Standard Plane Detection in 3D Fetal Ultrasound Using an Iterative Transformation Network

TL;DR

This paper introduces an Iterative Transformation Network that automatically detects standard fetal brain planes in 3D ultrasound volumes, reducing manual effort and improving accuracy with a CNN-based iterative approach.

Contribution

The novel ITN method uses an iterative CNN framework with multi-task learning for precise, automatic standard plane detection in 3D fetal ultrasound volumes.

Findings

Achieves ~3.8mm/12.7° error for transventricular plane

Achieves ~3.8mm/12.6° error for transcerebellar plane

Operates in under half a second per plane

Abstract

Standard scan plane detection in fetal brain ultrasound (US) forms a crucial step in the assessment of fetal development. In clinical settings, this is done by manually manoeuvring a 2D probe to the desired scan plane. With the advent of 3D US, the entire fetal brain volume containing these standard planes can be easily acquired. However, manual standard plane identification in 3D volume is labour-intensive and requires expert knowledge of fetal anatomy. We propose a new Iterative Transformation Network (ITN) for the automatic detection of standard planes in 3D volumes. ITN uses a convolutional neural network to learn the relationship between a 2D plane image and the transformation parameters required to move that plane towards the location/orientation of the standard plane in the 3D volume. During inference, the current plane image is passed iteratively to the network until it converges to the standard plane location. We explore the effect of using different transformation representations as regression outputs of ITN. Under a multi-task learning framework, we introduce additional classification probability outputs to the network to act as confidence measures for the regressed transformation parameters in order to further improve the localisation accuracy. When evaluated on 72 US volumes of fetal brain, our method achieves an error of 3.83mm/12.7 degrees and 3.80mm/12.6 degrees for the transventricular and transcerebellar planes respectively and takes 0.46s per plane. Source code is publicly available at https://github.com/yuanwei1989/plane-detection.