当前位置: X-MOL 学术Genet. Med. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Automated syndrome diagnosis by three-dimensional facial imaging.
Genetics in Medicine ( IF 6.6 ) Pub Date : 2020-06-01 , DOI: 10.1038/s41436-020-0845-y
Benedikt Hallgrímsson 1 , J David Aponte 1 , David C Katz 1 , Jordan J Bannister 2 , Sheri L Riccardi 3 , Nick Mahasuwan 4 , Brenda L McInnes 5 , Tracey M Ferrara 3 , Danika M Lipman 1 , Amanda B Neves 1 , Jared A J Spitzmacher 1 , Jacinda R Larson 1 , Gary A Bellus 6, 7 , Anh M Pham 8 , Elias Aboujaoude 9 , Timothy A Benke 6 , Kathryn C Chatfield 6 , Shanlee M Davis 6 , Ellen R Elias 6 , Robert W Enzenauer 10 , Brooke M French 11 , Laura L Pickler 6 , Joseph T C Shieh 12 , Anne Slavotinek 12 , A Robertson Harrop 13 , A Micheil Innes 5 , Shawn E McCandless 6 , Emily A McCourt 6 , Naomi J L Meeks 6 , Nicole R Tartaglia 6 , Anne C-H Tsai 6 , J Patrick H Wyse 14 , Jonathan A Bernstein 15 , Pedro A Sanchez-Lara 8 , Nils D Forkert 16 , Francois P Bernier 5 , Richard A Spritz 3 , Ophir D Klein 4, 12
Affiliation  

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.



中文翻译:

三维面部成像的自动化综合征诊断。

目的

深度表型分析是遗传病精准医学的新兴趋势。30-40% 的已知遗传综合征会影响面部形状。在这里,我们确定是否可以从人脸的 3D 图像中诊断出综合征。

方法

我们分析了 7057 名受试者的三维 (3D) 面部图像的变化:3327 名有 396 种不同的综合征、727 名亲属和 3003 名无关、未受影响的受试者。我们开发并测试了使用 3D 面部图像进行自动化综合征诊断的机器学习和参数化方法。

结果

不相关的、不受影响的受试者以 96% 的准确率被正确分类。综合考虑综合征和无关、未受影响的受试者,平衡准确率为 73%,平均灵敏度为 49%。排除不相关、未受影响的受试者显着提高了综合征诊断的平衡准确性 (78.1%) 和敏感性 (56.9%)。分类准确性的最佳预测指标是症状的表型严重程度和面部特征。令人惊讶的是,综合征受试者的未受影响的亲属经常被归类为综合征,通常是他们受影响亲属的综合征。

结论

通过定量 3D 面部成像进行深度表型分析在促进综合征诊断方面具有相当大的潜力。此外,“未受影响”亲属的 3D 面部成像可以识别未识别的病例或揭示半显性遗传的新例子。

更新日期:2020-06-01
down
wechat
bug