Research on Urine Sediment Images Recognition Based on Deep Learning
Detection of urine sediment microscopic images of human urine samples plays an important part in vitro examination. Doctors usually use automatic urine sediment analyzer to assist manual examine. At present, automatic urine sediment analyzers mostly use traditional method of artificial feature extra...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8902039/ |
| _version_ | 1819174324286783488 |
|---|---|
| author | Qingbo Ji Xun Li Zhiyu Qu Chong Dai |
| author_facet | Qingbo Ji Xun Li Zhiyu Qu Chong Dai |
| author_sort | Qingbo Ji |
| collection | DOAJ |
| description | Detection of urine sediment microscopic images of human urine samples plays an important part in vitro examination. Doctors usually use automatic urine sediment analyzer to assist manual examine. At present, automatic urine sediment analyzers mostly use traditional method of artificial feature extraction to recognize urine sediment images. However, traditional image processing methods based on the selection and combination of feature operators and classifiers require a lot of work and subjective experience for engineers in the implementation process. It's also difficult to deal with urine sediment images recognition tasks with large scale categories, and particles in some different categories are often confused in recognition using traditional image processing methods, such as red blood cells (RBCs) and white blood cells (WBCs). In this paper, a combination convolution neural network (CNN) recognition method with area feature algorithm is proposed. The disadvantage that CNN can weaken the area feature of input image is solved by area feature algorithm (AFA) proposed in this paper. The network models which use 300,000 urine sediment images for training can quickly and accurately recognize 10 categories of urine sediment images, and several confusing categories' recognition indexes are remarkably improved. The test accuracy in the test set reached 97%. |
| first_indexed | 2024-12-22T20:37:10Z |
| format | Article |
| id | doaj.art-4bf2e307ce5e4195ab0b85d9e209c351 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T20:37:10Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4bf2e307ce5e4195ab0b85d9e209c3512022-12-21T18:13:26ZengIEEEIEEE Access2169-35362019-01-01716671116672010.1109/ACCESS.2019.29537758902039Research on Urine Sediment Images Recognition Based on Deep LearningQingbo Ji0https://orcid.org/0000-0002-3973-3434Xun Li1https://orcid.org/0000-0001-6004-2913Zhiyu Qu2https://orcid.org/0000-0002-4823-0396Chong Dai3https://orcid.org/0000-0003-3423-8351College of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaCollege of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaCollege of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaCollege of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaDetection of urine sediment microscopic images of human urine samples plays an important part in vitro examination. Doctors usually use automatic urine sediment analyzer to assist manual examine. At present, automatic urine sediment analyzers mostly use traditional method of artificial feature extraction to recognize urine sediment images. However, traditional image processing methods based on the selection and combination of feature operators and classifiers require a lot of work and subjective experience for engineers in the implementation process. It's also difficult to deal with urine sediment images recognition tasks with large scale categories, and particles in some different categories are often confused in recognition using traditional image processing methods, such as red blood cells (RBCs) and white blood cells (WBCs). In this paper, a combination convolution neural network (CNN) recognition method with area feature algorithm is proposed. The disadvantage that CNN can weaken the area feature of input image is solved by area feature algorithm (AFA) proposed in this paper. The network models which use 300,000 urine sediment images for training can quickly and accurately recognize 10 categories of urine sediment images, and several confusing categories' recognition indexes are remarkably improved. The test accuracy in the test set reached 97%.https://ieeexplore.ieee.org/document/8902039/Automatic diagnosisdeep learningimage processingurine sediment |
| spellingShingle | Qingbo Ji Xun Li Zhiyu Qu Chong Dai Research on Urine Sediment Images Recognition Based on Deep Learning IEEE Access Automatic diagnosis deep learning image processing urine sediment |
| title | Research on Urine Sediment Images Recognition Based on Deep Learning |
| title_full | Research on Urine Sediment Images Recognition Based on Deep Learning |
| title_fullStr | Research on Urine Sediment Images Recognition Based on Deep Learning |
| title_full_unstemmed | Research on Urine Sediment Images Recognition Based on Deep Learning |
| title_short | Research on Urine Sediment Images Recognition Based on Deep Learning |
| title_sort | research on urine sediment images recognition based on deep learning |
| topic | Automatic diagnosis deep learning image processing urine sediment |
| url | https://ieeexplore.ieee.org/document/8902039/ |
| work_keys_str_mv | AT qingboji researchonurinesedimentimagesrecognitionbasedondeeplearning AT xunli researchonurinesedimentimagesrecognitionbasedondeeplearning AT zhiyuqu researchonurinesedimentimagesrecognitionbasedondeeplearning AT chongdai researchonurinesedimentimagesrecognitionbasedondeeplearning |