Dataset Information

Whole-Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer.

ABSTRACT:

Background

In endometrial cancer (EC), preoperative pelvic MRI is recommended for local staging, while final tumor stage and grade are established by surgery and pathology. MRI-based radiomic tumor profiling may aid in preoperative risk-stratification and support clinical treatment decisions in EC.

Purpose

To develop MRI-based whole-volume tumor radiomic signatures for prediction of aggressive EC disease.

Study type

Retrospective.

Population

A total of 138 women with histologically confirmed EC, divided into training (n_T = 108) and validation cohorts (n_V = 30).

Field strength/sequence

Axial oblique T₁ -weighted gradient echo volumetric interpolated breath-hold examination (VIBE) at 1.5T (71/138 patients) and DIXON VIBE at 3T (67/138 patients) at 2?minutes postcontrast injection.

Assessment

Primary tumors were manually segmented by two radiologists with 4 and 8?years' of experience. Radiomic tumor features were computed and used for prediction of surgicopathologically-verified deep (?50%) myometrial invasion (DMI), lymph node metastases (LNM), advanced stage (FIGO III?+?IV), nonendometrioid (NE) histology, and high-grade endometrioid tumors (E3). Corresponding analyses were also conducted using radiomics extracted from the axial oblique image slice depicting the largest tumor area.

Statistical tests

Logistic least absolute shrinkage and selection operator (LASSO) was applied for radiomic modeling in the training cohort. The diagnostic performances of the radiomic signatures were evaluated by area under the receiver operating characteristic curve in the training (AUC_T ) and validation (AUC_V ) cohorts. Progression-free survival was assessed using the Kaplan-Meier and Cox proportional hazard model.

Results

The whole-tumor radiomic signatures yielded AUC_T /AUC_V of 0.84/0.76 for predicting DMI, 0.73/0.72 for LNM, 0.71/0.68 for FIGO III?+?IV, 0.68/0.74 for NE histology, and 0.79/0.63 for high-grade (E3) tumor. Single-slice radiomics yielded comparable AUC_T but significantly lower AUC_V for LNM and FIGO III?+?IV (both P?T to the whole-tumor radiomic signatures for prediction of DMI, LNM, FIGO III?+?IV, and NE, but significantly lower AUC_T for E3 tumors (P?Data conclusionMRI-based whole-tumor radiomic signatures yield medium-to-high diagnostic performance for predicting aggressive EC disease. The signatures may aid in preoperative risk assessment and hence guide personalized treatment strategies in EC.

Level of evidence

4 TECHNICAL EFFICACY STAGE: 2.

SUBMITTER: Fasmer KE

PROVIDER: S-EPMC7894560 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Whole-Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer.

Fasmer Kristine E KE Hodneland Erlend E Dybvik Julie A JA Wagner-Larsen Kari K Trovik Jone J Salvesen Øyvind Ø Krakstad Camilla C Haldorsen Ingfrid H S IHS

Journal of magnetic resonance imaging : JMRI 20201116 3

<h4>Background</h4>In endometrial cancer (EC), preoperative pelvic MRI is recommended for local staging, while final tumor stage and grade are established by surgery and pathology. MRI-based radiomic tumor profiling may aid in preoperative risk-stratification and support clinical treatment decisions in EC.<h4>Purpose</h4>To develop MRI-based whole-volume tumor radiomic signatures for prediction of aggressive EC disease.<h4>Study type</h4>Retrospective.<h4>Population</h4>A total of 138 women with ...[more]

PMID: 33200420

Similar Datasets

Project description:Background The aim of this work was to investigate the ability of building prognostic models in non-small cell lung cancer (NSCLC) using radiomic features from positron emission tomography and computed tomography with 2-deoxy-2-[fluorine-18]fluoro-d-glucose (18F-FDG PET/CT) images based on a “rough” volume of interest (VOI) containing the tumor instead of its accurate delineation, which is a significant time-consuming bottleneck of radiomics analyses. Methods A cohort of 138 patients with stage II–III NSCLC treated with radiochemotherapy recruited retrospectively (n = 87) and prospectively (n = 51) was used. Two approaches were compared: firstly, the radiomic features were extracted from the delineated primary tumor volumes in both PET (using the automated fuzzy locally adaptive Bayesian, FLAB) and CT (using a semi-automated approach with 3D Slicer™) components. Both delineations were carried out within previously manually defined “rough” VOIs containing the tumor and the surrounding tissues, which were exploited for the second approach: the same features were extracted from this alternative VOI. Both sets for features were then combined with the clinical variables and processed through the same machine learning (ML) pipelines using the retrospectively recruited patients as the training set and the prospectively recruited patients as the testing set. Logistic regression (LR), random forest (RF), and support vector machine (SVM), as well as their consensus through averaging the output probabilities, were considered for feature selection and modeling for overall survival (OS) prediction as a binary classification (either median OS or 6 months OS). The resulting models were compared in terms of balanced accuracy, sensitivity, and specificity. Results Overall, better performance was achieved using the features from delineated tumor volumes. This was observed consistently across ML algorithms and for the two clinical endpoints. However, the loss of performance was not significant, especially when a consensus of the three ML algorithms was considered (0.89 vs. 0.88 and 0.78 vs. 0.77). Conclusion Our findings suggest that it is feasible to achieve similar levels of prognostic accuracy in radiomics-based modeling by relying on a faster and easier VOI definition, skipping a time-consuming tumor delineation step, thus facilitating automation of the whole radiomics workflow. The associated cost is a loss of performance in the resulting models, although this loss can be greatly mitigated when a consensus of several models is relied upon.

