AniLength: GUI-based automatic worm length measurement software using image processing and deep neural network

Abstract Accurately measuring the length of an animal’s body is essential to studying the effects of various chemicals, genes, and the environment on the animal’s growth. AniLength was developed to measure the body length of small worms present in images using hybrid image processing and deep neural network (DNN)-based image classification. The software not only includes a pretrained DNN model learned from approximately 16,000 images using ResNet-V2-101 for Caenorhabditis elegans analysis, but it can also perform new training using custom training images. AniLength is a user-friendly GUI-based software that runs on Microsoft Windows.

[1]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Derek Bradley,et al.  Adaptive Thresholding using the Integral Image , 2007, J. Graph. Tools.

[3]  R. Plasterk,et al.  A Caenorhabditis elegans Wild Type Defies the Temperature–Size Rule Owing to a Single Nucleotide Polymorphism in tra-3 , 2007, PLoS genetics.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Polina Golland,et al.  An image analysis toolbox for high-throughput C. elegans assays , 2012, Nature Methods.

[6]  Sangsub Jung,et al.  QuantWorm: A Comprehensive Software Package for Caenorhabditis elegans Phenotypic Assays , 2014, PloS one.

[7]  A. Leroi,et al.  Dietary regulation of hypodermal polyploidization in C. elegans , 2008, BMC Developmental Biology.

[8]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  D. Albertini,et al.  The environmental toxicant 2,3,7,8-tetrachlorodibenzo-p-dioxin disrupts morphogenesis of the rat pre-implantation embryo , 2008, BMC Developmental Biology.

[10]  Johannes E. Schindelin,et al.  Fiji: an open-source platform for biological-image analysis , 2012, Nature Methods.

[11]  Yiwen Zhu,et al.  Machine Learning at Microsoft with ML.NET , 2019, KDD.

[12]  Bernd Jähne,et al.  Digital Image Processing: Concepts, Algorithms, and Scientific Applications , 1991 .

[13]  Boanerges Aleman-Meza,et al.  Multi-endpoint, high-throughput study of nanomaterial toxicity in Caenorhabditis elegans. , 2015, Environmental science & technology.

[14]  David G H Andrews,et al.  A new method for measuring the size of nematodes using image processing , 2019, Biology methods & protocols.

[15]  Y. Ohshima,et al.  Control of body size in C. elegans dependent on food and insulin/IGF‐1 signal , 2011, Genes to cells : devoted to molecular & cellular mechanisms.

[16]  Kevin W Eliceiri,et al.  NIH Image to ImageJ: 25 years of image analysis , 2012, Nature Methods.

[17]  Brad T. Moore,et al.  WormSizer: High-throughput Analysis of Nematode Size and Shape , 2013, PloS one.