Automated segmentation of insect anatomy from micro-CT images using deep learning

Three-dimensional (3D) imaging, such as micro-computed tomography (micro-CT), is increasingly being used by organismal biologists for precise and comprehensive anatomical characterization. However, the segmentation of anatomical structures remains a bottleneck in research, often requiring tedious manual work. Here, we propose a pipeline for the fully-automated segmentation of anatomical structures in micro-CT images utilizing state-of-the-art deep learning methods, selecting the ant brain as a test case. We implemented the U-Net architecture for 2D image segmentation for our convolutional neural network (CNN), combined with pixel-island detection. For training and validation of the network, we assembled a dataset of semi-manually segmented brain images of 76 ant species. The trained network predicted the brain area in ant images fast and accurately; its performance tested on validation sets showed good agreement between the prediction and the target, scoring 80% Intersection over Union (IoU) and 90% Dice Coefficient (F1) accuracy. While manual segmentation usually takes many hours for each brain, the trained network takes only a few minutes. Furthermore, our network is generalizable for segmenting the whole neural system in full-body scans, and works in tests on distantly related and morphologically divergent insects (e.g., fruit flies). The latter suggests that methods like the one presented here generally apply across diverse taxa. Our method makes the construction of segmented maps and the morphological quantification of different species more efficient and scalable to large datasets, a step toward a big data approach to organismal anatomy.

三维（3D）成像技术，如显微计算机断层扫描（micro-computed tomography, micro-CT），正日益被个体生物学家用于精准且全面的解剖学特征表征。然而，解剖结构的图像分割仍是研究中的瓶颈，往往需要耗费大量繁琐的手动工作。本文提出一种基于当前最先进深度学习方法的显微CT图像解剖结构全自动分割处理流程，并以蚂蚁大脑作为测试案例。
我们为卷积神经网络（convolutional neural network, CNN）采用了用于二维图像分割的U-Net架构，并结合了像素岛检测（pixel-island detection）技术。为训练与验证该网络，我们构建了包含76个蚂蚁物种的半手动分割大脑图像数据集。
经训练的网络能够快速且准确地预测蚂蚁图像中的大脑区域；在验证集上的测试结果显示，其预测结果与标注目标契合度良好，交并比（Intersection over Union, IoU）得分达80%，戴斯系数（Dice Coefficient, F1）得分达90%。相较于单份大脑样本通常需要数小时的手动分割时长，经训练的网络仅需数分钟即可完成。
此外，该网络具备泛化能力，可用于全身扫描图像中的整个神经系统分割，且在亲缘关系较远、形态学差异显著的昆虫（例如果蝇）上的测试中表现良好。这一结果表明，本文提出的这类方法可广泛适用于不同类群的生物。
我们的方法使分割图谱构建以及不同物种的形态学量化工作变得更为高效，并可扩展至大规模数据集，为个体解剖学的大数据研究方法迈出了重要一步。