<i>Trichomonas vaginalis</i> Detection Using Two Convolutional Neural Networks with Encoder-Decoder Architecture
Diagnosis of <i>Trichomonas vaginalis</i> infection is one of the most important factors in the routine examination of leucorrhea. According to the motion characteristics of <i>Trichomonas vaginalis</i>, a viable detection method is the use of a microscopic camera to record v...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/6/2738 |
| _version_ | 1797540826229768192 |
|---|---|
| author | Xiangzhou Wang Xiaohui Du Lin Liu Guangming Ni Jing Zhang Juanxiu Liu Yong Liu |
| author_facet | Xiangzhou Wang Xiaohui Du Lin Liu Guangming Ni Jing Zhang Juanxiu Liu Yong Liu |
| author_sort | Xiangzhou Wang |
| collection | DOAJ |
| description | Diagnosis of <i>Trichomonas vaginalis</i> infection is one of the most important factors in the routine examination of leucorrhea. According to the motion characteristics of <i>Trichomonas vaginalis</i>, a viable detection method is the use of a microscopic camera to record videos of leucorrhea samples and video object detection algorithms for detection. Most <i>Trichomonas vaginalis</i> is defocused and displays as shadow regions on microscopic images, and it is hard to recognize the movement of shadow regions using traditional video object detection algorithms. In order to solve this problem, we propose two convolutional neural networks based on an encoder-decoder architecture. The first network has the ability to learn the difference between frames and utilizes the image and optical flow information of three consecutive frames as the input to perform rough detection. The second network corrects the coarse contours and uses the image information and the rough detection result of the current frame as the input to perform fine detection. With these two networks applied, the metric value of the mean intersection over union of <i>Trichomonas vaginalis</i> achieves 72.09% on test videos. The proposed networks can effectively detect defocused <i>Trichomonas vaginalis</i> and suppress false alarms caused by the motion of formed elements or impurities. |
| first_indexed | 2024-03-10T13:06:33Z |
| format | Article |
| id | doaj.art-326623baf44c45c386debfaf6d3d60b3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T13:06:33Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-326623baf44c45c386debfaf6d3d60b32023-11-21T11:04:07ZengMDPI AGApplied Sciences2076-34172021-03-01116273810.3390/app11062738<i>Trichomonas vaginalis</i> Detection Using Two Convolutional Neural Networks with Encoder-Decoder ArchitectureXiangzhou Wang0Xiaohui Du1Lin Liu2Guangming Ni3Jing Zhang4Juanxiu Liu5Yong Liu6MOEMIL Laboratory, School of Optoelectronic Information, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, ChinaMOEMIL Laboratory, School of Optoelectronic Information, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, ChinaMOEMIL Laboratory, School of Optoelectronic Information, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, ChinaMOEMIL Laboratory, School of Optoelectronic Information, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, ChinaMOEMIL Laboratory, School of Optoelectronic Information, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, ChinaMOEMIL Laboratory, School of Optoelectronic Information, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, ChinaMOEMIL Laboratory, School of Optoelectronic Information, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, ChinaDiagnosis of <i>Trichomonas vaginalis</i> infection is one of the most important factors in the routine examination of leucorrhea. According to the motion characteristics of <i>Trichomonas vaginalis</i>, a viable detection method is the use of a microscopic camera to record videos of leucorrhea samples and video object detection algorithms for detection. Most <i>Trichomonas vaginalis</i> is defocused and displays as shadow regions on microscopic images, and it is hard to recognize the movement of shadow regions using traditional video object detection algorithms. In order to solve this problem, we propose two convolutional neural networks based on an encoder-decoder architecture. The first network has the ability to learn the difference between frames and utilizes the image and optical flow information of three consecutive frames as the input to perform rough detection. The second network corrects the coarse contours and uses the image information and the rough detection result of the current frame as the input to perform fine detection. With these two networks applied, the metric value of the mean intersection over union of <i>Trichomonas vaginalis</i> achieves 72.09% on test videos. The proposed networks can effectively detect defocused <i>Trichomonas vaginalis</i> and suppress false alarms caused by the motion of formed elements or impurities.https://www.mdpi.com/2076-3417/11/6/2738<i>Trichomonas vaginalis</i> detectionrough and fine detectionvideo object detectionconvolutional neural networkencoder-decoder architecture |
| spellingShingle | Xiangzhou Wang Xiaohui Du Lin Liu Guangming Ni Jing Zhang Juanxiu Liu Yong Liu <i>Trichomonas vaginalis</i> Detection Using Two Convolutional Neural Networks with Encoder-Decoder Architecture Applied Sciences <i>Trichomonas vaginalis</i> detection rough and fine detection video object detection convolutional neural network encoder-decoder architecture |
| title | <i>Trichomonas vaginalis</i> Detection Using Two Convolutional Neural Networks with Encoder-Decoder Architecture |
| title_full | <i>Trichomonas vaginalis</i> Detection Using Two Convolutional Neural Networks with Encoder-Decoder Architecture |
| title_fullStr | <i>Trichomonas vaginalis</i> Detection Using Two Convolutional Neural Networks with Encoder-Decoder Architecture |
| title_full_unstemmed | <i>Trichomonas vaginalis</i> Detection Using Two Convolutional Neural Networks with Encoder-Decoder Architecture |
| title_short | <i>Trichomonas vaginalis</i> Detection Using Two Convolutional Neural Networks with Encoder-Decoder Architecture |
| title_sort | i trichomonas vaginalis i detection using two convolutional neural networks with encoder decoder architecture |
| topic | <i>Trichomonas vaginalis</i> detection rough and fine detection video object detection convolutional neural network encoder-decoder architecture |
| url | https://www.mdpi.com/2076-3417/11/6/2738 |
| work_keys_str_mv | AT xiangzhouwang itrichomonasvaginalisidetectionusingtwoconvolutionalneuralnetworkswithencoderdecoderarchitecture AT xiaohuidu itrichomonasvaginalisidetectionusingtwoconvolutionalneuralnetworkswithencoderdecoderarchitecture AT linliu itrichomonasvaginalisidetectionusingtwoconvolutionalneuralnetworkswithencoderdecoderarchitecture AT guangmingni itrichomonasvaginalisidetectionusingtwoconvolutionalneuralnetworkswithencoderdecoderarchitecture AT jingzhang itrichomonasvaginalisidetectionusingtwoconvolutionalneuralnetworkswithencoderdecoderarchitecture AT juanxiuliu itrichomonasvaginalisidetectionusingtwoconvolutionalneuralnetworkswithencoderdecoderarchitecture AT yongliu itrichomonasvaginalisidetectionusingtwoconvolutionalneuralnetworkswithencoderdecoderarchitecture |