Effectively Integrating CNN and Low-Complexity Transformer for Lung Cancer Tumor Prediction After Neoadjuvant Chemoimmunotherapy

e20071 Background: In recent years, multiple neoadjuvant treatment options have emerged for driver gene–positive, resectable Non-Small Cell Lung Cancer (NSCLC). However, the long-term prognosis of different treatment modalities and the specific populations that benefit most remain unclear. This study retrospectively compares multiple neoadjuvant and adjuvant strategies for driver gene–positive NSCLC, aiming to provide a reference for clinical decision-making. Methods: The medical records of patients with driver-gene-positive NSCLC who received neoadjuvant therapy and upfront surgery (US) with adjuvant targeted therapy (ATT) at Shandong Cancer Hospital and Institute from January 2021 to December 2023 were retrospectively reviewed. Patients were grouped into neoadjuvant targeted therapy (NTT), neoadjuvant chemoimmunotherapy (NCIT), neoadjuvant chemotherapy (NCT), and US+ATT. event-free survival (EFS) and overall survival (OS) were compared across the groups, and the subgroup analysis including pathological response and PD-L1 expression levels. Kaplan-Meier curves and log-rank tests were used to assess prognostic differences. Results: A total of 243 patients were included, and the median follow-up times for the NTT (n=39), NCIT (n=67), NCT (n=45), and US+ATT (n=92) groups were 23.05, 24.4, 24.9, and 23.7 months, respectively. NCIT significantly prolonged EFS compared with NCT (p=0.004). Focusing on patients with EGFR mutations, NTT combined with ATT showed no significant EFS or OS difference from NTT alone (p=0.124), but demonstrated a trend toward better EFS compared with US+ATT (after 1:1 propensity-score matching) (p=0.062). Compared with NCIT, NTT±ATT show no survival benefits; however, NCIT significantly improved EFS (p=0.001) over NCT without ATT with no OS benefit (p=0.234), and no major prognosis differences were observed between NCIT and NCT+ATT. Furthermore, among patients receiving NCIT, those who achieved a major pathological response (MPR) demonstrated significantly improved EFS (p=0.001) and OS (p=0.018). In the EGFR-mutant subgroup treated with NCIT, MPR status showed no significant impact on either EFS (p=0.128) or OS (p=0.221). Similarly, MPR status did not significantly influence survival outcomes in patients receiving NTT. Additionally, PD-L1 expression was not associated with survival outcomes. Conclusions: In patients with resectable, driver gene–positive NSCLC, NTT+ATT, NCT+ATT, and NCIT all demonstrate feasibility. Pathological response following NCIT was correlated with prognosis, suggesting it may serve as an important indicator for prognostic prediction. In the future, large-scale studies are warranted to further elucidate the long-term efficacy of different treatment strategies and to identify the patient populations most likely to benefit.

Neoadjuvant chemo-immunotherapy has increased the number of patients with advanced lung cancer eligible for surgery. However, only a small number of such patients respond to this approach. Intensive research is being conducted to identify biomarkers to predict the efficacy of neoadjuvant chemo-immunotherapy. Among these, blood predictive biomarkers are particularly promising, and have the advantages of being both non-invasive and cost effective. This study aims to evaluate the predictive value of blood biomarkers in determining the efficacy of neoadjuvant chemo-immunotherapy for patients with non-small cell lung cancer (NSCLC), addressing a critical need for more personalized treatment strategies in clinical practice. We retrospectively collected the data of 199 NSCLC patients who received neoadjuvant chemo-immunotherapy from January 1, 2021 to December 31, 2023, at Zhejiang Cancer Hospital. We then analyzed the performance of blood biomarkers in predicting the efficacy of neoadjuvant chemo-immunotherapy. The patients in the major pathological response (MPR) group had significantly higher pre-treatment squamous cell carcinoma antigen (SCCA) levels, and a significantly lower post-treatment platelet-lymphocyte ratio (PLR) than those in the non-MPR group. For patients with higher pre-treatment SCCA levels, the 1- and 2-year event-free survival (EFS) rates were 97.87% [95% confidence interval (CI): 94.99-100.00%] and 93.21% (95% CI: 84.32-100.00%), respectively. In those with lower pre-treatment SCCA levels, the 1- and 2-year EFS rates were 91.39% (95% CI: 84.93-98.35%) and 82.24% (95% CI: 72.42-93.39%), respectively. The survival analysis showed that higher pre-treatment SCCA levels were correlated with improved EFS (P=0.02) in patients receiving neoadjuvant chemo-immunotherapy. Conversely, for patients undergoing surgery alone, high pre-treatment SCCA levels were correlated with a poorer prognosis [disease-free survival (DFS), P=0.001]. These findings confirm the value of SCCA levels in predicting which patients will have a more favorable response to neoadjuvant chemo-immunotherapy. In patients receiving neoadjuvant chemo-immunotherapy, a high post-treatment PLR indicated a poorer prognosis (P=0.02). The Cox regression analysis indicated that the pre-treatment SCCA level (P=0.04) and post-treatment PLR (P=0.04) were independent predictive factors of EFS. In patients receiving neoadjuvant chemo-immunotherapy, high pre-treatment SCCA levels and low post-treatment PLRs were significantly associated with better efficacy and survival. Thus, these biomarkers could be used to guide the choice of treatment modalities.

