Search

A large fraction of monogenic disorders causes craniofacial abnormalities with characteristic facial morphology. These disorders can be diagnosed more efficiently with the support of computer-aided next-generation phenotyping tools, such as DeepGestalt. These tools have learned to associate facial phenotypes with the underlying syndrome through training on thousands of patient photographs. However, this "supervised" approach means that diagnoses are only possible if the disorder was part of the training set. To improve recognition of ultra-rare disorders, we created GestaltMatcher, which uses a deep convolutional neural network based on the DeepGestalt framework. We used photographs of 17,560 patients with 1,115 rare disorders to define a "Clinical Face Phenotype Space". Distance between cases in the phenotype space defines syndromic similarity, allowing test patients to be matched to a molecular diagnosis even when the disorder was not included in the training set. Similarities among patients with previously unknown disease genes can also be detected. Therefore, in concert with mutation data, GestaltMatcher could accelerate the clinical diagnosis of patients with ultra-rare disorders and facial dysmorphism, as well as enable the delineation of novel phenotypes.

A large fraction of monogenic disorders causes craniofacial abnormalities with characteristic facial morphology. These disorders can be diagnosed more efficiently with the support of computer-aided next-generation phenotyping tools, such as DeepGestalt. These tools have learned to associate facial phenotypes with the underlying syndrome through training on thousands of patient photographs. However, this “supervised” approach means that diagnoses are only possible if the disorder was part of the training set. To improve recognition of ultra-rare disorders, we created GestaltMatcher, which uses a deep convolutional neural network based on the DeepGestalt framework. We used photographs of 17,560 patients with 1,115 rare disorders to define a “Clinical Face Phenotype Space”. Distance between cases in the phenotype space defines syndromic similarity, allowing test patients to be matched to a molecular diagnosis even when the disorder was not included in the training set. Similarities among patients with previously unknown disease genes can also be detected. Therefore, in concert with mutation data, GestaltMatcher could accelerate the clinical diagnosis of patients with ultra-rare disorders and facial dysmorphism, as well as enable the delineation of novel phenotypes.

We propose to modify the common training protocols of optical flow, leading to sizable accuracy improvements without adding to the computational complexity of the training process. The improvement is based on observing the bias in sampling challenging data that exists in the current training protocol, and improving the sampling process. In addition, we find that both regularization and augmentation should decrease during the training protocol. Using an existing low parameters architecture, the method is ranked first on the MPI Sintel benchmark among all other methods, improving the best two frames method accuracy by more than 10%. The method also surpasses all similar architecture variants by more than 12% and 19.7% on the KITTI benchmarks, achieving the lowest Average End-Point Error on KITTI2012 among two-frame methods, without using extra datasets.