Meng Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Meng Yan has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
Andre Dekker
Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre
3 shared publicationsLeonard Wee
Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre
3 shared publicationsZhen Zhang
Department of Radiation Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Zhejiang Key Laboratory of Particle Radiotherapy Equipment
3 shared publicationsHan Cheng
Department of Radiation Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Zhejiang Key Laboratory of Particle Radiotherapy Equipment
2 shared publicationsJin Wang
Department of Radiation Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Zhejiang Key Laboratory of Particle Radiotherapy Equipment
2 shared publications- Lujun Zhao
Department of Radiation Oncology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, China
2 shared publications
Latest Publications
- 3 November 2026
- Published by American Association for Cancer Research (AACR) in Cancer Research
- p. OF1-OF23
Single-Cell and Spatial Transcriptomics Reveal CHCHD3 as a Therapeutic Target to Activate cGAS–STING and Overcome Immunosuppression in Lung Adenocarcinoma
A substantial proportion of patients with treatment-naïve lung adenocarcinoma (LUAD) exhibit intrinsic resistance to neoadjuvant chemoimmunotherapy, highlighting the need for mechanism-driven therapeutic strategies. In this study, we performed integrated single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics on clinical specimens from the CheckMate 816 trial to define the tumor immune microenvironment (TIME) dynamics associated with therapy resistance. The scRNA-seq data revealed distinct TIME features in nonresponders to neoadjuvant chemoimmunotherapy, characterized by the upregulation of CHCHD3. Mechanistically, CHCHD3 acted as a negative regulator of innate immunity by sequestering cGAS in mitochondria. This interaction between the CHCHD3 domain and the cGAS catalytic core reduced the cytosolic cGAS pool, thereby blunting STING-dependent signaling. Consequently, CHCHD3 knockout restored CXCL5/CXCL1 production, reduced M2-like tumor-associated macrophages, and promoted CD8+ T-cell infiltration. Integrated virtual and functional drug screening identified TN4510 as a small molecule that disrupts the CHCHD3–cGAS interface. TN4510 treatment effectively restored STING signaling and synergized with chemoimmunotherapy to suppress tumor growth in preclinical models. Together, these findings reveal that CHCHD3 drives chemoimmunotherapy resistance by sequestering cGAS to limit STING activation. Targeting CHCHD3 with TN4510 restores antitumor immunity, offering a translatable strategy to overcome treatment resistance in LUAD. Significance: Targeting CHCHD3 activates cGAS-STING signaling to stimulate anti-tumor immunity and sensitize lung cancer to chemoimmunotherapy, highlighting the therapeutic potential of this approach to improve patient outcomes.
- 3 November 2026
- Published by American Association for Cancer Research (AACR) in Cancer Research
- p. OF1-OF23
Single-Cell and Spatial Transcriptomics Reveal CHCHD3 as a Therapeutic Target to Activate cGAS–STING and Overcome Immunosuppression in Lung Adenocarcinoma
A substantial proportion of patients with treatment-naïve lung adenocarcinoma (LUAD) exhibit intrinsic resistance to neoadjuvant chemoimmunotherapy, highlighting the need for mechanism-driven therapeutic strategies. In this study, we performed integrated single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics on clinical specimens from the CheckMate 816 trial to define the tumor immune microenvironment (TIME) dynamics associated with therapy resistance. The scRNA-seq data revealed distinct TIME features in nonresponders to neoadjuvant chemoimmunotherapy, characterized by the upregulation of CHCHD3. Mechanistically, CHCHD3 acted as a negative regulator of innate immunity by sequestering cGAS in mitochondria. This interaction between the CHCHD3 domain and the cGAS catalytic core reduced the cytosolic cGAS pool, thereby blunting STING-dependent signaling. Consequently, CHCHD3 knockout restored CXCL5/CXCL1 production, reduced M2-like tumor-associated macrophages, and promoted CD8+ T-cell infiltration. Integrated virtual and functional drug screening identified TN4510 as a small molecule that disrupts the CHCHD3–cGAS interface. TN4510 treatment effectively restored STING signaling and synergized with chemoimmunotherapy to suppress tumor growth in preclinical models. Together, these findings reveal that CHCHD3 drives chemoimmunotherapy resistance by sequestering cGAS to limit STING activation. Targeting CHCHD3 with TN4510 restores antitumor immunity, offering a translatable strategy to overcome treatment resistance in LUAD. Significance: Targeting CHCHD3 activates cGAS-STING signaling to stimulate anti-tumor immunity and sensitize lung cancer to chemoimmunotherapy, highlighting the therapeutic potential of this approach to improve patient outcomes.
