Objective To investigate the expression characteristics, prognostic value, and correlation with immune infiltration of vasoactive intestinal peptide receptor 2 (VIPR2) in esophageal adenocarcinoma (ESAD). Methods Transcriptome data of 80 ESAD and 10 normal tissues were retrieved from the TCGA database. Immune-related differential genes were identified by integrating the ImmPort database. Cox regression analysis was applied to evaluate the prognostic significance of VIPR2. GSVA and ssGSEA were employed to assess the association between VIPR2 and immune-cell infiltration. Functional enrichment was performed using GO, KEGG, and GSEA. Results VIPR2 expression was significantly downregulated in ESAD tissues (P<0.05). High VIPR2 expression was associated with prolonged overall survival (HR=0.246, P=0.047), serving as an independent prognostic factor. Fifteen immune-cell types, including CD8⁺ T cells, NK cells, and dendritic cells, showed significantly higher infiltration in the VIPR2-high group, whereas Th17-cell abundance was decreased (P<0.05). Enrichment analyses revealed that VIPR2 participated in multiple tumor-immune pathways and was positively correlated with PD-1 and CTLA-4 expression (P<0.01). Conclusion VIPR2 may serve as a potential biomarker in the prognostic assessment and could modulate the tumor-immune microenvironment in ESAD.

Nowadays, lung cancer is the most common and lethal invasive tumor type in Chinese population, challenging overall health level. However, personalized early-stage treatment is currently still not widely implemented, and the choice of treatment highly depends on experience of physician. Based on deep learning and radiomics principles, deep-radiomics is important for establishing objective and promotable precision medicine plans. Among all aspects, the explainability of a model is critical for its usage in clinical practice. This paper discusses the technical aspects of explainable deep-radiomics in lung cancer, and analyzes challenges we are facing. Non-fully supervised learning methods, as a current hotspot in deep learning technology, can construct more trustworthy and practically valuable deep learning models through the co-design method of performance-interpretability. Medical artificial intelligence faces three core challenges in transitioning from the laboratory to hospitals: high-level cognitive demands, data privacy and generalization capabilities, and regulatory compliance. However, with appropriate design, non-fully supervised learning holds the greatest potential to bridge the gap between design and application, enabling broader adoption.

Objective To propose a lung artery segmentation method that integrates shape and position prior knowledge, aiming to solve the issues of inaccurate segmentation caused by the high similarity and small size differences between the lung arteries and surrounding tissues in CT images. Methods Based on the three-dimensional U-Net network architecture and relying on the PARSE 2022 database image data, shape and position prior knowledge was introduced to design feature extraction and fusion strategies to enhance the ability of lung artery segmentation. The data of the patients were divided into three groups: a training set, a validation set, and a test set. The performance metrics for evaluating the model included Dice Similarity Coefficient (DSC), sensitivity, accuracy, and Hausdorff distance (HD95). Results The study included lung artery imaging data from 203 patients, including 100 patients in the training set, 30 patients in the validation set, and 73 patients in the test set. Through the backbone network, a rough segmentation of the lung arteries was performed to obtain a complete vascular structure; the branch network integrating shape and position information was used to extract features of small pulmonary arteries, reducing interference from the pulmonary artery trunk and left and right pulmonary arteries. Experimental results showed that the segmentation model based on shape and position prior knowledge had a higher DSC (82.81%±3.20% vs. 80.47%±3.17% vs. 80.36%±3.43%), sensitivity (85.30%±8.04% vs. 80.95%±6.89% vs. 82.82%±7.29%), and accuracy (81.63%±7.53% vs. 81.19%±8.35% vs. 79.36%±8.98%) compared to traditional three-dimensional U-Net and V-Net methods. HD95 could reach (9.52±4.29) mm, which was 6.05 mm shorter than traditional methods, showing excellent performance in segmentation boundaries. Conclusion The lung artery segmentation method based on shape and position prior knowledge can achieve precise segmentation of lung artery vessels and has potential application value in tasks such as bronchoscopy or percutaneous puncture surgery navigation.

