Automatic detection, localization and segmentation of nano-particles with deep learning in microscopy images. (May 2019)

• Record Type: Journal Article
• Authors: Oktay, Ayse Betul; Gurses, Anıl
• Is Part Of: Micron. Volume 120(2019)
• Page Start: 113
• Page End: 119
• Publication Date: 2019-05
• Subjects: Nano-particle -- Deep learning -- Object detection -- MO-CNN -- Hough transform; Microscopy -- Periodicals; Electron Probe Microanalysis -- Periodicals; Microscopy -- Periodicals; Microscopie -- Périodiques; Microscopy; Periodicals; 502.82
• DOI: 10.1016/j.micron.2019.02.009
• Languages: English
• ISSNs: 0968-4328

Abstract

Highlights: A new deep learning based method is proposed for detection and boundary detection of round shaped nano-particles in microscopy images. The method provide the locations, sizes and numbers of particles in each image and provides quantitative information for further analysis. The method is tested and evaluated on a dataset containing 17 images at different scales. Abstract: With the growing amount of high resolution microscopy images automatic nano-particle detection, shape analysis and size determination have gained importance for providing quantitative support that gives important information for the evaluation of the material. In this paper, we present a new method for detection of nano-particles and determination of their shapes and sizes simultaneously with deep learning. The proposed method employs multiple output convolutional neural networks (MO-CNN) and has two outputs: first is the detection output that gives the locations of the particles and the other one is the segmentation output for providing the boundaries of the nano-particles. The final sizes of particles are determined with the modified Hough algorithm that runs on the segmentation output. The proposed method is tested and evaluated on a dataset containing 17 TEM images of Fe 3 O 4 and silica coated nano-particles. Also, we compared these results with U-net algorithm which is a popular deep learning method. The experiments showed that the proposed method has 98.23% accuracy for detection and 96.59% accuracy for segmentation of nano-particles.