- Open Access
- 17 April 2026
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 17
Correction: Cross-dataset adaptation of voxel-level deep radiomics for predicting survival in inoperable locally advanced NSCLC treated with immunotherapy
- 17 April 2026
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 17
Open AccessCorrection: Cross-dataset adaptation of voxel-level deep radiomics for predicting survival in inoperable locally advanced NSCLC treated with immunotherapy
- Open Access
- 3 March 2026
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 17, 1787518
Cross-dataset adaptation of voxel-level deep radiomics for predicting survival in inoperable locally advanced NSCLC treated with immunotherapy
Background and purpose: Predicting overall survival (OS) for inoperable locally advanced non-small cell lung cancer (LA-NSCLC) treated with immune checkpoint inhibitors remains challenging due to heterogeneous clinical response. Furthermore, the application of advanced deep learning is hindered by limited immunotherapy datasets. This study aimed to develop a novel prognostic framework by integrating voxel-level deep radiomics derived from pretreatment imaging with a knowledge transfer strategy to accurately predict OS. Materials and methods: A total of 526 patients were respectively identified. A non-immunotherapy dataset from the RTOG 0617 clinical trial was used to pre-train a Vision-Mamba deep learning model to learn tumor characteristics within manually delineated tumor regions. Voxel-level radiomics feature maps were generated within tumors and integrated with CT images for dual-input co-training. Using the same dual-input, a cross-dataset transfer learning strategy was then used to adapt the pre-trained models to the immunotherapy context by fine-tuning. The model’s performance was evaluated using the concordance index (C-index), time-dependent area under the receiver operating characteristic curve, Kaplan-Meier survival analysis, calibration curves, and decision curve analysis. Additionally, Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to suggest a possible interpretation of the model’s decision logic. Results: The proposed model demonstrated robust generalization ability. In the independent immunotherapy testing dataset, the model achieved a C-index of 0.73 (95% CI:0.63-0.82). The time-dependent AUCs for predicting 1-year and 2-year OS were 0.73 and 0.70, respectively. Calibration curves showed good agreement between predicted and observed survival probability. Stratification analysis showed distinct survival differences, with the high-risk group exhibiting significantly poorer OS compared to low-risk group (P<0.001). Conclusion: We developed a voxel-level deep radiomics framework that bridges the data gap in immunotherapy research through fine-tuning on a limited immunotherapy dataset, and subsequent validation on an independent immunotherapy testing dataset, demonstrating robust generalizability.
- 3 March 2026
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 17, 1787518
Open AccessCross-dataset adaptation of voxel-level deep radiomics for predicting survival in inoperable locally advanced NSCLC treated with immunotherapy
Background and purpose: Predicting overall survival (OS) for inoperable locally advanced non-small cell lung cancer (LA-NSCLC) treated with immune checkpoint inhibitors remains challenging due to heterogeneous clinical response. Furthermore, the application of advanced deep learning is hindered by limited immunotherapy datasets. This study aimed to develop a novel prognostic framework by integrating voxel-level deep radiomics derived from pretreatment imaging with a knowledge transfer strategy to accurately predict OS. Materials and methods: A total of 526 patients were respectively identified. A non-immunotherapy dataset from the RTOG 0617 clinical trial was used to pre-train a Vision-Mamba deep learning model to learn tumor characteristics within manually delineated tumor regions. Voxel-level radiomics feature maps were generated within tumors and integrated with CT images for dual-input co-training. Using the same dual-input, a cross-dataset transfer learning strategy was then used to adapt the pre-trained models to the immunotherapy context by fine-tuning. The model’s performance was evaluated using the concordance index (C-index), time-dependent area under the receiver operating characteristic curve, Kaplan-Meier survival analysis, calibration curves, and decision curve analysis. Additionally, Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to suggest a possible interpretation of the model’s decision logic. Results: The proposed model demonstrated robust generalization ability. In the independent immunotherapy testing dataset, the model achieved a C-index of 0.73 (95% CI:0.63-0.82). The time-dependent AUCs for predicting 1-year and 2-year OS were 0.73 and 0.70, respectively. Calibration curves showed good agreement between predicted and observed survival probability. Stratification analysis showed distinct survival differences, with the high-risk group exhibiting significantly poorer OS compared to low-risk group (P<0.001). Conclusion: We developed a voxel-level deep radiomics framework that bridges the data gap in immunotherapy research through fine-tuning on a limited immunotherapy dataset, and subsequent validation on an independent immunotherapy testing dataset, demonstrating robust generalizability.
