Automated syndrome diagnosis by three-dimensional facial imaging.

Autor: Hallgrímsson B; Department of Cell Biology & Anatomy, Alberta Children's Hospital Research Institute and McCaig Bone and Joint Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada. bhallgri@ucalgary.ca., Aponte JD; Department of Cell Biology & Anatomy, Alberta Children's Hospital Research Institute and McCaig Bone and Joint Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Katz DC; Department of Cell Biology & Anatomy, Alberta Children's Hospital Research Institute and McCaig Bone and Joint Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Bannister JJ; Biomedical Engineering Graduate Program, University of Calgary, Calgary, AB, Canada., Riccardi SL; Human Medical Genetics and Genomics Program and Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Mahasuwan N; Program in Craniofacial Biology and Department of Orofacial Sciences, University of California, San Francisco, CA, USA., McInnes BL; Department of Medical Genetics, Alberta Children's Hospital Research Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Ferrara TM; Human Medical Genetics and Genomics Program and Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Lipman DM; Department of Cell Biology & Anatomy, Alberta Children's Hospital Research Institute and McCaig Bone and Joint Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Neves AB; Department of Cell Biology & Anatomy, Alberta Children's Hospital Research Institute and McCaig Bone and Joint Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Spitzmacher JAJ; Department of Cell Biology & Anatomy, Alberta Children's Hospital Research Institute and McCaig Bone and Joint Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Larson JR; Department of Cell Biology & Anatomy, Alberta Children's Hospital Research Institute and McCaig Bone and Joint Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Bellus GA; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA.; Department of Pediatrics, Geisinger Medical Center, Danville, PA, USA., Pham AM; Department of Pediatrics, Cedars Sinai Medical Center & David Geffen School of Medicine at UCLA, Los Angeles, CA, USA., Aboujaoude E; Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA., Benke TA; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Chatfield KC; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Davis SM; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Elias ER; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Enzenauer RW; Department of Pediatric Ophthalmology, University of Colorado School of Medicine, Aurora, CO, USA., French BM; Department of Surgery, Division of Plastic and Reconstructive Surgery, University of Colorado School of Medicine, Aurora, CO, USA., Pickler LL; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Shieh JTC; Department of Pediatrics and Institute for Human Genetics, University of California, San Francisco, CA, USA., Slavotinek A; Department of Pediatrics and Institute for Human Genetics, University of California, San Francisco, CA, USA., Harrop AR; Department of Surgery, Alberta Children's Hospital Research Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Innes AM; Department of Medical Genetics, Alberta Children's Hospital Research Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., McCandless SE; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., McCourt EA; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Meeks NJL; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Tartaglia NR; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Tsai AC; Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA., Wyse JPH; Division of Ophthalmology, Department of Surgery & Department of Medical Genetics, Cummings School of Medicine, University of Calgary, Calgary, AB, Canada., Bernstein JA; Department of Pediatrics, Stanford School of Medicine, Stanford, CA, USA., Sanchez-Lara PA; Department of Pediatrics, Cedars Sinai Medical Center & David Geffen School of Medicine at UCLA, Los Angeles, CA, USA., Forkert ND; Department of Radiology, Alberta Children's Hospital Research Institute, and Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Bernier FP; Department of Medical Genetics, Alberta Children's Hospital Research Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada., Spritz RA; Human Medical Genetics and Genomics Program and Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA. richard.spritz@cuanschutz.edu., Klein OD; Program in Craniofacial Biology and Department of Orofacial Sciences, University of California, San Francisco, CA, USA. ophir.klein@ucsf.edu.; Department of Pediatrics and Institute for Human Genetics, University of California, San Francisco, CA, USA. ophir.klein@ucsf.edu.
Jazyk: angličtina
Zdroj: Genetics in medicine : official journal of the American College of Medical Genetics [Genet Med] 2020 Oct; Vol. 22 (10), pp. 1682-1693. Date of Electronic Publication: 2020 Jun 01.
DOI: 10.1038/s41436-020-0845-y
Abstrakt: Purpose: Deep phenotyping is an emerging trend in precision medicine for genetic disease. The shape of the face is affected in 30-40% of known genetic syndromes. Here, we determine whether syndromes can be diagnosed from 3D images of human faces.
Methods: We analyzed variation in three-dimensional (3D) facial images of 7057 subjects: 3327 with 396 different syndromes, 727 of their relatives, and 3003 unrelated, unaffected subjects. We developed and tested machine learning and parametric approaches to automated syndrome diagnosis using 3D facial images.
Results: Unrelated, unaffected subjects were correctly classified with 96% accuracy. Considering both syndromic and unrelated, unaffected subjects together, balanced accuracy was 73% and mean sensitivity 49%. Excluding unrelated, unaffected subjects substantially improved both balanced accuracy (78.1%) and sensitivity (56.9%) of syndrome diagnosis. The best predictors of classification accuracy were phenotypic severity and facial distinctiveness of syndromes. Surprisingly, unaffected relatives of syndromic subjects were frequently classified as syndromic, often to the syndrome of their affected relative.
Conclusion: Deep phenotyping by quantitative 3D facial imaging has considerable potential to facilitate syndrome diagnosis. Furthermore, 3D facial imaging of "unaffected" relatives may identify unrecognized cases or may reveal novel examples of semidominant inheritance.
Databáze: MEDLINE
Externí odkaz: