Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199
Abstract Background Immunotherapy and radiotherapy play crucial roles in the transformation therapy of locally advanced pancreatic cancer; however, the exploration of effective predictive biomarkers has been unsatisfactory. With the rapid development of radiomics, next-generation sequencing, and mac...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | Cancer Cell International |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12935-025-03639-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594428758327296 |
|---|---|
| author | Liang Qi Xiang Li Jiayao Ni Yali Du Qing Gu Baorui Liu Jian He Juan Du |
| author_facet | Liang Qi Xiang Li Jiayao Ni Yali Du Qing Gu Baorui Liu Jian He Juan Du |
| author_sort | Liang Qi |
| collection | DOAJ |
| description | Abstract Background Immunotherapy and radiotherapy play crucial roles in the transformation therapy of locally advanced pancreatic cancer; however, the exploration of effective predictive biomarkers has been unsatisfactory. With the rapid development of radiomics, next-generation sequencing, and machine learning, there is hope to identify biomarkers that can predict the efficacy of transformative treatment for locally advanced pancreatic cancer through simple and non-invasive clinical methods. Our study focuses on using computed tomography (CT), positron emission tomography/computed tomography (PET/CT), gene mutations, and baseline carbohydrate antigen 199 (CA199) to identify biomarkers for predicting the efficacy of transformative treatment. Methods We retrospectively collected data from 70 patients with locally advanced pancreatic cancer who had undergone a biopsy for pathological diagnosis. These patients had complete baseline enhanced CT images and baseline CA199 results. Among them, 65 patients had efficacy evaluation results after 4 treatment cycles, 54 patients had complete baseline PET/CT images, 51 patients had complete DNA mutation detection results, and 34 patients had both complete PET/CT images and DNA mutation detection results. Additionally, 47 patients had complete available CT images at baseline, after 2 treatment cycles, and after 4 treatment cycles. We extracted radiomic features from the original lesion-enhanced CT images (including baseline and subsequent follow-up CT scans), radiomic features from baseline 18F-fluoro-2-deoxy-2-D-glucose (18F-FDG) PET, and patient-specific features related to abdominal and visceral fat. We used short-term and long-term treatment efficacy as the prediction outcomes and performed statistical and machine learning-based feature selection and COX regression analysis to identify potentially predictive features. Subsequently, we separately or in combination modeled the CT features, PET features, baseline CA199, and gene mutation data to construct efficacy prediction models. Finally, we investigated the mixed effects model of the dynamic changes in CT features at baseline, after 2 treatment cycles, and after 4 treatment cycles on the prediction of short-term treatment efficacy. Results We found that a combination of CT radiomic features, including F1_ gray level co-occurrence matrix (GLCM), F2_gray level run length matrix (GLRLM), F5_neighboring gray tone difference matrix (NGTDM), and F6_Shape, PET radiomic features such as visceral adipose tissue (VAT), tumor-to-liver ratio (T/L), standardized uptake value mean (SUVmean), and GLCM, as well as baseline CA199, can be used to predict short-term treatment efficacy. Baseline CA199, GLCM, IntensityDirect, Shape, and PET/CT features are independent factors for long-term treatment efficacy. In constructing the short-term treatment efficacy prediction model, ensemble learning methods such as adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and RandomForest performed the best. However, in terms of model interpretability, decision tree methods provide the most intuitive display of the predictive details of the model. For the time series data of patients’ baseline CT, CT after 2 treatment cycles, and CT after 4 treatment cycles, long short-term memory (LSTM) modeling yielded better predictive models. Conclusion A multimodal combination of radiomics, DNA mutations, and baseline CA199 can predict the efficacy of transformative treatment in locally advanced pancreatic cancer. Various feature selection methods and multimodal fusion approaches contribute to guiding personalized and precise treatment for pancreatic cancer. |
| format | Article |
| id | doaj-art-9fe237a0ece4412b9e95b1c0d564b9f1 |
| institution | Kabale University |
| issn | 1475-2867 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Cancer Cell International |
| spelling | doaj-art-9fe237a0ece4412b9e95b1c0d564b9f12025-01-19T12:39:34ZengBMCCancer Cell International1475-28672025-01-0125111610.1186/s12935-025-03639-8Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199Liang Qi0Xiang Li1Jiayao Ni2Yali Du3Qing Gu4Baorui Liu5Jian He6Juan Du7The Comprehensive Cancer Centre, Department of Oncology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical SchoolDepartment of PET-CT/MRI, Harbin Medical University Cancer HospitalThe Comprehensive Cancer Centre, Department of Oncology, Nanjing Drum Tower Hospital Clinical College of Nanjing University of Chinese MedicineNational Key Laboratory for Novel Software Technology, Nanjing UniversityNational Key Laboratory for Novel Software Technology, Nanjing UniversityThe Comprehensive Cancer Centre, Department of Oncology, Nanjing Drum Tower Hospital Clinical College of Nanjing University of Chinese MedicineDepartment of Nuclear Medicine, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical SchoolThe Comprehensive Cancer Centre, Department of Oncology, Nanjing Drum Tower Hospital Clinical College of Nanjing University of Chinese MedicineAbstract Background Immunotherapy and radiotherapy play