A thorough interrogation of the immune landscape is crucial for immunotherapy strategy selection and prediction of clinical responses in non-small-cell lung cancer (NSCLC) patients. Single-cell RNA sequencing (scRNA-seq) techniques have prompted the opportunity to dissect the distinct immune signatures between lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC), the two major subtypes of NSCLC. Here, we performed scRNA-seq on 72,475 immune cells from 40 samples of tumor and matched adjacent normal tissues spanning 19 NSCLC patients, and drew a systematic immune cell transcriptome atlas. Joint analyses of the distinct cellular compositions, differentially expressed genes (DEGs), cell–cell interactions, pseudotime trajectory, transcriptomic factors and prognostic factors based on The Cancer Genome Atlas (TCGA), revealed the central roles of cytotoxic and effector T and NK cells and the distinct functional macrophages (Mφ) subtypes in the immune microenvironment heterogeneity between LUAD and LUSC. The dominant subtype of Mφ was FABP4-Mφ in LUAD and SPP1-Mφ in LUSC. Importantly, we identified a novel lymphocyte-related Mφ cluster, which we named SELENOP-Mφ, and further established its antitumor role in both types, especially in LUAD. Our comprehensive depiction of the immune heterogeneity and definition of Mφ clusters could help design personalized treatment for lung cancer patients in clinical practice.

Lung cancer is one of the most leading causes of death throughout the world, and the precision medical management of it is of urgent requirement. Artificial intelligence (AI) consisting of numerous advanced techniques has been widely applied in the field of medical care. Meanwhile, radiomics based on traditional machine learning also does a great job in mining information through medical images. With the integration of AI and radiomics, great progress has been made in the early diagnosis, specific characterization, and prognosis of lung cancer, which has aroused attention all over the world. In this study, we gave a brief review of the current application of AI and radiomics for precision medical management in lung cancer.

Background: Diagnosis of multiple lung nodules has become convenient and frequent due to the improvement of computed tomography (CT) scans. However, to distinguish intrapulmonary metastasis (IPM) from multiple primary lung cancer (MPLC) remains challenging. Herein, for the accurate optimization of therapeutic options, we propose a comprehensive algorithm for multiple lung carcinomas based on a multidisciplinary approach, and investigate the prognosis of patients who underwent surgical resection.Methods: Patients with multiple lung carcinomas who were treated at West China Hospital of Sichuan University from April, 2009 to December, 2017, were retrospectively identified. A comprehensive algorithm combining histologic assessment, molecular analysis, and imaging information was used to classify nodules as IPM or MPLC. The Kaplan-Meier method was used to estimate survival rates, and the relevant factors were evaluated using the log-rank test or Cox proportional hazards model. Results:The study included 576 patients with 1,295 lung tumors in total. Significant differences were observed between the clinical features of 171 patients with IPM and 405 patients with MPLC. The final classification consistency was 0.65 and 0.72 compared with the criteria of Martini and Melamed (MM) and the American College of Chest Physicians (ACCP), respectively. Patients with independent primary tumors had better overall survival (OS) than patients with intra-pulmonary metastasis (HR =3.99, 95% CI: 2.86-5.57; P<0.001). Nodal involvement and radiotherapy were independent prognostic factors. Conclusions:The comprehensive algorithm was a relevant tool for classifying multifocal lung tumors as MPLC or IPM, and could help doctors with precise decision-making in routine clinical practice. Patients with multiple lesions without lymph node metastasis or without radiotherapy tended to have a better prognosis.

Background The advent of immune checkpoint inhibitors (ICIs) therapy has resulted in significant survival benefits in patients with non-small-cell lung cancer (NSCLC) without increasing toxicity. However, the utilisation of immunotherapy for small-cell lung cancer (SCLC) remains unclear, with a scarcity of systematic comparisons of therapeutic effects and safety of immunotherapy in these two major lung cancer subtypes. Herein, we aimed to provide a comprehensive landscape of immunotherapy and systematically review its specific efficacy and safety in advanced lung cancer, accounting for histological types. Methods We identified studies assessing immunotherapy for lung cancer with predefined endpoints, including overall survival (OS), progression-free survival (PFS), objective response rate (ORR), and treatment-related adverse events (TRAE), from PubMed, Embase, Medline, and Cochrane library. A random-effects or fixed-effect model was adopted according to different settings. Results Overall, 38 trials with 20,173 patients with lung cancer were included in this study. ICI therapy resulted in a significantly prolonged survival in both patients with NSCLC and SCLC when compared with chemotherapy (hazard ratio [HR] = 0.74; 95% confidence interval [CI], 0.70–0.79] and [HR = 0.82; 95% CI, 0.75–0.90], respectively). The magnitude of disease control and survival benefits appeared superior with ICI plus standard of care (SOC) when compared with SOC alone. OS and PFS advantages were observed only when immunotherapy was employed as the first-line treatment in patients with SCLC. Conclusion ICI therapy is a promising therapeutic option in patients with NSCLC and SCLC. ICI plus SOC can be recommended as the optimal first-line treatment for patients with SCLC, and double-target ICIs combined with SOC are recommended in patients with NSCLC as both the first and subsequent lines of treatment. Additionally, non-first-line immunotherapy is not recommended in patients with SCLC.

Respiratory diseases impose a tremendous global health burden on large patient populations. In this study, we aimed to develop DeepMRDTR, a deep learning-based medical image interpretation system for the diagnosis of major respiratory diseases based on the automated identification of a wide range of radiological abnormalities through computed tomography (CT) and chest X-ray (CXR) from real-world, large-scale datasets. DeepMRDTR comprises four networks (two CT-Nets and two CXR-Nets) that exploit contrastive learning to generate pre-training parameters that are fine-tuned on the retrospective dataset collected from a single institution. The performance of DeepMRDTR was evaluated for abnormality identification and disease diagnosis on data from two different institutions: one was an internal testing dataset from the same institution as the training data and the second was collected from an external institution to evaluate the model generalizability and robustness to an unrelated population dataset. In such a difficult multi-class diagnosis task, our system achieved the average area under the receiver operating characteristic curve (AUC) of 0.856 (95% confidence interval (CI):0.843–0.868) and 0.841 (95%CI:0.832–0.887) for abnormality identification, and 0.900 (95%CI:0.872–0.958) and 0.866 (95%CI:0.832–0.887) for major respiratory diseases’ diagnosis on CT and CXR datasets, respectively. Furthermore, to achieve a clinically actionable diagnosis, we deployed a preliminary version of DeepMRDTR into the clinical workflow, which was performed on par with senior experts in disease diagnosis, with an AUC of 0.890 and a Cohen’s k of 0.746–0.877 at a reasonable timescale; these findings demonstrate the potential to accelerate the medical workflow to facilitate early diagnosis as a triage tool for respiratory diseases which supports improved clinical diagnoses and decision-making.