Platelet Detection Based on Improved YOLO_v3
Platelet detection and counting play a greatly significant role in medical field, especially in routine blood tests which can be used to judge blood status and diagnose related diseases. Therefore, platelet detection is valuable for diagnosing related blood diseases such as liver-related diseases. B...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Association for the Advancement of Science (AAAS)
2022-01-01
|
| Series: | Cyborg and Bionic Systems |
| Online Access: | http://dx.doi.org/10.34133/2022/9780569 |
| _version_ | 1811258473669722112 |
|---|---|
| author | Renting Liu Chunhui Ren Miaomiao Fu Zhengkang Chu Jiuchuan Guo |
| author_facet | Renting Liu Chunhui Ren Miaomiao Fu Zhengkang Chu Jiuchuan Guo |
| author_sort | Renting Liu |
| collection | DOAJ |
| description | Platelet detection and counting play a greatly significant role in medical field, especially in routine blood tests which can be used to judge blood status and diagnose related diseases. Therefore, platelet detection is valuable for diagnosing related blood diseases such as liver-related diseases. Blood analyzers and visual microscope counting were widely used for platelet detection, but the experimental procedure took nearly 20 minutes and can only be performed by a professional doctor. In recent years, technological breakthroughs in artificial intelligence have made it possible to detect red blood cells through deep learning methods. However, due to the inaccessibility of platelet datasets and the small size of platelets, deep learning-based platelet detection studies are almost nonexistent. In this paper, we carried out experiments for platelet detection based on commonly used object detection models, such as Single Shot Multibox Detector (SSD), RetinaNet, Faster_rcnn, and You Only Look Once_v3 (YOLO_v3). Compared with the other three models, YOLO_v3 can detect platelets more effectively. And we proposed three ideas for improvement based on YOLO_v3. Our study demonstrated that YOLO_v3 can be adopted for platelet detection accurately and in real time. We also implemented YOLO_v3 with multiscale fusion, YOLO_v3 with anchor box clustering, and YOLO_v3 with match parameter on our self-created dataset and, respectively, achieved 1.8% higher average precision (AP), 2.38% higher AP, and 2.05% higher AP than YOLO_v3. The comprehensive experiments revealed that YOLO_v3 with the improved ideas performs better in platelet detection than YOLO_v3. |
| first_indexed | 2024-04-12T18:14:57Z |
| format | Article |
| id | doaj.art-6ff7e006d4964c0d87d5d5108eff9260 |
| institution | Directory Open Access Journal |
| issn | 2692-7632 |
| language | English |
| last_indexed | 2024-04-12T18:14:57Z |
| publishDate | 2022-01-01 |
| publisher | American Association for the Advancement of Science (AAAS) |
| record_format | Article |
| series | Cyborg and Bionic Systems |
| spelling | doaj.art-6ff7e006d4964c0d87d5d5108eff92602022-12-22T03:21:41ZengAmerican Association for the Advancement of Science (AAAS)Cyborg and Bionic Systems2692-76322022-01-01202210.34133/2022/9780569Platelet Detection Based on Improved YOLO_v3Renting Liu0Chunhui Ren1Miaomiao Fu2Zhengkang Chu3Jiuchuan Guo4School of Information and Communication Engineering, University of Electronic Science and Technology, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology, Chengdu 611731, ChinaSchool of Automation Engineering, University of Electronic Science and Technology, Chengdu 611731, ChinaPlatelet detection and counting play a greatly significant role in medical field, especially in routine blood tests which can be used to judge blood status and diagnose related diseases. Therefore, platelet detection is valuable for diagnosing related blood diseases such as liver-related diseases. Blood analyzers and visual microscope counting were widely used for platelet detection, but the experimental procedure took nearly 20 minutes and can only be performed by a professional doctor. In recent years, technological breakthroughs in artificial intelligence have made it possible to detect red blood cells through deep learning methods. However, due to the inaccessibility of platelet datasets and the small size of platelets, deep learning-based platelet detection studies are almost nonexistent. In this paper, we carried out experiments for platelet detection based on commonly used object detection models, such as Single Shot Multibox Detector (SSD), RetinaNet, Faster_rcnn, and You Only Look Once_v3 (YOLO_v3). Compared with the other three models, YOLO_v3 can detect platelets more effectively. And we proposed three ideas for improvement based on YOLO_v3. Our study demonstrated that YOLO_v3 can be adopted for platelet detection accurately and in real time. We also implemented YOLO_v3 with multiscale fusion, YOLO_v3 with anchor box clustering, and YOLO_v3 with match parameter on our self-created dataset and, respectively, achieved 1.8% higher average precision (AP), 2.38% higher AP, and 2.05% higher AP than YOLO_v3. The comprehensive experiments revealed that YOLO_v3 with the improved ideas performs better in platelet detection than YOLO_v3.http://dx.doi.org/10.34133/2022/9780569 |
| spellingShingle | Renting Liu Chunhui Ren Miaomiao Fu Zhengkang Chu Jiuchuan Guo Platelet Detection Based on Improved YOLO_v3 Cyborg and Bionic Systems |
| title | Platelet Detection Based on Improved YOLO_v3 |
| title_full | Platelet Detection Based on Improved YOLO_v3 |
| title_fullStr | Platelet Detection Based on Improved YOLO_v3 |
| title_full_unstemmed | Platelet Detection Based on Improved YOLO_v3 |
| title_short | Platelet Detection Based on Improved YOLO_v3 |
| title_sort | platelet detection based on improved yolo v3 |
| url | http://dx.doi.org/10.34133/2022/9780569 |
| work_keys_str_mv | AT rentingliu plateletdetectionbasedonimprovedyolov3 AT chunhuiren plateletdetectionbasedonimprovedyolov3 AT miaomiaofu plateletdetectionbasedonimprovedyolov3 AT zhengkangchu plateletdetectionbasedonimprovedyolov3 AT jiuchuanguo plateletdetectionbasedonimprovedyolov3 |