Automated syndrome diagnosis by three-dimensional facial imaging.
Ontology highlight
ABSTRACT: 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.
SUBMITTER: Hallgrimsson B
PROVIDER: S-EPMC7521994 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Cantú syndrome (CS) was first described in 1982, and is caused by pathogenic variants in ABCC9 and KCNJ8 encoding regulatory and pore forming subunits of ATP-sensitive potassium (KATP ) channels, respectively. It is characterized by congenital hypertrichosis, osteochondrodysplasia, extensive cardiovascular abnormalities and distinctive facial anomalies including a broad nasal bridge, long philtrum, epicanthal folds, and prominent lips. Many genetic syndromes, such as CS, involve facial anomalies that serve as a significant clue in the initial identification of the respective disorder before clinical or molecular diagnosis are undertaken. However, an overwhelming number of CS patients receive misdiagnoses based on an evaluation of coarse facial features. By analyzing three-dimensional images of CS faces, we quantified facial dysmorphology in a cohort of both male and female CS patients with confirmed ABCC9 variants. Morphometric analysis of different regions of the face revealed gender-specific significant differences in face shape. Moreover, we show that 3D facial photographs can distinguish between CS and other genetic disorders with specific facial dysmorphologies that have been mistaken for CS-associated anomalies in the past, hence assisting in an earlier clinical and molecular diagnosis. This optimizes genetic counseling and reduces stress for patients and parents by avoiding unnecessary misdiagnosis.
| S-EPMC7217184 | biostudies-literature
Project description:Automated phenotyping is essential for the creation of large, highly standardized datasets from anatomical imaging data. Such datasets can support large-scale studies of complex traits or clinical studies related to precision medicine or clinical trials. We have developed a method that generates three-dimensional landmark data that meet the requirements of standard geometric morphometric analyses. The method is robust and can be implemented without high-performance computing resources. We validated the method using both direct comparison to manual landmarking on the same individuals and also analyses of the variation patterns and outlier patterns in a large dataset of automated and manual landmark data. Direct comparison of manual and automated landmarks reveals that automated landmark data are less variable, but more highly integrated and reproducible. Automated data produce covariation structure that closely resembles that of manual landmarks. We further find that while our method does produce some landmarking errors, they tend to be readily detectable and can be fixed by adjusting parameters used in the registration and control-point steps. Data generated using the method described here have been successfully used to study the genomic architecture of facial shape in two different genome-wide association studies of facial shape.
| S-EPMC5345630 | biostudies-literature
Project description:SignificancePhotoacoustic tomography (PAT) has great potential in monitoring disease progression and treatment response in breast cancer. However, due to variations in breast repositioning, there is a chance of geometric misalignment between images. Further, poor repositioning can affect light fluence distribution and imaging field-of-view, making images different from one another. The net effect is that it becomes challenging to distinguish between image changes due to repositioning effects and those due to true biological variations.AimThe aim is to develop a three-dimensional image registration framework for geometrically aligning repeated PAT volumetric images, which are potentially affected by repositioning effects such as misalignment, changed radiant exposure conditions, and different fields-of-view.ApproachThe proposed framework involves the use of a coordinate-based neural network to represent the displacement field between pairs of PAT volumetric images. A loss function based on normalized cross correlation and Frangi vesselness feature extraction at multiple scales was implemented. We refer to our image registration framework as MUVINN-reg, which stands for multiscale vesselness-based image registration using neural networks. The approach was tested on a longitudinal dataset of healthy volunteer breast PAT images acquired with the hybrid photoacoustic-ultrasound Photoacoustic Mammoscope 3 imaging system. The registration performance was also tested under unfavorable repositioning conditions such as intentional mispositioning, and variation in breast-supporting cup size between measurements.ResultsA total of 13 pairs of repeated PAT scans were included in this study. MUVINN-reg showed excellent performance in co-registering each pair of images. The proposed framework was shown to be robust to image intensity shifts and field-of-view changes. Furthermore, MUVINN-reg could align vessels at imaging depths greater than 4 cm.ConclusionsThe proposed framework will enable the use of PAT for quantitative and reproducible monitoring of disease progression and treatment response.
