Image Synthesis and Modified BlendMask Instance Segmentation for Automated Nanoparticle Phenotyping
作者全名:"Tang, Xiaoqin; Lv, Lingpeng; Javanmardi, Shima; Wang, Yunfeng; Fan, Jingchuan; Verbeek, Fons J.; Xiao, Guoqiang"
作者地址:"[Tang, Xiaoqin; Lv, Lingpeng; Wang, Yunfeng; Xiao, Guoqiang] Southwest Univ, Sch Comp & Informat Sci, Chongqing 400715, Peoples R China; [Javanmardi, Shima; Verbeek, Fons J.] Leiden Univ, Leiden Inst Adv Comp Sci, Nl-2333 CA Leiden, Netherlands; [Fan, Jingchuan] Chongqing Med Univ, Inst Life Sci, Chongqing 400700, Peoples R China"
通信作者:"Tang, XQ (通讯作者),Southwest Univ, Sch Comp & Informat Sci, Chongqing 400715, Peoples R China."
来源:IEEE TRANSACTIONS ON MEDICAL IMAGING
ESI学科分类:CLINICAL MEDICINE
WOS号:WOS:001122030500028
JCR分区:Q1
影响因子:8.9
年份:2023
卷号:42
期号:12
开始页:3665
结束页:3677
文献类型:Article
关键词:Image segmentation; Nanoparticles; Image synthesis; Feature extraction; Pipelines; Task analysis; Scanning electron microscopy; Microscope image synthesis; instance segmentation; deep learning; nanoparticle phenotyping
摘要:"Automated nanoparticle phenotyping is a critical aspect of high-throughput drug research, which requires analyzing nanoparticle size, shape, and surface topography from microscopy images. To automate this process, we present an instance segmentation pipeline that partitions individual nanoparticles on microscopy images. Our pipeline makes two key contributions. Firstly, we synthesize diverse and approximately realistic nanoparticle images to improve robust learning. Secondly, we improve the BlendMask model to segment tiny, overlapping, or sparse particle images. Specifically, we propose a parameterized approach for generating novel pairs of single particles and their masks, encouraging greater diversity in the training data. To synthesize more realistic particle images, we explore three particle placement rules and an image selection criterion. The improved one-stage instance segmentation network extracts distinctive features of nanoparticles and their context at both local and global levels, which addresses the data challenges associated with tiny, overlapping, or sparse nanoparticles. Extensive experiments demonstrate the effectiveness of our pipeline for automating nanoparticle partitioning and phenotyping in drug research using microscopy images."
基金机构:Fundamental Research Funds for the Central Universities
基金资助正文:No Statement Available