**1. Introduction**

Down syndrome (DS) is the chromosomal abnormality caused in humans when extra genes from chromosome 21 are transferred to a newly produced embryo. It affects the fetal development leading to physical and mental abnormalities. The babies with DS have a distinct appearance than normal babies. Some of the DS victims are shown in **Figure 1**. The babies suffering from DS are likely to have retardation in growth and the mental problems. DS, in general, cannot be cured; the simplest way to avoid the babies with DS is to detect the fetus with DS and prevent it from being born.

DS is not a rare phenomenon and the occurrence of this phenomenon is eventually improving throughout the world. Patterson [1] in his work "Molecular genetic

**Figure 1.** *Victims of DS (courtesy: www.womens-health-advice.com).*

analysis of Down Syndrome" states that more than 1 in 1000 neonates has DS. A stats report [2] shows that i) the risk of DS in the global birth rate is 0.00125% ii) women in the age of 30 and below have 0.001% risk of DS iii) women in the age of 45 have 0.022% risk of DS. The abortion rates in DS-affected pregnancies [3] have amplified to 67–92% in the United States and Europe.

aneuploidy. If an EIF is detected in an ultrasound image, the pregnant women with EIF fetus feel dreadful mental pressure fearing that they would deliver DS affected baby [2]. This psychological weight caused in the pregnant ladies can undesirably affect the fetus. To cut the down the psychological weight of the pregnant ladies and to guarantee that the fetus is unaffected with DS, women with EIF symptoms are

*Comparison of nasal bone between normal fetus and DS related fetus (courtesy: http://babysmith2014.blogspot.com).*

*Ultrasonic Detection of Down Syndrome Using Multiscale Quantiser with Convolutional…*

*DOI: http://dx.doi.org/10.5772/intechopen.96502*

Amniocentesis, Percutaneous umbilical blood inspecting and Chorionic villus sampling methods are the most non-ultrasonic method for detecting DS. Amniocentesis is a method of collecting a little amount of the amniotic fluid that surrounds the fetus and analysing it for trisomy 21. It is carried in the light of ultrasonic guidance. It is advised after the 15th week of pregnancy. This method has the high risk of leaking amniotic fluid, miscarriage, needle injury to fetus and infection transmission. Percutaneous umbilical blood sampling (PUBS) is a method of collecting the blood from the umbilical cord and tests it for chromosomal defects. It is performed in the 18th week of the pregnancy. PUBS have a higher risk of miscarriage. Chorionic villus sampling (CVS) is a method of analysing the chromosomes in the cells taken from the placenta. CVS is performed between 9th and 14th weeks of the pregnancy. This method suffers from the drawbacks like miscarriage and uterine infection problems. As the relativity of EIF with DS is very low, it would not be advisable to request women with EIF fetus to undergo Amniocentesis, CVS and PUBS. There is a great need to coin a new mechanism that can differentiate DS related EIF fetus from the normal EIF fetus through ultrasound testing. This research aims at bringing a new

prescribed to go through chorionic villus sampling and amniocentesis.

**Figure 3.**

**163**

invention that can detect DS based on EIF through an ultrasound scan.

• A new medical parameter EIF is used for the detection of DS

and extracting the EIF in the ultrasound fetal images

the nasal bone hypoplasia in the training phase

• A new image segmentation algorithm Multi-scale Quantized Convolution Neural Network (MSQCNN) is developed and used for accurately detecting

• Cross-Correlation Technique (CCT) is employed to confirm DS by analysing

• A new supervised classification scheme Enhanced Learning Vector Quantiser (ELVQ) is utilised to differentiate the normal EIF from the EIF related to DS.

Introduction of the problem statement, the necessity for this research and the challenges present in this research had already been well discussed in section 1. The

The major contributions of this chapter are:

In medical world, ultrasonographic markers like nuchal fold, nasal bone hypoplasia and femur length are often seen as a symptom of DS. Nuchal fold is a skin fold noted at the backside of neck in the fetus during the second trimester. Increased thickness in the nuchal fold is observed as the most sensitive symptom of DS. A comparison of the nuchal fold between the normal fetus and DS affected fetus is shown in **Figure 2**.

