Interactive Segmentation Model for Placenta Segmentation from 3D Ultrasound images

TL;DR

This paper evaluates the effectiveness of a human-in-the-loop interactive segmentation model for placenta segmentation in 3D ultrasound images, demonstrating its robustness and efficiency compared to state-of-the-art models.

Contribution

It introduces a human-in-the-loop approach tailored for 3D ultrasound placenta segmentation, outperforming existing models in accuracy and efficiency.

Findings

Human-in-the-loop model achieves Dice score of 0.95

Model is effective with fewer prompts

Code is publicly available

Abstract

Placenta volume measurement from 3D ultrasound images is critical for predicting pregnancy outcomes, and manual annotation is the gold standard. However, such manual annotation is expensive and time-consuming. Automated segmentation algorithms can often successfully segment the placenta, but these methods may not consistently produce robust segmentations suitable for practical use. Recently, inspired by the Segment Anything Model (SAM), deep learning-based interactive segmentation models have been widely applied in the medical imaging domain. These models produce a segmentation from visual prompts provided to indicate the target region, which may offer a feasible solution for practical use. However, none of these models are specifically designed for interactively segmenting 3D ultrasound images, which remain challenging due to the inherent noise of this modality. In this paper, we evaluate publicly available state-of-the-art 3D interactive segmentation models in contrast to a human-in-the-loop approach for the placenta segmentation task. The Dice score, normalized surface Dice, averaged symmetric surface distance, and 95-percent Hausdorff distance are used as evaluation metrics. We consider a Dice score of 0.95 a successful segmentation. Our results indicate that the human-in-the-loop segmentation model reaches this standard. Moreover, we assess the efficiency of the human-in-the-loop model as a function of the amount of prompts. Our results demonstrate that the human-in-the-loop model is both effective and efficient for interactive placenta segmentation. The code is available at \url{https://github.com/MedICL-VU/PRISM-placenta}.