Treatment of locally advanced unresectable non-small cell lung cancer (NSCLC) is a significant challenge, especially for patients with IIIA/IIIB NSCLC. Patients receiving neoadjuvant chemoimmunotherapy (NCI) show improved pathological responses and disease-free survival (DFS) compared to those receiving Neoadjuvant chemotherapy (NC). However, there is still no consensus on the treatment for potentially resectable stage IIIA/IIIB NSCLC. This retrospective study included 71 patients newly diagnosed with stage III NSCLC at our institution between 2017 and 2023: 46 patients received NCI and 25 patients received NC followed by surgical resection. Their clinicopathological characteristics were reviewed and analyzed. Patients who received NCI had a significantly longer DFS. The median DFS was 15 months in the NC group (hazard ratio: 0.186, 95% confidence interval[CI]: 0.073-0.479; P<0.001) but had not been reached in the NCI group. The percentage of patients achieving a major pathologic response was 65.9% (29/44, 95% CI: 50.0%-79.1%) with NCI and 16.7% (4/24, 95% CI: 5.5%-38.2%) with NC alone(P<0.001). The percentage of patients with pathologic complete response was 36.4% (16/44, 95% CI: 22.8%-52.3%) after NCI compared with 8.3% (2/24, 95% CI: 1.5%-28.5%) after NC (P = 0.012). The survival curve shows that the overall survival for the NCI group has a better trend than that of the NC group, but there is no significant difference (P=0.193). The incidence of all-grade adverse events was greater in the NCI group than in the NC group (80.4% vs. 64.0%). The incidence of grade ≥3 adverse events was 10.9% (n=5) and 8.0% (n=2), respectively; however, these differences were insignificant. NCI is more effective and safer for patients with potentially resectable stage IIIA/IIIB NSCLC. Compared with NC alone, NCI significantly improves the pathological response and DFS without increasing adverse events.

IntroductionFew studies have focused on the optimal cycles of neoadjuvant chemoimmunotherapy (NCI). This study introduced minimal residual disease (MRD) based on circulating tumor DNA (ctDNA), and investigated the association between ctDNA-MRD and NCI cycles and pathological response.Materials and methodsThis study was based on a phase III trial (NCT05157776). The patients with IIIA NSCLC without driver genes were given two cycles of NCI (initial two-cycle NCI), after which they were 1:1 randomly assigned to the two-cycle NCI groups (no additional NCI) or four-cycle NCI group (with another two cycles of NCI).ResultsThis study involved 13 patients with 28 blood samples. At the start of the study, ctDNA-MRD was detected in 10 out of the 13 patients (77%). The pathologically complete response (pCR) rate was higher in the four-cycle NCI group (3/6, 50%) than in the two-cycle NCI group (1/7, 14.2%). Remarkably, the subgroup that achieved ctDNA-MRD elimination after two cycles and kept elimination after additional two cycles had the highest pCR rate (3/4, 75.0%). Correspondently, the subgroup that did not achieve ctDNA-MRD elimination after two cycles and kept existence after additional two cycles had the lowest pCR rate (0/2, 0%). Generally, in the four-cycle group, a strong correlation between ctDNA-MRD and radiological assessment was observed (5/6, 83.3%).ConclusionPatients with locally advanced NSCLC who achieved ctDNA-MRD elimination after two-cycle NCI were more likely to benefit from additional two-cycle NCI, manifesting higher pCR rates. ctDNA-MRD could be a promising tool to determine the optimal cycle of NCI.Clinical Trial RegistrationClinicaltrial.gov, NCT05157776.

