Immune checkpoint inhibitors (ICIs) have significantly improved the prognosis of patients with lung cancer. However, checkpoint inhibitor-related pneumonitis (CIP), as one of the most severe immune-related adverse events, lacks well-defined diagnostic criteria and reliable risk stratification tools. Radiomics enables high-throughput feature extraction from computed tomography images and provides a non-invasive technical approach for the early identification and risk stratification of CIP. This article systematically reviews the recent advances in the application of radiomics to risk prediction, diagnosis and differential diagnosis, and prognostic evaluation of CIP in lung cancer immunotherapy. Furthermore, it explores the value of integrating radiomics with multi-omics data in elucidating the pathogenesis of CIP, as well as the role of explainable artificial intelligence (XAI) in enhancing the clinical trustworthiness of models. .
Lung cancer is one of the malignancies with the highest incidence and mortality rates worldwide, with non-small cell lung cancer (NSCLC) accounting for the vast majority. Patients with postoperative central nervous system (CNS) metastasis have a dismal prognosis, highlighting the urgent need for more precise molecular biomarkers. Although circulating tumor DNA (ctDNA)-based molecular residual disease (MRD) testing can predict postoperative recurrence, its utility in detecting CNS metastasis remains debated. This review examines the association between MRD status and CNS recurrence risk, synthesizes evidence linking MRD status to overall survival (OS), and explores mechanisms underlying false-negative results of peripheral blood MRD in CNS metastasis detection alongside potential clinical strategies. Current evidence indicates that MRD positivity correlates with increased overall recurrence risk and shortened OS; some studies suggest a potential increase in CNS recurrence, yet direct evidence specifically targeting intracranial recurrence-free survival (iRFS) remains insufficient. MRD-negative patients generally have favorable prognosis; however, a subset of high-risk patients - those with epidermal growth factor receptor (EGFR) mutations, stage III disease, or adenocarcinoma - may still develop isolated CNS metastases, primarily due to the blood-brain barrier limiting ctDNA release. Adjuvant Osimertinib reduces CNS recurrence risk, though recurrence remains high within the first year after treatment discontinuation. MRD status serves as an important prognostic stratification tool after NSCLC resection, but negative peripheral blood MRD does not completely exclude CNS recurrence risk. Comprehensive assessment integrating imaging, risk factors, and cerebrospinal fluid testing is therefore warranted. .
Extensive-stage small cell lung cancer (ES-SCLC) is characterized by rapid progression, a high risk of recurrence, and poor prognosis, and remains a major therapeutic challenge in lung cancer. In recent years, immune checkpoint inhibitors combined with Platinum-Etoposide chemotherapy have become the standard first-line treatment for ES-SCLC, driving a shift from conventional chemotherapy toward multimodal combination strategies and precision-guided patient stratification, while creating both new opportunities and challenges for further therapeutic improvement. Following the clinical treatment pathway, this review summarizes advances in multidisciplinary combination treatment for ES-SCLC, including chemotherapy, immunotherapy, targeted therapy, radiotherapy, and traditional Chinese medicine, with emphasis on standard regimens, maintenance therapy, clinical limitations, and emerging research directions. This review aimed to provide a reference for individualized treatment and comprehensive disease management of ES-SCLC in the era of precision medicine. .
Brain metastasis in non-small cell lung cancer (NSCLC) is shaped by continuous interactions between tumor cells and the brain-specific microenvironment. Vascular, glial and immune components contribute to intracranial colonization, immune escape and therapeutic resistance, while single-cell and spatial omics reveal heterogeneity in cellular states, communication networks and spatial niches. This review summarizes NSCLC brain metastasis and intracranial colonization, the brain metastatic microenvironment and tumor-microenvironment interactions, and discusses the heterogeneity revealed by single-cell and spatial omics and its potential relevance to therapeutic response and patient stratification. .
Immune checkpoint inhibitors combined with Platinum-based Etopositde chemotherapy have become the first-line standard treatment for extensive-stage small cell lung cancer (ES-SCLC). However, treatment benefit varies substantially among patients, and the proportion of long-term survivors remains limited. In recent years, the molecular classification framework comprising SCLC-A, SCLC-N, SCLC-P and SCLC-I, based on the expression patterns of ASCL1, NEUROD1 and POU2F3 as well as immune-inflammatory status, has provided a new basis for understanding the heterogeneity of immunotherapy response and for developing precision stratified treatment in ES-SCLC. To standardize the clinical translation of molecular subtyping in ES-SCLC immunotherapy, this consensus was developed by multidisciplinary experts from respiratory medicine, oncology, pathology, radiation oncology, and basic medical sciences. Based on domestic and international evidence and clinical experience, the consensus provides recommendations on key issues, including first-line immunotherapy for ES-SCLC, molecular subtyping systems and immune microenvironment characteristics, testing and implementation pathways, immunotherapy-related biomarkers, subtype-informed treatment strategies, and dynamic monitoring. This consensus emphasizes that molecular subtyping should currently be positioned as a tool for biological and clinical research stratification based on standard treatment, and should not be used as an independent basis for treatment decisions. Immunohistochemistry can serve as an important method for qualified centers to conduct subtyping exploration and translational research. The SCLC-I subtype may provide a useful reference for biomarker-based stratification and immunotherapy benefit prediction. For different subtypes, delta-like ligand 3 (DLL3)-targeted therapy, epigenetic regulation, the MYC/AURKA axis, and poly (ADP-ribose) polymerase (PARP) inhibitors can be important choices for subsequent treatment optimization. This consensus aims to standardize pathological testing and clinical application of molecular subtyping in ES-SCLC, facilitate stratified management and individualized treatment optimization based on molecular subtypes, and provide a foundation for building a precision immunotherapy system. .
