InferVision (China)

ObjectivePresent study aimed to quantitatively evaluate the association between fundus tessellated density (FTD) and subfoveal choroidal thickness (SFCT) in children with different refractive statuses and to explore the potential of FTD as a non-invasive biomarker for monitoring myopic progression.MethodsA cross-sectional study was conducted involving 619 eyes of 315 children aged 6–12 years. Participants were classified into four refractive groups: hyperopia, pre-myopia, low myopia, and moderate-to-high myopia. FTD was quantitatively assessed using artificial intelligence (AI)-based analysis of color fundus photographs. SFCT and central subfield thickness (CST) were measured using swept-source optical coherence tomography (SS-OCT). Correlation and threshold effect analyses were performed to examine the relationship between FTD and SFCT.ResultsSFCT decreased significantly with increasing myopic severity (p < 0.001), while FTD showed a corresponding increase (p < 0.001). A significant negative correlation was observed between FTD and SFCT in pre-myopia (r = −0.183, p = 0.019), low myopia (r = −0.335, p < 0.001), and moderate-to-high myopia (r = −0.222, p = 0.008) groups, but not in hyperopia (p = 0.454). A nonlinear threshold effect was identified: when SFCT decreased below 148.90 μm in the overall cohort, FTD increased markedly, suggesting that this value may serve as a potential reference point for myopia management. This threshold decreased with higher myopic severity. CST did not follow a linear gradient with refraction but was increased in moderate-to-high myopia.ConclusionFTD and SFCT are significantly associated in a nonlinear manner in myopic children, with a defined threshold effect that varies by refractive status. AI-based FTD measurement offers a reproducible and accessible method for quantifying early structural changes in myopia. The identified nonlinear relationship and threshold suggest that combined assessment of FTD and SFCT may hold promise for improving early detection and monitoring of pediatric myopic progression, warranting further longitudinal validation.

Coronary artery calcification (CAC) provides robust prediction for major adverse cardiovascular events (MACE), but current techniques disregard plaque distribution and protective effects of high CAC density. We investigated whether a novel CAC-dispersion and density (CAC-DAD) score will exhibit superior prognostic value compared with the Agatston score (AS) for MACE prediction. We conducted a multicenter, retrospective, cross-sectional study of 961 patients (median age, 67 years; 61% men) who underwent cardiac computed tomography for cardiovascular or perioperative risk assessment. Blinded analyzers applied deep learning algorithms to noncontrast scans to calculate the CAC-DAD score, which adjusts for the spatial distribution of CAC and assigns a protective weight factor for lesions with ≥1000 Hounsfield units. Associations were assessed using frailty regression. Over a median follow-up of 30 (30-460) days, 61 patients experienced MACE (nonfatal myocardial infarction or cardiovascular mortality). An elevated CAC-DAD score (≥2050 based on optimal cutoff) captured more MACE than AS ≥400 (74% versus 57%; P=0.002). Univariable analysis revealed that an elevated CAC-DAD score, AS ≥400 and AS ≥100, age, diabetes, hypertension, and statin use predicted MACE. On multivariable analysis, only the CAC-DAD score (hazard ratio, 2.57 [95% CI, 1.43-4.61]; P=0.002), age, statins, and diabetes remained significant. The inclusion of the CAC-DAD score in a predictive model containing demographic factors and AS improved the C statistic from 0.61 to 0.66 (P=0.008). The fully automated CAC-DAD score improves MACE prediction compared with the AS. Patients with a high CAC-DAD score, including those with a low AS, may be at higher risk and warrant intensification of their preventative therapies.