Tertiary lymphoid structures (TLS) existence is correlated with favorable prognosis in many types of cancer including non-small cell lung cancer (NSCLC). However, TLS formation and its relationship with treatment response...

BackgroundPerioperative, adjuvant, and neoadjuvant chemoimmunotherapy have all demonstrated significant clinical benefit in resectable non-small cell lung cancer (NSCLC). To better inform personalized treatment decision-making, we conducted a systematic review and network meta-analysis to compare the efficacy and safety of these three chemoimmunotherapy strategies, according to different disease stage (IB–II vs. IIIA–IIIB) and programmed cell death ligand 1 (PD-L1) expression.MethodsA systematic literature search was conducted through PubMed, Embase, ClinicalTrials.gov, and the Cochrane Central Register of Controlled Trials up to April 1, 2025. Relevant conference proceedings were also included. Randomized controlled trials (RCTs) comparing two or more treatment options for patients with resectable NSCLC were included. Eligible trials were selected by two researchers independently according to predefined criteria. The Cochrane Collaboration’s tool was used to evaluate the risk of bias. Data were extracted following PRISMA guidelines, either a fixed-effect or random-effect model was applied depending on heterogeneity. The primary outcome was event-free survival (EFS). Secondary outcomes included overall survival (OS) and the incidence of grade ≥3 treatment-related adverse events (TRAEs). Subgroup analyses were performed by disease stage, PD-L1 expression and Eastern Cooperative Oncology Group (ECOG) performance status (PS).ResultsTwenty-one RCTs involving 12,258 patients with resectable NSCLC were included in this network meta-analysis. The outcomes were evaluated by a Bayesian fixed-effect model. For patients with stage IB–II NSCLC, perioperative chemoimmunotherapy was comparable with adjuvant chemoimmunotherapy [hazard ratio (HR) 1.06, 95% confidence interval (CI): 0.64 to 1.77; P=0.82] and neoadjuvant chemoimmunotherapy (HR 0.78, 95% CI: 0.37 to 1.62; P=0.51) in terms of EFS. In contrast, for patients with stage IIIA–IIIB NSCLC, both perioperative chemoimmunotherapy (HR 0.32, 95% CI: 0.16–0.64; P=0.001) and neoadjuvant chemoimmunotherapy (HR 0.31, 95% CI: 0.14 to 0.69; P=0.004) were associated with significantly improved EFS compared to adjuvant chemoimmunotherapy. All three chemoimmunotherapy strategies showed benefit in PD-L1-positive patients, but only perioperative chemoimmunotherapy significantly improved EFS versus neoadjuvant chemotherapy in PD-L1-negative (tumor proportion score <1%) patients (HR 0.74, 95% CI: 0.60 to 0.91; P=0.005). Additionally, perioperative chemoimmunotherapy was also the only approach that led to significant improvement in EFS for patients with ECOG PS ≥1 (HR 0.55, 95% CI: 0.43 to 0.72; P<0.001). Notably, perioperative chemoimmunotherapy was associated with a higher incidence of grade ≥3 TRAEs compared to neoadjuvant chemoimmunotherapy (OR 1.63, 95% CI: 1.02 to 2.59; P=0.041).ConclusionsPerioperative, adjuvant and neoadjuvant chemoimmunotherapy were all suitable for patients with stage IB–II NSCLC, while perioperative and neoadjuvant chemoimmunotherapy may represent more favorable options for stage III disease. In patients with PD-L1-negative expression or ECOG PS ≥1, only perioperative chemoimmunotherapy was associated with improved EFS versus chemotherapy. Our findings might benefit future individualized immunochemotherapy for resectable NSCLC.

