Linear regression

Biology

Transfer of learning

Statistics

Similarity (geometry)

Geomorphology

Fetus

Economics

Computer science

Sørensen–Dice coefficient

Geology

Image segmentation

Genetics

Regression

Segmentation

Head (geology)

Task (project management)

Pattern recognition (psychology)

Mathematics

Management

Image (mathematics)

Artificial intelligence

Deep learning

Convolutional neural network

Machine learning

Pregnancy

Fetal head

Computer Methods and Programs in Biomedicine

Measuring head-circumference (HC) length from ultrasound (US) images is a crucial clinical task to assess fetus growth. To lower intra- and inter-operator variability in HC length measuring, several computer-assisted solutions have been proposed in the years. Recently, a large number of deep-learning approaches is addressing the problem of HC delineation through the segmentation of the whole fetal head via convolutional neural networks (CNNs). Since the task is a edge-delineation problem, we propose a different strategy based on regression CNNs. The proposed framework consists of a region-proposal CNN for head localization and centering, and a regression CNN for accurately delineate the HC. The first CNN is trained exploiting transfer learning, while we propose a training strategy for the regression CNN based on distance fields. The framework was tested on the HC18 Challenge dataset, which consists of 999 training and 335 testing images. A mean absolute difference of 1.90 ( ± 1.76) mm and a Dice similarity coefficient of 97.75 ( ± 1.32) % were achieved, overcoming approaches in the literature. The experimental results showed the effectiveness of the proposed framework, proving its potential in supporting clinicians during the clinical practice.

A regression framework to head-circumference delineation from US fetal images