggested that facial recognition technology based on deep learning networks has high accuracy in disease diagnosis, providing a reference for further development and application of this technology.
Collapse
Affiliation(s)
- Xinru Kong
- Shandong University of Traditional Chinese Medicine, No. 16369, Jingshi Road, Lixia District, Jinan City, Shandong Province 250355, China
- Department of Vertigo Center, Air Force Specialized Medical Center, Beijing 100142, China
| | - Ziyue Wang
- Shandong University of Traditional Chinese Medicine, No. 16369, Jingshi Road, Lixia District, Jinan City, Shandong Province 250355, China
| | - Jie Sun
- Rizhao Central Hospital, Rizhao, Shandong 276800, China
| | - Xianghua Qi
- Department of Neurology II, Affiliated Hospital of Shandong University of Traditional Chinese Medicine, No. 16369, Jingshi Road, Lixia District, Jinan City, Shandong Province 25000, China
| | - Qianhui Qiu
- Department of Otolaryngology and Head and Neck Surgery, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Cardiovsacular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Science, Guangzhou 510000, China
| | - Xiao Ding
- Department of Neurology II, Affiliated Hospital of Shandong University of Traditional Chinese Medicine, No. 16369, Jingshi Road, Lixia District, Jinan City, Shandong Province 25000, China
| |
Collapse
|
2
|
Ciancia S, Goedegebuure WJ, Grootjen LN, Hokken-Koelega ACS, Kerkhof GF, van der Kaay DCM. Computer-aided facial analysis as a tool to identify patients with Silver-Russell syndrome and Prader-Willi syndrome. Eur J Pediatr 2023:10.1007/s00431-023-04937-x. [PMID: 36947243 PMCID: PMC10257592 DOI: 10.1007/s00431-023-04937-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/28/2022] [Revised: 03/03/2023] [Accepted: 03/15/2023] [Indexed: 03/23/2023]
Abstract
Genetic syndromes often show facial features that provide clues for the diagnosis. However, memorizing these features is a challenging task for clinicians. In the last years, the app Face2Gene proved to be a helpful support for the diagnosis of genetic diseases by analyzing features detected in one or more facial images of affected individuals. Our aim was to evaluate the performance of the app in patients with Silver-Russell syndrome (SRS) and Prader-Willi syndrome (PWS). We enrolled 23 pediatric patients with clinically or genetically diagnosed SRS and 29 pediatric patients with genetically confirmed PWS. One frontal photo of each patient was acquired. Top 1, top 5, and top 10 sensitivities were analyzed. Correlation with the specific genetic diagnosis was investigated. When available, photos of the same patient at different ages were compared. In the SRS group, Face2Gene showed top 1, top 5, and top 10 sensitivities of 39%, 65%, and 91%, respectively. In 41% of patients with genetically confirmed SRS, SRS was the first syndrome suggested, while in clinically diagnosed patients, SRS was suggested as top 1 in 33% of cases (p = 0.74). Face2Gene performed better in younger patients with SRS: in all patients in whom a photo taken at a younger age than the age of enrollment was available, SRS was suggested as top 1, albeit with variable degree of probability. In the PWS group, the top 1, top 5, and top 10 sensitivities were 76%, 97%, and 100%, respectively. PWS was suggested as top 1 in 83% of patients genetically diagnosed with paternal deletion of chromosome 15q11-13 and in 60% of patients presenting with maternal uniparental disomy of chromosome 15 (p = 0.17). The performance was uniform throughout the investigated age range (1-15 years). CONCLUSION In addition to a thorough medical history and detailed clinical examination, the Face2Gene app can be a useful tool to support clinicians in identifying children with a potential diagnosis of SRS or PWS. WHAT IS KNOWN • Several genetic syndromes present typical facial features that may provide clues for the diagnosis. • Memorizing all syndromic facial characteristics is a challenging task for clinicians. WHAT IS NEW • Face2Gene may represent a useful support for pediatricians for the diagnosis of genetic syndromes. • Face2Gene app can be a useful tool to integrate in the diagnostic path of patients with SRS and PWS.