Project description:BACKGROUND:Recently, radiomics has emerged as a non-invasive, imaging-based tissue characterization method in multiple cancer types. One limitation for robust and reproducible analysis lies in the inter-reader variability of the tumor annotations, which can potentially cause differences in the extracted feature sets and results. In this study, the diagnostic potential of a rapid and clinically feasible VOI (Volume of Interest)-based approach to radiomics is investigated to assess MR-derived parameters for predicting molecular subtype, hormonal receptor status, Ki67- and HER2-Expression, metastasis of lymph nodes and lymph vessel involvement as well as grading in patients with breast cancer. METHODS:A total of 98 treatment-naïve patients (mean 59.7 years, range 28.0-89.4) with BI-RADS 5 and 6 lesions who underwent a dedicated breast MRI prior to therapy were retrospectively included in this study. The imaging protocol comprised dynamic contrast-enhanced T1-weighted imaging and T2-weighted imaging. Tumor annotations were obtained by drawing VOIs around the primary tumor lesions followed by thresholding. From each segmentation, 13.118 quantitative imaging features were extracted and analyzed with machine learning methods. Validation was performed by 5-fold cross-validation with 25 repeats. RESULTS:Predictions for molecular subtypes obtained AUCs of 0.75 (HER2-enriched), 0.73 (triple-negative), 0.65 (luminal A) and 0.69 (luminal B). Differentiating subtypes from one another was highest for HER2-enriched vs triple-negative (AUC 0.97), followed by luminal B vs triple-negative (0.86). Receptor status predictions for Estrogen Receptor (ER), Progesterone Receptor (PR) and Hormone receptor positivity yielded AUCs of 0.67, 0.69 and 0.69, while Ki67 and HER2 Expressions achieved 0.81 and 0.62. Involvement of the lymph vessels could be predicted with an AUC of 0.8, while lymph node metastasis yielded an AUC of 0.71. Models for grading performed similar with an AUC of 0.71 for Elston-Ellis grading and 0.74 for the histological grading. CONCLUSION:Our preliminary results of a rapid approach to VOI-based tumor-annotations for radiomics provides comparable results to current publications with the perks of clinical suitability, enabling a comprehensive non-invasive platform for breast tumor decoding and phenotyping.

Project description:BackgroundOvarian preservation treatment (OPT) was recommended in young women with early-stage endometrial cancer [superficial myometrial invasion (MI) and grades (G) 1/2-endometrioid adenocarcinoma (EEC)]. A radiomics nomogram was developed to assist radiologists in assessing the depth of MI and in selecting eligible patients for OPT.MethodsFrom February 2014 to May 2021, 209 G 1/2-EEC patients younger than 45 years (mean 39 ± 4.3 years) were included. Of them, 104 retrospective patients were enrolled in the primary group, and 105 prospective patients were enrolled in the validation group. The radiomics features were extracted based on multi-parametric magnetic resonance imaging, and the least absolute shrinkage and selection operator algorithm was applied to reduce the dimensionality of the data and select the radiomics features that correlated with the depth of MI in G 1/2-EEC patients. A radiomics nomogram for evaluating the depth of MI was developed by combing the selected radiomics features with the cancer antigen 125 and tumor size. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic performance of the radiomics nomogram and of radiologists without and with the aid of the radiomics nomogram. The net reclassification index (NRI) and total integrated discrimination index (IDI) based on the total included patients to assess the clinical benefit of radiologists with the radiomics nomogram were calculated.ResultsIn the primary group, for evaluating the depth of MI, the AUCs were 0.96 for the radiomics nomogram; 0.80 and 0.86 for radiologists 1 and 2 without the aid of the nomogram, respectively; and 0.98 and 0.98 for radiologists 1 and 2 with the aid of the nomogram, respectively. In the validation group, the AUCs were 0.88 for the radiomics nomogram; 0.82 and 0.83 for radiologists 1 and 2 without the aid of the nomogram, respectively; and 0.94 and 0.94 for radiologists 1 and 2 with the aid of the nomogram, respectively. The yielded NRI and IDI values were 0.29 and 0.43 for radiologist 1 and 0.23 and 0.37 for radiologist 2, respectively.ConclusionsThe radiomics nomogram outperformed radiologists and could help radiologists in assessing the depth of MI and selecting eligible OPTs in G 1/2-EEC patients.

