Auckland Bioengineering Institute, The University of Auckland, Auckland, 1142, New Zealand.
Department of Cardiology, Second Hospital of Tianjin Medical University, and Tianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular Disease, Tianjin Institute of Cardiology, Tianjin, 300201, PR China.
Comput Biol Med. 2018 Jul 1;98:147-158. doi: 10.1016/j.compbiomed.2018.05.015. Epub 2018 May 16.
Segmentation of histological images is one of the most crucial tasks for many biomedical analyses involving quantification of certain tissue types, such as fibrosis via Masson's trichrome staining. However, challenges are posed by the high variability and complexity of structural features in such images, in addition to imaging artifacts. Further, the conventional approach of manual thresholding is labor-intensive, and highly sensitive to inter- and intra-image intensity variations. An accurate and robust automated segmentation method is of high interest. We propose and evaluate an elegant convolutional neural network (CNN) designed for segmentation of histological images, particularly those with Masson's trichrome stain. The network comprises 11 successive convolutional - rectified linear unit - batch normalization layers. It outperformed state-of-the-art CNNs on a dataset of cardiac histological images (labeling fibrosis, myocytes, and background) with a Dice similarity coefficient of 0.947. With 100 times fewer (only 300,000) trainable parameters than the state-of-the-art, our CNN is less susceptible to overfitting, and is efficient. Additionally, it retains image resolution from input to output, captures fine-grained details, and can be trained end-to-end smoothly. To the best of our knowledge, this is the first deep CNN tailored to the problem of concern, and may potentially be extended to solve similar segmentation tasks to facilitate investigations into pathology and clinical treatment.
组织学图像分割是许多涉及定量分析特定组织类型（如通过 Masson 三色染色进行纤维化分析）的生物医学分析中最关键的任务之一。然而，这些图像中的结构特征具有高度可变性和复杂性，加上成像伪影，这给图像分割带来了挑战。此外，传统的手动阈值分割方法既费力又容易受到图像内和图像间强度变化的影响。因此，需要一种准确且稳健的自动化分割方法。我们提出并评估了一种专门用于组织学图像分割的优雅卷积神经网络（CNN），特别是那些具有 Masson 三色染色的图像。该网络由 11 个连续的卷积-修正线性单元-批量归一化层组成。在一个包含心脏组织学图像（标记纤维化、心肌和背景）的数据集上，该网络的 Dice 相似系数为 0.947，优于最先进的 CNN。与最先进的 CNN 相比，我们的 CNN 具有 100 倍更少的可训练参数（仅 30 万），因此不易发生过拟合，且效率更高。此外，它保留了从输入到输出的图像分辨率，捕捉到了细微的细节，并且可以顺利地进行端到端训练。据我们所知，这是第一个专门针对相关问题的深度 CNN，并且可能会扩展到解决类似的分割任务，以促进对病理学和临床治疗的研究。