crucial roles in the transformation therapy of locally advanced pancreatic cancer; however, the exploration of effective predictive biomarkers has been unsatisfactory. With the rapid development of radiomics, next-generation sequencing, and machine learning, there is hope to identify biomarkers that can predict the efficacy of transformative treatment for locally advanced pancreatic cancer through simple and non-invasive clinical methods. Our study focuses on using computed tomography (CT), positron emission tomography/computed tomography (PET/CT), gene mutations, and baseline carbohydrate antigen 199 (CA199) to identify biomarkers for predicting the efficacy of transformative treatment. Methods We retrospectively collected data from 70 patients with locally advanced pancreatic cancer who had undergone a biopsy for pathological diagnosis. These patients had complete baseline enhanced CT images and baseline CA199 results. Among them, 65 patients had efficacy evaluation results after 4 treatment cycles, 54 patients had complete baseline PET/CT images, 51 patients had complete DNA mutation detection results, and 34 patients had both complete PET/CT images and DNA mutation detection results. Additionally, 47 patients had complete available CT images at baseline, after 2 treatment cycles, and after 4 treatment cycles. We extracted radiomic features from the original lesion-enhanced CT images (including baseline and subsequent follow-up CT scans), radiomic features from baseline 18F-fluoro-2-deoxy-2-D-glucose (18F-FDG) PET, and patient-specific features related to abdominal and visceral fat. We used short-term and long-term treatment efficacy as the prediction outcomes and performed statistical and machine learning-based feature selection and COX regression analysis to identify potentially predictive features. Subsequently, we separately or in combination modeled the CT features, PET features, baseline CA199, and gene mutation data to construct efficacy prediction models. Finally, we investigated the mixed effects model of the dynamic changes in CT features at baseline, after 2 treatment cycles, and after 4 treatment cycles on the prediction of short-term treatment efficacy. Results We found that a combination of CT radiomic features, including F1_ gray level co-occurrence matrix (GLCM), F2_gray level run length matrix (GLRLM), F5_neighboring gray tone difference matrix (NGTDM), and F6_Shape, PET radiomic features such as visceral adipose tissue (VAT), tumor-to-liver ratio (T/L), standardized uptake value mean (SUVmean), and GLCM, as well as baseline CA199, can be used to predict short-term treatment efficacy. Baseline CA199, GLCM, IntensityDirect, Shape, and PET/CT features are independent factors for long-term treatment efficacy. In constructing the short-term treatment efficacy prediction model, ensemble learning methods such as adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and RandomForest performed the best. However, in terms of model interpretability, decision tree methods provide the most intuitive display of the predictive details of the model. For the time series data of patients’ baseline CT, CT after 2 treatment cycles, and CT after 4 treatment cycles, long short-term memory (LSTM) modeling yielded better predictive models. Conclusion A multimodal combination of radiomics, DNA mutations, and baseline CA199 can predict the efficacy of transformative treatment in locally advanced pancreatic cancer. Various feature selection methods and multimodal fusion approaches contribute to guiding personalized and precise treatment for pancreatic cancer.https://doi.org/10.1186/s12935-025-03639-8Radiomics18F-FDG PET/CTFeature selectionMachine learning |
| spellingShingle | Liang Qi Xiang Li Jiayao Ni Yali Du Qing Gu Baorui Liu Jian He Juan Du Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199 Cancer Cell International Radiomics 18F-FDG PET/CT Feature selection Machine learning |
| title | Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199 |
| title_full | Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199 |
| title_fullStr | Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199 |
| title_full_unstemmed | Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199 |
| title_short | Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199 |
| title_sort | construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on ct 18f fdg pet ct dna mutation and ca199 |
| topic | Radiomics 18F-FDG PET/CT Feature selection Machine learning |
| url | https://doi.org/10.1186/s12935-025-03639-8 |
| work_keys_str_mv | AT liangqi constructionoffeatureselectionandefficacypredictionmodelfortransformationtherapyoflocallyadvancedpancreaticcancerbasedonct18ffdgpetctdnamutationandca199 AT xiangli constructionoffeatureselectionandefficacypredictionmodelfortransformationtherapyoflocallyadvancedpancreaticcancerbasedonct18ffdgpetctdnamutationandca199 AT jiayaoni constructionoffeatureselectionandefficacypredictionmodelfortransformationtherapyoflocallyadvancedpancreaticcancerbasedonct18ffdgpetctdnamutationandca199 AT yalidu constructionoffeatureselectionandefficacypredictionmodelfortransformationtherapyoflocallyadvancedpancreaticcancerbasedonct18ffdgpetctdnamutationandca199 AT qinggu constructionoffeatureselectionandefficacypredictionmodelfortransformationtherapyoflocallyadvancedpancreaticcancerbasedonct18ffdgpetctdnamutationandca199 AT baoruiliu constructionoffeatureselectionandefficacypredictionmodelfortransformationtherapyoflocallyadvancedpancreaticcancerbasedonct18ffdgpetctdnamutationandca199 AT jianhe constructionoffeatureselectionandefficacypredictionmodelfortransformationtherapyoflocallyadvancedpancreaticcancerbasedonct18ffdgpetctdnamutationandca199 AT juandu constructionoffeatureselectionandefficacypredictionmodelfortransformationtherapyoflocallyadvancedpancreaticcancerbasedonct18ffdgpetctdnamutationandca199 |