System to predict the gestational age and extracting the features such as length of the fetus and its orientation.

ABSTRACT:

In this study we are creating a system to predict the gestational age, fetal head detection and length of the head using image processing techniques. Image processing is a method to perform some operation on image inorder to enhance the image by preprocessing or to extract some features from the image. It is a type of signal processing in which input is image and output may be image or features associated with it. Image Processing toolbox such as matlab provides a comprehensive set of reference standard algorithm and workflow application for image processing, analysis, visualization and algorithm development. Digital image processing techniques help in manipulation of the digital images by using computers. The three general phases that all types of data have to undergo while using digital technique are preprocessing, segmentation and feature extraction.

This work mainly focuses on developing a system to predict the gestational age and extracting the features such as length of the fetus and its orientation. Three trimester wise ultrasound images of pregnant ladies are collected from different sources for the study. The ultrasound images are smoothened using various filters and segmenting the ROI for feature extraction

PROJECT OUTPUT VIDEO:

EXISTING SYSTEM:

Traditional approaches to GA estimation include (a) menstrual dating, which makes use of the first day of the last menstrual period (LMP) as a reference point for the EDD and (b) extraction of diameter and circumference measurements from 2D ultrasound (US) images of the fetal cranium, abdomen, and femur.

These measurements are regressed to population-based dating charts to estimate age and assess normality of fetal growth.

DISADVANTAGES OF EXISTING SYSTEM:

Beyond 24 post-menstrual weeks, measurement accuracy is dependent on operator expertise and compromised by increasing biological variation, inconsistencies in skull size approximation, and subjectivity in 2D diagnostic plane finding, all contributing to age approximation errors.

As pregnancy advances and biological variation amongst normal fetuses increases, the range of values of each biometric measurement associated with a specific GA also increases and so equations based upon size become less accurate. In practice, this means that whilst the predictive error at 22 weeks’ GA is considered acceptable in the majority of clinical settings, the predictive error at 28–42 weeks (±18 days) is considered to offer little clinical value

PROPOSED SYSTEM:

This work mainly focuses on developing a system to predict the gestational age and extracting the features such as length of the fetus and its orientation. Three trimester wise ultrasound images of pregnant ladies are collected from different sources for the study. The ultrasound images are smoothened using various filters and segmenting the ROI for feature extraction

ADVANTAGES OF PROPOSED SYSTEM:

Medical Image Processing is a wide platform which helps in maintaining the body healthy,therefore image processing related to medical has a vital role in present condition. Ultrasound scan used to monitor the baby’s movement and overall growth of the embryo. The scan during each trimester helps to know whether the baby is in a normal condition. In medical image processing after the biomedical image enhancement & proper analysis, they can be efficiently processed & objectively evaluated.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

• System            : Pentium Dual Core.

• Hard Disk       : 120 GB.

• Monitor          : 15’’ LED

• Input Devices : Keyboard, Mouse

• Ram                : 1GB.

SOFTWARE REQUIREMENTS:

• Operating system : Windows 7.

• Coding Language : MATLAB.

• Tool                       : MATLAB R2013A /2018