Automated measurement of fetal head circumference
We will use the data from the automated measurement of fetal head circumference
competition on the Grand Challenge website. During pregnancy, ultrasound imaging is
used to measure the fetal head circumference. The measurement can be used to monitor the
growth of the fetus. The dataset contains the two-dimensional (2D) ultrasound images of
the standard plane.
More about the problem Code: https://bit.ly/2RMqPfJ
The first column represents the ultrasound image, while the second column represents the corresponding annotation. Our task is to form a autoencoder model that can find these mask.
Data description
The dataset for this challenge contains a total of 1334 two-dimensional (2D) ultrasound
images of the standard plane that can be used to measure the HC.
The data is divided into a training set of 999 images and a test set of 335 images. The size
of each 2D ultrasound image is 800 by 540 pixels with a pixel size ranging from 0.052 to
0.326 mm.
The training set also includes an image with the manual annotation of the head circumference
for each HC, which was made by a trained sonographer.
Loss function (Dice Loss)
Training Results
Training and validation loss:
Training and validation accuracy:
Testing Results
