Objective To clarify the relationship between intracranial pressure monitoring and prognosis of patients with traumatic brain injury after decompressive craniectomy.Methods From December 2015 to December 2017,48 head-injured patients in Affiliated Suzhou Hospital of Nanjing Medical University were enrolled,who were underwent decompressive craniectomy in this retrospective study.The patients were subdivided into 2 groups based on whether postoperative was monitored (n =19) or not (n =29).The prognosis was evaluated by Glasgow Outcome Scale score,with 1 point of prognosis death,2 to 3 points of poor prognosis,and 4 to 5 points of good prognosis.Count data were expressed as a percentage (％).Count data were expressed as percentage (％).The chi-square test was used to compare the difference in the rate of good prognosis and mortality between the two groups.Results The mortality of monitoring group (10.5％) was significantly lower than that of control group (37.9％) (x2 =4.365 5,P =0.036 7) during hospitalization,The rate of good prognosis in the monitoring group (68.4％) and the control group (44.8％) was not statistically significant (x2 =2.573 8,P =0.108 6).Condusion The study showed that continuous monitoring in patients with severe craniocerebral injury could reduce the mortality of patients during hospitalization,but had no significant effect on the improvement of prognosis.

In recent years,deep learning,a pivotal subset of artificial intelligence machine learning,has achieved noteworthy advancements in the medical domain.It facilitates precise detection,diagnosis and prognostic assessment of various diseases through the analysis of medical images.Within ophthalmology,deep learning techniques have found wide-spread application in the diagnosis and prediction of thyroid-related eye diseases,orbital blowout fracture,melanoma,bas-al cell carcinoma,orbital abscess,lymphoma,retinoblastoma and other diseases.Leveraging images from computed tomo-graphy,magnetic resonance imaging and even pathological sections,this technology demonstrates a capacity to diagnose,differentiate and stage orbital diseases and ocular tumors with a high level of accuracy comparable to that of expert clini-cians.The promising prospects of this technology are expected to enhance the diagnosis and treatment of related diseases,concurrently reducing the time and cost associated with clinical practices.This review consolidates the latest research pro-gress on the application of artificial intelligence deep learning in orbital diseases and ocular tumors,aiming to furnish clini-cians with up-to-date information and developmental trends in this field,thereby furthering the clinical application and widespread adoption of this technology.

The finite element method(FEM)is a widely employed mathematical technique in mechanical research that divides an object into discrete and interacting finite elements. Medically, finite element analysis(FEA)enables the simulation of biomechanical experiments that are challenging to conduct. Orbital surgery poses significant challenges to ophthalmologists due to its inherent difficulty and steep learning curve. FEM enables the simulation and analysis of the mechanical properties of orbital tissue, offering a novel approach for diagnosing and treating orbital-related diseases. With technological advancements, FEM has significantly matured in the diagnosis and treatment of orbital diseases, becoming a popular area of research in orbital biomechanics. This paper reviewed the latest advancements in orbital FEM, encompassing the development of orbital FEA models, simulation of orbital structure, and its application in orbital-related diseases. Additionally, the limitations of FEM and future research directions are also discussed. As a digital tool for auxiliary diagnosis and treatment, orbital FEA will progressively unlock its potential for diagnosing and treating orbital diseases alongside technological advancements.