Hip Osteoarthritis (OA) is a common disease among the middle-aged and elderly people. Conventionally, hip OA is diagnosed by manually assessing X-ray images. This study took the hip joint as the object of observation and explored the diagnostic value of deep learning in hip osteoarthritis. A deep convolutional neural network (CNN) was trained and tested on 420 hip X-ray images to automatically diagnose hip OA. This CNN model achieved a balance of high sensitivity of 95.0% and high specificity of 90.7%, as well as an accuracy of 92.8% compared to the chief physicians. The CNN model performance is comparable to an attending physician with 10 years of experience. The results of this study indicate that deep learning has promising potential in the field of intelligent medical image diagnosis practice.

No abstract

LiNi 0.5-x P 2x Mn 1.5-x O 4 (x = 0, 0.005, 0.01, and 0.02) submicrograins in regular octahedral shape with merely {111} surface facets and truncated octahedral shape with both {111} and {100} surface planes were obtained by the solid-state reaction method. The effect of doping P on ions arrangement, grain morphology, and the electrochemical performance of lithium nickel manganese oxide was investigated. The characterizations of X-ray diffraction (XRD), Raman, X-ray photoelectron spectroscopy (XPS), and selected area electron diffraction (SAED) confirm more Mn 3+ ions in the structure to enhance the cationic disorder degree of LiNi 0.5 Mn 1.5 O 4 after Pdoping. Comparing the LiNi 0.5 Mn 1.5 O 4 and LiNi 0.495 P 0.01 Mn 1.495 O 4 samples both with regular octahedral morpology, their electrochemical performance could be remarkably improved by more disordered transition metal ions arrangement leading to higher conductivity of Li-ions and electrons. However, when the amount of P-doping further increased, the rate and cycle ability of the LiNi 0.480 P 0.04 Mn 1.480 O 4 sample in truncated octahedral shape worsen dramatically even with a higher degree of cationic disorder. This could be on account of the crystal planes starting to dominate the electrochemical performance instead of ions arrangement under high voltage and large rate: the {111} facet is more favorable to the lithium ion transport than the {100} crystal plane for LiNi 0.5 Mn 1.5 O 4 submicrograins during charge and discharge.

Ultrasound elasticity imaging has been developed over the last decade to estimate tissue stiffness. Shear wave elasticity imaging (SWEI) quantifies tissue stiffness by measuring the speed of propagating shear waves following acoustic radiation force excitation. This work presents the sequencing and data processing protocols of SWEI using a Verasonics system. The selection of the sequence parameters in a Verasonics programming script is discussed in detail. The data processing pipeline to calculate group shear wave speed (SWS), including tissue motion estimation, data filtering, and SWS estimation is demonstrated. In addition, the procedures for calibration of beam position, scanner timing, and transducer face heating are provided to avoid SWS measurement bias and transducer damage.