UPI-Net: Semantic Contour Detection in Placental Ultrasound

TL;DR

This paper introduces UPI-Net, a novel deep learning model designed for accurate semantic contour detection of the utero-placental interface in ultrasound images, incorporating global context to improve detection accuracy.

Contribution

The paper proposes UPI-Net, a lightweight model that captures long-range dependencies and multi-scale features for improved placental boundary detection in ultrasound images.

Findings

UPI-Net outperforms existing methods in contour detection metrics.

Global context modeling reduces false positives in UPI detection.

Efficient architecture maintains low computational overhead.

Abstract

Semantic contour detection is a challenging problem that is often met in medical imaging, of which placental image analysis is a particular example. In this paper, we investigate utero-placental interface (UPI) detection in 2D placental ultrasound images by formulating it as a semantic contour detection problem. As opposed to natural images, placental ultrasound images contain specific anatomical structures thus have unique geometry. We argue it would be beneficial for UPI detectors to incorporate global context modelling in order to reduce unwanted false positive UPI predictions. Our approach, namely UPI-Net, aims to capture long-range dependencies in placenta geometry through lightweight global context modelling and effective multi-scale feature aggregation. We perform a subject-level 10-fold nested cross-validation on a placental ultrasound database (4,871 images with labelled UPI from 49 scans). Experimental results demonstrate that, without introducing considerable computational overhead, UPI-Net yields the highest performance in terms of standard contour detection metrics, compared to other competitive benchmarks.