Objective To develop an artificial intelligence (AI)-driven lung cancer database by structuring and standardizing clinical data, enabling advanced data mining for lung cancer research, and providing high-quality data for real-world studies. Methods Building on the extensive clinical data resources of the Department of Thoracic Surgery at Peking Union Medical College Hospital, this study utilized machine learning techniques, particularly natural language processing (NLP), to automatically process unstructured data from electronic medical records, examination reports, and pathology reports, converting them into structured formats. Data governance and automated cleaning methods were employed to ensure data integrity and consistency. Results As of September 2024, the database included comprehensive data from 18 811 patients, encompassing inpatient and outpatient records, examination and pathology reports, physician orders, and follow-up information, creating a well-structured, multi-dimensional dataset with rich variables. The database’s real-time querying and multi-layer filtering functions enabled researchers to efficiently retrieve study data that meet specific criteria, significantly enhancing data processing speed and advancing research progress. In a real-world application exploring the prognosis of non-small cell lung cancer, the database facilitated the rapid analysis of prognostic factors. Research findings indicated that factors such as tumor staging and comorbidities had a significant impact on patient survival rates, further demonstrating the database’s value in clinical big data mining. Conclusion The AI-driven lung cancer database enhances data management and analysis efficiency, providing strong support for large-scale clinical research, retrospective studies, and disease management. With the ongoing integration of large language models and multi-modal data, the database’s precision and analytical capabilities are expected to improve further, providing stronger support for big data mining and real-world research of lung cancer.

Objective To explore the application of artificial intelligence (AI) in the standardized training of thoracic surgery residents, specifically in enhancing clinical skills and anatomical understanding through AI-assisted lung nodule identification and lung segment anatomy teaching. Methods Thoracic surgery residents undergoing standardized training at Peking Union Medical College Hospital from September 2023 to September 2024 were selected. They were randomly assigned to a trial group and a control group using a random number table. The trial group used AI-assisted three-dimensional reconstruction technology for lung nodule identification, while the control group used conventional chest CT images. After basic teaching and self-practice, the ability to identify lung nodules on the same patient CT images was evaluated, and feedback was collected through questionnaires. Results A total of 72 residents participated in the study, including 30 (41.7%) males and 42 (58.3%) females, with an average age of (24.0±3.0) years. The trial group showed significantly better overall diagnostic accuracy for lung nodules (91.9% vs. 73.3%) and lung segment identification (100.0% vs. 83.70%) compared to the control group, and the reading time was significantly shorter [ (118.5±10.5) s vs. (332.1±20.2) s, P<0.01]. Questionnaire results indicated that 94.4% of the residents had a positive attitude toward AI technology, and 91.7% believed that it improved diagnostic accuracy. Conclusion AI-assisted teaching significantly improves thoracic surgery residents’ ability to read images and clinical thinking, providing a new direction for the reform of standardized training.

Lung cancer, particularly non-small cell lung cancer (NSCLC), is a leading cause of cancer-related mortality worldwide. In recent years, metabolomics has emerged as a key systems biology approach for analyzing small-molecule metabolites in cells, tissues and organisms. It provides new strategies for early diagnosis and metabolic profiling. Additionally, metabolomics plays a crucial role in studying resistance mechanisms in lung cancer. Tumor cell metabolic reprogramming is a key driving factor in the initiation and progression of lung cancer. Metabolomics studies have revealed how lung cancer cells regulate critical pathways such as energy metabolism, lipid metabolism, and amino acid metabolism to adapt to the demands of rapid proliferation and invasive metastasis. This review summarizes the latest advances in metabolomics research in lung cancer, focusing on the characteristics of metabolic reprogramming, the identification of potential metabolic biomarkers, and the prospects of metabolomics in early diagnosis and the elucidation of resistance mechanisms in lung cancer.
.
Humans ; Metabolomics/methods* ; Lung Neoplasms/pathology* ; Animals ; Biomarkers, Tumor/metabolism*

Thymoma is a malignant tumor originating from thymus epithelial cells, with an incidence of 1.3-2.6 per million. Due to its low incidence, lack of cells and animal models, there are relatively few studies on thymoma, and its diagnosis and treatment progress is relatively slow. The update of 5th edition of WHO Classification of Thoracic Tumors in 2021 and the NCCN( National Comprehensive Cancer Network) Clinical Practice Guidelines in Oncology: Thymoma and Thymoma Cancer in 2024 put forward many new views and suggestions on the diagnosis and treatment strategy of thymoma. This article reviews the research and treatment of thymoma based on the latest research progress in recent years, aiming to improve the clinician's understanding of thymoma, provide reference for treatment, and promote the research of thymoma.

