Accuracy improvement of quantification information using super-resolution with convolutional neural network for microscopy images. (April 2020)

• Record Type: Journal Article
• Authors: Kang, Mi-Sun; Cha, Eunju; Kang, Eunhee; Ye, Jong Chul; Her, Nam-Gu; Oh, Jeong-Woo; Nam, Do-Hyun; Kim, Myoung-Hee; Yang, Sejung
• Is Part Of: Biomedical signal processing and control. Volume 58(2020)
• Publication Date: 2020-04
• Subjects: Image quantification -- Convolutional neural network -- Super-resolution -- Fluorescence microscope images; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2020.101846
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Generation of 40× high-quality images from 10× microscopic images using a deep-learning-based super resolution method. Comparison of image enhancement performances through extracted morphological features. Accuracy improvement of feature extraction using high resolution images generated based on a deep learning method. Abstract: Background and Objective: Microscope images are used for cell biology and clinical analysis. In general, microscopic images of 10× magnification are frequently used for cell imaging because of environmental limitations such as reagent drying, photo-bleaching, and photo-toxicity. However, there is a limit to the image quality of a 10× image to obtain more accurate information. Therefore, it is necessary to improve the image quality. Methods: In this paper, we propose a novel method to improve quantification accuracy using a super-resolution with a convolutional neural network (CNN) with image-based cell phenotypic profiling to predict the responses of glioblastoma cells to a drug using automatic image processing. For this approach, we first generate 40× high-quality images from originally obtained 10× images using a CNN-based method. Next, we manually obtain segmented images from three experts as ground-truth images to evaluate the quantitative improvement of segmentation. Intensity-based automatic segmentation results for cell nuclei morphological features for the 10× original images and CNN-based 40× images are compared with the ground-truth images. Results: The segmentation accuracy of the CNN-based 40× images is more similar to that of the manual segmenting results than that of the 10× images, as the Sørensen–Dice similarity coefficient. In addition, the CNN-based 40× image results are more similar to those of the manual results than those of the 10× images. Conclusions: We confirmed that the proposed method is more effective than the conventional method. It is expected that this approach will be helpful in evaluating the drug responses of patients by improving the accuracy of image-based cell phenotypic profiling.