The clinical outcome of resectable non-small-cell lung cancer (NSCLC) patients receiving neoadjuvant chemoimmunotherapy is good but varies greatly. In addition, the pathological response after neoadjuvant chemoimmunotherapy is significantly associated with survival outcomes. The aim of this retrospective study was to identify which population of patients with locally advanced and oligometastatic NSCLC has a favorable pathological response after neoadjuvant chemoimmunotherapy. NSCLC patients treated with neoadjuvant chemoimmunotherapy were enrolled between February 2018 and April 2022. Data on clinicopathological features were collected and evaluated. Multiplex immunofluorescence was performed on pre-treatment puncture specimens and surgically resected specimens. In total, 29 patients with stages III and IV locally advanced or oligometastatic NSCLC who received neoadjuvant chemoimmunotherapy and R0 resection were enrolled. The results showed that 55% (16/29) of patients had a major pathological response (MPR) and 41% (12/29) of patients had a complete pathological response (pCR). In the stroma area of the pre-treatment specimen, the higher infiltration of CD3+ PD-L1+ tumor-infiltrating lymphocytes (TILs) and the lower infiltration of CD4+ and CD4+ FOXP3+ TILs were more likely to appear in patients with pCR. However, in the tumor area, the higher infiltration of CD8+ TILs was more likely to appear in patients with non-MPR. In the post-treatment specimen, we found increased infiltration of CD3+ CD8+ , CD8+ GZMB+ , and CD8+ CD69+ TILs and decreased infiltration of PD-1+ TILs both in the stroma and tumor areas. Neoadjuvant chemoimmunotherapy achieved an MPR rate of 55% and induced greater immune infiltration. In addition, we observed that the baseline TILs and their spatial distribution correlate to the pathological response.

ObjectivesTo evaluate the effects of neoadjuvant chemoimmunotherapy on pulmonary function and the incidence of postoperative pulmonary complications in real-world non-small-cell lung cancer patients.MethodsA retrospective analysis of stage II-IIIB non-small-cell lung cancer patients who received neoadjuvant chemoimmunotherapy across 3 medical institutions was conducted. Clinical data and perioperative outcomes were evaluated.ResultsA total of 386 patients were screened and enrolled in the study cohort, and all patients underwent surgery after completing neoadjuvant chemoimmunotherapy. Postoperatively, 61 patients developed postoperative pulmonary complications, among whom 25 were diagnosed with checkpoint inhibitor-related pneumonia. The postoperative mortality rate was 2.8% (11/386), with all deaths attributed to severe postoperative checkpoint inhibitor-related pneumonia. The diffusing capacity of the lung for carbon monoxide tended to decrease after neoadjuvant chemoimmunotherapy, with 39% of patients developing impaired pulmonary function post-treatment. After controlling for confounding variables via propensity score matching analysis, impaired pulmonary function after treatment was associated with postoperative pulmonary complications. Multivariable logistic regression analysis revealed that prior lung disease (odds ratio, [OR]: 1.63; 95% CI, 1.02-3.31, P = .037), impaired pulmonary function after treatment (OR: 2.78; 95% CI, 1.38-5.24, P < .001), lymph node metastasis (OR: 3.05; 95% CI, 1.65-6.21, P < .001), and elevated preoperative interleukin-6 levels (OR: 1.58; 95% CI, 1.36-1.83, P < .001) were high risk factors for postoperative pulmonary complications.ConclusionsImpaired pulmonary function after neoadjuvant chemoimmunotherapy is associated with the development of postoperative pulmonary complications. Post-treatment impaired pulmonary function, lymph node metastasis, prior lung disease, and elevated preoperative interleukin-6 levels are risk factors for postoperative pulmonary complications.Clinical Registration NumberA Retrospective Study on Pulmonary Function Changes and Safety in Patients Receiving Neoadjuvant Chemoimmunotherapy (IIT2024733).

