基于动态增强磁共振成像的乳腺肿瘤分割是计算放射学乳腺癌分析的重要一步。手动肿瘤标注是耗时且需要医学知识，有偏差、易犯错误和用户间差异性。现代训练表明，深度学习表示在图像分割中具有能力。在这里，我们描述了一种基于编码器-解码器架构的三维连接 UNets，用于从三维磁共振成像中分割肿瘤。由于受限的训练数据集大小，我们使用变分自编码器出口来更新输入图像本身，以识别共享解码器并对其层执行附加控制。基于连接 UNets 的初始分割，采用全连接的三维临时无序域来增强分割结果，通过发现二维相邻区域和三维体积统计值。此外，采用 3D 连接模块评估来保持大模块的连续性，并降低分割噪声。该方法已在两个广泛提供的数据集（INbreast 和数字乳腺病理学筛查数据库的筛查数据集）上进行评估。该方法还使用私人数据集进行评估。实验结果表明，该方法优于现有的乳腺肿瘤分割方法。版权所有 ©2022 The Association of University Radiologists。由 Elsevier Inc. 发布。保留所有权利。

Breast tumor segmentation based on Dynamic Contrast-Enhanced Magnetic Resonance Imaging is significant step for computable radiomics analysis of breast cancer. Manual tumor annotation is time-consuming process and involves medical acquaintance, biased, inclined to error, and inter-user discrepancy. A number of modern trainings have revealed the capability of deep learning representations in image segmentation.Here, we describe a 3D Connected-UNets for tumor segmentation from 3D Magnetic Resonance Imagings based on encoder-decoder architecture. Due to a restricted training dataset size, a variational auto-encoder outlet is supplementary to renovate the input image itself in order to identify the shared decoder and execute additional controls on its layers. Based on initial segmentation of Connected-UNets, fully connected 3D provisional unsystematic domain is used to enhance segmentation outcomes by discovering 2D neighbor areas and 3D volume statistics. Moreover, 3D connected modules evaluation is used to endure around large modules and decrease segmentation noise.The proposed method has been assessed on two widely offered datasets, explicitly INbreast and the curated breast imaging subset of digital database for screening mammography The proposed model has also been estimated using a private dataset.The experimental results show that the proposed model outperforms the state-of-the-art methods for breast tumor segmentation.Copyright © 2022 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.