Nucleinet: an encoder-decoder convolutional neural network for nuclei image denoising
Scalable image data analysis is widely demanded in biomedical diagnosis by leveraging rapidly developed optical technology and advanced machine learning algorithm. However, bio-image obtained for single molecular or cell always have additive and multiplicative noise and requires denoising with b...
| Glavni avtor: | |
|---|---|
| Drugi avtorji: | |
| Format: | Thesis |
| Jezik: | English |
| Izdano: |
2017
|
| Teme: | |
| Online dostop: | http://hdl.handle.net/10356/72577 |
| _version_ | 1826124618568564736 |
|---|---|
| author | Hu, Yifei |
| author2 | Yu Hao |
| author_facet | Yu Hao Hu, Yifei |
| author_sort | Hu, Yifei |
| collection | NTU |
| description | Scalable image data analysis is widely demanded in biomedical
diagnosis by leveraging rapidly developed optical technology
and advanced machine learning algorithm. However, bio-image
obtained for single molecular or cell always have additive and
multiplicative noise and requires denoising with better resolution
in diagnosis. This dissertation proposed a high-throughput bioimage
denoising method for different kinds of threedimensional
microscopy cell images. Using a convolutional encoderdecoder
network, one can provide a scalable bio-image platform,
called NucleiNet, to automatically segment, classify and track cell
nuclei. Using a benchmark of 2480 nuclei images, the experiment
results show that the network achieves a 0.98 F-score and 0.99
pixel-wise accuracy, which means that over 95% of nuclei were
successfully detected with no merging nuclei found.
Key words: Image denoising, Convolutional neural network, Machine
learning, Bio-image processing |
| first_indexed | 2024-10-01T06:23:19Z |
| format | Thesis |
| id | ntu-10356/72577 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:23:19Z |
| publishDate | 2017 |
| record_format | dspace |
| spelling | ntu-10356/725772023-07-04T15:05:33Z Nucleinet: an encoder-decoder convolutional neural network for nuclei image denoising Hu, Yifei Yu Hao School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Scalable image data analysis is widely demanded in biomedical diagnosis by leveraging rapidly developed optical technology and advanced machine learning algorithm. However, bio-image obtained for single molecular or cell always have additive and multiplicative noise and requires denoising with better resolution in diagnosis. This dissertation proposed a high-throughput bioimage denoising method for different kinds of threedimensional microscopy cell images. Using a convolutional encoderdecoder network, one can provide a scalable bio-image platform, called NucleiNet, to automatically segment, classify and track cell nuclei. Using a benchmark of 2480 nuclei images, the experiment results show that the network achieves a 0.98 F-score and 0.99 pixel-wise accuracy, which means that over 95% of nuclei were successfully detected with no merging nuclei found. Key words: Image denoising, Convolutional neural network, Machine learning, Bio-image processing Master of Science (Electronics) 2017-08-29T04:12:30Z 2017-08-29T04:12:30Z 2017 Thesis http://hdl.handle.net/10356/72577 en 62 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Hu, Yifei Nucleinet: an encoder-decoder convolutional neural network for nuclei image denoising |
| title | Nucleinet: an encoder-decoder convolutional neural network for nuclei image denoising |
| title_full | Nucleinet: an encoder-decoder convolutional neural network for nuclei image denoising |
| title_fullStr | Nucleinet: an encoder-decoder convolutional neural network for nuclei image denoising |
| title_full_unstemmed | Nucleinet: an encoder-decoder convolutional neural network for nuclei image denoising |
| title_short | Nucleinet: an encoder-decoder convolutional neural network for nuclei image denoising |
| title_sort | nucleinet an encoder decoder convolutional neural network for nuclei image denoising |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | http://hdl.handle.net/10356/72577 |
| work_keys_str_mv | AT huyifei nucleinetanencoderdecoderconvolutionalneuralnetworkfornucleiimagedenoising |