| S-EPMC10787589 | biostudies-literature
Project description:The examination of hematoxylin and eosin (H&E)-stained tissues on glass slides by conventional light microscopy is the foundation for histopathological diagnosis. However, this conventional method has some limitations in x-y axes due to its relatively narrow range of observation area and in z-axis due to its two-dimensionality. In this study, we applied a CUBIC pipeline, which is the most powerful tissue-clearing and three-dimensional (3D)-imaging technique, to clinical pathology. CUBIC was applicable to 3D imaging of both normal and abnormal patient-derived, human lung and lymph node tissues. Notably, the combination of deparaffinization and CUBIC enabled 3D imaging of specimens derived from paraffin-embedded tissue blocks, allowing quantitative evaluation of nuclear and structural atypia of an archival malignant lymphoma tissue. Furthermore, to examine whether CUBIC can be applied to practical use in pathological diagnosis, we performed a histopathological screening of a lymph node metastasis based on CUBIC, which successfully improved the sensitivity in detecting minor metastatic carcinoma nodules in lymph nodes. Collectively, our results indicate that CUBIC significantly contributes to retrospective and prospective clinicopathological diagnosis, which might lead to the establishment of a novel field of medical science based on 3D histopathology.
| S-EPMC5571108 | biostudies-literature
Project description:Three-dimensional (3D) surface imaging using stereophotogrammetry has become increasingly popular in clinical settings, offering advantages for surgical planning and outcome evaluation. The handheld Vectra H1 is a low-cost, highly portable system that offers several advantages over larger stationary cameras, but independent technical validation is currently lacking. In this study, 3D facial images of 26 adult participants were captured with the Vectra H1 system and the previously validated 3dMDface system. Using error magnitude statistics, 136 linear distances were compared between cameras. In addition, 3D facial surfaces from each system were registered, heat maps generated, and global root mean square (RMS) error calculated. The 136 distances were highly comparable across the two cameras, with an average technical error of measurement (TEM) value of 0.84mm (range 0.19-1.54mm). The average RMS value of the 26 surface-to-surface comparisons was 0.43mm (range 0.33-0.59mm). In each case, the vast majority of the facial surface differences were within a ±1mm threshold. Areas exceeding ±1mm were generally limited to facial regions containing hair or subject to facial microexpressions. These results indicate that 3D facial surface images acquired with the Vectra H1 system are sufficiently accurate for most clinical applications.
| S-EPMC5803347 | biostudies-literature
Project description:ObjectiveTo determine three-dimensional (3D) effects of three different rapid maxillary expansion (RME) appliances on facial soft tissues.Materials and methodsForty-two children (18 boys, 24 girls) who required RME treatment were included in this study. Patients were randomly divided into three equal groups: banded RME, acrylic splint RME, and modified acrylic splint RME. For each patient, 3D images were obtained before treatment (T1) and at the end of the 3-month retention (T2) with the 3dMD system.ResultsWhen three RME appliances were compared in terms of the effects on the facial soft tissues, there were no significant differences among them. The mouth and nasal width showed a significant increase in all groups. Although the effect of the acrylic splint RME appliances on total face height was less than that of the banded RME, there was no significant difference between the appliances. The effect of the modified acrylic splint appliance on the upper lip was significant according to the volumetric measurements (P < .01).ConclusionsThere were no significant differences among three RME appliances on the facial soft tissues. The modified acrylic splint RME produced a more protrusive effect on the upper lip.
| S-EPMC8601490 | biostudies-literature
Project description:Three-dimensional (3D) optical imaging of whole biological organs with microscopic resolution has remained a challenge. Most versions of such imaging techniques require special preparation of the tissue specimen. Here we demonstrate microtomy-assisted photoacoustic microscopy (mPAM) of mouse brains and other organs, which automatically acquires serial distortion-free and registration-free images with endogenous absorption contrasts. Without tissue staining or clearing, mPAM generates micrometer-resolution 3D images of paraffin- or agarose-embedded whole organs with high fidelity, achieved by label-free simultaneous sensing of DNA/RNA, hemoglobins, and lipids. mPAM provides histology-like imaging of cell nuclei, blood vessels, axons, and other anatomical structures, enabling the application of histopathological interpretation at the organelle level to analyze a whole organ. Its deep tissue imaging capability leads to less sectioning, resulting in negligible sectioning artifact. mPAM offers a new way to better understand complex biological organs.
