Development of a deep learning method to identify acute ischaemic stroke lesions on brain CT.

Background: CT is commonly used to image patients with ischaemic stroke but radiologist interpretation may be delayed. Machine learning techniques can provide rapid automated CT assessment but are usually developed from annotated images which necessarily limits the size and representation of development data sets. We aimed to develop a deep learning (DL) method using CT brain scans that were labelled but not annotated for the presence of ischaemic lesions.

Active site substitutions delineate distinct classes of eubacterial flap endonuclease.

FENs (flap endonucleases) play essential roles in DNA replication, pivotally in the resolution of Okazaki fragments. In eubacteria, DNA PolI (polymerase I) contains a flap processing domain, the N-terminal 5'-->3' exonuclease. We present evidence of paralogous FEN-encoding genes present in many eubacteria.