Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III–IV d-MMR/MSI-H colorectal cancer
Background Neoadjuvant immunotherapy significantly improves the pathological complete response (pCR) rate in colorectal cancer (CRC). However, the lack of reliable tools to accurately identify responders remains a key barrier to its widespread clinical adoption. This study aimed to develop an interp...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2025-08-01
|
| Series: | Journal for ImmunoTherapy of Cancer |
| Online Access: | https://jitc.bmj.com/content/13/8/e011569.full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849774330912702464 |
|---|---|
| author | Xuan Zhang Zhenhui Li Yiwen Zhang Yanli Li Xi Zhong Wenjing Jiang Xiaobo Chen Zaiyi Liu Liebin Huang Caixia Zhang Lizhu Liu Ruimin You Xiaoping Yi |
| author_facet | Xuan Zhang Zhenhui Li Yiwen Zhang Yanli Li Xi Zhong Wenjing Jiang Xiaobo Chen Zaiyi Liu Liebin Huang Caixia Zhang Lizhu Liu Ruimin You Xiaoping Yi |
| author_sort | Xuan Zhang |
| collection | DOAJ |
| description | Background Neoadjuvant immunotherapy significantly improves the pathological complete response (pCR) rate in colorectal cancer (CRC). However, the lack of reliable tools to accurately identify responders remains a key barrier to its widespread clinical adoption. This study aimed to develop an interpretable radiomics model guided by immunophenotypes to predict response to preoperative immunotherapy in CRC, with the goal of enabling more precise and personalized treatment strategies.Methods First, we retrospectively collected 108 patients with CRC from the center who underwent preoperative CT and RNA sequencing. Immunophenotypes were characterized through unsupervised clustering of tumor-infiltrating immune cells at RNA level, with subsequent validation by CD3 and CD8 spatial distributions at immunohistochemical (IHC) level. Furthermore, patients from center II (n=19) and center III (n=22) receiving neoadjuvant immunotherapy were assigned to training and validation cohorts. Through a two-stage selection process, immunophenotype-associated radiomic features were initially identified, followed by immunotherapy response-related radiomics features that were further identified. Eventually, an interpretable immunotherapy response prediction model was developed by integrating a decision tree algorithm with SHapley Additive exPlanations (SHAP) analysis.Results Two immunophenotypes (immune-hot and immune-cold) were identified, compared with the immune-cold, the former exhibited more abundant RNA-based immune cell infiltration and higher densities of CD3 and CD8 T cells in both the core tumor and invasive margin areas. A decision tree model integrating three key radiomic features achieved an area under the curve of 0.904 (95% CI: 0.679 to 1.000) in an independent validation cohort. SHAP analysis identified higher large dependence emphasis and lower variance as potential predictors of pCR, which quantified the homogeneity of the tumors.Conclusion Two immunophenotypes were constructed and identified at both bulk RNA level and IHC level. An interpretable and accurate radiomics model was constructed to guide personalized immunotherapy strategies in clinical practice. |
| format | Article |
| id | doaj-art-3f8b952d5f7e4426b0df2fcb36020760 |
| institution | DOAJ |
| issn | 2051-1426 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | Journal for ImmunoTherapy of Cancer |
| spelling | doaj-art-3f8b952d5f7e4426b0df2fcb360207602025-08-20T03:01:45ZengBMJ Publishing GroupJournal for ImmunoTherapy of Cancer2051-14262025-08-0113810.1136/jitc-2025-011569Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III–IV d-MMR/MSI-H colorectal cancerXuan Zhang0Zhenhui Li1Yiwen Zhang2Yanli Li3Xi Zhong4Wenjing Jiang5Xiaobo Chen6Zaiyi Liu7Liebin Huang8Caixia Zhang9Lizhu Liu10Ruimin You11Xiaoping Yi12Department of Colorectal surgery, The Third Affiliated Hospital of Kunming Medical University，Yunnan Cancer Hospital，Peking University Cancer Hospital Yunnan, Kunming, Yunnan, ChinaDepartment of Radiology, The Third Affiliated Hospital of Kunming Medical University，Yunnan Cancer Hospital，Peking University Cancer Hospital Yunnan, Kunming, Yunnan, ChinaDepartment of Radiology, The Third Affiliated Hospital of Kunming Medical University，Yunnan Cancer Hospital，Peking University Cancer Hospital Yunnan, Kunming, Yunnan, ChinaDepartment of Radiology, The Third Affiliated Hospital of Kunming Medical University，Yunnan Cancer Hospital，Peking University Cancer Hospital Yunnan, Kunming, Yunnan, ChinaDepartment of Medical Imaging, Guangzhou Medical University Affiliated Cancer Hospital, Guangzhou, Guangdong, ChinaDepartment of Radiology, Guangdong Provincial People`s Hospital, Guangdong Academy of Medical Science, Guangzhou, Guangdong, ChinaDepartment of Radiology, Guangdong Provincial People`s Hospital, Guangdong Academy of Medical Science, Guangzhou, Guangdong, ChinaDepartment of Radiology, Guangdong Provincial People`s