Detection and Segmentation of Breast Masses Based on Multi-Layer Feature Fusion.

In breast mass detection, there are many different sizes of masses in the image. However, when the existing target detection model is directly used to detect the breast mass, it is easy to appear the phenomenon of misdetection and missed detection. Therefore, in order to improve the detection accuracy of breast masses, this paper proposed a target detection model D-Mask R-CNN based on Mask R-CNN, which is suitable for breast masses detection. Firstly, this paper improved the internal structure of FPN, and modified the lateral connection mode in the original FPN structure to dense connection. Secondly, modified the size of the anchor of RPN to improve the location accuracy of breast masses. Finally, Soft-NMS was used to replace the NMS in the original model to reduce the possibility that the correct prediction results may be eliminated during the NMS process. This paper used the CBIS-DDSM dataset for all experiments. The results showed that the mAP value of the improved model for detecting breast masses reached 0.66 in the test set, which was 0.05 higher than that of the original Mask R-CNN.

Caulobacter crescentus ß sliding clamp employs a noncanonical regulatory model of DNA replication.

The eubacterial ß sliding clamp (DnaN) plays a crucial role in DNA metabolism through direct interactions with DNA, polymerases, and a variety of protein factors. A canonical protein-DnaN interaction has been identified in Escherichia coli and some other species, during which protein partners are tethered into the conserved canonical hydrophobic crevice of DnaN via the consensus ß-binding motif. Caulobacter crescentus is an excellent research model for use in the investigation of DNA replication and cell-cycle regulation due to its unique asymmetric cell division pattern with restricted replication initiation; however, little is known about the specific features of C. crescentus DnaN (CcDnaN). Here, we report a significant divergence in the association of CcDnaN with proteins based on docking analysis and crystal structures that show that the ß-binding motifs of its protein partners bind a novel pocket instead of the canonical site. Pull-down and isothermal titration calorimetry results revealed that mutations within the novel pocket disrupt protein-CcDnaN interactions. It was also shown by replication and regulatory inactivation of DnaA assays that mediation of protein interaction by the novel pocket is closely related to the performance of CcDnaN during replication and the DnaN-mediated regulation process. Moreover, assessments of clamp competition showed that DNA does not compete with protein partners when binding to the novel pocket. Overall, our structural and biochemical analyses provide strong evidence that CcDnaN employs a noncanonical protein association pattern.