Enter your keyword

2-s2.0-85076886046

[vc_empty_space][vc_empty_space]

Risk Zone Estimation of Newborn Jaundice Based on Skin Color Image Analysis

Juliastuti E.a, Nadhira V.a, Satwika Y.W.a, Aziz N.A.a, Zahra N.a

a Instrumentation and Control Research Group, Institut Teknologi Bandung, Bandung, Indonesia

[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2019 IEEE.indirect hyperbilirubinemia or Baby Jaundice is a yellow discoloration of baby’s skin and eyes caused by the accumulation of unconjugated bilirubin. Based on de Greef’s research, 84% of newborns suffer from jaundice. Severe baby jaundice can lead to mental disorder or even death. Presently, the screening of baby jaundice is done based on doctor’s visual observation. This screening method is very subjective and therefore further validation is needed through bilirubin level measurement of patient’s blood sample. A research of baby jaundice identification method based on skin color image analysis is conducted in order to produce data objectively. This method is developed by processing image through several steps. Firstly, the image undergoes pre-processing to be filtered and color-corrected using a color card. Next, the image is segmented using K-Means method to acquire baby skin color. The image is then processed in 3 color spaces, which are RGB, HSV, and YCbCr. Subsequently, a histogram of intensity over pixel number is extracted from each channel of these color spaces, resulting in 9 histograms. From each histogram, 4 statistic parameters are calculated, which consists of mean, standard deviation, skewness, and kurtosis, generating 36 statistic parameters. After that, all statistic parameters are made as input variables for the validation and modelling of multivariable linear regression with an output variable of estimated bilirubin level. Validation aims to evaluate redundant and significant variables using 120 training data. The criteria of selection are variables with Variance Inflation Factor less than 10 and p-value less than 0.05. Finally, an estimation model is obtained which contains 5 variables with significant correlation over bilirubin levels. The obtained model resulted in a multiple correlation (multiple-R) of 0.71, categorized as a strong regression. Furthermore, the model is tested using 18 test data, which resulted in a multiple-R of 0.95, which also categorized as having strong regression. To complement the bilirubin level estimation, risk zone estimation is also done, that result in 84% data fit to the actual risk zone, with tolerance on false positives and false data in critical risk zones.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]bilirubin,Hyperbilirubinemia,Identification method,Multi-variable linear regression,Multiple correlation,newborn jaundice,Significant variables,Statistic parameters[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]bilirubin,image processing,indirect hyperbilirubinemia,newborn jaundice[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICA.2019.8916752[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]