This study aims to develop and validate a radiomics model based on 18F-fluorodeoxyglucose positron emission tomography-computed tomography ([18F]FDG PET-CT) images to predict pathological complete response (pCR) to neoadjuvant chemoimmunotherapy in non-small cell lung cancer (NSCLC). One hundred eighty-five patients receiving neoadjuvant chemoimmunotherapy for NSCLC at 5 centers from January 2019 to December 2022 were included and divided into a training cohort and a validation cohort. Radiomics models were constructed via the least absolute shrinkage and selection operator (LASSO) method. The performances of models were evaluated by the area under the receiver operating characteristic curve (AUC). In addition, genetic analyses were conducted to reveal the underlying biological basis of the radiomics score. After the LASSO process, 9 PET-CT radiomics features were selected for pCR prediction. In the validation cohort, the ability of PET-CT radiomics model to predict pCR was shown to have an AUC of 0.818 (95% confidence interval [CI], 0.711, 0.925), which was better than the PET radiomics model (0.728 [95% CI, 0.610, 0.846]), CT radiomics model (0.732 [95% CI, 0.607, 0.857]), and maximum standard uptake value (0.603 [95% CI, 0.473, 0.733]) (p < 0.05). Moreover, a high radiomics score was related to the upregulation of pathways suppressing tumor proliferation and the infiltration of antitumor immune cell. The proposed PET-CT radiomics model was capable of predicting pCR to neoadjuvant chemoimmunotherapy in NSCLC patients. This study indicated that the generated 18F-fluorodeoxyglucose positron emission tomography-computed tomography radiomics model could predict pathological complete response to neoadjuvant chemoimmunotherapy, implying the potential of our radiomics model to personalize the neoadjuvant chemoimmunotherapy in lung cancer patients. • Recognizing patients potentially benefiting neoadjuvant chemoimmunotherapy is critical for individualized therapy of lung cancer. • [18F]FDG PET-CT radiomics could predict pathological complete response to neoadjuvant immunotherapy in non-small cell lung cancer. • [18F]FDG PET-CT radiomics model could personalize neoadjuvant chemoimmunotherapy in lung cancer patients.

To date, no meta-analyses have comprehensively assessed the association of neoadjuvant chemoimmunotherapy with clinical outcomes in non-small cell lung cancer (NSCLC) in randomized and nonrandomized settings. In addition, there exists controversy concerning the efficacy of neoadjuvant chemoimmunotherapy for patients with NSCLC with programmed cell death 1 ligand 1 (PD-L1) levels less than 1%. To compare neoadjuvant chemoimmunotherapy with chemotherapy by adverse events and surgical, pathological, and efficacy outcomes using recently published randomized clinical trials and nonrandomized trials. MEDLINE and Embase were systematically searched from January 1, 2013, to October 25, 2023, for all clinical trials of neoadjuvant chemoimmunotherapy and chemotherapy that included at least 10 patients. Observational studies and trials reporting the use of neoadjuvant radiotherapy, including chemoradiotherapy, molecular targeted therapy, or immunotherapy monotherapy, were excluded. Surgical, pathological, and efficacy end points and adverse events were pooled using a random-effects meta-analysis. Among 43 eligible trials comprising 5431 patients (4020 males [74.0%]; median age range, 55-70 years), there were 8 randomized clinical trials with 3387 patients. For randomized clinical trials, pooled overall survival (hazard ratio, 0.65; 95% CI, 0.54-0.79; I2 = 0%), event-free survival (hazard ratio, 0.59; 95% CI, 0.52-0.67; I2 = 14.9%), major pathological response (risk ratio, 3.42; 95% CI, 2.83-4.15; I2 = 31.2%), and complete pathological response (risk ratio, 5.52; 95% CI, 4.25-7.15; I2 = 27.4%) favored neoadjuvant chemoimmunotherapy over neoadjuvant chemotherapy. For patients with baseline tumor PD-L1 levels less than 1%, there was a significant benefit in event-free survival for neoadjuvant chemoimmunotherapy compared with chemotherapy (hazard ratio, 0.74; 95% CI, 0.62-0.89; I2 = 0%). This study found that neoadjuvant chemoimmunotherapy was superior to neoadjuvant chemotherapy across surgical, pathological, and efficacy outcomes. These findings suggest that patients with resectable NSCLC with tumor PD-L1 levels less than 1% may have an event-free survival benefit with neoadjuvant chemoimmunotherapy.

