With the continuous deepening of the concept of precision diagnosis and treatment for lung cancer, how to achieve higher efficiency and accuracy in the screening, diagnosis, and treatment pathways in clinical practice has become an important issue that urgently needs to be overcome. The current clinical difficulty lies in the fact that despite continuous advancements in imaging and molecular diagnostic technologies, there are still limitations in manual efficiency and subjective experience when it comes to massive data analysis and multi-scale feature extraction. Artificial intelligence (AI), especially algorithm systems based on deep learning, is an innovative technology capable of deeply empowering medical big data. This method utilizes algorithms such as convolutional neural networks, combined with radiomics, pathomics, and multi-modal data fusion analysis, demonstrating immense potential in early precise detection and benign-malignant differentiation of pulmonary nodules, digital pathological subtype recognition and non-invasive prediction of driver genes, precise 3D surgical planning and automatic delineation of radiotherapy target volumes, as well as dynamic risk warning during follow-up. This innovative technology provides a brand-new solution for realizing intelligent and individualized lung cancer diagnosis and treatment models. This consensus, based on the latest evidence from evidence-based medicine and combined with the development trends in the AI field and real-world clinical needs, was ultimately formed by gathering the consensus opinions of multidisciplinary experts in radiology, pathology, thoracic surgery, and other fields. The main content covers the application specifications of AI in the three core scenarios of lung cancer screening, diagnosis, and treatment, the technical standards for data collection and algorithm validation, as well as the ethical and regulatory challenges faced at the current stage. It aims to clarify the applicable boundaries of AI as a clinical auxiliary decision support tool, providing scientific guidance and standardized exploration directions for peers currently engaged in or planning to carry out AI-assisted clinical diagnosis, treatment, and translation of lung cancer.

INTRODUCTION: In this study, we aimed to compare the performance of a convolutional neural network (CNN)-based deep learning model that was trained on a dataset of normal and abnormal paediatric elbow radiographs with that of paediatric emergency department (ED) physicians on a binomial classification task. METHODS: A total of 1,314 paediatric elbow lateral radiographs (patient mean age 8.2 years) were retrospectively retrieved and classified based on annotation as normal or abnormal (with pathology). They were then randomly partitioned to a development set (993 images); first and second tuning (validation) sets (109 and 100 images, respectively); and a test set (112 images). An artificial intelligence (AI) model was trained on the development set using the EfficientNet B1 network architecture. Its performance on the test set was compared to that of five physicians (inter-rater agreement: fair). Performance of the AI model and the physician group was tested using McNemar test. RESULTS: The accuracy of the AI model on the test set was 80.4% (95% confidence interval [CI] 71.8%-87.3%), and the area under the receiver operating characteristic curve (AUROC) was 0.872 (95% CI 0.831-0.947). The performance of the AI model vs. the physician group on the test set was: sensitivity 79.0% (95% CI: 68.4%-89.5%) vs. 64.9% (95% CI: 52.5%-77.3%; P = 0.088); and specificity 81.8% (95% CI: 71.6%-92.0%) vs. 87.3% (95% CI: 78.5%-96.1%; P = 0.439). CONCLUSION The AI model showed good AUROC values and higher sensitivity, with the P-value at nominal significance when compared to the clinician group.
Humans ; Deep Learning ; Child ; Retrospective Studies ; Male ; Female ; Radiography/methods* ; ROC Curve ; Elbow/diagnostic imaging* ; Neural Networks, Computer ; Child, Preschool ; Elbow Joint/diagnostic imaging* ; Emergency Service, Hospital ; Adolescent ; Infant ; Artificial Intelligence

[This corrects the article DOI: 10.1016/j.apsb.2022.05.019.].

