Enhancing Nanoparticle Detection in Interferometric Scattering (iSCAT) Microscopy Using a Mask R-CNN

Abstract

Interferometric scattering microscopy (iSCAT) is a label-free optical microscopy technique that enables imaging of individual nano-objects such as nanoparticles, viruses, and proteins. Essential to this technique is the suppression of background scattering and identification of signals from nano-objects. In the presence of substrates with high roughness, scattering heterogeneities in the background, when coupled with tiny stage movements, cause features in the background to be manifested in background-suppressed iSCAT images. Traditional computer vision algorithms detect these background features as particles, limiting the accuracy of object detection in iSCAT experiments. Here, we present a pathway to improve particle detection in such situations using supervised machine learning via a mask region-based convolutional neural network (mask R-CNN). Using a model iSCAT experiment of 19.2 nm gold nanoparticles adsorbing to a rough layer-by-layer polyelectrolyte film, we develop a method to generate labeled datasets using experimental background images and simulated particle signals and train the mask R-CNN using limited computational resources via transfer learning. We then compare the performance of the mask R-CNN trained with and without inclusion of experimental backgrounds in the dataset against that of a traditional computer vision object detection algorithm, Haar-like feature detection, by analyzing data from the model experiment. Results demonstrate that including representative backgrounds in training datasets improved the mask R-CNN in differentiating between background and particle signals and elevated performance by markedly reducing false positives. The methodology for creating a labeled dataset with representative experimental backgrounds and simulated signals facilitates the application of machine learning in iSCAT experiments with strong background scattering and thus provides a useful workflow for future researchers to improve their image processing capabilities.

Label-Free Imaging of DNA Interactions with 2D Materials

“…The data may contain more information about naked DNA’s internal configurations and dynamics. We envision that better control over the background signal and new future analyses incorporating iSCAT PSF modeling or deep-learning , will give more insights into these aspects. Since we avoid modification to DNA’s biophysical properties arising from labeling DNA with dye, our method will help to guide the computational modeling of DNA–2D material interactions. , Our measurements were performed with a temporal resolution of ∼11 ms, but other iSCAT instruments demonstrated a temporal resolution of up 1 MHz .…”

The use of graphic design elements in commercial architectural design in the context of intelligence

“…Mask R-CNN is a classification-based instance segmentation neural network proposed by Dr. Kai-Ming He, which uses a convolutional neural network to extract features of the target and then adds different branches at the end of the convolutional neural network, which can accomplish the task of instance segmentation [18]. In order to deeply analyze the structure and function of the Mask R-CNN network, four aspects are studied, including network structure, loss function, gradient descent algorithm, and training part implementation, respectively.…”

Label-free imaging of DNA interactions with 2D materials

“…The data may contain more information about naked DNA’s internal configurations and dynamics. We envision that better control over the background signal and new future analyses incorporating iSCAT PSF modeling or deep-learning 41,68 will give more insights into these aspects. Since we avoid modification to DNA’s biophysical properties arising from labeling DNA with dye 48 our method will help to guide the computational modelling of DNA-2D material interactions 36,66 .…”