e20591 Background: Non–small cell lung cancer (NSCLC) is one of the main leading causes of cancer mortality in the world. NSCLC is incurable in most patients with potentially resectable locally advanced stage IIIB disease. Numerous studies suggest that advantageous chemoimmunotherapy is a promising treatment for resectable NSCLC. The determination of PD-L1, T-cell receptor (TCR) repertoire and tumor mutational burden (TMB) have been reported to predict the response to immunotherapy. However, the value of pathologic response determination in the context of neoadjuvant chemoimmunotherapy in resectable stage IIIB NSCLC is limited. Therefore, it is necessary to identify biomarkers for the prediction of the benefit from neoadjuvant chemoimmunotherapy in patients with potentially resectable stage IIIB NSCLC. Methods: A total of 15 patients with potentially resectable clinical stage IIIB NSCLC were enrolled into the study receiving neoadjuvant sintilimab (200mg IV Q3W) plus chemotherapy therapies for 4-6 weeks followed by surgery. All peripheral blood and tissue samples were collected and detected by using TCR repertoire sequencing before and after chemoimmunotherapy. The patients were divided into MPR group (n=5) and non-MPR group (n=10) according to MPR (&lt;10% viable tumour at resection) as an index. Furthermore, TMB spectra of 1021-gene panels and PD-L1 immunohistochemical staining were performed in paraffin-embedded human NSCLC tissue before neoadjuvant chemoimmunotherapy. The Pearson correlation coefficient method was used to analyze correlation. The ROC analysis were performed using “pROC” R package. Results: In baseline tissue samples, the levels of TMB and NAD were higher in MPR compared with non-MPR groups (P=0.0328, P=0.015, respectively). The negative correlation was existed between pretreatment tissue TCR richness and TMB in non-MPR group (P=0.028, R=-0.66). In MPR group, TCR clones and evenness showed significant difference (P=0.00237, P=0.04658, respectively). In non-MPR group, the TCR repertoire of tissue in posttreatment showed significant difference compared with those of pretreatment, including clones (P=1.04x10-6), shannon’s diversity (P=0.00142), evenness (P=0.00433), richness (P=0.00591). The clinical data showed that MPR patients with DDR mutation had longer DFS after sintilimab plus chemotherapy therapies (18.4±5.41 months, X-squared=9.8, P=0.02034). DDR mutation, TMB and TCR richness revealed better sensitivity and specificity to classify patients achieving MPR after neoadjuvant chemoimmunotherapy (AUC=1.000, AUC=0.796, AUC=0.773, respectively). Conclusions: This study confirmed the superiority of neoadjuvant chemoimmunotherapy in patients with potentially resectable stage IIIB NSCLC in terms of MPR. TCR repertoire, TMB and DDR mutation were associated with pathologic response to neoadjuvant chemoimmunotherapy as biomarkers for effective anti-tumor immunity. Clinical trial information: ChiCTR2000040673 .

ObjectiveStage III non-small cell lung cancer (NSCLC) is a heterogeneous group of diseases. For this subset of patients, clinical management is still under debate and prognosis remains poor so far. In the present study, we aimed to evaluate the feasibility and safety of robotic-assisted thoracic surgery after neoadjuvant chemoimmunotherapy in stage III NSCLC.MethodsA real-world prospective cohort study was performed in a single-center setting from April 2021 to May 2022. Patients who were diagnosed with resectable or potentially resectable stage IIIA–B NSCLC and received neoadjuvant chemoimmunotherapy followed by robotic-assisted thoracic surgery were enrolled. Pathological response to neoadjuvant chemoimmunotherapy, treatment-related adverse events, and surgical outcomes of these patients were evaluated.ResultsA total of 44 patients who underwent robotic-assisted thoracic surgery after three doses of neoadjuvant chemoimmunotherapy were included in this study. Of these, 36 of 44 (81.8%) patients had a major pathological response, and 26 (59.1%) had a pathological complete response based on pathological examination of surgical specimen. Eight patients (18.2%) suffered grade 3 treatment-related adverse events, including neutropenia (n = 4), increased aminotransferases (n = 3), anemia (n = 1), and cutaneous capillary endothelial proliferation (n = 1). Robotic-assisted thoracic surgery was performed subsequently, and R0 resection was achieved in all patients. Only two (4.5%) patients required conversion to thoracotomy. Surgical complications occurred in five (11.4%) patients, including air leak (n = 3), chylothorax (n = 2), and surgical site infection (n = 1). There was no re-surgery or postoperative mortality within 90 days.ConclusionRobotic-assisted thoracic surgery following neoadjuvant chemoimmunotherapy showed good feasibility and safety in stage III NSCLC. It was not associated with unexpected perioperative morbidity or mortality and may be a promising therapeutic option in stage III NSCLC. These results need further confirmation by more large-scale clinical trials.