The increasing complexity of lung surgeries necessitates the need for enhanced imaging support to improve the precision and efficiency of preoperative planning. Despite the promise of 3D reconstruction, clinical adoption remains limited due to time constraints and insufficient validation. To address this, we evaluate an artificial intelligence-driven 3D reconstruction system for pulmonary vessels and bronchi in a retrospective, multi-center multi-reader multi-case study. Using a two-stage crossover design, ten thoracic surgeons assess 140 cases with and without the system’s assistance. The system significantly improves the accuracy of anatomical variant identification by 8% (p < 0.01), reducing errors by 41%. Improvements in secondary endpoints are also observed. Operation procedure selection accuracy is improved by 8%, with a 35% decrease in errors. Preoperative planning time is decreased by 25%, and user satisfaction is high at 99%. These benefits are consistent across surgeons of varying experience. In conclusion, the artificial intelligence-driven 3D reconstruction system significantly improves the identification of anatomical variants, addressing a critical need in preoperative planning for thoracic surgery.

Abstract Rationale: Evaluate the application value of a new two-dimensional electrical impedance tomography system (2D-EIT) for real-time monitoring of reperfusion efficacy in acute pulmonary embolism (PE). Methods: Five patients with acute PE, aged between 18 and 75, suitable for percutaneous catheter aspiration thrombectomy, were included in the study. All enrolled patients completed CTPA and EIT examinations, with the interval between EIT and CTPA being less than 2 hours. The percutaneous catheter aspiration thrombectomy was performed within 6 hours after pulmonary embolism was diagnosed by CTPA and EIT, and which were repeated within 2 hours post-procedure. The perfusion signals were acquired by a pulsatility signal-based algorithm for EIT. Results: 3 males and 2 females were included. All 5 patients were diagnosed with segment-level or higher pulmonary embolism via CTPA, with four cases involving the right pulmonary artery trunk and one case involving the left pulmonary artery trunk. EIT examination showed ventilation/perfusion mismatch that closely matched the thromboembolic regions indicated by CTPA. Perfusion was assessed before and after surgery using EIT images. The numbers in Figure 1 represent the perfusion percentage of image within each Region of Interest (ROI) to the entire image. Paired t-test analysis showed that the mean left/right (depending on the position of thrombectomy) lung perfusion percentage increased from 18.67%±14.04% to 42.61%±13.00%(P = 0.001), of which the mean anterior perfusion percentage increased from 9.17%±12.52 to 18.17%±12.00% (P = 0.169), and the mean posterior perfusion percentage increased from 9.50%7.98± to 24.44%±11.23 (P = 0.019). Conclusion: 2D-EIT perfusion images holds promise in making real-time, effective evaluation of reperfusion efficacy possible in acute PE. Figure 1. The CTPA and 2D-EIT ventilation and perfusion images of patients with acute pulmonary embolisms before and after treatments. Ventilation and perfusion signals were indicated in blue and red, respectively, and the higher color brightness represented a stronger signal.The white arrows showed the filling defects of the perfusion in EIT and CTPA images.

Accurate and efficient estimation of the equivalent factor (EF) in equivalent consumption minimization strategy (ECMS) is pivotal for achieving desirable economy effects in plug-in hybrid electric vehicles (PHEV). To this end, a real-time predictive ECMS (PECMS) for cost optimality in series PHEVs is proposed, which aims to minimize the total cost associated with fuel consumption, battery degradation, and electricity usage. A generalized unified constraint for battery power command is developed to establish the minimum feasible control domain in powertrain, thereby reducing control complexity and deriving minimal usable EF bounds. Building upon this unified constraint, a universal approach for estimating EF bounds is introduced, independent of specific control objectives or powertrain configurations. Subsequently, a concise and efficient EF tuning approach based on the golden section method is formulated to estimate the appropriate EF for PECMS in real time. With this EF determination, optimal battery power commands are computed by solving the Hamilton function. Simulation and hardware-in-the-loop test results verify the effectiveness of the proposed strategy in reducing operational cost, accurately estimating EF bounds, and achieving efficient EF tuning in real-time applications.