Collapse
Affiliation(s)
- Silvia Ciancia
- Department of Pediatrics, Subdivision of Endocrinology, Erasmus University Medical Center, Sophia Children's Hospital, Rotterdam, Netherlands
- Post-Graduate School of Pediatrics, Department of Medical and Surgical Sciences for Mothers, Children and Adults, University of Modena and Reggio Emilia, Modena, Italy
| | - Wesley J Goedegebuure
- Department of Pediatrics, Subdivision of Endocrinology, Erasmus University Medical Center, Sophia Children's Hospital, Rotterdam, Netherlands
| | - Lionne N Grootjen
- Department of Pediatrics, Subdivision of Endocrinology, Erasmus University Medical Center, Sophia Children's Hospital, Rotterdam, Netherlands
| | - Anita C S Hokken-Koelega
- Department of Pediatrics, Subdivision of Endocrinology, Erasmus University Medical Center, Sophia Children's Hospital, Rotterdam, Netherlands
| | - Gerthe F Kerkhof
- Department of Pediatrics, Subdivision of Endocrinology, Erasmus University Medical Center, Sophia Children's Hospital, Rotterdam, Netherlands
| | - Daniëlle C M van der Kaay
- Department of Pediatrics, Subdivision of Endocrinology, Erasmus University Medical Center, Sophia Children's Hospital, Rotterdam, Netherlands.
| |
Collapse
|
3
|
Minatogawa M, Unzaki A, Morisaki H, Syx D, Sonoda T, Janecke AR, Slavotinek A, Voermans NC, Lacassie Y, Mendoza-Londono R, Wierenga KJ, Jayakar P, Gahl WA, Tifft CJ, Figuera LE, Hilhorst-Hofstee Y, Maugeri A, Ishikawa K, Kobayashi T, Aoki Y, Ohura T, Kawame H, Kono M, Mochida K, Tokorodani C, Kikkawa K, Morisaki T, Kobayashi T, Nakane T, Kubo A, Ranells JD, Migita O, Sobey G, Kaur A, Ishikawa M, Yamaguchi T, Matsumoto N, Malfait F, Miyake N, Kosho T. Clinical and molecular features of 66 patients with musculocontractural Ehlers-Danlos syndrome caused by pathogenic variants in CHST14 (mcEDS- CHST14). J Med Genet 2021; 59:865-877. [PMID: 34815299 PMCID: PMC9411915 DOI: 10.1136/jmedgenet-2020-107623] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2020] [Accepted: 09/25/2021] [Indexed: 12/24/2022]
Abstract
BACKGROUND Musculocontractural Ehlers-Danlos syndrome is caused by biallelic loss-of-function variants in CHST14 (mcEDS-CHST14) or DSE (mcEDS-DSE). Although 48 patients in 33 families with mcEDS-CHST14 have been reported, the spectrum of pathogenic variants, accurate prevalence of various manifestations and detailed natural history have not been systematically investigated. METHODS We collected detailed and comprehensive clinical and molecular information regarding previously reported and newly identified patients with mcEDS-CHST14 through international collaborations. RESULTS Sixty-six patients in 48 families (33 males/females; 0-59 years), including 18 newly reported patients, were evaluated. Japanese was the predominant ethnicity (27 families), associated with three recurrent variants. No apparent genotype-phenotype correlation was noted. Specific craniofacial (large fontanelle with delayed closure, downslanting palpebral fissures and hypertelorism), skeletal (characteristic finger morphologies, joint hypermobility, multiple congenital contractures, progressive talipes deformities and recurrent joint dislocation), cutaneous (hyperextensibility, fine/acrogeria-like/wrinkling palmar creases and bruisability) and ocular (refractive errors) features were observed in most patients (>90%). Large subcutaneous haematomas, constipation, cryptorchidism, hypotonia and motor developmental delay were also common (>80%). Median ages at the initial episode of dislocation or large subcutaneous haematoma were both 6 years. Nine patients died; their median age was 12 years. Several features, including joint and skin characteristics (hypermobility/extensibility and fragility), were significantly more frequent in patients with mcEDS-CHST14 than in eight reported patients with mcEDS-DSE. CONCLUSION This first international collaborative study of mcEDS-CHST14 demonstrated that the subtype represents a multisystem disorder with unique set of clinical phenotypes consisting of multiple malformations and progressive fragility-related manifestations; these require lifelong, multidisciplinary healthcare approaches.
