RÉSUMÉ
Objective To develop and validate a deep learning model for automatic identification of liver CT contrast-enhanced phases.Methods A total of 766 patients with liver CT contrast-enhanced images were retrospectively collected.A three-phase classification model and an arterial phase(AP)classification model were developed,so as to automatically identify liver CT contrast-enhanced phases as early arterial phase(EAP)or late arterial phase(LAP),portal venous phase(PVP),and equilibrium phase(EP).In addition,221 patients with liver CT contrast-enhanced images in 5 different hospitals were used for external validation.The annotation results of radiologists were used as a reference standard to evaluate the model performances.Results In the external validation datasets,the accuracy in identifying each enhanced phase reached to 90.50%-99.70%.Conclusion The automatic identification model of liver CT contrast-enhanced phases based on residual network may provide an efficient,objective,and unified image quality control tool.
RÉSUMÉ
Objective To study the stability of lumbar spine after transforaminal lumbar interbody fusion (TLIF) surgery combined with a novel articular process fixation system (APFS). Methods Based on the validated finite element model of L3-S1 intact segment (Model A), TLIF surgery was simulated to establish bilateral pedicle screw TLIF model (Model B), right unilateral pedicle screw TLIF model (Model C), APFS combined with right pedicle screw fixation TLIF model (Model D). The range of motion (ROM) of the lumbar spine model and stress distributions on pedicle screws, APFS and interbody fusion cages under different working conditions were observed. Results The overall ROMs of Models B, C, and D under different working conditions were comparable, which were all smaller than those of the physiological model. Compared with Models B and C, the maximum compressive stress of the right pedicle screw and the interbody fusion cage in Model D was the smallest or between Models B and C under different working conditions. Model D had the largest peak stress of APFS and right pedicle screw during anterior flexion. Conclusions APFS combined with contralateral pedicle screw fixation can be used as a novel fixation method for TLIF surgery of lumbar spine.
RÉSUMÉ
Objective To conduct a biomechanical evaluation of the four internal fixation methods to treat transverse acetabular fracture and find the b est one. Methods The transverse acetabular fracture models were created by osteo tomy in 12 pairs of embalmed cadaveric hip joints, and fixed with one of the fou r different methods: an anterior column plate (P/N), an anterior column plate w ith a posterior column screw (P+S), a posterior column plate with an anterior screw (S+P) and two posterior column plates (N/P?2). The biomechanical stabi lity was evaluated on longitudinal displacement, level displacement and stiffnes s measurements for fixed fracture fragments which were under 800 Newton vertical compression load. Results The longitudinal displacement in S+P was 3.99mm, in P+S 4.09mm, in N/P?2 5.07mm and in P/N 5.66mm; the level displacement in S+P was 0.015mm, in P+S 0.016mm, in N/P?2 0.022mm and in P/N 0.025mm; the average stiffness in S+P was 205.77N/mm, in P+S 207.52N/mm, in N/P?2 162.36N/mm and i n P/N 146.67N/mm. There were significant differences between the groups of S+P and P+S and the groups of N/P?2 and P/N (P