- 30 October 2025
- Published by Springer Nature in European Radiology
- Vol. 36 (4) , 2603-2614
Malignant pleural mesothelioma classification and survival prediction with CT imaging using ResNet
Objectives This study aims to achieve accurate differentiation of malignant pleural mesothelioma (MPM) from metastatic pleural disease (MPD) and to predict the overall survival of MPM. Materials and methods This IRB-approved retrospective study included 385 subjects in total (85 patients with malignant mesothelioma and 290 with MPD secondary to lung adenocarcinoma). A ResNet-3D-18 model was trained on annotated pretreatment CT scans to distinguish MPM from MPD. Using chronological segregation, the training cohort included 70 histologically confirmed mesothelioma and 258 MPD cases, with an independent test cohort of 15 MPM and 32 MPD cases for validation. A multivariate logistic regression model served as the clinical benchmark for comparison. Deep learning features extracted from the trained ResNet model were then assessed for their prognostic utility in MPM patients using a random forest classifier. Model performance was evaluated at both lesion- and patient-levels, with metrics including the area under the ROC curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. Results The ResNet-3D-18 model demonstrated excellent discriminative performance in differentiating MPM from MPD, with mean AUCs of 0.972 (95% CI 0.947–0.990) and 0.840 (95% CI 0.757–0.929) in the training and independent test cohorts. Compared to the clinical model, the deep learning approach showed higher sensitivity (0.867 vs. 0.533) in the independent test dataset. For overall survival prediction in MPM patients, the random forest classifier achieved an AUC of 0.829 (95% CI 0.663–0.943) in 5-fold cross-validation. Conclusions ResNet-3D-18 classification model has excellent abilities in differentiating MPM from MPD, and morphological distinctions between MPM and MPD also contain prognostic information. Key Points Question The rising global incidence of malignant pleural mesothelioma contrasts with persistent diagnostic challenges. Findings Deep learning-derived discriminative features simultaneously contain prognostic information. Clinical relevance This study bridges the gap between radiological findings and clinical decision-making in MPM, offering a reproducible tool for early diagnosis and personalized prognosis prediction based on CT imaging alone. Graphical Abstract
- 30 October 2025
- Published by Springer Nature in European Radiology
- Vol. 36 (4) , 2603-2614
Malignant pleural mesothelioma classification and survival prediction with CT imaging using ResNet
Objectives This study aims to achieve accurate differentiation of malignant pleural mesothelioma (MPM) from metastatic pleural disease (MPD) and to predict the overall survival of MPM. Materials and methods This IRB-approved retrospective study included 385 subjects in total (85 patients with malignant mesothelioma and 290 with MPD secondary to lung adenocarcinoma). A ResNet-3D-18 model was trained on annotated pretreatment CT scans to distinguish MPM from MPD. Using chronological segregation, the training cohort included 70 histologically confirmed mesothelioma and 258 MPD cases, with an independent test cohort of 15 MPM and 32 MPD cases for validation. A multivariate logistic regression model served as the clinical benchmark for comparison. Deep learning features extracted from the trained ResNet model were then assessed for their prognostic utility in MPM patients using a random forest classifier. Model performance was evaluated at both lesion- and patient-levels, with metrics including the area under the ROC curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. Results The ResNet-3D-18 model demonstrated excellent discriminative performance in differentiating MPM from MPD, with mean AUCs of 0.972 (95% CI 0.947–0.990) and 0.840 (95% CI 0.757–0.929) in the training and independent test cohorts. Compared to the clinical model, the deep learning approach showed higher sensitivity (0.867 vs. 0.533) in the independent test dataset. For overall survival prediction in MPM patients, the random forest classifier achieved an AUC of 0.829 (95% CI 0.663–0.943) in 5-fold cross-validation. Conclusions ResNet-3D-18 classification model has excellent abilities in differentiating MPM from MPD, and morphological distinctions between MPM and MPD also contain prognostic information. Key Points Question The rising global incidence of malignant pleural mesothelioma contrasts with persistent diagnostic challenges. Findings Deep learning-derived discriminative features simultaneously contain prognostic information. Clinical relevance This study bridges the gap between radiological findings and clinical decision-making in MPM, offering a reproducible tool for early diagnosis and personalized prognosis prediction based on CT imaging alone. Graphical Abstract