Thymoma is a malignant tumor originating from thymus epithelial cells, with an incidence of 1.3-2.6 per million. Due to its low incidence, lack of cells and animal models, there are relatively few studies on thymoma, and its diagnosis and treatment progress is relatively slow. The update of 5th edition of WHO Classification of Thoracic Tumors in 2021 and the NCCN( National Comprehensive Cancer Network) Clinical Practice Guidelines in Oncology: Thymoma and Thymoma Cancer in 2024 put forward many new views and suggestions on the diagnosis and treatment strategy of thymoma. This article reviews the research and treatment of thymoma based on the latest research progress in recent years, aiming to improve the clinician's understanding of thymoma, provide reference for treatment, and promote the research of thymoma.

Due to the advancement of 16S rRNA sequencing technology, the lower respiratory tract microbiota, which was considered non-existent, has been revealed. The correlation between these microorganisms and diseases such as tumor has been a hot topic in recent years. As the bacteria in the surrounding can infiltrate the tumors, researchers have also begun to pay attention to the biological behavior of tumor bacteria and their interaction with tumors. In this review, we present the characteristic of the lower respiratory tract bacteria and summarize recent research findings on the relationship between these microbiota and lung cancer. On top of that, we also summarize the basic feature of bacteria in tumors and focus on the characteristic of the bacteria in lung cancer. The relationship between bacteria in lung cancer and tumor development is also been discussed. Finally, we review the potential clinical applications of bacterial communities in the lower respiratory tract and lung cancer, and summarize key points of sample collection, sequencing, and contamination control, hoping to provide new ideas for the screening and treatment of tumors.
.
Humans ; Lung Neoplasms ; RNA, Ribosomal, 16S/genetics* ; Bacteria/genetics* ; Microbiota ; Respiratory System ; Lung/microbiology*

Objective:To summarize and analyze the clinical outcome of minimally invasive McKeown esophagectomy for esophageal squamous cell carcinoma.Methods:We retrospectively analyzed the clinical data of patients with esophageal squamous cell carcinoma who received minimally invasive McKeown esophagectomy in Peking Union Medical College Hospital from January 2017 to December 2022. Improved anesthesia methods, monitoring of recurrent laryngeal nerve, minimally invasive gastrostomy, and jejunostomy techniques were introduced in surgical procedure. We evaluated perioperative data and long-term follow-up survival in these patients.Results:A total of 226 esophageal squamous cell carcinoma patients who met the inclusion and exclusion criteria were enrolled, of which 48.2% received neoadjuvant therapy. The mean operation time was( 327 ± 68) min, with a total of 40.5(33, 50) lymph nodes and 27(19, 33) thoracic lymph nodes harvested. The postoperative hospital stay was 9(7, 12) days, and the postoperative complication rate was 36.3%. In terms of learning curve, after 50 patients intraoperative blood loss, postoperative hospital stay, and recurrent laryngeal nerve injury rate were significantly decreased. The number of total lymph nodes, thoracic lymph nodes, and the 106tbl harvested was significantly increased. The median follow-up time was 23.5(14, 47) months, with a loss of follow-up rate of 3.5%. The overall 2-year and 5-year survival rates were 82.6% and 71.8%, respectively.Conclusion:Improved minimally invasive McKeown esophagectomy for esophageal squamous cell carcinoma are safe and acceptable. Learning curve can be shortened, with increased lymph node harvested and decreased postoperative complications, which improving the short-term and long-term outcomes of patients.