| S-EPMC5680318 | biostudies-literature
Project description:Many genetic syndromes involve a facial gestalt that suggests a preliminary diagnosis to an experienced clinical geneticist even before a clinical examination and genotyping are undertaken. Previously, using visualization and pattern recognition, we showed that dense surface models (DSMs) of full face shape characterize facial dysmorphology in Noonan and in 22q11 deletion syndromes. In this much larger study of 696 individuals, we extend the use of DSMs of the full face to establish accurate discrimination between controls and individuals with Williams, Smith-Magenis, 22q11 deletion, or Noonan syndromes and between individuals with different syndromes in these groups. However, the full power of the DSM approach is demonstrated by the comparable discriminating abilities of localized facial features, such as periorbital, perinasal, and perioral patches, and the correlation of DSM-based predictions and molecular findings. This study demonstrates the potential of face shape models to assist clinical training through visualization, to support clinical diagnosis of affected individuals through pattern recognition, and to enable the objective comparison of individuals sharing other phenotypic or genotypic properties.
| S-EPMC1285182 | biostudies-literature
Project description:Objective: Facial changes are common among nearly all acromegalic patients. As they develop slowly, patients often fail to notice such changes before they become obvious. Consequently, diagnosis and treatment are often delayed. So far, convenient and accurate early detection of this disease is still unavailable. This study is designed to combine the use of 3D imaging and machine learning techniques in facial feature analysis and identification of acromegalic patients, in an effort to ascertain how both techniques performed in terms of applicability and value in the early detection of the disease. Methods: One hundred and twenty-four participants including 62 patients with acromegaly and 62 matched controls were enrolled. Using three-dimensional imaging techniques, 58 facial parameters were measured on each face. A two-way analysis of variance (ANOVA) and a post-hoc t-tests were conducted to examine the variations of these parameters with disease status and gender. Using linear discriminant analysis (LDA), we further distinguished patients from controls, characterized what combinations of the parameters could best predict disease state and their relative contributions. Results: Patients are significantly different from normal subjects in many variables, and facial changes of male patients are more significant than female ones. Both male and female patients present following major changes: the increase of facial length and breadth, the widening and elevation of the nose, the thickening of vermilion and the enlargement of the mandible. Facial variables which strongly related to the pathological states can be used to predict the morbid state with high accuracy (prediction accuracies 92.86% in females, p < 0.0001 and 75% in males, p < 0.001). We have further testified that only a few variables play a vital role in disease prediction and the vital combination of variables vary with gender. Conclusions: Three-dimensional imaging enables comprehensive and accurate quantification of facial characteristics, which makes it a promising technique to investigate facial features of acromegalic patients. In combination with machine learning technique, patients can be accurately identified and predicted by their facial variables. This approach might be beneficial for the early detection of acromegalic patients and timely consultation to improve their outcomes.
| S-EPMC7403213 | biostudies-literature
Project description:The facial colliculus (FC), an important landmark for planning a surgical approach to brainstem cavernous malformation (BCM), is a microstructure; therefore, it may be difficult to identify on magnetic resonance imaging (MRI). Three-dimensional (3D) images may improve the FC-identification certainty; hence, this study attempted to validate the FC-identification certainty between two-dimensional (2D) and 3D images of patients with a normal brainstem and those with BCM. In this retrospective study, we included 10 patients with a normal brainstem and 10 patients who underwent surgery for BCM. The region of the FC in 2D and 3D images was independently identified by three neurosurgeons, three times in each case, using the method for continuously distributed test results (0-100). The intra- and inter-rater reliability of the identification certainty were confirmed using the intraclass correlation coefficient (ICC). The FC-identification certainty for 2D and 3D images was compared using the Wilcoxon signed-rank test. The ICC (1,3) and ICC (3,3) in both groups ranged from 0.88 to 0.99; therefore, the intra- and inter-rater reliability were good. In both groups, the FC-identification certainty was significantly higher for 3D images than for 2D images (normal brainstem group; 82.4 vs. 61.5, P = .0020, BCM group; 40.2 vs. 24.6, P = .0059 for the unaffected side, 29.3 vs. 17.3, P = .0020 for the affected side). In the normal brainstem and BCM groups, 3D images had better FC-identification certainty. 3D images are effective for the identification of the FC.
| S-EPMC8258009 | biostudies-literature