Literature DB >> 32550136

Dense-UNet: a novel multiphoton in vivo cellular image segmentation model based on a convolutional neural network.

Sijing Cai1,2, Yunxian Tian3,4, Harvey Lui3,4, Haishan Zeng3,4, Yi Wu1,5, Guannan Chen1,5.   

Abstract

BACKGROUND: Multiphoton microscopy (MPM) offers a feasible approach for the biopsy in clinical medicine, but it has not been used in clinical applications due to the lack of efficient image processing methods, especially the automatic segmentation technology. Segmentation technology is still one of the most challenging assignments of the MPM imaging technique.
METHODS: The MPM imaging segmentation model based on deep learning is one of the most effective methods to address this problem. In this paper, the practicability of using a convolutional neural network (CNN) model to segment the MPM image of skin cells in vivo was explored. A set of MPM in vivo skin cells images with a resolution of 128×128 was successfully segmented under the Python environment with TensorFlow. A novel deep-learning segmentation model named Dense-UNet was proposed. The Dense-UNet, which is based on U-net structure, employed the dense concatenation to deepen the depth of the network architecture and achieve feature reuse. This model included four expansion modules (each module consisted of four down-sampling layers) to extract features.
RESULTS: Sixty training images were taken from the dorsal forearm using a femtosecond Ti:Sa laser running at 735 nm. The resolution of the images is 128×128 pixels. Experimental results confirmed that the accuracy of Dense-UNet (92.54%) was higher than that of U-Net (88.59%), with a significantly lower loss value of 0.1681. The 90.60% Dice coefficient value of Dense-UNet outperformed U-Net by 11.07%. The F1-Score of Dense-UNet, U-Net, and Seg-Net was 93.35%, 90.02%, and 85.04%, respectively.
CONCLUSIONS: The deepened down-sampling path improved the ability of the model to capture cellular fined-detailed boundary features, while the symmetrical up-sampling path provided a more accurate location based on the test result. These results were the first time that the segmentation of MPM in vivo images had been adopted by introducing a deep CNN to bridge this gap in Dense-UNet technology. Dense-UNet has reached ultramodern performance for MPM images, especially for in vivo images with low resolution. This implementation supplies an automatic segmentation model based on deep learning for high-precision segmentation of MPM images in vivo. 2020 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Entities:  

Keywords:  Skin in vivo; U-Net; dense-UNet; image segmentation; multiphoton microscopy (MPM)

Year:  2020        PMID: 32550136      PMCID: PMC7276369          DOI: 10.21037/qims-19-1090

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  14 in total

1.  A Novel Approach to Segment Skin Lesions in Dermoscopic Images Based on a Deformable Model.

Authors:  Zhen Ma; João Manuel R S Tavares
Journal:  IEEE J Biomed Health Inform       Date:  2015-01-08       Impact factor: 5.772

2.  Image segmentation for integrated multiphoton microscopy and reflectance confocal microscopy imaging of human skin in vivo.

Authors:  Guannan Chen; Harvey Lui; Haishan Zeng
Journal:  Quant Imaging Med Surg       Date:  2015-02

3.  Multimodal imaging platform for optical virtual skin biopsy enabled by a fiber-based two-color ultrafast laser source.

Authors:  Hsiang-Yu Chung; Rüdiger Greinert; Franz X Kärtner; Guoqing Chang
Journal:  Biomed Opt Express       Date:  2019-01-10       Impact factor: 3.732

4.  Automated classification of hepatocellular carcinoma differentiation using multiphoton microscopy and deep learning.

Authors:  Hongxin Lin; Chao Wei; Guangxing Wang; Hu Chen; Lisheng Lin; Ming Ni; Jianxin Chen; Shuangmu Zhuo
Journal:  J Biophotonics       Date:  2019-04-01       Impact factor: 3.207

5.  Perfectly registered multiphoton and reflectance confocal video rate imaging of in vivo human skin.

Authors:  Hequn Wang; Anthony M D Lee; Zack Frehlick; Harvey Lui; David I McLean; Shuo Tang; Haishan Zeng
Journal:  J Biophotonics       Date:  2012-07-02       Impact factor: 3.207

6.  Automatic 3D segmentation of multiphoton images: a key step for the quantification of human skin.

Authors:  Etienne Decencière; Emmanuelle Tancrède-Bohin; Petr Dokládal; Serge Koudoro; Ana-Maria Pena; Thérèse Baldeweck
Journal:  Skin Res Technol       Date:  2013-02-26       Impact factor: 2.365

7.  Phasor analysis of multiphoton spectral images distinguishes autofluorescence components of in vivo human skin.

Authors:  Farzad Fereidouni; Arjen N Bader; Anne Colonna; Hans C Gerritsen
Journal:  J Biophotonics       Date:  2013-04-11       Impact factor: 3.207

8.  A novel multiphoton microscopy images segmentation method based on superpixel and watershed.

Authors:  Weilin Wu; Jinyong Lin; Shu Wang; Yan Li; Mingyu Liu; Gaoqiang Liu; Jianyong Cai; Guannan Chen; Rong Chen
Journal:  J Biophotonics       Date:  2016-04-19       Impact factor: 3.207

9.  Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance.

