Predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes
Abstract Background The abundance of immune and stromal cells in the tumor microenvironment (TME) is informative of levels of inflammation, angiogenesis, and desmoplasia. Radiomics, an approach of extracting quantitative features from radiological imaging to characterize diseases, have been shown to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-04-01
|
| Series: | BMC Cancer |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12885-021-08122-x |
| _version_ | 1818730093027000320 |
|---|---|
| author | Dooman Arefan Ryan M. Hausler Jules H. Sumkin Min Sun Shandong Wu |
| author_facet | Dooman Arefan Ryan M. Hausler Jules H. Sumkin Min Sun Shandong Wu |
| author_sort | Dooman Arefan |
| collection | DOAJ |
| description | Abstract Background The abundance of immune and stromal cells in the tumor microenvironment (TME) is informative of levels of inflammation, angiogenesis, and desmoplasia. Radiomics, an approach of extracting quantitative features from radiological imaging to characterize diseases, have been shown to predict molecular classification, cancer recurrence risk, and many other disease outcomes. However, the ability of radiomics methods to predict the abundance of various cell types in the TME remains unclear. In this study, we employed a radio-genomics approach and machine learning models to predict the infiltration of 10 cell types in breast cancer lesions utilizing radiomic features extracted from breast Dynamic Contrast Enhanced Magnetic Resonance Imaging. Methods We performed a retrospective study utilizing 73 patients from two independent institutions with imaging and gene expression data provided by The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA), respectively. A set of 199 radiomic features including shape-based, morphological, texture, and kinetic characteristics were extracted from the lesion volumes. To capture one-to-one relationships between radiomic features and cell type abundance, we performed linear regression on each radiomic feature/cell type abundance combination. Each regression model was tested for statistical significance. In addition, multivariate models were built for the cell type infiltration status (i.e. “high” vs “low”) prediction. A feature selection process via Recursive Feature Elimination was applied to the radiomic features on the training set. The classification models took the form of a binary logistic extreme gradient boosting framework. Two evaluation methods including leave-one-out cross validation and external independent test, were used for radiomic model learning and testing. The models’ performance was measured via area under the receiver operating characteristic curve (AUC). Results Univariate relationships were identified between a set of radiomic features and the abundance of fibroblasts. Multivariate models yielded leave-one-out cross validation AUCs ranging from 0.5 to 0.83, and independent test AUCs ranging from 0.5 to 0.68 for the multiple cell type invasion predictions. Conclusions On two independent breast cancer cohorts, breast MRI-derived radiomics are associated with the tumor’s microenvironment in terms of the abundance of several cell types. Further evaluation with larger cohorts is needed. |
| first_indexed | 2024-12-17T22:56:18Z |
| format | Article |
| id | doaj.art-98040f8e13ba4178a895e104e1a1f4c7 |
| institution | Directory Open Access Journal |
| issn | 1471-2407 |
| language | English |
| last_indexed | 2024-12-17T22:56:18Z |
| publishDate | 2021-04-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cancer |
| spelling | doaj.art-98040f8e13ba4178a895e104e1a1f4c72022-12-21T21:29:33ZengBMCBMC Cancer1471-24072021-04-012111910.1186/s12885-021-08122-xPredicting cell invasion in breast tumor microenvironment from radiological imaging phenotypesDooman Arefan0Ryan M. Hausler1Jules H. Sumkin2Min Sun3Shandong Wu4Department of Radiology, University of Pittsburgh School of MedicineDepartment of Biomedical Informatics, University of Pittsburgh School of MedicineDepartment of Radiology, University of Pittsburgh School of MedicineDivision of Oncology, University of Pittsburgh Medical Center Hillman Cancer Center at St. MargaretDepartment of Radiology, University of Pittsburgh School of MedicineAbstract Background The abundance of immune and stromal cells in the tumor microenvironment (TME) is informative of levels of inflammation, angiogenesis, and desmoplasia. Radiomics, an approach of extracting quantitative features from radiological imaging to characterize diseases, have been shown to predict molecular classification, cancer recurrence risk, and many other disease outcomes. However, the ability of radiomics methods to predict the abundance of various cell types in the TME remains unclear. In this study, we employed a radio-genomics approach and machine learning models to predict the infiltration of 10 cell types in breast cancer lesions utilizing radiomic features extracted from breast Dynamic Contrast Enhanced Magnetic Resonance Imaging. Methods We performed a retrospective study utilizing 73 patients from two independent institutions with imaging and gene expression data provided by The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA), respectively. A set of 199 radiomic features including shape-based, morphological, texture, and kinetic characteristics were extracted from the lesion volumes. To capture one-to-one relationships between radiomic features and cell type abundance, we performed linear regression on each radiomic feature/cell type abundance combination. Each regression model was tested for statistical significance. In addition, multivariate models were built for the cell type infiltration status (i.e. “high” vs “low”) prediction. A feature selection process via Recursive Feature Elimination was applied to the radiomic features on the training set. The classification models took the form of a binary logistic extreme gradient boosting framework. Two evaluation methods including leave-one-out cross validation and external independent test, were used for radiomic model learning and testing. The models’ performance was measured via area under the receiver operating characteristic curve (AUC). Results Univariate relationships were identified between a set of radiomic features and the abundance of fibroblasts. Multivariate models yielded leave-one-out cross validation AUCs ranging from 0.5 to 0.83, and independent test AUCs ranging from 0.5 to 0.68 for the multiple cell type invasion predictions. Conclusions On two independent breast cancer cohorts, breast MRI-derived radiomics are associated with the tumor’s microenvironment in terms of the abundance of several cell types. Further evaluation with larger cohorts is needed.https://doi.org/10.1186/s12885-021-08122-xBreast cancerRadio-genomicsMachine learningTumor microenvironmentCell typeRadiomics |
| spellingShingle | Dooman Arefan Ryan M. Hausler Jules H. Sumkin Min Sun Shandong Wu Predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes BMC Cancer Breast cancer Radio-genomics Machine learning Tumor microenvironment Cell type Radiomics |
| title | Predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes |
| title_full | Predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes |
| title_fullStr | Predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes |
| title_full_unstemmed | Predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes |
| title_short | Predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes |
| title_sort | predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes |
| topic | Breast cancer Radio-genomics Machine learning Tumor microenvironment Cell type Radiomics |
| url | https://doi.org/10.1186/s12885-021-08122-x |
| work_keys_str_mv | AT doomanarefan predictingcellinvasioninbreasttumormicroenvironmentfromradiologicalimagingphenotypes AT ryanmhausler predictingcellinvasioninbreasttumormicroenvironmentfromradiologicalimagingphenotypes AT juleshsumkin predictingcellinvasioninbreasttumormicroenvironmentfromradiologicalimagingphenotypes AT minsun predictingcellinvasioninbreasttumormicroenvironmentfromradiologicalimagingphenotypes AT shandongwu predictingcellinvasioninbreasttumormicroenvironmentfromradiologicalimagingphenotypes |