Background: and Purpose Limited evidence exists on the effectiveness of endovascular treatment (EVT) for acute posterior circulation tandem lesion (PCTL). This study aimed to explore the role of extracranial vertebral artery (VA) stenting in patients with PCTL stroke undergoing EVT. Methods: Individual patient data were pooled from the BASILAR (EVT for Acute Basilar Artery Occlusion Study) and PERSIST (Posterior Circulation Ischemic Stroke) registries. Patients with PCTLs who underwent EVT were included in the present cohort and divided into the stenting and nonstenting groups based on the placement of extracranial VA stents. The primary efficacy outcome was the modified Rankin Scale (mRS) scores at 90 days and 1 year. Safety outcomes included 24-hour symptomatic intracranial hemorrhage (sICH) and all-cause mortality at 90 days and 1 year post-surgery. Results: A combined dataset of 1,320 patients with posterior circulation artery occlusion, including 263 (19.9%) with tandem lesions, of whom 217 (median age, 65 years; 82.9% male) met the inclusion criteria for the analysis. The stenting group had 84 (38.7%) patients, while the non-stenting group had 133 (61.3%). After adjustment for the potential confounders, extracranial VA stenting was associated with favorable shifts in mRS scores at both 90 days (adjusted common odds ratio [OR], 2.30; 95% confidence interval [CI], 1.23–4.28; P<0.01) and 1 year (adjusted OR [aOR], 2.04; 95% CI [1.05–3.97]; P=0.04), along with lower rate of mortality at both 90 days (aOR, 0.45; 95% CI [0.21–0.93]; P=0.01) and 1 year (aOR, 0.36; 95% CI [0.16–0.79]; P=0.01), with no significant difference in sICH incidence (aOR, 0.35; 95% CI [0.06–1.98]; P=0.24). Conclusion Extracranial VA stenting during EVT may improve functional outcomes and reduce mortality in patients with PCTL strokes.

Objective:To compare the efficacy of early versus delayed reconstruction of anterior cruciate ligament (ACL) ruptures under arthroscopy.Methods:A retrospective cohort study was conducted to analyze the clinical data of 260 young adults with ACL ruptures admitted to 940th Hospital of Joint Logistic Support Force of PLA from January 2022 to June 2024, including 171 males and 89 females, aged 18-45 years [(25.6±5.9)years]. Left knee was involved in 127 patients, while the right in 133 patients. All the patients underwent arthroscopic ACL reconstruction with autologous tendon grafts, of whom 130 patients were treated within 3 months after injury (early reconstruction group) but other 130 treated at 3 months after injury (delayed reconstruction group). The operative duration and intraoperative bleeding were compared between the two groups. The incidence of medial meniscus (MM) and lateral meniscus (LM) tears and the incidence of corresponding types of tears were recorded intraoperatively in the two groups. Tegner score and Lysholm score preoperatively, at 3 months postoperatively, and at the last follow-up were detected. Visual analogue scale (VAS) scores at 3 months postoperatively and at the last follow-up and postoperative complication rate were compared between the two groups.Results:All the patients were followed up for 6-15 months [(9.1±3.2)months]. There were no significant differences in operative duration or intraoperative bleeding between the two groups ( P>0.05). The incidence of MM tears in the early reconstruction group was 22.3% (29/130), lower than 34.6% (45/130) in the delayed reconstruction group ( P<0.05). There was no significant difference in the incidence of LM tears between the two groups ( P>0.05). The incidence of MM bucket-handle tears in the early reconstruction group was 2.3% (3/130), lower than 9.2% (12/130) in the delayed reconstruction group ( P<0.05), while no significant difference in the incidence of other types of meniscus tears was found between the two groups ( P>0.05). There were no significant differences in Tegner score or Lysholm score preoperatively between the two groups ( P>0.05). At 3 months postoperatively and at the last follow-up, the Tegner scores in the early reconstruction group were (7.4±1.3)points and (8.6±0.7)points, higher than (6.4±1.5)points and (7.9±0.6)points in the delayed reconstruction group and the Lysholm scores were (82.1±7.1)points and (90.7±3.8)points in the early reconstruction group, higher than (79.5±6.8)points and (86.3±4.0)points in the delayed reconstruction group ( P<0.01). There were no significant differences in VAS scores between the two groups at 3 months postoperatively or at the last follow-up ( P>0.05). The postoperative complication rate was 8.5% (11/130) in the early reconstruction group and 12.3% (16/130) in the delayed reconstruction group ( P>0.05). Conclusion:For young patients with ACL rupture, arthroscopic reconstruction within 3 months after injury can reduce the incidence of MM tear and bucket-handle tear and improve knee function without increasing the incidence of other complications when compared with delayed reconstruction at 3 months after injury.

