A radiomics signature derived from CT imaging to predict MSI status and immunotherapy outcomes in gastric cancer: a multi-cohort study
Abstract Background Accurate microsatellite instability (MSI) testing is essential for identifying gastric cancer (GC) patients eligible for immunotherapy. We aimed to develop and validate a CT-based radiomics signature to predict MSI and immunotherapy outcomes in GC. Methods This retrospective mult...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-04-01
|
| Series: | BMC Cancer |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12885-024-12174-0 |
| _version_ | 1827291499245600768 |
|---|---|
| author | Peng-chao Zhan Shuo Yang Xing Liu Yu-yuan Zhang Rui Wang Jia-xing Wang Qing-ya Qiu Yu Gao Dong-bo Lv Li-ming Li Cheng-long Luo Zhi-wei Hu Zhen Li Pei-jie Lyu Pan Liang Jian-bo Gao |
| author_facet | Peng-chao Zhan Shuo Yang Xing Liu Yu-yuan Zhang Rui Wang Jia-xing Wang Qing-ya Qiu Yu Gao Dong-bo Lv Li-ming Li Cheng-long Luo Zhi-wei Hu Zhen Li Pei-jie Lyu Pan Liang Jian-bo Gao |
| author_sort | Peng-chao Zhan |
| collection | DOAJ |
| description | Abstract Background Accurate microsatellite instability (MSI) testing is essential for identifying gastric cancer (GC) patients eligible for immunotherapy. We aimed to develop and validate a CT-based radiomics signature to predict MSI and immunotherapy outcomes in GC. Methods This retrospective multicohort study included a total of 457 GC patients from two independent medical centers in China and The Cancer Imaging Archive (TCIA) databases. The primary cohort (n = 201, center 1, 2017–2022), was used for signature development via Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression analysis. Two independent immunotherapy cohorts, one from center 1 (n = 184, 2018–2021) and another from center 2 (n = 43, 2020–2021), were utilized to assess the signature’s association with immunotherapy response and survival. Diagnostic efficiency was evaluated using the area under the receiver operating characteristic curve (AUC), and survival outcomes were analyzed via the Kaplan-Meier method. The TCIA cohort (n = 29) was included to evaluate the immune infiltration landscape of the radiomics signature subgroups using both CT images and mRNA sequencing data. Results Nine radiomics features were identified for signature development, exhibiting excellent discriminative performance in both the training (AUC: 0.851, 95%CI: 0.782, 0.919) and validation cohorts (AUC: 0.816, 95%CI: 0.706, 0.926). The radscore, calculated using the signature, demonstrated strong predictive abilities for objective response in immunotherapy cohorts (AUC: 0.734, 95%CI: 0.662, 0.806; AUC: 0.724, 95%CI: 0.572, 0.877). Additionally, the radscore showed a significant association with PFS and OS, with GC patients with a low radscore experiencing a significant survival benefit from immunotherapy. Immune infiltration analysis revealed significantly higher levels of CD8 + T cells, activated CD4 + B cells, and TNFRSF18 expression in the low radscore group, while the high radscore group exhibited higher levels of T cells regulatory and HHLA2 expression. Conclusion This study developed a robust radiomics signature with the potential to serve as a non-invasive biomarker for GC’s MSI status and immunotherapy response, demonstrating notable links to post-immunotherapy PFS and OS. Additionally, distinct immune profiles were observed between low and high radscore groups, highlighting their potential clinical implications. |
| first_indexed | 2024-04-24T12:38:03Z |
| format | Article |
| id | doaj.art-2551b165d35c4fa2a27b87bce7ed1ccf |
| institution | Directory Open Access Journal |
| issn | 1471-2407 |
| language | English |
| last_indexed | 2024-04-24T12:38:03Z |
| publishDate | 2024-04-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cancer |
| spelling | doaj.art-2551b165d35c4fa2a27b87bce7ed1ccf2024-04-07T11:21:22ZengBMCBMC Cancer1471-24072024-04-0124111410.1186/s12885-024-12174-0A radiomics signature derived from CT imaging to predict MSI status and immunotherapy outcomes in gastric cancer: a multi-cohort studyPeng-chao Zhan0Shuo Yang1Xing Liu2Yu-yuan Zhang3Rui Wang4Jia-xing Wang5Qing-ya Qiu6Yu Gao7Dong-bo Lv8Li-ming Li9Cheng-long Luo10Zhi-wei Hu11Zhen Li12Pei-jie Lyu13Pan Liang14Jian-bo Gao15Department of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, The Second Hospital, Cheello College of Medicine, Shandong UniversityDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Interventional Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Interventional Medicine, The Second Hospital, Cheello College of Medicine, Shandong UniversityZhengzhou University Medical CollegeDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Interventional Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, The First Affiliated Hospital of Zhengzhou UniversityAbstract Background Accurate microsatellite instability (MSI) testing is essential for identifying gastric cancer (GC) patients eligible for immunotherapy. We aimed to develop and validate a CT-based radiomics signature to predict MSI and immunotherapy outcomes in GC. Methods This retrospective multicohort study included a total of 457 GC patients from two independent medical centers in China and The Cancer Imaging Archive (TCIA) databases. The primary cohort (n = 201, center 1, 2017–2022), was used for signature development via Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression analysis. Two independent immunotherapy cohorts, one from