Deep ensemble learning enables highly accurate classification of stored red blood cell morphology.

Changes in red blood cell (RBC) morphology distribution have emerged as a quantitative biomarker for the degradation of RBC functional properties during hypothermic storage. Previously published automated methods for classifying the morphology of stored RBCs often had insufficient accuracy and relied on proprietary code and datasets, making them difficult to use in many research and clinical applications. Here we describe the development and validation of a highly accurate open-source RBC morphology classification pipeline based on ensemble deep learning (DL).

Conical drill bit for optimized external ventricular drain placement: a proof-of-concept study.

Objective: Despite external ventricular drain (EVD) procedures being commonplace in neurosurgical practice, suboptimal placement rates remain high, and complications are not uncommon. The angle of the EVD catheter insertion and the accuracy of the drill hole placement are major factors determining successful EVD placement that are dependent on the drill bit morphology. The standard cylindrical 2-fluted twist drill bit creates a relatively deep and narrow drill hole that requires precise positioning, has limited visibility of the drill hole bottom and restricted catheter angular adjustment range, and poses the risk of inadvertent dural puncture.