Department of Optics and Quantum Electronics, University of Szeged, Dóm tér 9, Szeged, 6720, Hungary.
Institute of Genetics, Biological Research Centre, Temesvári körút 62, Szeged, 6726, Hungary.
Sci Rep. 2023 Jan 28;13(1):1582. doi: 10.1038/s41598-023-28539-7.
Object detection is an image analysis task with a wide range of applications, which is difficult to accomplish with traditional programming. Recent breakthroughs in machine learning have made significant progress in this area. However, these algorithms are generally compatible with traditional pixelated images and cannot be directly applied for pointillist datasets generated by single molecule localization microscopy (SMLM) methods. Here, we have improved the averaging method developed for the analysis of SMLM images of sarcomere structures based on a machine learning object detection algorithm. The ordered structure of sarcomeres allows us to determine the location of the proteins more accurately by superimposing SMLM images of identically assembled proteins. However, the area segmentation process required for averaging can be extremely time-consuming and tedious. In this work, we have automated this process. The developed algorithm not only finds the regions of interest, but also classifies the localizations and identifies the true positive ones. For training, we used simulations to generate large amounts of labelled data. After tuning the neural network's internal parameters, it could find the localizations associated with the structures we were looking for with high accuracy. We validated our results by comparing them with previous manual evaluations. It has also been proven that the simulations can generate data of sufficient quality for training. Our method is suitable for the identification of other types of structures in SMLM data.
目标检测是一项具有广泛应用的图像分析任务，传统编程难以完成。机器学习的最新突破在这一领域取得了重大进展。然而，这些算法通常与传统的像素化图像兼容，无法直接应用于单分子定位显微镜 (SMLM) 方法生成的点状数据集。在这里，我们改进了基于机器学习目标检测算法开发的用于分析肌节结构 SMLM 图像的平均方法。肌节的有序结构允许我们通过叠加相同组装的蛋白质的 SMLM 图像，更准确地确定蛋白质的位置。然而，平均所需的区域分割过程可能非常耗时且乏味。在这项工作中，我们实现了自动化。开发的算法不仅可以找到感兴趣的区域，还可以对定位进行分类并识别真正的阳性定位。我们使用模拟生成大量标记数据来训练。在调整神经网络的内部参数后，它可以高精度地找到与我们正在寻找的结构相关的定位。我们通过与之前的手动评估进行比较来验证我们的结果。事实证明，模拟可以生成足够高质量的数据用于训练。我们的方法适用于 SMLM 数据中其他类型结构的识别。
