Comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high-grade glioma treated with immunotherapy
Abstract Background Radiomic analysis of quantitative features extracted from segmented medical images can be used for predictive modeling of prognosis in brain tumor patients. Manual segmentation of the tumor components is time-consuming and poses significant reproducibility issues. We compare the...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | Cancer Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40644-024-00818-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585420922159104 |
|---|---|
| author | Qi Wan Clifford Lindsay Chenxi Zhang Jisoo Kim Xin Chen Jing Li Raymond Y. Huang David A. Reardon Geoffrey S. Young Lei Qin |
| author_facet | Qi Wan Clifford Lindsay Chenxi Zhang Jisoo Kim Xin Chen Jing Li Raymond Y. Huang David A. Reardon Geoffrey S. Young Lei Qin |
| author_sort | Qi Wan |
| collection | DOAJ |
| description | Abstract Background Radiomic analysis of quantitative features extracted from segmented medical images can be used for predictive modeling of prognosis in brain tumor patients. Manual segmentation of the tumor components is time-consuming and poses significant reproducibility issues. We compare the prediction of overall survival (OS) in recurrent high-grade glioma(HGG) patients undergoing immunotherapy, using deep learning (DL) classification networks along with radiomic signatures derived from manual and convolutional neural networks (CNN) automated segmentation. Materials and methods We retrospectively retrieved 154 cases of recurrent HGG from multiple centers. Tumor segmentation was performed by expert radiologists and a convolutional neural network (CNN). From the segmented tumors, 2553 radiomic features were extracted for each case. A robust feature subset was selected using intraclass correlation coefficient analysis between manual and automated segmentations. The data was divided into a 9:1 ratio and validated through ten-fold cross-validation and tested on a rotating test set. Features selection was done by the Kruskal–Wallis test. The Radiomics-based OS predictions, generated using Support Vector Machine (SVM), were compared between the two segmentation approaches and against OS prediction by the CNN model adapted for classification. Model efficacy was evaluated using the area under the receiver operating characteristic curve (AUC). Results The clinical model AUC for OS prediction was 0.640 ± 0.013 (mean ± 95% confidence interval) in the training set and 0.610 ± 0.131 in the test set. The radiomics prediction of OS based on manual segmentation outperformed automatic segmentation (AUC of 0.662 ± 0.122 vs. 0.471 ± 0.086, respectively) in the test set. Robust features improved the performance of manual segmentation to AUC of 0.700 ± 0.102, of automated segmentation to 0.554 ± 0.085. The CNN prognosis model demonstrated promising results, with an average AUC of 0.755 ± 0.071 for training sets and 0.700 ± 0.101 for the test set. Conclusion Manual segmentation-derived radiomic features outperformed automated segmentation-derived features for predicting OS in recurrent high-grade glioma patients undergoing immunotherapy. The end-to-end CNN prognosis model performed similarly to radiomics modeling using manual-segmentation-derived features without the need for segmentation. The potential time-saving must be weighed against the lower interpretability of end-to-end black box modeling. |
| format | Article |
| id | doaj-art-4f64974697234e80b48186832708d64f |
| institution | Kabale University |
| issn | 1470-7330 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Cancer Imaging |
| spelling | doaj-art-4f64974697234e80b48186832708d64f2025-01-26T12:50:37ZengBMCCancer Imaging1470-73302025-01-012511910.1186/s40644-024-00818-0Comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high-grade glioma treated with immunotherapyQi Wan0Clifford Lindsay1Chenxi Zhang2Jisoo Kim3Xin Chen4Jing Li5Raymond Y. Huang6David A. Reardon7Geoffrey S. Young8Lei Qin9Department of Radiology, the Key Laboratory of Advanced Interdisciplinary Studies Center, the First Affiliated Hospital of Guangzhou Medical UniversityDepartment of Radiology, Division of Biomedical Imaging and Bioengineering, UMass Chan Medical SchoolDigital Medical Research Center, School of Basic Medical Sciences, Fudan UniversityDepartment of Radiology, Brigham and Women’s Hospital, Harvard Medical SchoolGuangzhou First People’s Hospital, School of Medicine, South China University of TechnologyDepartment of Radiology, the Affiliated Cancer Hospital of Zhengzhou University (Henan Cancer Hospital)Department of Radiology, Brigham and Women’s Hospital, Harvard Medical SchoolCenter for Neuro-Oncology, Dana-Farber Cancer Institute, Harvard Medical SchoolDepartment of Radiology, Brigham and