Project description:ObjectivesTo create a radiomics approach based on multiparametric magnetic resonance imaging (mpMRI) features extracted from an auto-fixed volume of interest (VOI) that quantifies the phenotype of clinically significant (CS) peripheral zone (PZ) prostate cancer (PCa).MethodsThis study included 206 patients with 262 prospectively called mpMRI prostate imaging reporting and data system 3-5 PZ lesions. Gleason scores > 6 were defined as CS PCa. Features were extracted with an auto-fixed 12-mm spherical VOI placed around a pin point in each lesion. The value of dynamic contrast-enhanced imaging(DCE), multivariate feature selection and extreme gradient boosting (XGB) vs. univariate feature selection and random forest (RF), expert-based feature pre-selection, and the addition of image filters was investigated using the training (171 lesions) and test (91 lesions) datasets.ResultsThe best model with features from T2-weighted (T2-w) + diffusion-weighted imaging (DWI) + DCE had an area under the curve (AUC) of 0.870 (95% CI 0.980-0.754). Removal of DCE features decreased AUC to 0.816 (95% CI 0.920-0.710), although not significantly (p = 0.119). Multivariate and XGB outperformed univariate and RF (p = 0.028). Expert-based feature pre-selection and image filters had no significant contribution.ConclusionsThe phenotype of CS PZ PCa lesions can be quantified using a radiomics approach based on features extracted from T2-w + DWI using an auto-fixed VOI. Although DCE features improve diagnostic performance, this is not statistically significant. Multivariate feature selection and XGB should be preferred over univariate feature selection and RF. The developed model may be a valuable addition to traditional visual assessment in diagnosing CS PZ PCa.Key points• T2-weighted and diffusion-weighted imaging features are essential components of a radiomics model for clinically significant prostate cancer; addition of dynamic contrast-enhanced imaging does not significantly improve diagnostic performance. • Multivariate feature selection and extreme gradient outperform univariate feature selection and random forest. • The developed radiomics model that extracts multiparametric MRI features with an auto-fixed volume of interest may be a valuable addition to visual assessment in diagnosing clinically significant prostate cancer.

Project description:BackgroundCurrently, there is no reliable blood-based marker to track tumor recurrence in endometrial cancer (EC) patients. Liquid biopsies, specifically, circulating tumor DNA (ctDNA) analysis emerged as a way to monitor tumor metastasis. The objective of this study was to examine the feasibility of ctDNA in recurrence surveillance and prognostic evaluation of high-risk EC.MethodsTumor tissues from nine high-risk EC patients were collected during primary surgery and tumor DNA was subjected to next generation sequencing to obtain the initial mutation spectrum using a 78 cancer-associated gene panel. Baseline and serial post-operative plasma samples were collected and droplet digital PCR (ddPCR) assays for patient-specific mutations were developed to track the mutations in the ctDNA in serial plasma samples. Log-rank test was used to assess the association between detection of ctDNA before or after surgery and disease-free survival.ResultsSomatic mutations were identified in all of the cases. The most frequent mutated genes were PTEN, FAT4, ARID1A, TP53, ZFHX3, ATM, and FBXW7. For each patient, personalized ddPCR assays were designed for one-to-three high-frequent mutations. DdPCR analysis and tumor panel sequencing had a high level of agreement in the assessment of the mutant allele fractions in baseline tumor tissue DNA. CtDNA was detected in 67% (6 of 9) of baseline plasma samples, which was not predictive of disease-free survival (DFS). CtDNA was detected in serial post-operative plasma samples (ctDNA tracking) of 44% (4 of 9) of the patients, which predicted tumor relapse. The DFS was a median of 9 months (ctDNA detected) versus median DFS undefined (ctDNA not detected), with a hazard ratio of 17.43 (95% CI, 1.616-188.3). The sensitivity of post-operative ctDNA detection in estimating tumor relapse was 100% and specificity was 83.3%, which was superior to CA125 or HE4.ConclusionsPersonalized ctDNA detection was effective and stable for high-risk EC. CtDNA tracking in post-operative plasma is valuable for predicting tumor recurrence.

Dataset Information

Whole-Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer.

Background

Purpose

Study type

Population

Field strength/sequence

Assessment

Statistical tests

Results

Level of evidence

Publications

Whole-Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure