**5. Conclusion**

tematization and throughput compared to large-scale genotyping efforts [22]. Beyond these clinical aspects, dysmorphology has contributed much to current understanding of the ge‐ netic basis of human development [1]. Moreover, imprecise and nonstandardized nomencla‐ ture, especially of facial features, places a major difficulty for the communication between clinical geneticists [2]. It has to be noted that neither 2D nor 3D methods have direct applica‐ bility in clinical practice yet, as the number of specified syndromes is still very small [2].

As Boehringer [2] emphasize, database support with respect to facial traits is limited at present to apply similar studies as we do to establish better applications. Distinctive dys‐ morphic frontal faces specific to dysmorphic genotype-phenotype diseases are needed to train the system. Currently, in our study, a very limited number of dysmorphic genetic dis‐ eases by using frontal faces have been trained for further recognition process. There are sev‐ eral genetic databases such as eMERGE (Electronic Medical Records and Genomics) and PhenX (Consensus Measures for Phenotypes and Exposures), Dysmorphology Database in Oxford Medical Databases (OMD) and OMIM. One of which named OMD is more appropri‐ ate for our study, because it is better prepared to reveal genotype-phenotype associations in terms of images and taxonomy of dysmorphology, although it has very limited number of frontal faces for syndromes. One of the reasons that we work on frontal 2D image analysis is that this prominent database (OMD) that we aim to include into the study contains 2D ge‐ netic dysmorphic images rather than 3D videos by which the number of frames are captured and recorded. Moreover, most of the geneticists studying on dysmorphic diseases usually keep 2D images of their patients in their databases. The main drawback of the majority of 3D face recognition approaches is that they need all the elements of the system to be well calibrated and synchronized to acquire accurate 3D data (texture and depth maps) [19]. That will make it easier for investigators to collect and analyze the 2D dysmorphic data associat‐ ed with genotypes. Whereas capturing of 3D information results in a richer data set and al‐ lows for excellent visualization despite the difficulties in possessing the technology and in detecting 3D as mentioned by Kau [13]13, 2D analysis has several advantages in practical use: equipment is cheap and it is easy to handle [2]. Conventional and digital two-dimen‐ sional (2D) photography offer rapid and easy capture of facial images. 3D analysis of syn‐ dromes would sure give better results as depicted in Hommond's study [6]. However, the lack of available data in 3D invalidates any methodology implemented for the near future. Of course, recognition of face shape does not imply a diagnosis. A diagnosis is made by an appropriately trained clinician backed up, whenever possible, by genetic testing. For some dysmorphic syndromes there is no definitive genetic test and a clinical diagnosis has to suf‐ fice. For others, for example Noonan syndrome, a number of important genes may have been identified, but mutations for those genes may not be found in some children for whom

A masking is not applied to remove the background of the cropped faces in our study. By employing a background mask, which simply provides a face shaped region, the effect of

13 Due to inherent faults in technology and the distortion of light, none of the 3D imaging systems is accurate over the full field of view. Furthermore, all systems suffer from a potential for patient movement and alterations of facial ex‐

there is a compelling clinical diagnosis [3].

84 Decision Support System

pression between the multiple views needed to construct a 3D model of the face.

In terms of future technological support, two (2D) or three-dimensional (3D) models of fa‐ cial morphology are showing potential in syndrome delineation and discrimination, in ana‐ lyzing individual dysmorphology, and in contributing to multi-disciplinary and multispecies studies of genotype–phenotype correlations [7]. Our study is an example of substantiating this potential. We describe a new approach to syndrome identification by merging several algorithms. The algorithms that we included in our study are not novel. They have been utilized in many studies so far. However we included most essential ones in a robust composite understanding in a way to serve the everyday needs of the medical pro‐ fessionals who work in dysmorphology.

The preliminary results indicate that computer based diagnostic decision support systems such as the one we have established might be very helpful to assist medical professionals in genotype-phenotype dysmorphic diagnosis. The study reveals that the differences between facial regions such as facial landmarks, eyebrows, hair, lips, and chins can give the possibili‐ ty of predicting the diagnosis of syndromes. It may contribute to the medical professionals in several aspects. Some of these are:


**•** FaceGP DDSS methodology can provide genetic screening which is a preliminary process of applying standard analysis to large populations to pick up underlying symptoms of ge‐ netic disorders. Genetic screening is not a diagnosis, but can produce a differential diag‐ nosis which would lead to a definitive diagnosis and hence to early intervention and treatment.