Collapse
Affiliation(s)
- Mari Minatogawa
- Department of Medical Genetics, Shinshu University School of Medicine, Matsumoto, Japan.,Center for Medical Genetics, Shinshu University Hospital, Matsumoto, Japan
| | - Ai Unzaki
- Department of Medical Genetics, Shinshu University School of Medicine, Matsumoto, Japan.,Center for Medical Genetics, Shinshu University Hospital, Matsumoto, Japan.,Problem-Solving Oriented Training Program for Advanced Medical Personnel: NGSD (Next Generation Super Doctor) Project, Matsumoto, Japan
| | - Hiroko Morisaki
- Department of Medical Genetics, Sakakibara Heart Institute, Tokyo, Japan.,Department of Bioscience and Genetics, National Cerebral and Cardiovascular Center, Suita, Japan
| | - Delfien Syx
- Center for Medical Genetics, Ghent University Hospital, Ghent, Belgium.,Department of Biomolecular Medicine, Ghent University, Ghent, Belgium
| | - Tohru Sonoda
- Department of Occupational Therapy, School of Health and Science, Kyushu University of Health and Welfare, Nobeoka, Japan
| | - Andreas R Janecke
- Department of Pediatrics I, Medical University of Innsbruck, Innsbruck, Austria.,Division of Human Genetics, Medical University of Innsbruck, Innsbruck, Austria
| | - Anne Slavotinek
- Division of Genetics, Department of Pediatrics, University of California, San Francisco, San Francisco, CA, USA
| | - Nicol C Voermans
- Department of Neurology, Donders Institute for Brain, Cognition and Behavior, Radboud University Medical Centre, Nijmegen, The Netherlands
| | - Yves Lacassie
- Department of Pediatrics, Louisiana State University Health Science Center, New Orleans, LA, USA.,Division of Clinical Genetics and Department of Genetics, Children's Hospital of New Orleans, New Orleans, LA, USA
| | - Roberto Mendoza-Londono
- Division of Clinical and Metabolic Genetics, Department of Pediatrics, The Hospital for Sick Children, Toronto, Ontario, Canada
| | - Klaas J Wierenga
- Department of Clinical Genomics, Mayo Clinic, Jacksonville, FL, USA
| | - Parul Jayakar
- Division of Genetics and Metabolism, Nicklaus Children's Hospital, Miami, FL, USA
| | - William A Gahl
- Undiagnosed Diseases Program, Office of the NIH Director, National Institutes of Health, Bethesda, MD, USA.,Medical Genetics Branch, National Human Genome Research Institute, National Institutes of Health, Bethesda, MD, USA
| | - Cynthia J Tifft
- Undiagnosed Diseases Program, Office of the NIH Director, National Institutes of Health, Bethesda, MD, USA.,Medical Genetics Branch, National Human Genome Research Institute, National Institutes of Health, Bethesda, MD, USA
| | - Luis E Figuera
- División de Genética, Centro de Investigación Biomédica de Occidente, Instituto Mexicano del Seguro Social, Guadalajara, Mexico
| | | | - Alessandra Maugeri
- Department of Clinical Genetics, VU University Medical Centre Amsterdam, Amsterdam, The Netherlands
| | - Ken Ishikawa
- Department of Pediatrics, Iwate Medical University, Morioka, Japan
| | - Tomoko Kobayashi
- Department of Pediatrics, Tohoku University School of Medicine, Sendai, Japan.,Department of Preventive Medicine and Epidemiology, Tohoku Medical Megabank Organization, Tohoku University, Sendai, Japan.,Graduate School of Medicine, Tohoku University, Senda, Japan
| | - Yoko Aoki
- Department of Medical Genetics, Tohoku University School of Medicine, Sendai, Japan
| | - Toshihiro Ohura
- Division of Clinical Laboratory, Sendai City Hospital, Sendai, Japan
| | - Hiroshi Kawame
- Division of Genomic Medicine Support and Genetic Counseling, Tohoku Medical Megabank Organization, Tohoku University, Sendai, Japan.,Miyagi Children's Hospital, Sendai, Japan.,Division of Clinical Genetics, Jikei University Hospital, Tokyo, Japan
| | - Michihiro Kono
- Department of Dermatology, Nagoya University Graduate School of Medicine Faculty of Medicine, Nagoya, Japan.,Department of Dermatology and Plastic Surgery, Akita University Graduate School of Medicine School of Medicine, Akita, Akita, Japan
| | - Kosuke Mochida
- Department of Dermatology, University of Miyazaki Faculty of Medicine, Miyazaki, Japan
| | - Chiho Tokorodani
- Department of Pediatrics, Kochi Health Sciences Center, Kochi, Japan
| | - Kiyoshi Kikkawa
- Department of Pediatrics, Kochi Health Sciences Center, Kochi, Japan
| | - Takayuki Morisaki
- Department of Bioscience and Genetics, National Cerebral and Cardiovascular Center, Suita, Japan.,Division of Molecular Pathology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan.,Department of Internal Medicine, IMSUT Hospital, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan
| | | | - Takaya Nakane
