腹部肿瘤分割是肿瘤筛查和诊断过程中至关重要但具有挑战性的步骤。虽然 3D 分割模型提供了强大的性能，但它们需要大量的计算资源。此外，在 3D 数据中，肿瘤通常只占一小部分，导致数据不平衡，并可能忽略关键信息。相反，2D分割模型具有轻量级结构，但忽略了切片间的相关性，存在边缘切片中肿瘤丢失的风险。为了应对这些挑战，本文提出了一种新颖的位置感知和关键切片特征共享二维肿瘤分割模型（PAKS-Net）。利用 Swin-Transformer，我们有效地对每个切片内的全局特征进行建模，从而促进基本信息的提取。此外，我们引入了位置感知模块来捕获肿瘤与其相应器官之间的空间关系，从而减轻周围器官组织的噪声和干扰。为了提高边缘切片分割的准确性，我们使用关键切片来辅助其他切片的分割，以优先考虑肿瘤区域。通过对三个腹部肿瘤分割CT数据集和一个肺部肿瘤分割CT数据集的广泛实验，PAKS-Net表现出了优越的性能，在KiTS19、LiTS17、胰腺和LOTUS数据集上达到0.893、0.769、0.598和0.738肿瘤DSC，超越了3D分割模型，同时用更少的参数保持计算效率。版权所有 © 2024。由 Elsevier Ltd 出版。

Abdominal tumor segmentation is a crucial yet challenging step during the screening and diagnosis of tumors. While 3D segmentation models provide powerful performance, they demand substantial computational resources. Additionally, in 3D data, tumors often represent a small portion, leading to imbalanced data and potentially overlooking crucial information. Conversely, 2D segmentation models have a lightweight structure, but disregard the inter-slice correlation, risking the loss of tumor in edge slices. To address these challenges, this paper proposes a novel Position-Aware and Key Slice Feature Sharing 2D tumor segmentation model (PAKS-Net). Leveraging the Swin-Transformer, we effectively model the global features within each slice, facilitating essential information extraction. Furthermore, we introduce a Position-Aware module to capture the spatial relationship between tumors and their corresponding organs, mitigating noise and interference from surrounding organ tissues. To enhance the edge slice segmentation accuracy, we employ key slices to assist in the segmentation of other slices to prioritize tumor regions. Through extensive experiments on three abdominal tumor segmentation CT datasets and a lung tumor segmentation CT dataset, PAKS-Net demonstrates superior performance, reaching 0.893, 0.769, 0.598 and 0.738 tumor DSC on the KiTS19, LiTS17, pancreas and LOTUS datasets, surpassing 3D segmentation models, while remaining computationally efficient with fewer parameters.Copyright © 2024. Published by Elsevier Ltd.