**Figure 2.**

*Comparison of nuchal fold between normal fetus and DS related fetus (courtesy: http://babysmith2014.blog spot.com).*

Nasal bone hypoplasia is a condition where the nasal bone of the fetus appears to be very small. It has to be noted that 70% of DS [4] fetuses have no nasal bone or smaller nasal bone. A comparison of nasal bone analysis between the normal fetus and DS related fetus is shown in **Figure 3**.

Femur length is the measure of the longest bone in the fetus. Shortening of femur length is considered as the symptom of DS. Recently, Echogenic Intracardiac Foci (EIF) had been considered as a new symptom of DS. Many clinical researches affirm that the presence of EIF is considered as a potential indication of DS. An EIF is named as an intense white shape that is found in the heart of the fetus. It can be examined through the ultrasound. An article "Ultrasound Findings" expresses that EIF is seen in around 1 out of each 20 or 30 pregnancies (3–5%). EIF is associated with 12% of foetuses with DS [5] and biventricular EIF suffers higher risk for

*Ultrasonic Detection of Down Syndrome Using Multiscale Quantiser with Convolutional… DOI: http://dx.doi.org/10.5772/intechopen.96502*

**Figure 3.** *Comparison of nasal bone between normal fetus and DS related fetus (courtesy: http://babysmith2014.blogspot.com).*

aneuploidy. If an EIF is detected in an ultrasound image, the pregnant women with EIF fetus feel dreadful mental pressure fearing that they would deliver DS affected baby [2]. This psychological weight caused in the pregnant ladies can undesirably affect the fetus. To cut the down the psychological weight of the pregnant ladies and to guarantee that the fetus is unaffected with DS, women with EIF symptoms are prescribed to go through chorionic villus sampling and amniocentesis.

Amniocentesis, Percutaneous umbilical blood inspecting and Chorionic villus sampling methods are the most non-ultrasonic method for detecting DS. Amniocentesis is a method of collecting a little amount of the amniotic fluid that surrounds the fetus and analysing it for trisomy 21. It is carried in the light of ultrasonic guidance. It is advised after the 15th week of pregnancy. This method has the high risk of leaking amniotic fluid, miscarriage, needle injury to fetus and infection transmission. Percutaneous umbilical blood sampling (PUBS) is a method of collecting the blood from the umbilical cord and tests it for chromosomal defects. It is performed in the 18th week of the pregnancy. PUBS have a higher risk of miscarriage. Chorionic villus sampling (CVS) is a method of analysing the chromosomes in the cells taken from the placenta. CVS is performed between 9th and 14th weeks of the pregnancy. This method suffers from the drawbacks like miscarriage and uterine infection problems.

As the relativity of EIF with DS is very low, it would not be advisable to request women with EIF fetus to undergo Amniocentesis, CVS and PUBS. There is a great need to coin a new mechanism that can differentiate DS related EIF fetus from the normal EIF fetus through ultrasound testing. This research aims at bringing a new invention that can detect DS based on EIF through an ultrasound scan.

The major contributions of this chapter are:


Introduction of the problem statement, the necessity for this research and the challenges present in this research had already been well discussed in section 1. The

analysis of Down Syndrome" states that more than 1 in 1000 neonates has DS. A stats report [2] shows that i) the risk of DS in the global birth rate is 0.00125% ii) women in the age of 30 and below have 0.001% risk of DS iii) women in the age of 45 have 0.022% risk of DS. The abortion rates in DS-affected pregnancies [3] have

In medical world, ultrasonographic markers like nuchal fold, nasal bone hypoplasia and femur length are often seen as a symptom of DS. Nuchal fold is a skin fold noted at the backside of neck in the fetus during the second trimester. Increased thickness in the nuchal fold is observed as the most sensitive symptom of DS. A comparison of the nuchal fold between the normal fetus and DS affected fetus is