Objective To investigate the epidemiological characteristics of knee osteoarthritis(KOA)among military personnel in plateau regions and to explore its risk factors.Methods From July 2023 to July 2024,a multi-stage stratified cluster random sampling method was employed to survey the prevalence of KOA and related risk factors among military personnel in the northwest plateau regions of China,covering different altitudes(1500-4500 m)and geographical areas(Gansu,Qinghai,Tibet,and Xinjiang).All study subjects were divided into KOA and non-KOA groups based on the presence or absence of KOA.Variables including age,gender,body mass index(BMI),education level,smoking status,military rank,military branch,service duration,regional altitude,annual average temperature,training duration,perceived training intensity,and history of knee injury were selected for univariate analyses between groups.Variables with P<0.05 in the univariate analyses were included in the binary multifactor logistic regression to identify risk factors for KOA.Results A total of 3000 questionnaires were distributed,and 2854 valid questionnaires were collected,with a response rate of 95.13%.The sample included 2584 males and 270 females,with 510 cases of KOA,resulting in a prevalence rate of 17.9%.Univariate analysis showed that there were statistically significant differences between KOA and non-KOA groups in terms of age,BMI,smoking status,military rank,military branch,service duration,regional altitude,annual average temperature,training duration,perceived training intensity,and history of knee injury(P<0.05).However,no significant differences were found in gender and education level(P>0.05).Binary multivariate logistic regression analysis revealed that older age(OR=1.382,P=0.017),higher BMI(P<0.01),smoking(OR=1.929,P<0.01),higher military rank(OR=1.485,P=0.007),being a member of the Armed Police(P<0.01),longer service duration(P<0.01),higher regional altitude(OR=1.459,P<0.01),lower annual average temperature(OR=1.188,P=0.001),longer training duration(P<0.01),higher perceived training intensity(OR=2.450,P<0.01),and history of knee injury(OR=2.768,P=0.002)were independent risk factors for KOA.Conclusions Older age,overweight/obesity,smoking,higher military rank,being a member of the Armed Police,longer service duration,higher altitude,cold climate,longer training duration,higher training intensity,and history of knee injury are independent risk factors for KOA among military personnel in the northwest plateau regions of China.

Objective:To explore the potential advantages and application prospects of cardiopulmonary resuscitation ventilation mode (CPRV) for ventilation during CPR, through comparing of the resuscitation effect of CPRV, intermittent positive pressure ventilation (IPPV) and impedance threshold device (ITD) during advanced cardiovascular life support (ACLS).Methods:30 miniature landrace pigs [weighing (31.7±4.5) kg] were randomly divided into three groups: CPRV group, IPPV group and ITD group (10 pigs in each group). Each animal received 5 min of chest compressions only CPR after 3 min of untreated ventricular fibrillation. Then in the ACLS stage, chest compressions and mechanical ventilation (tidal volume of 7 mL/kg, respiratory rate 10 times/min) were performed according to the divided groups. Defibrillation was delivered after 16 min of ACLS, and intravenous epinephrine was administered for the pigs without return of spontaneous circulation (ROSC). A second defibrillation was delivered after 2 more minutes of CPR. Blood gases, respiratory parameters, and hemodynamic parameters were collected at baseline, ACLS 8 min and ACLS 16 min. ROSC after defibrillation was also recorded.Results:At ACLS 8 min and 16 min, intrathoracic high pressure and intrathoracic pressure variability of CPRV group were significantly higher than those of IPPV and ITD group, while the absolute value of intrathoracic negative pressure in CPRV group was higher than that in IPPV group (all P <0.01), but no difference was found between CPRV group and ITD group. The levels of arterial pH, PaO 2 and venous oxygen saturation in CPRV group were significantly higher than those in IPPV group and ITD group during ACLS, while PaCO 2 was significantly lower in CPRV group than in IPPV group and ITD group (all P <0.05). Aortic blood pressure, coronary perfusion pressure and carotid blood flow during ACLS in CPRV group were significantly higher than those in IPPV group, and right atrial pressure of CPRV group was significantly lower than that of IPPV group (all P <0.05). Coronary perfusion pressure of CPRV group was significantly higher than that of ITD group at ACLS 16 min but not ACLS 8 min, and there were no differences of aortic blood pressure and carotid blood flow between CPRV group and ITD group. The total ROSC rate in the CPRV group (90%) was significantly higher than that in the IPPV group (30%) and the ITD group (40%) (P <0.05). Conclusion:Ventilation with CPRV during ACLS showed better ventilation, oxygenation, hemodynamic effects and higher ROSC than IPPV and ITD, and the use of CPRV during CPR shows a certain application prospect.