- Department of Pediatrics, Faculty of Medicine, University of Yamanashi, Chuo, Japan
| | - Akiharu Kubo
- Department of Dermatology, Keio University School of Medicine, Tokyo, Japan
| | - Judith D Ranells
- Department of Pediatrics, University of South Florida, College of Medicine, Tampa, FL, USA
| | - Ohsuke Migita
- Department of Clinical Genetics, St. Marianna University, School of Medicine, Kawasaki, Japan
| | - Glenda Sobey
- EDS National Diagnostic Service, Sheffield Children's Hospital, Sheffield, UK
| | - Anupriya Kaur
- Department of Pediatrics (Genetics Division), Advanced Pediatric Cente, Post Graduate Institute of Medical Education and Research, Chandigarh, Chandigarh, India
| | - Masumi Ishikawa
- Department of Medical Genetics, Shinshu University School of Medicine, Matsumoto, Japan.,Center for Medical Genetics, Shinshu University Hospital, Matsumoto, Japan
| | - Tomomi Yamaguchi
- Department of Medical Genetics, Shinshu University School of Medicine, Matsumoto, Japan.,Center for Medical Genetics, Shinshu University Hospital, Matsumoto, Japan.,Division of Clinical Sequencing, Shinshu University School of Medicine, Matsumoto, Japan
| | - Naomichi Matsumoto
- Department of Human Genetics, Yokohama City University Graduate School of Medicine, Yokohama, Japan
| | - Fransiska Malfait
- Center for Medical Genetics, Ghent University Hospital, Ghent, Belgium.,Department of Biomolecular Medicine, Ghent University, Ghent, Belgium
| | - Noriko Miyake
- Department of Human Genetics, Yokohama City University Graduate School of Medicine, Yokohama, Japan
| | - Tomoki Kosho
- Department of Medical Genetics, Shinshu University School of Medicine, Matsumoto, Japan .,Center for Medical Genetics, Shinshu University Hospital, Matsumoto, Japan.,Division of Clinical Sequencing, Shinshu University School of Medicine, Matsumoto, Japan.,Research Center for Supports to Advanced Science, Shinshu University, Matsumoto, Japan
| |
Collapse
|
4
|
Daykin E, Fleischer N, Abdelwahab M, Hassib N, Schiffmann R, Ryan E, Sidransky E. Investigation of a dysmorphic facial phenotype in patients with Gaucher disease types 2 and 3. Mol Genet Metab 2021; 134:274-280. [PMID: 34663554 DOI: 10.1016/j.ymgme.2021.09.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/03/2021] [Revised: 09/27/2021] [Accepted: 09/28/2021] [Indexed: 10/20/2022]
Abstract
Gaucher disease (GD) is a rare lysosomal storage disorder that is divided into three subtypes based on presentation of neurological manifestations. Distinguishing between the types has important implications for treatment and counseling. Yet, patients with neuronopathic forms of GD, types 2 and 3, often present at young ages and can have overlapping phenotypes. It has been shown that new technologies employing artificial intelligence and facial recognition software can assist with dysmorphology assessments. Though classically not associated nor previously described with a dysmorphic facial phenotype, this study investigated whether a facial recognition platform could distinguish between photos of patients with GD2 and GD3 and discriminate between them and photos of healthy controls. Each cohort included over 100 photos. A cross validation scheme including a series of binary comparisons between groups was used. Outputs included a composite photo of each cohort and either a receiver operating characteristic curve or a confusion matrix. Binary comparisons showed that the software could correctly group photos at least 89% of the time. Multiclass comparison between GD2, GD3, and healthy controls demonstrated a mean accuracy of 76.6%, compared to a 37.7% chance for random comparison. Both GD2 and GD3 have now been added to the facial recognition platform as established syndromes that can be identified by the algorithm. These results suggest that facial recognition and artificial intelligence, though no substitute for other diagnostic methods, may aid in the recognition of neuronopathic GD. The algorithm, in concert with other clinical features, also appears to distinguish between young patients with GD2 and GD3, suggesting that this tool can help facilitate earlier implementation of appropriate management.
Collapse
Affiliation(s)
- Emily Daykin
- Medical Genetics Branch, NHGRI, NIH, Bethesda, MD, USA
| | | | - Magy Abdelwahab
- Cairo University Pediatric Hospital, and Social and Preventive Medicine Center, Kasr Elainy Hospital, Cairo, Egypt
| | - Nehal Hassib
- Orodental Genetics, National Research Center, Cairo, Egypt
| | | | - Emory Ryan
- Medical Genetics Branch, NHGRI, NIH, Bethesda, MD, USA
| | | |
Collapse
|