This study aims to develop an end-to-end deep learning (DL) model to predict neoadjuvant chemotherapy (NACT) response in osteosarcoma (OS) patients using routine magnetic resonance imaging (MRI). We retrospectively analyzed data from 112 patients with histologically confirmed OS who underwent NACT prior to surgery. Multi-sequence MRI data (including T2-weighted and contrast-enhanced T1-weighted images) and physician annotations were utilized to construct an end-to-end DL model. The model integrates ResUNet for automatic tumor segmentation and 3D-ResNet-18 for predicting NACT efficacy. Model performance was assessed using area under the curve (AUC) and accuracy (ACC). Among the 112 patients, 51 exhibited a good NACT response, while 61 showed a poor response. No statistically significant differences were found in age, sex, alkaline phosphatase levels, tumor size, or location between these groups (P > 0.05). The ResUNet model achieved robust performance, with an average Dice coefficient of 0.579 and average Intersection over Union (IoU) of 0.463. The T2-weighted 3D-ResNet-18 classification model demonstrated superior performance in the test set with an AUC of 0.902 (95% CI: 0.766-1), ACC of 0.783, sensitivity of 0.909, specificity of 0.667, and F1 score of 0.800. Our proposed end-to-end DL model can effectively predict NACT response in OS patients using routine MRI, offering a potential tool for clinical decision-making.

BackgroundAccurate detection of hepatocellular carcinoma (HCC) in multiphasic contrast CT is essential for effective treatment and surgical planning. However, the variety of CT images, the misdiagnosis and missed diagnosis, and the inconsistent diagnosis among different radiologists pose challenges to accurate detection which demands sufficient clinical experience and can be time-consuming and labor-intensive.PurposeTo evaluate the detection performance of an artificial intelligence (AI)-assisted platform for HCC by the external validation dataset.MethodsCT images pathologically diagnosed with HCC from December 2021 to June 2023 were retrospectively analyzed to evaluate the detection ability of the AI-assisted platform. The AI-assisted platform is designed based on a two-phase segmentation approach, integrating coarse and fine segmentation techniques to accurately identify and delineate hepatic lesions. The CT images were annotated and confirmed by the experienced radiologists using InferScholar software as the “gold standard”. The automatic HCC segmentation performed by the AI-assisted platform was used to compare with the annotation of radiologists. Furthermore, we also did subgroup analysis depending on the size and location of HCC to explore the impact factors of HCC detectability. The segmentation accuracies were evaluated by Dice coefficient (Dice), accuracy, recall, precision, and F1-score. Our study focused on evaluating the efficacy of the AI-assisted platform in clinical settings.ResultsOne Hundred Forty HCC patients were finally included in this study. The artificial intelligence (AI)-assisted platform’s performance was rigorously assessed by comparing the segmentation outcomes with standard diagnostic criteria. The average dice score of the AI-assisted platform is 0.8819, which showed a high detection performance for HCC. Besides, for the subgroup analysis, the model also demonstrated high performance in diameter greater than 20 mm with all results exceeding 0.9, and all final evaluation index values for the location analysis were consistently exceeding 0.97. All the results showed comparable performance with radiologists. Our results demonstrate that the product not only accurately segments HCC lesions but also provides valuable insights into lesion characteristics that are essential for effective treatment planning.ConclusionThis study validates the effectiveness of the artificial intelligence-assisted platform in detecting HCC lesions and analyzing lesion size and location. It can serve as an auxiliary tool to help radiologists identify, locate, and assess lesions.

In 6G networks, Multi-access Edge Computing (MEC) enables ultra-low latency and high reliability for Internet of Things (IoT) applications. However, optimizing resource allocation in MEC is challenging due to dynamic network conditions and limited computational resources. To address these challenges, this study proposes a Hybrid Multi-Objective Soft Actor-Critic (HMO-SAC) algorithm, which integrates Multi-Objective Reinforcement Learning (MORL) within a hybrid action space. The method dynamically balances multiple optimization objectives, leveraging a hybrid action space to make decisions involving both discrete and continuous parameters, such as task offloading targets and resource allocation. Additionally, an Improved Near-on Experience Replay (INER) mechanism is introduced to mitigate extrapolation errors in off-policy sampled data. Simulation results demonstrate that HMO-SAC improves convergence speed by 14% on average and reduces the task completion time and energy consumption by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$23\%$</tex-math></inline-formula> compared to state-of-the-art methods.