Protein Crystal Instance Segmentation Based on Mask R-CNN
Jiangping Qin, Yan Zhang, Huan Zhou, Yu Feng, Bo Sun, Qisheng Wang
Abstract
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.