TY - GEN
T1 - Automated Cerebral Lateral Ventricle Ratio Measurement from 2-Dimensional Fetal Ultrasound Image to Predict Ventriculomegaly
AU - Nabila, Maratun
AU - Fatoni, Muhammad Hilman
AU - Sardjono, Tri Arief
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/17
Y1 - 2020/11/17
N2 - Fetal Ventriculomegaly (VM) is described as dilatation of the cerebral ventricles on ultrasound evaluation. According to the ventricular diameter, VM can be categorized as mild, moderate, and severe. Ventriculomegaly can be diagnosed using sonography by identifying abnormal ventricular size based on ventricular diameter or Lateral Ventricle Ratio (LVR). In this study, a method of measuring LVR is proposed to overcome data variability. The image first enters the pre-processing stage, then enters the Hough Transform stage to determine the Region of Interest (ROI). Next, continued by segmentation and feature extraction stage to obtain the Choroid Plexus to produce LVR. This stage replaces the step of manually laying down the calipers. Finally, measurements are taken to determine the condition of the ventricles and its relationship with ventriculomegaly. From this method, the accuracy of the algorithm compared to the real conditions is 68.42%, precision of 67.56%, sensitivity of 100%, and specificity of 7.69%.
AB - Fetal Ventriculomegaly (VM) is described as dilatation of the cerebral ventricles on ultrasound evaluation. According to the ventricular diameter, VM can be categorized as mild, moderate, and severe. Ventriculomegaly can be diagnosed using sonography by identifying abnormal ventricular size based on ventricular diameter or Lateral Ventricle Ratio (LVR). In this study, a method of measuring LVR is proposed to overcome data variability. The image first enters the pre-processing stage, then enters the Hough Transform stage to determine the Region of Interest (ROI). Next, continued by segmentation and feature extraction stage to obtain the Choroid Plexus to produce LVR. This stage replaces the step of manually laying down the calipers. Finally, measurements are taken to determine the condition of the ventricles and its relationship with ventriculomegaly. From this method, the accuracy of the algorithm compared to the real conditions is 68.42%, precision of 67.56%, sensitivity of 100%, and specificity of 7.69%.
KW - hough transform
KW - lateral ventricle ratio
KW - ventriculomegaly
UR - http://www.scopus.com/inward/record.url?scp=85099640686&partnerID=8YFLogxK
U2 - 10.1109/CENIM51130.2020.9297908
DO - 10.1109/CENIM51130.2020.9297908
M3 - Conference contribution
AN - SCOPUS:85099640686
T3 - CENIM 2020 - Proceeding: International Conference on Computer Engineering, Network, and Intelligent Multimedia 2020
SP - 64
EP - 69
BT - CENIM 2020 - Proceeding
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2020
Y2 - 17 November 2020 through 18 November 2020
ER -