Choudhury Pranjal, Boruah Bosanta R
Department of Physics, Indian Institute of Technology Guwahati, Guwahati, Assam, India.
J Microsc. 2025 Feb;297(2):153-164. doi: 10.1111/jmi.13362. Epub 2024 Oct 4.
Single-molecule localization microscopy (SMLM), which has revolutionized nanoscale imaging, faces challenges in densely labelled samples due to fluorophore clustering, leading to compromised localization accuracy. In this paper, we propose a novel convolutional neural network (CNN)-assisted approach to address the issue of locating the clustered fluorophores. Our CNN is trained on a diverse data set of simulated SMLM images where it learns to predict point spread function (PSF) locations by generating Gaussian blobs as output. Through rigorous evaluation, we demonstrate significant improvements in PSF localization accuracy, especially in densely labelled samples where traditional methods struggle. In addition, we employ blob detection as a post-processing technique to refine the predicted PSF locations and enhance localization precision. Our study underscores the efficacy of CNN in addressing clustering challenges in SMLM, thereby advancing spatial resolution and enabling deeper insights into complex biological structures.
单分子定位显微镜（SMLM）彻底改变了纳米级成像，但由于荧光团聚集，在密集标记的样本中面临挑战，导致定位精度受损。在本文中，我们提出了一种新颖的卷积神经网络（CNN）辅助方法来解决聚集荧光团的定位问题。我们的CNN在多样化的模拟SMLM图像数据集上进行训练，在该数据集中它通过生成高斯斑点作为输出，学习预测点扩散函数（PSF）位置。通过严格评估，我们证明了PSF定位精度有显著提高，特别是在传统方法难以处理的密集标记样本中。此外，我们采用斑点检测作为后处理技术来细化预测的PSF位置并提高定位精度。我们的研究强调了CNN在解决SMLM中的聚集挑战方面的有效性，从而提高了空间分辨率，并能够更深入地洞察复杂的生物结构。