Hospital, Guangdong Academy of Medical Science, Guangzhou, Guangdong, ChinaDepartment of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong, ChinaDepartment of Radiology, The Third Affiliated Hospital of Kunming Medical University，Yunnan Cancer Hospital，Peking University Cancer Hospital Yunnan, Kunming, Yunnan, ChinaDepartment of Radiology, The Third Affiliated Hospital of Kunming Medical University，Yunnan Cancer Hospital，Peking University Cancer Hospital Yunnan, Kunming, Yunnan, ChinaDepartment of Radiology, The Third Affiliated Hospital of Kunming Medical University，Yunnan Cancer Hospital，Peking University Cancer Hospital Yunnan, Kunming, Yunnan, ChinaDepartment of Radiology, Central South University, Changsha, Hunan, ChinaBackground Neoadjuvant immunotherapy significantly improves the pathological complete response (pCR) rate in colorectal cancer (CRC). However, the lack of reliable tools to accurately identify responders remains a key barrier to its widespread clinical adoption. This study aimed to develop an interpretable radiomics model guided by immunophenotypes to predict response to preoperative immunotherapy in CRC, with the goal of enabling more precise and personalized treatment strategies.Methods First, we retrospectively collected 108 patients with CRC from the center who underwent preoperative CT and RNA sequencing. Immunophenotypes were characterized through unsupervised clustering of tumor-infiltrating immune cells at RNA level, with subsequent validation by CD3 and CD8 spatial distributions at immunohistochemical (IHC) level. Furthermore, patients from center II (n=19) and center III (n=22) receiving neoadjuvant immunotherapy were assigned to training and validation cohorts. Through a two-stage selection process, immunophenotype-associated radiomic features were initially identified, followed by immunotherapy response-related radiomics features that were further identified. Eventually, an interpretable immunotherapy response prediction model was developed by integrating a decision tree algorithm with SHapley Additive exPlanations (SHAP) analysis.Results Two immunophenotypes (immune-hot and immune-cold) were identified, compared with the immune-cold, the former exhibited more abundant RNA-based immune cell infiltration and higher densities of CD3 and CD8 T cells in both the core tumor and invasive margin areas. A decision tree model integrating three key radiomic features achieved an area under the curve of 0.904 (95% CI: 0.679 to 1.000) in an independent validation cohort. SHAP analysis identified higher large dependence emphasis and lower variance as potential predictors of pCR, which quantified the homogeneity of the tumors.Conclusion Two immunophenotypes were constructed and identified at both bulk RNA level and IHC level. An interpretable and accurate radiomics model was constructed to guide personalized immunotherapy strategies in clinical practice.https://jitc.bmj.com/content/13/8/e011569.full |
| spellingShingle | Xuan Zhang Zhenhui Li Yiwen Zhang Yanli Li Xi Zhong Wenjing Jiang Xiaobo Chen Zaiyi Liu Liebin Huang Caixia Zhang Lizhu Liu Ruimin You Xiaoping Yi Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III–IV d-MMR/MSI-H colorectal cancer Journal for ImmunoTherapy of Cancer |
| title | Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III–IV d-MMR/MSI-H colorectal cancer |
| title_full | Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III–IV d-MMR/MSI-H colorectal cancer |
| title_fullStr | Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III–IV d-MMR/MSI-H colorectal cancer |
| title_full_unstemmed | Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III–IV d-MMR/MSI-H colorectal cancer |
| title_short | Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III–IV d-MMR/MSI-H colorectal cancer |
| title_sort | immunophenotype guided interpretable radiomics model for predicting neoadjuvant anti pd 1 response in stage iii iv d mmr msi h colorectal cancer |
| url | https://jitc.bmj.com/content/13/8/e011569.full |
| work_keys_str_mv | AT xuanzhang immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT zhenhuili immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT yiwenzhang immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT yanlili immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT xizhong immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT wenjingjiang immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT xiaobochen immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT zaiyiliu immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT liebinhuang immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT caixiazhang immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT lizhuliu immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT ruiminyou immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer AT xiaopingyi immunophenotypeguidedinterpretableradiomicsmodelforpredictingneoadjuvantantipd1responseinstageiiiivdmmrmsihcolorectalcancer |