center 1 (n = 184, 2018–2021) and another from center 2 (n = 43, 2020–2021), were utilized to assess the signature’s association with immunotherapy response and survival. Diagnostic efficiency was evaluated using the area under the receiver operating characteristic curve (AUC), and survival outcomes were analyzed via the Kaplan-Meier method. The TCIA cohort (n = 29) was included to evaluate the immune infiltration landscape of the radiomics signature subgroups using both CT images and mRNA sequencing data. Results Nine radiomics features were identified for signature development, exhibiting excellent discriminative performance in both the training (AUC: 0.851, 95%CI: 0.782, 0.919) and validation cohorts (AUC: 0.816, 95%CI: 0.706, 0.926). The radscore, calculated using the signature, demonstrated strong predictive abilities for objective response in immunotherapy cohorts (AUC: 0.734, 95%CI: 0.662, 0.806; AUC: 0.724, 95%CI: 0.572, 0.877). Additionally, the radscore showed a significant association with PFS and OS, with GC patients with a low radscore experiencing a significant survival benefit from immunotherapy. Immune infiltration analysis revealed significantly higher levels of CD8 + T cells, activated CD4 + B cells, and TNFRSF18 expression in the low radscore group, while the high radscore group exhibited higher levels of T cells regulatory and HHLA2 expression. Conclusion This study developed a robust radiomics signature with the potential to serve as a non-invasive biomarker for GC’s MSI status and immunotherapy response, demonstrating notable links to post-immunotherapy PFS and OS. Additionally, distinct immune profiles were observed between low and high radscore groups, highlighting their potential clinical implications.https://doi.org/10.1186/s12885-024-12174-0Gastric cancerMSIImmunotherapyRadiomics signaturemRNA-seq |
| spellingShingle | Peng-chao Zhan Shuo Yang Xing Liu Yu-yuan Zhang Rui Wang Jia-xing Wang Qing-ya Qiu Yu Gao Dong-bo Lv Li-ming Li Cheng-long Luo Zhi-wei Hu Zhen Li Pei-jie Lyu Pan Liang Jian-bo Gao A radiomics signature derived from CT imaging to predict MSI status and immunotherapy outcomes in gastric cancer: a multi-cohort study BMC Cancer Gastric cancer MSI Immunotherapy Radiomics signature mRNA-seq |
| title | A radiomics signature derived from CT imaging to predict MSI status and immunotherapy outcomes in gastric cancer: a multi-cohort study |
| title_full | A radiomics signature derived from CT imaging to predict MSI status and immunotherapy outcomes in gastric cancer: a multi-cohort study |
| title_fullStr | A radiomics signature derived from CT imaging to predict MSI status and immunotherapy outcomes in gastric cancer: a multi-cohort study |
| title_full_unstemmed | A radiomics signature derived from CT imaging to predict MSI status and immunotherapy outcomes in gastric cancer: a multi-cohort study |
| title_short | A radiomics signature derived from CT imaging to predict MSI status and immunotherapy outcomes in gastric cancer: a multi-cohort study |
| title_sort | radiomics signature derived from ct imaging to predict msi status and immunotherapy outcomes in gastric cancer a multi cohort study |
| topic | Gastric cancer MSI Immunotherapy Radiomics signature mRNA-seq |
| url | https://doi.org/10.1186/s12885-024-12174-0 |
| work_keys_str_mv | AT pengchaozhan aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT shuoyang aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT xingliu aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT yuyuanzhang aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT ruiwang aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT jiaxingwang aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT qingyaqiu aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT yugao aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT dongbolv aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT limingli aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT chenglongluo aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT zhiweihu aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT zhenli aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT peijielyu aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT panliang aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT jianbogao aradiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT pengchaozhan radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT shuoyang radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT xingliu radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT yuyuanzhang radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT ruiwang radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT jiaxingwang radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT qingyaqiu radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT yugao radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT dongbolv radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT limingli radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT chenglongluo radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT zhiweihu radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT zhenli radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT peijielyu radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT panliang radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy AT jianbogao radiomicssignaturederivedfromctimagingtopredictmsistatusandimmunotherapyoutcomesingastriccanceramulticohortstudy |