Women’s Hospital, Harvard Medical SchoolDepartment of Imaging, Dana-Farber Cancer Institute, Harvard Medical SchoolAbstract Background Radiomic analysis of quantitative features extracted from segmented medical images can be used for predictive modeling of prognosis in brain tumor patients. Manual segmentation of the tumor components is time-consuming and poses significant reproducibility issues. We compare the prediction of overall survival (OS) in recurrent high-grade glioma(HGG) patients undergoing immunotherapy, using deep learning (DL) classification networks along with radiomic signatures derived from manual and convolutional neural networks (CNN) automated segmentation. Materials and methods We retrospectively retrieved 154 cases of recurrent HGG from multiple centers. Tumor segmentation was performed by expert radiologists and a convolutional neural network (CNN). From the segmented tumors, 2553 radiomic features were extracted for each case. A robust feature subset was selected using intraclass correlation coefficient analysis between manual and automated segmentations. The data was divided into a 9:1 ratio and validated through ten-fold cross-validation and tested on a rotating test set. Features selection was done by the Kruskal–Wallis test. The Radiomics-based OS predictions, generated using Support Vector Machine (SVM), were compared between the two segmentation approaches and against OS prediction by the CNN model adapted for classification. Model efficacy was evaluated using the area under the receiver operating characteristic curve (AUC). Results The clinical model AUC for OS prediction was 0.640 ± 0.013 (mean ± 95% confidence interval) in the training set and 0.610 ± 0.131 in the test set. The radiomics prediction of OS based on manual segmentation outperformed automatic segmentation (AUC of 0.662 ± 0.122 vs. 0.471 ± 0.086, respectively) in the test set. Robust features improved the performance of manual segmentation to AUC of 0.700 ± 0.102, of automated segmentation to 0.554 ± 0.085. The CNN prognosis model demonstrated promising results, with an average AUC of 0.755 ± 0.071 for training sets and 0.700 ± 0.101 for the test set. Conclusion Manual segmentation-derived radiomic features outperformed automated segmentation-derived features for predicting OS in recurrent high-grade glioma patients undergoing immunotherapy. The end-to-end CNN prognosis model performed similarly to radiomics modeling using manual-segmentation-derived features without the need for segmentation. The potential time-saving must be weighed against the lower interpretability of end-to-end black box modeling.https://doi.org/10.1186/s40644-024-00818-0High-grade gliomaConvolutional neural networksDeep learningRadiomicsOverall survival |
| spellingShingle | Qi Wan Clifford Lindsay Chenxi Zhang Jisoo Kim Xin Chen Jing Li Raymond Y. Huang David A. Reardon Geoffrey S. Young Lei Qin Comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high-grade glioma treated with immunotherapy Cancer Imaging High-grade glioma Convolutional neural networks Deep learning Radiomics Overall survival |
| title | Comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high-grade glioma treated with immunotherapy |
| title_full | Comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high-grade glioma treated with immunotherapy |
| title_fullStr | Comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high-grade glioma treated with immunotherapy |
| title_full_unstemmed | Comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high-grade glioma treated with immunotherapy |
| title_short | Comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high-grade glioma treated with immunotherapy |
| title_sort | comparative analysis of deep learning and radiomic signatures for overall survival prediction in recurrent high grade glioma treated with immunotherapy |
| topic | High-grade glioma Convolutional neural networks Deep learning Radiomics Overall survival |
| url | https://doi.org/10.1186/s40644-024-00818-0 |
| work_keys_str_mv | AT qiwan comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy AT cliffordlindsay comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy AT chenxizhang comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy AT jisookim comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy AT xinchen comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy AT jingli comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy AT raymondyhuang comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy AT davidareardon comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy AT geoffreysyoung comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy AT leiqin comparativeanalysisofdeeplearningandradiomicsignaturesforoverallsurvivalpredictioninrecurrenthighgradegliomatreatedwithimmunotherapy |