Radiology

Pattern recognition (psychology)

Fetus

Feature (linguistics)

Fetal head

Biology

Philosophy

Ultrasound

Ground truth

Artificial intelligence

Pregnancy

Computer science

Linguistics

Feature extraction

Computer vision

Genetics

Medicine

Convolutional neural network

Ultrasound in Medicine & Biology

Machine learning for ultrasound image analysis and interpretation can be helpful in automated image classification in large-scale retrospective analyses to objectively derive new indicators of abnormal fetal development that are embedded in ultrasound images. Current approaches to automatic classification are limited to the use of either image patches (cropped images) or the global (whole) image. As many fetal organs have similar visual features, cropped images can misclassify certain structures such as the kidneys and abdomen.

Decision Fusion-Based Fetal Ultrasound Image Plane Classification Using Convolutional Neural Networks