Authors:  Yading Yuan; Ming Chao; Yeh-Chi Lo
Journal:  IEEE Trans Med Imaging       Date:  2017-04-18       Impact factor: 10.048

10.  Label-free molecular profiling for identification of biomarkers in carcinogenesis using multimodal multiphoton imaging.

Authors:  Yuan Liu; Haohua Tu; Sixian You; Eric J Chaney; Marina Marjanovic; Stephen A Boppart
Journal:  Quant Imaging Med Surg       Date:  2019-05
View more
  17 in total

1.  Recognition and Segmentation of Individual Bone Fragments with a Deep Learning Approach in CT Scans of Complex Intertrochanteric Fractures: A Retrospective Study.

Authors:  Lv Yang; Shan Gao; Pengfei Li; Jiancheng Shi; Fang Zhou
Journal:  J Digit Imaging       Date:  2022-06-16       Impact factor: 4.056

2.  TransConver: transformer and convolution parallel network for developing automatic brain tumor segmentation in MRI images.

Authors:  Junjie Liang; Cihui Yang; Mengjie Zeng; Xixi Wang
Journal:  Quant Imaging Med Surg       Date:  2022-04

3.  Machine-assisted interpolation algorithm for semi-automated segmentation of highly deformable organs.

Authors:  Dishane C Luximon; Yasin Abdulkadir; Phillip E Chow; Eric D Morris; James M Lamb
Journal:  Med Phys       Date:  2021-11-27       Impact factor: 4.071

4.  Automatic coronary artery calcium scoring on routine chest computed tomography (CT): comparison of a deep learning algorithm and a dedicated calcium scoring CT.

Authors:  Cheng Xu; Heng Guo; Minfeng Xu; Miao Duan; Ming Wang; Peijun Liu; Xinyi Luo; Zhengyu Jin; Hui Liu; Yining Wang
Journal:  Quant Imaging Med Surg       Date:  2022-05

5.  Image restoration of motion artifacts in cardiac arteries and vessels based on a generative adversarial network.

Authors:  Fuquan Deng; Qian Wan; Yingting Zeng; Yanbin Shi; Huiying Wu; Yu Wu; Weifeng Xu; Greta S P Mok; Xiaochun Zhang; Zhanli Hu
Journal:  Quant Imaging Med Surg       Date:  2022-05

6.  The ImageJ ecosystem: Open-source software for image visualization, processing, and analysis.

Authors:  Alexandra B Schroeder; Ellen T A Dobson; Curtis T Rueden; Pavel Tomancak; Florian Jug; Kevin W Eliceiri
Journal:  Protein Sci       Date:  2020-11-20       Impact factor: 6.725

7.  Three-dimensional characterizations of two-photon excitation fluorescence images of elastic fibers affected by cutaneous scar duration.

Authors:  Yongping Lin; Hongxin Lin; Xiaoqin Zhu; Guannan Chen
Journal:  Quant Imaging Med Surg       Date:  2021-08

8.  Deep learning based fully automatic segmentation of the left ventricular endocardium and epicardium from cardiac cine MRI.

Authors:  Yan Wang; Yue Zhang; Zhaoying Wen; Bing Tian; Evan Kao; Xinke Liu; Wanling Xuan; Karen Ordovas; David Saloner; Jing Liu
Journal:  Quant Imaging Med Surg       Date:  2021-04

9.  LCPR-Net: low-count PET image reconstruction using the domain transform and cycle-consistent generative adversarial networks.

Authors:  Hengzhi Xue; Qiyang Zhang; Sijuan Zou; Weiguang Zhang; Chao Zhou; Changjun Tie; Qian Wan; Yueyang Teng; Yongchang Li; Dong Liang; Xin Liu; Yongfeng Yang; Hairong Zheng; Xiaohua Zhu; Zhanli Hu
Journal:  Quant Imaging Med Surg       Date:  2021-02

10.  FractalCovNet architecture for COVID-19 Chest X-ray image Classification and CT-scan image Segmentation.

Authors:  Hemalatha Munusamy; J M Karthikeyan; G Shriram; S Thanga Revathi; S Aravindkumar
Journal:  Biocybern Biomed Eng       Date:  2021-07-08       Impact factor: 4.314

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.