An Application of Pixel Interval Down-Sampling (PID) for Dense Tiny Microorganism Counting on Environmental Microorganism Images
This paper proposes a novel pixel interval down-sampling network (PID-Net) for dense tiny object (yeast cells) counting tasks with higher accuracy. The PID-Net is an end-to-end convolutional neural network (CNN) model with an encoder–decoder architecture. The pixel interval down-sampling operations...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/14/7314 |
| _version_ | 1797407535599190016 |
|---|---|
| author | Jiawei Zhang Xin Zhao Tao Jiang Md Mamunur Rahaman Yudong Yao Yu-Hao Lin Jinghua Zhang Ao Pan Marcin Grzegorzek Chen Li |
| author_facet | Jiawei Zhang Xin Zhao Tao Jiang Md Mamunur Rahaman Yudong Yao Yu-Hao Lin Jinghua Zhang Ao Pan Marcin Grzegorzek Chen Li |
| author_sort | Jiawei Zhang |
| collection | DOAJ |
| description | This paper proposes a novel pixel interval down-sampling network (PID-Net) for dense tiny object (yeast cells) counting tasks with higher accuracy. The PID-Net is an end-to-end convolutional neural network (CNN) model with an encoder–decoder architecture. The pixel interval down-sampling operations are concatenated with max-pooling operations to combine the sparse and dense features. This addresses the limitation of contour conglutination of dense objects while counting. The evaluation was conducted using classical segmentation metrics (the Dice, Jaccard and Hausdorff distance) as well as counting metrics. The experimental results show that the proposed PID-Net had the best performance and potential for dense tiny object counting tasks, which achieved 96.97% counting accuracy on the dataset with 2448 yeast cell images. By comparing with the state-of-the-art approaches, such as Attention U-Net, Swin U-Net and Trans U-Net, the proposed PID-Net can segment dense tiny objects with clearer boundaries and fewer incorrect debris, which shows the great potential of PID-Net in the task of accurate counting. |
| first_indexed | 2024-03-09T03:42:56Z |
| format | Article |
| id | doaj.art-e9759925e626433f82a37f6e6bff36ec |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T03:42:56Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e9759925e626433f82a37f6e6bff36ec2023-12-03T14:37:53ZengMDPI AGApplied Sciences2076-34172022-07-011214731410.3390/app12147314An Application of Pixel Interval Down-Sampling (PID) for Dense Tiny Microorganism Counting on Environmental Microorganism ImagesJiawei Zhang0Xin Zhao1Tao Jiang2Md Mamunur Rahaman3Yudong Yao4Yu-Hao Lin5Jinghua Zhang6Ao Pan7Marcin Grzegorzek8Chen Li9Microscopic Image and Medical Image Analysis Group, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110819, ChinaSchool of Resources and Civil Engineering, Northeastern University, Shenyang 110819, ChinaSchool of Control Engineering, Chengdu University of Information Technology, Chengdu 610225, ChinaMicroscopic Image and Medical Image Analysis Group, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110819, ChinaStevens Institute of Technology, Hoboken, NJ 07030, USADepartment of Environmental Engineering, National Chung Hsing University, 145 Xingda Rd., Taichung 402, TaiwanMicroscopic Image and Medical Image Analysis Group, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110819, ChinaSchool of Life Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaInstitute of Medical Informatics, University of Luebeck, 23562 Luebeck, GermanyMicroscopic Image and Medical Image Analysis Group, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110819, ChinaThis paper proposes a novel pixel interval down-sampling network (PID-Net) for dense tiny object (yeast cells) counting tasks with higher accuracy. The PID-Net is an end-to-end convolutional neural network (CNN) model with an encoder–decoder architecture. The pixel interval down-sampling operations are concatenated with max-pooling operations to combine the sparse and dense features. This addresses the limitation of contour conglutination of dense objects while counting. The evaluation was conducted using classical segmentation metrics (the Dice, Jaccard and Hausdorff distance) as well as counting metrics. The experimental results show that the proposed PID-Net had the best performance and potential for dense tiny object counting tasks, which achieved 96.97% counting accuracy on the dataset with 2448 yeast cell images. By comparing with the state-of-the-art approaches, such as Attention U-Net, Swin U-Net and Trans U-Net, the proposed PID-Net can segment dense tiny objects with clearer boundaries and fewer incorrect debris, which shows the great potential of PID-Net in the task of accurate counting.https://www.mdpi.com/2076-3417/12/14/7314yeast countingimage segmentationpixel interval down-samplingtiny objects |
| spellingShingle | Jiawei Zhang Xin Zhao Tao Jiang Md Mamunur Rahaman Yudong Yao Yu-Hao Lin Jinghua Zhang Ao Pan Marcin Grzegorzek Chen Li An Application of Pixel Interval Down-Sampling (PID) for Dense Tiny Microorganism Counting on Environmental Microorganism Images Applied Sciences yeast counting image segmentation pixel interval down-sampling tiny objects |
| title | An Application of Pixel Interval Down-Sampling (PID) for Dense Tiny Microorganism Counting on Environmental Microorganism Images |
| title_full | An Application of Pixel Interval Down-Sampling (PID) for Dense Tiny Microorganism Counting on Environmental Microorganism Images |
| title_fullStr | An Application of Pixel Interval Down-Sampling (PID) for Dense Tiny Microorganism Counting on Environmental Microorganism Images |
| title_full_unstemmed | An Application of Pixel Interval Down-Sampling (PID) for Dense Tiny Microorganism Counting on Environmental Microorganism Images |
| title_short | An Application of Pixel Interval Down-Sampling (PID) for Dense Tiny Microorganism Counting on Environmental Microorganism Images |
| title_sort | application of pixel interval down sampling pid for dense tiny microorganism counting on environmental microorganism images |
| topic | yeast counting image segmentation pixel interval down-sampling tiny objects |
| url | https://www.mdpi.com/2076-3417/12/14/7314 |
| work_keys_str_mv | AT jiaweizhang anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT xinzhao anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT taojiang anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT mdmamunurrahaman anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT yudongyao anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT yuhaolin anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT jinghuazhang anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT aopan anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT marcingrzegorzek anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT chenli anapplicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT jiaweizhang applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT xinzhao applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT taojiang applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT mdmamunurrahaman applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT yudongyao applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT yuhaolin applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT jinghuazhang applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT aopan applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT marcingrzegorzek applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages AT chenli applicationofpixelintervaldownsamplingpidfordensetinymicroorganismcountingonenvironmentalmicroorganismimages |