Background: and Purpose Limited evidence exists on the effectiveness of endovascular treatment (EVT) for acute posterior circulation tandem lesion (PCTL). This study aimed to explore the role of extracranial vertebral artery (VA) stenting in patients with PCTL stroke undergoing EVT. Methods: Individual patient data were pooled from the BASILAR (EVT for Acute Basilar Artery Occlusion Study) and PERSIST (Posterior Circulation Ischemic Stroke) registries. Patients with PCTLs who underwent EVT were included in the present cohort and divided into the stenting and nonstenting groups based on the placement of extracranial VA stents. The primary efficacy outcome was the modified Rankin Scale (mRS) scores at 90 days and 1 year. Safety outcomes included 24-hour symptomatic intracranial hemorrhage (sICH) and all-cause mortality at 90 days and 1 year post-surgery. Results: A combined dataset of 1,320 patients with posterior circulation artery occlusion, including 263 (19.9%) with tandem lesions, of whom 217 (median age, 65 years; 82.9% male) met the inclusion criteria for the analysis. The stenting group had 84 (38.7%) patients, while the non-stenting group had 133 (61.3%). After adjustment for the potential confounders, extracranial VA stenting was associated with favorable shifts in mRS scores at both 90 days (adjusted common odds ratio [OR], 2.30; 95% confidence interval [CI], 1.23–4.28; P<0.01) and 1 year (adjusted OR [aOR], 2.04; 95% CI [1.05–3.97]; P=0.04), along with lower rate of mortality at both 90 days (aOR, 0.45; 95% CI [0.21–0.93]; P=0.01) and 1 year (aOR, 0.36; 95% CI [0.16–0.79]; P=0.01), with no significant difference in sICH incidence (aOR, 0.35; 95% CI [0.06–1.98]; P=0.24). Conclusion Extracranial VA stenting during EVT may improve functional outcomes and reduce mortality in patients with PCTL strokes.

With the widespread adoption of low-dose CT screening and the extensive application of high-resolution CT, the detection rate of sub-centimeter lung nodules has significantly increased. How to scientifically manage these nodules while avoiding overtreatment and diagnostic delays has become an important clinical issue. Among them, lung nodules with a consolidation tumor ratio less than 0.25, dominated by ground-glass shadows, are particularly worthy of attention. The therapeutic challenge for this group is how to achieve precise and complete resection of nodules during surgery while maximizing the preservation of the patient's lung function. The "watershed topography map" is a new technology based on big data and artificial intelligence algorithms. This method uses Dicom data from conventional dose CT scans, combined with microscopic (22-24 levels) capillary network anatomical watershed features, to generate high-precision simulated natural segmentation planes of lung sub-segments through specific textures and forms. This technology forms fluorescent watershed boundaries on the lung surface, which highly fit the actual lung anatomical structure. By analyzing the adjacent relationship between the nodule and the watershed boundary, real-time, visually accurate positioning of the nodule can be achieved. This innovative technology provides a new solution for the intraoperative positioning and resection of lung nodules. This consensus was led by four major domestic societies, jointly with expert teams in related fields, oriented to clinical practical needs, referring to domestic and foreign guidelines and consensus, and finally formed after multiple rounds of consultation, discussion, and voting. The main content covers the theoretical basis of the "watershed topography map" technology, indications, operation procedures, surgical planning details, and postoperative evaluation standards, aiming to provide scientific guidance and exploration directions for clinical peers who are currently or plan to carry out lung nodule resection using the fluorescent microscope watershed analysis method.

Background: and Purpose Limited evidence exists on the effectiveness of endovascular treatment (EVT) for acute posterior circulation tandem lesion (PCTL). This study aimed to explore the role of extracranial vertebral artery (VA) stenting in patients with PCTL stroke undergoing EVT. Methods: Individual patient data were pooled from the BASILAR (EVT for Acute Basilar Artery Occlusion Study) and PERSIST (Posterior Circulation Ischemic Stroke) registries. Patients with PCTLs who underwent EVT were included in the present cohort and divided into the stenting and nonstenting groups based on the placement of extracranial VA stents. The primary efficacy outcome was the modified Rankin Scale (mRS) scores at 90 days and 1 year. Safety outcomes included 24-hour symptomatic intracranial hemorrhage (sICH) and all-cause mortality at 90 days and 1 year post-surgery. Results: A combined dataset of 1,320 patients with posterior circulation artery occlusion, including 263 (19.9%) with tandem lesions, of whom 217 (median age, 65 years; 82.9% male) met the inclusion criteria for the analysis. The stenting group had 84 (38.7%) patients, while the non-stenting group had 133 (61.3%). After adjustment for the potential confounders, extracranial VA stenting was associated with favorable shifts in mRS scores at both 90 days (adjusted common odds ratio [OR], 2.30; 95% confidence interval [CI], 1.23–4.28; P<0.01) and 1 year (adjusted OR [aOR], 2.04; 95% CI [1.05–3.97]; P=0.04), along with lower rate of mortality at both 90 days (aOR, 0.45; 95% CI [0.21–0.93]; P=0.01) and 1 year (aOR, 0.36; 95% CI [0.16–0.79]; P=0.01), with no significant difference in sICH incidence (aOR, 0.35; 95% CI [0.06–1.98]; P=0.24). Conclusion Extracranial VA stenting during EVT may improve functional outcomes and reduce mortality in patients with PCTL strokes.