Contrast-Invariant Self-supervised Segmentation for Quantitative Placental MRI

TL;DR

This paper introduces a contrast-invariant, self-supervised segmentation method for placental MRI that leverages multi-echo data to improve robustness and generalization without manual annotations.

Contribution

It presents a novel framework combining masked autoencoding, pseudo-labeling, and semantic matching for multi-echo placental segmentation, addressing boundary contrast and motion artifacts.

Findings

Outperforms single-echo and naive fusion baselines

Generalizes effectively across different echo times

First systematic use of multi-echo MRI for placental segmentation

Abstract

Accurate placental segmentation is essential for quantitative analysis of the placenta. However, this task is particularly challenging in T2*-weighted placental imaging due to: (1) weak and inconsistent boundary contrast across individual echoes; (2) the absence of manual ground truth annotations for all echo times; and (3) motion artifacts across echoes caused by fetal and maternal movement. In this work, we propose a contrast-augmented segmentation framework that leverages complementary information across multi-echo T2*-weighted MRI to learn robust, contrast-invariant representations. Our method integrates: (i) masked autoencoding (MAE) for self-supervised pretraining on unlabeled multi-echo slices; (ii) masked pseudo-labeling (MPL) for unsupervised domain adaptation across echo times; and (iii) global-local collaboration to align fine-grained features with global anatomical context. We further introduce a semantic matching loss to encourage representation consistency across echoes of the same subject. Experiments on a clinical multi-echo placental MRI dataset demonstrate that our approach generalizes effectively across echo times and outperforms both single-echo and naive fusion baselines. To our knowledge, this is the first work to systematically exploit multi-echo T2*-weighted MRI for placental segmentation.