**References**

[1] Smithson, S. F., & Winter, R. M. (2004). Diagnosis in Dysmorphology: Clues from the

Diagnostic Decision Support System in Dysmorphology

http://dx.doi.org/10.5772/51118

87

[2] Boehringer, S., Vollmar, T., Tasse, C., & Wurtz, R. (2006). Syndrome identification based on 2D analysis software. *European Journal of Human Genetics*, 14(10), 1082-1089.

[3] Hammond, P. (2011). What's in a face? 31 March 2008 http://www.hospitalmanage‐

[5] Loos, H. S., Wieczorek, D., Wurtz, R. P., et al. (2003). Computer-based recognition of

[6] Hammond, P., Hutton, T. J., Allanson, J. E., et al. (2005). Discriminating power of lo‐ calized three-dimensional facial morphology. *Am J Hum Genet*, 77(6), 999-1010.

[7] Hammond, P. (2007). The use of 3D face shape modelling in dysmorphology. *Arch*

[8] Douglas, T. S., & Mutsvangwa, T. E. M. (2010). A review of facial image analysis for delineation of the facial phenotype associated with fetal alcohol syndrome. *Am J Med*

[9] Kapoor, S., Khanna, S., & Bhatia, R. (2010). Facial gesture recognition using correla‐ tion and mahalanobis distance. *International journal of computer science and information*

[10] Turk, M. A., & Pentland, A. P. (1991). Face recognition using eigenfaces. *IEEE Conf.*

[11] Iancu, C., Corcoran, P., & Costache, G. (2007). A review of face recognition techni‐ ques for in-camera applications. In Signals, Circuits and Systems, 2007. ISSCS 2007.

[12] Aldridge, K. A., Boyadjiev, S. T., Capone, G., et al. (2005). Precision and Error of Three-Dimensional Phenotypic Measures Acquired From 3dMD Photogrammetric

[13] Kau, C. H., Rich, Mond. S., Incrapera, A., English, J., & Xia, J. J. (2007). Three-dimen‐ sional surface acquisition systems for the study of facial morphology and their appli‐ cation to maxillofacial surgery. *Int J Med Robotics Comput Assist Surg*, 3(2), 97-110.

[14] Gul, A. B. (2003). Holistic Face Recognition by Dimension Reduction. *Master Thesis.*

[15] Akalin, V. (2003). Face Recognition Using Eigenfaces and Neural Networks. *Master*

[4] Farkas, L. G. (1998). Anthropometry of the head and face. New York, Raven Press.

Skin. *The British Journal of Dermatology*, 151(5), 953-60.

dysmorphic faces. *Eur J Hum Genet*, 11(8), 555-60.

*on Computer Vision and Pattern Recognitio*, 586-591.

International Symposium on July (2007). , 1, 1-4.

Images. *American Journal of Medical Genetics*, 138A(3), 247-253 .

*Dis Child*, 92(12), 1120-1126.

*Genet Part A*, 152A(2), 528-536.

*security*, 7(2), 267-272.

*METU*.

*Thesis. METU*.

ment.net/features/feature1767/ (accessed 21 September 2011

The hope is that the FaceGP DDSS methodology will be widely adopted by the scientific community, fostering a new era of cooperation and collaboration and facilitating crossstudy. Based on user feedback, we expect to continue to update the functionality of the methodology. As the data gathering for age groups and ethnic groups becomes more stand‐ ardized and evolved internationally in the sense of dysmorphology, general implementa‐ tions valid for everybody will be more possible.

#### **5.1. Future work**

Further improvement in diagnosing/recognition seems to be possible by integrating a back‐ ground cropping mask algorithm that simply provides a face shaped region and minimize the effect of background change [15].

The dysmorphic faces from main databases as well as from individual databases referring to the names of the diseases should be both categorized and trained by the application for further better diagnostic decision support. This is a huge time consuming and challenging process needed to be done in the near future for the easy acceptance of the methodology by the scientific community. We intend to extend this work to a wider environment by including domain experts from academic and government institutions by deploying the methodology at sever‐ al sites including as possible as many syndromes. Furthermore, 3D image processing and fetus image analysis in dysmorphology is going to be the subject of our future study.