e20584 Background: The combination of immune checkpoint inhibitors (ICIs) with chemotherapy (chemoimmunotherapy) in the neoadjuvant setting have achieved favorable clinical benefits in non-small cell lung cancer (NSCLC), but the underlying molecular mechanism has not been fully elucidated. Methods: To identify factors associated with the clinical outcome, single-cell RNA/TCR sequencing was performed using 10x Genomics on CD45+ immune cells isolated from tumor and multiple immune-relevant tissues and peripheral blood of four treatment-naïve and eight neoadjuvant chemoimmunotherapy treated IIIA NSCLC patients (responders versus non-responders). Bioinformatics analysis was used to screen immune cell factors associated with therapy response in single-cell sequencing profiles, and results were verified at protein level by flow cytometry, multiplex fluorescent immunohistochemistry (mIHC) and ELISA. Results: A total of 186,477 immune cells from 48 samples were acquired after quality-control filtering. The synergistic increase of B cells and CD4+ T cells are associated with positive therapeutic response of neoadjuvant chemoimmunotherapy. B cell class switching to IgG1 and IgG3 plays a critical role in anti-tumor immune response in tumor lesion, and this process is driven by increased IL-21 protein secreted by infiltrated T follicular helper (Tfh) cells after neoadjuvant chemoimmunotherapy. Several critical events lead to the positive clinical outcome during neoadjuvant chemoimmunotherapy, including the diminished activated TNFRSF4+ regulatory T cells (Tregs), increased LAMP3+ dendritic cells (DCs), high pretreatment peripheral blood T-cell diversity, and the expansion of intratumoral CD4+ T clones and peripheral CD8+ T clones. A validation cohort of 26 treatment-naïve and 30 neoadjuvant chemoimmunotherapy treated IIIA NSCLC patients verified these findings. Conclusions: Single-cell profiling of the immune response to neoadjuvant chemoimmunotherapy uncovered several critical factors of anti-tumor immune response and provided insight of potential novel predictive factors and therapeutic targets for improving the efficacy of treatment in NSCLC.

To investigate if delta-radiomics features have the potential to predict the major pathological response (MPR) to neoadjuvant chemoimmunotherapy in non-small cell lung cancer (NSCLC) patients. Two hundred six stage IIA-IIIB NSCLC patients from three institutions (Database1 = 164; Database2 = 21; Database3 = 21) who received neoadjuvant chemoimmunotherapy and surgery were included. Patients in Database1 were randomly assigned to the training dataset and test dataset, with a ratio of 0.7:0.3. Patients in Database2 and Database3 were used as two independent external validation datasets. Contrast-enhanced CT scans were obtained at baseline and before surgery. The delta-radiomics features were defined as the relative net change of radiomics features between baseline and preoperative. The delta-radiomics model and pre-treatment radiomics model were established. The performance of Immune-Related Response Evaluation Criteria in Solid Tumors (iRECIST) for predicting MPR was also evaluated. Half of the patients (106/206, 51.5%) showed MPR after neoadjuvant chemoimmunotherapy. For predicting MPR, the delta-radiomics model achieved a satisfying area under the curves (AUCs) values of 0.768, 0.732, 0.833, and 0.716 in the training, test, and two external validation databases, respectively, which showed a superior predictive performance than the pre-treatment radiomics model (0.644, 0.616, 0.475, and 0.608). Compared with iRECIST criteria (0.624, 0.572, 0.650, and 0.466), a mixed model that combines delta-radiomics features and iRECIST had higher AUC values for MPR prediction of 0.777, 0.761, 0.850, and 0.670 in four sets. The delta-radiomics model demonstrated superior diagnostic performance compared to pre-treatment radiomics model and iRECIST criteria in predicting MPR preoperatively in neoadjuvant chemoimmunotherapy for stage II-III NSCLC. Delta-radiomics features based on the relative net change of radiomics features between baseline and preoperative CT scans serve a vital support tool in accurately identifying responses to neoadjuvant chemoimmunotherapy, which can help physicians make more appropriate treatment decisions. •The performances of pre-treatment radiomics model and iRECIST model in predicting major pathological response of neoadjuvant chemoimmunotherapy were unsatisfactory. •The delta-radiomics features based on relative net change of radiomics features between baseline and preoperative CT scans may be used as a noninvasive biomarker for predicting major pathological response of neoadjuvant chemoimmunotherapy. •Combining delta-radiomics features and iRECIST can further improve the predictive performance of responses to neoadjuvant chemoimmunotherapy.

A combined model using pre-treatment CT radiomics and clinicopathological features of non-small cell lung cancer to predict major pathological responses after neoadjuvant chemoimmunotherapy