RESUMO
PURPOSE: Multifaceted factors contribute to inferior outcomes following anterior cruciate ligament (ACL) reconstruction surgery. A particular focus is placed on the posterior tibial slope (PTS). This study introduces the integration of machine learning and artificial intelligence (AI) for efficient measurements of tibial slopes on magnetic resonance imaging images as a promising solution. This advancement aims to enhance risk stratification, diagnostic insights, intervention prognosis and surgical planning for ACL injuries. METHODS: Images and demographic information from 120 patients who underwent ACL reconstruction surgery were used for this study. An AI-driven model was developed to measure the posterior lateral tibial slope using the YOLOv8 algorithm. The accuracy of the lateral tibial slope, medial tibial slope and tibial longitudinal axis measurements was assessed, and the results reached high levels of reliability. This study employed machine learning and AI techniques to provide objective, consistent and efficient measurements of tibial slopes on MR images. RESULTS: Three distinct models were developed to derive AI-based measurements. The study results revealed a substantial correlation between the measurements obtained from the AI models and those obtained by the orthopaedic surgeon across three parameters: lateral tibial slope, medial tibial slope and tibial longitudinal axis. Specifically, the Pearson correlation coefficients were 0.673, 0.850 and 0.839, respectively. The Spearman rank correlation coefficients were 0.736, 0.861 and 0.738, respectively. Additionally, the interclass correlation coefficients were 0.63, 0.84 and 0.84, respectively. CONCLUSION: This study establishes that the deep learning-based method for measuring posterior tibial slopes strongly correlates with the evaluations of expert orthopaedic surgeons. The time efficiency and consistency of this technique suggest its utility in clinical practice, promising to enhance workflow, risk assessment and the customization of patient treatment plans. LEVEL OF EVIDENCE: Level III, cross-sectional diagnostic study.
RESUMO
Microfluidics is a rapidly growing discipline that involves studying and manipulating fluids at reduced length scale and volume, typically on the scale of micro- or nanoliters. Under the reduced length scale and larger surface-to-volume ratio, advantages of low reagent consumption, faster reaction kinetics, and more compact systems are evident in microfluidics. However, miniaturization of microfluidic chips and systems introduces challenges of stricter tolerances in designing and controlling them for interdisciplinary applications. Recent advances in artificial intelligence (AI) have brought innovation to microfluidics from design, simulation, automation, and optimization to bioanalysis and data analytics. In microfluidics, the Navier-Stokes equations, which are partial differential equations describing viscous fluid motion that in complete form are known to not have a general analytical solution, can be simplified and have fair performance through numerical approximation due to low inertia and laminar flow. Approximation using neural networks trained by rules of physical knowledge introduces a new possibility to predict the physicochemical nature. The combination of microfluidics and automation can produce large amounts of data, where features and patterns that are difficult to discern by a human can be extracted by machine learning. Therefore, integration with AI introduces the potential to revolutionize the microfluidic workflow by enabling the precision control and automation of data analysis. Deployment of smart microfluidics may be tremendously beneficial in various applications in the future, including high-throughput drug discovery, rapid point-of-care-testing (POCT), and personalized medicine. In this review, we summarize key microfluidic advances integrated with AI and discuss the outlook and possibilities of combining AI and microfluidics.
