tUbe net: a generalisable deep learning tool for 3D vessel segmentation
tUbe net: a generalisable deep learning tool for 3D vessel segmentation
复制标题
DOI：
10.1101/2023.07.24.550334
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
N. Holroyd;Zhongwang Li;C. Walsh;Emmeline Brown;R. Shipley;S. Walker-Samuel
中科院分区：
文献类型：
--
作者：
N. Holroyd;Zhongwang Li;C. Walsh;Emmeline Brown;R. Shipley;S. Walker-Samuel
深度学习已成为生物图像分析的宝贵工具，但是，虽然 cellpose 等开源细胞注释软件得到广泛使用，但用于三维 (3D) 血管注释的等效工具并不存在。由于血管系统受到多种疾病的直接影响，因此血管成像的定量分析具有重大的医学意义。然而，用于此任务的现有深度学习方法专门针对特定的组织类型或成像方式。我们提出了一种用于脉管系统分割的新深度学习模型，该模型可推广到组织、模式、尺度和病理学。为了创建通用模型，使用光学成像、计算断层扫描和光声成像等多种模式的数据来训练 3D 卷积神经网络。通过这种不同的训练集，模型被迫学习船舶跨模式和规模的共同特征。此后，使用最少量的手动标记的地面实况数据对通用模型进行了微调，以适应不同的应用。研究发现，通用模型可以专门用于分割新数据集，并且精度很高，只需使用该数据集体积的 0.3% 即可进行微调。因此，该模型使用户能够准确分割 3D 血管网络，而无需标记大量训练数据。
Deep learning has become an invaluable tool for bioimage analysis but, while open-source cell annotation software such as cellpose are widely used, an equivalent tool for three-dimensional (3D) vascular annotation does not exist. With the vascular system being directly impacted by a broad range of diseases, there is significant medical interest in quantitative analysis for vascular imaging. However, existing deep learning approaches for this task are specialised to particular tissue types or imaging modalities. We present a new deep learning model for segmentation of vasculature that is generalisable across tissues, modalities, scales and pathologies. To create a generalisable model, a 3D convolutional neural network was trained using data from multiple modalities including optical imaging, computational tomography and photoacoustic imaging. Through this varied training set, the model was forced to learn common features of vessels cross-modality and scale. Following this, the general model was fine-tuned to different applications with a minimal amount of manually labelled ground truth data. It was found that the general model could be specialised to segment new datasets, with a high degree of accuracy, using as little as 0.3% of the volume of that dataset for fine-tuning. As such, this model enables users to produce accurate segmentations of 3D vascular networks without the need to label large amounts of training data.