Whole‐Volume Tumor <scp>MRI</scp> Radiomics for Prognostic Modeling in Endometrial Cancer

Fasmer, Kristine Eldevik; Hodneland, Erlend; Dybvik, Julie Andrea; Wagner-Larsen, Kari; Trovik, Jone; Salvesen, Øyvind; Krakstad, Camilla; Haldorsen, Ingfrid S.

doi:10.1002/jmri.27444

Cited by 62 publications

(77 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This suggests a large overlap in prognostic power for many of the texture variables, and that the employed model for analyzing the texture variables impacts the derived results. The LASSO Cox regression model used for radiomic features selection and the risk score assessment in the present study is, however, in line with methods used by others to develop RPIs in cancers [ 21 , 29 , 30 , 31 ].…”

Section: Discussionmentioning

confidence: 71%

An MRI-Based Radiomic Prognostic Index Predicts Poor Outcome and Specific Genetic Alterations in Endometrial Cancer

Jacob

Dybvik

Ytre-Hauge

et al. 2021

JCM

Self Cite

View full text Add to dashboard Cite

Integrative tumor characterization linking radiomic profiles to corresponding gene expression profiles has the potential to identify specific genetic alterations based on non-invasive radiomic profiling in cancer. The aim of this study was to develop and validate a radiomic prognostic index (RPI) based on preoperative magnetic resonance imaging (MRI) and assess possible associations between the RPI and gene expression profiles in endometrial cancer patients. Tumor texture features were extracted from preoperative 2D MRI in 177 endometrial cancer patients. The RPI was developed using least absolute shrinkage and selection operator (LASSO) Cox regression in a study cohort (n = 95) and validated in an MRI validation cohort (n = 82). Transcriptional alterations associated with the RPI were investigated in the study cohort. Potential prognostic markers were further explored for validation in an mRNA validation cohort (n = 161). The RPI included four tumor texture features, and a high RPI was significantly associated with poor disease-specific survival in both the study cohort (p < 0.001) and the MRI validation cohort (p = 0.030). The association between RPI and gene expression profiles revealed 46 significantly differentially expressed genes in patients with a high RPI versus a low RPI (p < 0.001). The most differentially expressed genes, COMP and DMBT1, were significantly associated with disease-specific survival in both the study cohort and the mRNA validation cohort. In conclusion, a high RPI score predicts poor outcome and is associated with specific gene expression profiles in endometrial cancer patients. The promising link between radiomic tumor profiles and molecular alterations may aid in developing refined prognostication and targeted treatment strategies in endometrial cancer.

show abstract

Section: Discussionmentioning

confidence: 71%

An MRI-Based Radiomic Prognostic Index Predicts Poor Outcome and Specific Genetic Alterations in Endometrial Cancer

Jacob

Dybvik

Ytre-Hauge

et al. 2021

JCM

Self Cite

View full text Add to dashboard Cite

show abstract

“…The study of Yan et al [14] manifested that MRI-based radiomics achieved high diagnostic performance for predicting LVSI of EC preoperatively, and was helpful for early identi cation of poor prognosis. In addition, the whole-tumor radiomic features were found to signi cantly predict progression-free survival at hazard ratios of 4.6-9.8 in the research of Fasmer et al [33] , albeit in a small sample size. Although the sample size, MRI sequence, and radiomic parameter extraction methods were different in the previous study, we cannot deny that radiomics and texture analysis may mine more prognostic information than clinical factors, and can be used as a biomarker to assist clinical practice.…”

Section: Discussionmentioning

confidence: 87%

MRI-based Radiomics and ADC Values Are Related to Recurrence of Endometrial Carcinoma：A Preliminary Analysis

Zhang

Fang

Dong

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: To identify predictive value of apparent diffusion coefficient (ADC) values and magnetic resonance imaging (MRI)-based radiomics for all recurrences in patients with endometrial carcinoma (EC).Methods: One hundred and seventy-four EC patients who were treated with operation and followed up in our institution were retrospectively reviewed. Baseline clinicopathological features and ADC values were analyzed. Radiomic parameters were extracted on T2 weighted imaging and screened by logistic regression, and then a radiomics signature was developed to calculate the radiomic score (radscore). Kaplan–Meier analysis was performed and a Cox regression model was used to evaluate the correlation between clinicopathological features, ADC values and radiology with recurrence.Results: ADC values showed inverse correlation with recurrence, while radscore was positively associated with recurrence. In univariate analyses, FIGO stage, pathological types, myometrial invasion, lymphovascular space invasion (LVSI), ADC value and radscore were associated with recurrence. In multivariate Cox analysis, pathological types, ADC and radscore were independent risk factors for recurrence.Conclusions: ADC value and radscore were independent predictors of recurrence of EC, which can supplement prognostic information in addition to clinicopathological information and provide basis for individualized treatment and follow-up plan.

show abstract

“…An AUC of MLR was confirmed to 0.840, and a discrimination accuracy of 72.2% and specificity of 77.8% for the testing dataset. However, the AUC, sensitivity, and specificity of the AdaBoost in the testing dataset relative dropper are 68.5, 66.7, and 66.7% (26)(27)(28).…”

Section: Discussionmentioning

confidence: 92%

Machine Learning Models on ADC Features to Assess Brain Changes of Children With Pierre Robin Sequence

et al. 2021

View full text Add to dashboard Cite

In order to evaluate brain changes in young children with Pierre Robin sequence (PRs) using machine learning based on apparent diffusion coefficient (ADC) features, we retrospectively enrolled a total of 60 cases (42 in the training dataset and 18 in the testing dataset) which included 30 PRs and 30 controls from the Children's Hospital Affiliated to the Nanjing Medical University from January 2017–December 2019. There were 21 and nine PRs cases in each dataset, with the remainder belonging to the control group in the same age range. A total of 105 ADC features were extracted from magnetic resonance imaging (MRI) data. Features were pruned using least absolute shrinkage and selection operator (LASSO) regression and seven ADC features were developed as the optimal signatures for training machine learning models. Support vector machine (SVM) achieved an area under the receiver operating characteristic curve (AUC) of 0.99 for the training set and 0.85 for the testing set. The AUC of the multivariable logistic regression (MLR) and the AdaBoost for the training and validation dataset were 0.98/0.84 and 0.94/0.69, respectively. Based on the ADC features, the two groups of cases (i.e., the PRs group and the control group) could be well-distinguished by the machine learning models, indicating that there is a significant difference in brain development between children with PRs and normal controls.

show abstract

Whole‐Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer

Cited by 62 publications

References 32 publications

An MRI-Based Radiomic Prognostic Index Predicts Poor Outcome and Specific Genetic Alterations in Endometrial Cancer

An MRI-Based Radiomic Prognostic Index Predicts Poor Outcome and Specific Genetic Alterations in Endometrial Cancer

MRI-based Radiomics and ADC Values Are Related to Recurrence of Endometrial Carcinoma：A Preliminary Analysis

Machine Learning Models on ADC Features to Assess Brain Changes of Children With Pierre Robin Sequence

Contact Info

Product

Resources

About