SAM-Driven Weakly Supervised Nodule Segmentation with Uncertainty-Aware Cross Teaching

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Xingyue, Li, Peiqi, Luo, Xiangde, Yang, Meng, Chang, Shi, Li, Zhongyu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910533729386496
author Zhao, Xingyue
Li, Peiqi
Luo, Xiangde
Yang, Meng
Chang, Shi
Li, Zhongyu
author_facet Zhao, Xingyue
Li, Peiqi
Luo, Xiangde
Yang, Meng
Chang, Shi
Li, Zhongyu
contents Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by medical professionals, a process that is both costly and labor-intensive. Recently, segmentation foundation models like SAM have shown impressive generalizability on natural images, suggesting their potential as pseudo-labelers. However, accurate prompts remain crucial for their success in medical images. In this work, we devise a novel weakly supervised framework that effectively utilizes the segmentation foundation model to generate pseudo-labels from aspect ration annotations for automatic nodule segmentation. Specifically, we develop three types of bounding box prompts based on scalable shape priors, followed by an adaptive pseudo-label selection module to fully exploit the prediction capabilities of the foundation model for nodules. We also present a SAM-driven uncertainty-aware cross-teaching strategy. This approach integrates SAM-based uncertainty estimation and label-space perturbations into cross-teaching to mitigate the impact of pseudo-label inaccuracies on model training. Extensive experiments on two clinically collected ultrasound datasets demonstrate the superior performance of our proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13553
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAM-Driven Weakly Supervised Nodule Segmentation with Uncertainty-Aware Cross Teaching
Zhao, Xingyue
Li, Peiqi
Luo, Xiangde
Yang, Meng
Chang, Shi
Li, Zhongyu
Computer Vision and Pattern Recognition
Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by medical professionals, a process that is both costly and labor-intensive. Recently, segmentation foundation models like SAM have shown impressive generalizability on natural images, suggesting their potential as pseudo-labelers. However, accurate prompts remain crucial for their success in medical images. In this work, we devise a novel weakly supervised framework that effectively utilizes the segmentation foundation model to generate pseudo-labels from aspect ration annotations for automatic nodule segmentation. Specifically, we develop three types of bounding box prompts based on scalable shape priors, followed by an adaptive pseudo-label selection module to fully exploit the prediction capabilities of the foundation model for nodules. We also present a SAM-driven uncertainty-aware cross-teaching strategy. This approach integrates SAM-based uncertainty estimation and label-space perturbations into cross-teaching to mitigate the impact of pseudo-label inaccuracies on model training. Extensive experiments on two clinically collected ultrasound datasets demonstrate the superior performance of our proposed method.
title SAM-Driven Weakly Supervised Nodule Segmentation with Uncertainty-Aware Cross Teaching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.13553