Deep Fish: Deep Learning-Based Classification of Zebrafish Deformation for High-Throughput Screening
Deep Fish: Deep Learning-Based Classification of Zebrafish Deformation for High-Throughput Screening
复制标题
DOI：
10.1177/1087057116667894
复制
发表时间：
2017-01-01
期刊：
影响因子：
3.1
通讯作者：
Wahlby, Carolina
中科院分区：
文献类型：
--
作者：
Ishaq, Omer;Sadanandan, Sajith Kecheril;Wahlby, Carolina
斑马鱼（Danio rerio）是生物医学研究中重要的脊椎动物模式生物，由于其早期发育过程中透明的身体，特别适合于形态学筛选。深度学习已经成为数据分析的主导范式，并在计算机视觉和图像分析中找到了许多应用。在这里，我们展示了深度学习方法在多鱼微孔板中对全身斑马鱼变形进行准确高通量分类的潜力。深度学习使用原始图像数据作为输入，而不需要专业知识来进行特征设计或分割参数的优化。我们在最少84张图像上训练了深度学习分类器（在数据增强之前），并在一个看不见的测试数据集上实现了92.8%的分类准确率，这与基于用户指定的分割和变形指标的先前最先进技术（95%）相当。通过数字化从图像中去除整条鱼或部分鱼的消融研究表明，分类器从图像前景中学习到了有区别的特征，并且我们观察到头部区域的变形，而不是视觉上明显的弯曲尾巴，对于良好的分类性能更重要。
Zebrafish (Danio rerio) is an important vertebrate model organism in biomedical research, especially suitable for morphological screening due to its transparent body during early development. Deep learning has emerged as a dominant paradigm for data analysis and found a number of applications in computer vision and image analysis. Here we demonstrate the potential of a deep learning approach for accurate high-throughput classification of whole-body zebrafish deformations in multifish microwell plates. Deep learning uses the raw image data as an input, without the need of expert knowledge for feature design or optimization of the segmentation parameters. We trained the deep learning classifier on as few as 84 images (before data augmentation) and achieved a classification accuracy of 92.8% on an unseen test data set that is comparable to the previous state of the art (95%) based on user-specified segmentation and deformation metrics. Ablation studies by digitally removing whole fish or parts of the fish from the images revealed that the classifier learned discriminative features from the image foreground, and we observed that the deformations of the head region, rather than the visually apparent bent tail, were more important for good classification performance.