OBJECTIVES: Non-small cell lung cancer (NSCLC) is associated with poor prognosis, with 30% of patients diagnosed at an advanced stage. Mutations in the EGFR and KRAS genes are important prognostic factors for NSCLC, and targeted therapies can significantly improve survival in these patients. Although tissue biopsy remains the gold standard for detecting gene mutations, it has limitations, including invasiveness, sampling errors due to tumor heterogeneity, and poor reproducibility. This study aims to develop machine learning models based on radiomic features to predict EGFR and KRAS gene mutation status in NSCLC patients, thereby providing a reference for precision oncology. METHODS: Imaging and mutation data from eligible NSCLC patients were obtained from the publicly available Lung-PET-CT-Dx dataset in The Cancer Imaging Archive (TCIA). A three-dimensional-convolutional neural network (3D-CNN) was used to extract imaging features from the regions of interest (ROI). The LightGBM algorithm was employed to build classification models for predicting EGFR and KRAS gene mutation status. Model performance was evaluated using 5-fold cross-validation, with receiver operator characteristic (ROC) curves, area under the curve (AUC), accuracy, sensitivity, and specificity used for validation. RESULTS: The models effectively predicted EGFR and KRAS mutations in NSCLC patients, achieving an AUC of 0.95 for EGFR mutations and 0.90 for KRAS. The models also demonstrated high accuracy (EGFR 89.66%; KRAS 87.10%), sensitivity (EGFR 93.33%; KRAS 87.50%), and specificity (EGFR 85.71%; KRAS 86.67%). CONCLUSIONS A radiogenomics-machine learning predictive model can serve as a non-invasive tool for anticipating EGFR and KRAS gene mutation status in NSCLC patients.
Humans ; Carcinoma, Non-Small-Cell Lung/diagnostic imaging* ; Lung Neoplasms/diagnostic imaging* ; Mutation ; Proto-Oncogene Proteins p21(ras)/genetics* ; ErbB Receptors/genetics* ; Machine Learning ; Positron Emission Tomography Computed Tomography ; Female ; Male ; Neural Networks, Computer ; Middle Aged ; Aged

Tumor is a serious threat to human health. At present, surgical resection, chemoradiotherapy, targeted therapy and immunotherapy are the main therapeutic strategies. Monoclonal antibody has gradually become an indispensable drug type in the clinical treatment of cancer due to its high efficiency and low toxicity. Phage antibody library technology (PALT) is a novel monoclonal antibody preparation technique. The recombinant immunoglobulin variable region of heavy chain (VH)/variable region of light chain (VL) gene is integrated into the phage vector, and the antibody is expressed on the phage surface in the form of fusion protein to obtain a diverse antibody library. Through the process of adsorption-elution-amplification, the antibody library can be screened to obtain the antibody molecule with specific binding antigen as well as its gene sequence. PALT has the advantages of short antibody production cycle, strong plasticity of antibody structure, large antibody yield, high diversity and direct production of humanized antibodies. It has been used in screening tumor markers and preparation of antibody drugs for breast cancer, gastric cancer, lung cancer and liver cancer. This article reviews the recent progress and the application of PALT in tumor therapy.
Humans ; Bacteriophages/genetics* ; Immunoglobulin Variable Region/genetics* ; Gene Library ; Antibodies, Monoclonal/therapeutic use* ; Immunotherapy ; Peptide Library

Malignant tumors are diseases that seriously threaten human health and social development. Traditional tumor therapies such as surgery, radiotherapy, chemotherapy and targeted therapy cannot fully meet the needs of clinical treatment, and emerging immunotherapy has become a research hotspot in the field of tumor treatment. Immune checkpoint inhibitors (ICIs) have been approved as a tumor immunotherapy method for the treatment of various tumors, such as lung cancer, liver cancer, stomach cancer and colorectal cancer, etc. However, during the clinical use of ICIs, only a small number of patients experienced durable responses, which also led to drug resistance and adverse reactions. Therefore, the identification and development of predictive biomarkers is crucial to improve the therapeutic efficacy of ICIs. The predictive biomarkers of tumor ICIs mainly include tumor biomarkers, tumor microenvironment biomarkers, circulation-related biomarkers, host environmental biomarkers and combinatorial biomarkers. They are of great significance for screening, individualized treatment and prognosis evaluation of tumor patients. This article reviews the advances of predictive markers for tumor ICIs therapy.
Humans ; Immune Checkpoint Inhibitors/therapeutic use* ; Lung Neoplasms ; Biomarkers ; Immunotherapy/methods* ; Biomarkers, Tumor/genetics* ; Prognosis ; Tumor Microenvironment

The estimated new cases of breast cancer (BC) patients were 2.26 million in 2020, which accounted for 11.7% of all cancer patients, making it the most prevalent cancer worldwide. Early detection, diagnosis and treatment are crucial to reduce the mortality, and improve the prognosis of BC patients. Despite the widespread use of mammography screening as a tool for BC screening, the false positive, radiation, and overdiagnosis are still pressing issues that need to be addressed. Therefore, it is urgent to develop accessible, stable, and reliable biomarkers for non-invasive screening and diagnosis of BC. Recent studies indicated that the circulating tumor cell DNA (ctDNA), carcinoembryonic antigen (CEA), carbohydrate antigen 15-3 (CA15-3), extracellular vesicles (EV), circulating miRNAs and BRCA gene from blood, and the phospholipid, miRNAs, hypnone and hexadecane from urine, nipple aspirate fluid (NAF) and volatile organic compounds (VOCs) in exhaled gas were closely related to the early screening and diagnosis of BC. This review summarizes the advances of the above biomarkers in the early screening and diagnosis of BC.
Humans ; Female ; Biomarkers, Tumor ; Early Detection of Cancer ; Breast Neoplasms/diagnosis* ; Prognosis ; MicroRNAs/genetics*

Medical ethics is the standard ofbehavior toadjust the relationship between medical personnel and patients,medical personnel,medical personnel and society.It is a general social morality in medical field in special performance.Teachers should carry through the ethics education to the end,making students smoothly enter society from the school,cultivating good ethics during the process of learning basic knowledge of oral cavity,and developing high-quality oral physicians for our country.