- 24 February 2023
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 182, 109581
Computed tomography and radiation dose images-based deep-learning model for predicting radiation pneumonitis in lung cancer patients after radiation therapy
- 24 February 2023
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 182, 109581
Computed tomography and radiation dose images-based deep-learning model for predicting radiation pneumonitis in lung cancer patients after radiation therapy
- Open Access
- 21 October 2022
- Published by MDPI AG in Current Oncology
- Vol. 29 (10) , 7979-7986
The Impact of Chemosensitivity on the Outcome of Brain Metastases in Small-Cell Lung Cancer: A Retrospective Analysis
Purpose: The purpose of this study was to investigate the prognostic differences between patients with small-cell lung cancer (SCLC) with different chemosensitivity to first-line chemotherapy who developed brain metastasis (BM) as the first site of progression. Methods: Patients with a BM after first-line treatment in the Tianjin Cancer Hospital were retrospectively analyzed. According to the time-free interval (TFI) between the completion of first-line chemotherapy and the onset of the BM, the patients were divided into the chemo-sensitive group (TFI ≥ 90 days, n = 145) and the chemo-resistant group (TFI < 90 days, n = 97). The survival time, which was calculated from the diagnosis of the BM, was analyzed after the onset of brain metastasis (BM-OS). Survival curves were plotted using the Kaplan–Meier method, and differences between groups were compared using the log-rank test. Results: In total, the median BM-OS was 8.4 months. The median BM-OS in the chemo-sensitive group was 8.8 months, and it was 8.0 months in the chemo-resistant group (p = 0.538). In patients without extracranial progression (n = 193), the median BM-OSes in the chemo-sensitive and chemo-resistant groups were 9.4 months and 9.7 months, respectively (p = 0.947). In patients with extracranial progression (n = 49), the median BM-OSes in the chemo-sensitive and chemo-resistant groups were 5.4 months and 4.2 months, respectively (p = 0.161). Conclusions: After the development of a BM as the first site of progression following chemotherapy in patients with SCLC, the prognosis of chemo-sensitive patients was not necessarily superior to chemo-resistant patients, especially in patients without extracranial progression.
- 21 October 2022
- Published by MDPI AG in Current Oncology
- Vol. 29 (10) , 7979-7986
Open AccessThe Impact of Chemosensitivity on the Outcome of Brain Metastases in Small-Cell Lung Cancer: A Retrospective Analysis
Purpose: The purpose of this study was to investigate the prognostic differences between patients with small-cell lung cancer (SCLC) with different chemosensitivity to first-line chemotherapy who developed brain metastasis (BM) as the first site of progression. Methods: Patients with a BM after first-line treatment in the Tianjin Cancer Hospital were retrospectively analyzed. According to the time-free interval (TFI) between the completion of first-line chemotherapy and the onset of the BM, the patients were divided into the chemo-sensitive group (TFI ≥ 90 days, n = 145) and the chemo-resistant group (TFI < 90 days, n = 97). The survival time, which was calculated from the diagnosis of the BM, was analyzed after the onset of brain metastasis (BM-OS). Survival curves were plotted using the Kaplan–Meier method, and differences between groups were compared using the log-rank test. Results: In total, the median BM-OS was 8.4 months. The median BM-OS in the chemo-sensitive group was 8.8 months, and it was 8.0 months in the chemo-resistant group (p = 0.538). In patients without extracranial progression (n = 193), the median BM-OSes in the chemo-sensitive and chemo-resistant groups were 9.4 months and 9.7 months, respectively (p = 0.947). In patients with extracranial progression (n = 49), the median BM-OSes in the chemo-sensitive and chemo-resistant groups were 5.4 months and 4.2 months, respectively (p = 0.161). Conclusions: After the development of a BM as the first site of progression following chemotherapy in patients with SCLC, the prognosis of chemo-sensitive patients was not necessarily superior to chemo-resistant patients, especially in patients without extracranial progression.