Abstract：
Fluorine 18(18F) fluorodeoxyglucose positron emission tomography and Computed Tomography (PET/CT) is the preferred imaging method of choice for the diagnosis and treatment of many cancers. However, factors such as low-contrast organ and tissue images, and the original scale of tumors pose huge obstacles to the accurate segmentation of tumors. In this work, we propose a novel model ASE-Net which is used for multimodality tumor segmentation. Firstly, we propose a pseudo-enhanced CT image generation method based on metabolic intensity to generate pseudo-enhanced CT images as additional input, which reduces the learning of the network in the spatial position of PET/CT and increases the discriminability of the corresponding structural positions of the high and low metabolic region. Second, unlike previous networks that directly segment tumors of all scales, we propose an Adaptive-Scale Attention Supervision Module at the skip connections, after combining the results of all paths, tumors of different scales will be given different receptive fields. Finally, Dual Path Block is used as the backbone of our network to leverage the ability of residual learning for feature reuse and dense connection for exploring new features. Our experimental results on two clinical PET/CT datasets demonstrate the effectiveness of our proposed network and achieve 78.56% and 72.57% in Dice Similarity Coefficient, respectively, which has better performance compared to state-of-the-art network models, whether for large or small tumors. The proposed model will help pathologists formulate more accurate diagnoses by providing reference opinions during diagnosis, consequently improving patient survival rate.
摘要：
氟18（18F）氟脱氧葡萄糖正电子发射断层扫描和计算机断层扫描（PET/CT）是诊断和治疗许多癌症的首选成像方法。然而,低对比度器官和组织图像等因素，肿瘤的原始尺度对肿瘤的准确分割构成了巨大的障碍。在这项工作中,我们提出了一种用于多模态肿瘤分割的新模型ASE-Net。首先,提出了一种基于代谢强度的伪增强CT图像生成方法,以生成伪增强CT图像作为附加输入,这减少了网络在PET/CT空间位置的学习，并增加了高代谢区域和低代谢区域的相应结构位置的可判别性。第二,与以前直接分割所有规模肿瘤的网络不同，我们在跳过连接处提出了一个自适应尺度的注意力监督模块，在组合所有路径的结果后，不同规模的肿瘤将被赋予不同的感受野。最后,DualPathBlock被用作我们网络的骨干，以利用残差学习的功能重用和密集连接来探索新功能。我们在两个临床PET/CT数据集上的实验结果证明了我们提出的网络的有效性，并在骰子相似性系数中达到了78.56％和72.57％，分别,与最先进的网络模型相比具有更好的性能，无论是大肿瘤还是小肿瘤。所提出的模型将通过在诊断过程中提供参考意见来帮助病理学家制定更准确的诊断，从而提高患者生存率。