Nasal bone hypoplasia is a condition where the nasal bone of the fetus appears to be very small. It has to be noted that 70% of DS [4] fetuses have no nasal bone or smaller nasal bone. A comparison of nasal bone analysis between the normal fetus

Femur length is the measure of the longest bone in the fetus. Shortening of femur length is considered as the symptom of DS. Recently, Echogenic Intracardiac Foci (EIF) had been considered as a new symptom of DS. Many clinical researches affirm that the presence of EIF is considered as a potential indication of DS. An EIF is named as an intense white shape that is found in the heart of the fetus. It can be examined through the ultrasound. An article "Ultrasound Findings" expresses that EIF is seen in around 1 out of each 20 or 30 pregnancies (3–5%). EIF is associated with 12% of foetuses with DS [5] and biventricular EIF suffers higher risk for

*Comparison of nuchal fold between normal fetus and DS related fetus (courtesy: http://babysmith2014.blog*

amplified to 67–92% in the United States and Europe.

*Victims of DS (courtesy: www.womens-health-advice.com).*

*Computational Optimization Techniques and Applications*

and DS related fetus is shown in **Figure 3**.

shown in **Figure 2**.

**Figure 2.**

*spot.com).*

**162**

**Figure 1.**

rest of this chapter is structured as follows. A complete view of related studies is provided in section 2. The proposed methodology is elucidated in section 3. The test results and comparisons are elaborated in section 4. Future research directions and conclusion are briefed in section 5 and section 6.

Shafia Shakoor, Humera Ismail and Shama Munim [18] explored the experimental results in fetuses with EIF. The trial was experimented in Pakistan and the outcomes showed that 95.77% of the fetuses were normal, just 4.2% recorded abnormalities in heart and 0% had DS. Aaron B. Caughey, Deirdre J. Lyell et.al [19] assessed the impact of isolated EIF for screening DS. The investigation affirmed the use of EIF as a screening factor may prompt an immense number of amniocenteses

*Ultrasonic Detection of Down Syndrome Using Multiscale Quantiser with Convolutional…*

The following observations are evident from the recent researches carried out in

Histopathology is the assessment of tissues in the impacted organs of the body. The extensive growth of the computerised image processing has given rise to a new diagnostic methodology termed as computer-assisted diagnosis (CAD). CAD assists the radiologists for disease detection, diagnosis and prognosis prediction. Diagnosis of DS based on EIF is one of the difficult issues that could be tackled by CAD methodology. The efficiency of imaging techniques and CAD can be unitedly employed to substitute the traditional DS diagnostic methods like amniocentesis and chronic sampling.

The proposed system "Ultrasonic Detection of Down Syndrome using Multiscale Quantiser with Convolution Neural Network" uses a medical parameter EIF for the detection of DS. It is designed with the aim of discriminating the normal EIF from DS related EIF. It consists of two phases i) training phase and ii) testing phase. Training phase involves learning and forming the knowledge cluster of EIF related to DS. Testing phase involves classifying the diagnostic ultrasound fetal image as DS positive or negative, based on the knowledge cluster. An architecture diagram of the

Not all the fetus that contain EIF result in DS, only few patterns of EIF can cause

DS. The aim of this phase is to find the characteristics of DS-related EIF. The training phase includes five steps i) Image Pre-Processing using Neuro-Fuzzy Filter – to eliminate the speckle noise in the ultrasound fetal image that can hinder the

this field I) The most often utilised parameters for the identification of DS are nuchal fold, femur length and nasal bone hypoplasia ii) Association of DS and EIF is relatively low iii) There exist a need and necessity for developing a computerised methodology for spotting DS, as the manual diagnosis requires some artifacts.

and miscarriages to decide a rare DS fetus.

*DOI: http://dx.doi.org/10.5772/intechopen.96502*

proposed system is given below in **Figure 4**.

**3.1 Training phase**

*The architecture of the proposed system.*

**Figure 4.**

**165**

**3. Proposed methodology**
