Protein Crystal Instance Segmentation Based on Mask R-CNN
Protein crystallization is the bottleneck in macromolecular crystallography, and crystal recognition is a very important step in the experiment. To improve the recognition accuracy by image classification algorithms further, the Mask R-CNN model is introduced for the detection of protein crystals in...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Crystals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4352/11/2/157 |
| _version_ | 1827603649693483008 |
|---|---|
| author | Jiangping Qin Yan Zhang Huan Zhou Feng Yu Bo Sun Qisheng Wang |
| author_facet | Jiangping Qin Yan Zhang Huan Zhou Feng Yu Bo Sun Qisheng Wang |
| author_sort | Jiangping Qin |
| collection | DOAJ |
| description | Protein crystallization is the bottleneck in macromolecular crystallography, and crystal recognition is a very important step in the experiment. To improve the recognition accuracy by image classification algorithms further, the Mask R-CNN model is introduced for the detection of protein crystals in this paper. Because the protein crystal image is greatly affected by backlight and precipitate, the contrast limit adaptive histogram equalization (CLAHE) is applied with Mask R-CNN. Meanwhile, the Transfer Learning method is used to optimize the parameters in Mask R-CNN. Through the comparison experiments between this combined algorithm and the original algorithm, it shows that the improved algorithm can effectively improve the accuracy of segmentation. |
| first_indexed | 2024-03-09T05:44:41Z |
| format | Article |
| id | doaj.art-ecf3bd2ca3244ac8b503989baab81002 |
| institution | Directory Open Access Journal |
| issn | 2073-4352 |
| language | English |
| last_indexed | 2024-03-09T05:44:41Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Crystals |
| spelling | doaj.art-ecf3bd2ca3244ac8b503989baab810022023-12-03T12:22:55ZengMDPI AGCrystals2073-43522021-02-0111215710.3390/cryst11020157Protein Crystal Instance Segmentation Based on Mask R-CNNJiangping Qin0Yan Zhang1Huan Zhou2Feng Yu3Bo Sun4Qisheng Wang5Shanghai Institute of Applied Physics, Chinese Academy of Sciences, Shanghai 201210, ChinaLogistics Engineering College, Shanghai Maritime University, Shanghai 201306, ChinaShanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, ChinaShanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, ChinaShanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, ChinaShanghai Institute of Applied Physics, Chinese Academy of Sciences, Shanghai 201210, ChinaProtein crystallization is the bottleneck in macromolecular crystallography, and crystal recognition is a very important step in the experiment. To improve the recognition accuracy by image classification algorithms further, the Mask R-CNN model is introduced for the detection of protein crystals in this paper. Because the protein crystal image is greatly affected by backlight and precipitate, the contrast limit adaptive histogram equalization (CLAHE) is applied with Mask R-CNN. Meanwhile, the Transfer Learning method is used to optimize the parameters in Mask R-CNN. Through the comparison experiments between this combined algorithm and the original algorithm, it shows that the improved algorithm can effectively improve the accuracy of segmentation.https://www.mdpi.com/2073-4352/11/2/157protein crystalMask R-CNNinstance segmentationtransfer learning |
| spellingShingle | Jiangping Qin Yan Zhang Huan Zhou Feng Yu Bo Sun Qisheng Wang Protein Crystal Instance Segmentation Based on Mask R-CNN Crystals protein crystal Mask R-CNN instance segmentation transfer learning |
| title | Protein Crystal Instance Segmentation Based on Mask R-CNN |
| title_full | Protein Crystal Instance Segmentation Based on Mask R-CNN |
| title_fullStr | Protein Crystal Instance Segmentation Based on Mask R-CNN |
| title_full_unstemmed | Protein Crystal Instance Segmentation Based on Mask R-CNN |
| title_short | Protein Crystal Instance Segmentation Based on Mask R-CNN |
| title_sort | protein crystal instance segmentation based on mask r cnn |
| topic | protein crystal Mask R-CNN instance segmentation transfer learning |
| url | https://www.mdpi.com/2073-4352/11/2/157 |
| work_keys_str_mv | AT jiangpingqin proteincrystalinstancesegmentationbasedonmaskrcnn AT yanzhang proteincrystalinstancesegmentationbasedonmaskrcnn AT huanzhou proteincrystalinstancesegmentationbasedonmaskrcnn AT fengyu proteincrystalinstancesegmentationbasedonmaskrcnn AT bosun proteincrystalinstancesegmentationbasedonmaskrcnn AT qishengwang proteincrystalinstancesegmentationbasedonmaskrcnn |