Dataset Information

The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups.

ABSTRACT:

Background

Manual delineation of volume of interest (VOI) is widely used in current radiomics analysis, suffering from high variability. The tolerance of delineation differences and possible influence on each step of radiomics analysis are not clear, requiring quantitative assessment. The purpose of our study was to investigate the effects of delineation of VOIs on radiomics analysis for the preoperative prediction of metastasis in nasopharyngeal carcinoma (NPC) and sentinel lymph node (SLN) metastasis in breast cancer.

Methods

This study retrospectively enrolled two datasets (NPC group: 238 cases; SLN group: 146 cases). Three operations, namely, erosion, smoothing, and dilation, were implemented on the VOIs accurately delineated by radiologists to generate diverse VOI variations. Then, we extracted 2068 radiomics features and evaluated the effects of VOI differences on feature values by the intra-class correlation coefficient (ICC). Feature selection was conducted by Maximum Relevance Minimum Redundancy combined with 0.632+ bootstrap algorithms. The prediction performance of radiomics models with random forest classifier were tested on an independent validation cohort by the area under the receive operating characteristic curve (AUC).

Results

The larger the VOIs changed, the fewer features with high ICCs. Under any variation, SLN group showed fewer features with ICC???0.9 compared with NPC group. Not more than 15% top-predictive features identical to the accurate VOIs were observed across feature selection. The differences of AUCs of models derived from VOIs across smoothing or dilation with 3 pixels were not statistically significant compared with the accurate VOIs (p?>?0.05) except for T2-weighted fat suppression images (smoothing: 0.845 vs. 0.725, p?=?0.001; dilation: 0.800 vs. 0.725, p?=?0.042). Dilation with 5 and 7 pixels contributed to remarkable AUCs in SLN group but the opposite in NPC group. The radiomics models did not perform well when tested by data from other delineations.

Conclusions

Differences in delineation of VOIs affected radiomics analysis, related to specific disease and MRI sequences. Differences from smooth delineation or expansion with 3 pixels width around the tumors or lesions were acceptable. The delineation for radiomics analysis should follow a predefined and unified standard.

SUBMITTER: Zhang X

PROVIDER: S-EPMC6925418 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups.

Zhang Xiao X Zhong Liming L Zhang Bin B Zhang Lu L Du Haiyan H Lu Lijun L Zhang Shuixing S Yang Wei W Feng Qianjin Q

Cancer imaging : the official publication of the International Cancer Imaging Society 20191221 1

<h4>Background</h4>Manual delineation of volume of interest (VOI) is widely used in current radiomics analysis, suffering from high variability. The tolerance of delineation differences and possible influence on each step of radiomics analysis are not clear, requiring quantitative assessment. The purpose of our study was to investigate the effects of delineation of VOIs on radiomics analysis for the preoperative prediction of metastasis in nasopharyngeal carcinoma (NPC) and sentinel lymph node ( ...[more]

PMID: 31864421

Similar Datasets

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: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:BackgroundIn 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.PurposeTo develop MRI-based whole-volume tumor radiomic signatures for prediction of aggressive EC disease.Study typeRetrospective.PopulationA total of 138 women with histologically confirmed EC, divided into training (nT = 108) and validation cohorts (nV = 30).Field strength/sequenceAxial 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.AssessmentPrimary 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 testsLogistic 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 (AUCT ) and validation (AUCV ) cohorts. Progression-free survival was assessed using the Kaplan-Meier and Cox proportional hazard model.ResultsThe whole-tumor radiomic signatures yielded AUCT /AUCV 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 AUCT but significantly lower AUCV for LNM and FIGO III + IV (both P < 0.05). Tumor volume yielded comparable AUCT to the whole-tumor radiomic signatures for prediction of DMI, LNM, FIGO III + IV, and NE, but significantly lower AUCT for E3 tumors (P < 0.05). All of the whole-tumor radiomic signatures significantly predicted poor progression-free survival with hazard ratios of 4.6-9.8 (P < 0.05 for all).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 evidence4 TECHNICAL EFFICACY STAGE: 2.

Project description:BackgroundAccurate tumor bed delineation after breast-conserving surgery is important. However, consistency among observers on standard postoperative radiotherapy planning CT is low and volumes can be large due to seroma formation. A preoperative delineation of the tumor might be more consistent. Therefore, the purpose of this study was to determine the consistency of preoperative target volume delineation on CT and MRI for breast-conserving radiotherapy.MethodsTumors were delineated on preoperative contrast-enhanced (CE) CT and newly developed 3D CE-MR images, by four breast radiation oncologists. Clinical target volumes (CTVs) were created by addition of a 1.5 cm margin around the tumor, excluding skin and chest wall. Consistency in target volume delineation was expressed by the interobserver variability. Therefore, the conformity index (CI), center of mass distance (dCOM) and volumes were calculated. Tumor characteristics on CT and MRI were scored by an experienced breast radiologist.ResultsPreoperative tumor delineation resulted in a high interobserver agreement with a high median CI for the CTV, for both CT (0.80) and MRI (0.84). The tumor was missed on CT in 2/14 patients (14%). Leaving these 2 patients out of the analysis, CI was higher on MRI compared to CT for the GTV (p<0.001) while not for the CTV (CT (0.82) versus MRI (0.84), p=0.123). The dCOM did not differ between CT and MRI. The median CTV was 48 cm3 (range 28-137 cm3) on CT and 59 cm3 (range 30-153 cm3) on MRI (p<0.001). Tumor shapes and margins were rated as more irregular and spiculated on CE-MRI.ConclusionsThis study showed that preoperative target volume delineation resulted in small target volumes with a high consistency among observers. MRI appeared to be necessary for tumor detection and the visualization of irregularities and spiculations. Regarding the tumor delineation itself, no clinically relevant differences in interobserver variability were observed. These results will be used to study the potential for future MRI-guided and neoadjuvant radiotherapy.Trial registrationInternational Clinical Trials Registry Platform NTR3198.

Project description:BackgroundInter-observer delineation variation has been detailed for many years in almost every tumor location. Inadequate delineation can impair the chance of cure and/or increase toxicity. The aim of our original work was to prospectively improve the homogeneity of delineation among all of the senior radiation oncologists in the Nord-Pas de Calais region, irrespective of the conditions of practice.MethodsAll 11 centers were involved. The first studied cancer was prostate cancer. Three clinical cases were studied: a low-risk prostate cancer case (case 1), a high-risk prostate cancer case (pelvic nodes, case 2) and a case of post-operative biochemical elevated PSA (case 3). All of the involved physicians delineated characteristically the clinical target volume (CTV) and organs at risk. The volumes were compared using validated indexes: the volume ratio (VR), common and additional volumes (CV and AV), volume overlap (VO) and Dice similarity coefficient (DSC). A second delineation of the same three cases was performed after discussion of the slice results and the choice of shared guidelines to evaluate homogenization. A comparative analysis of the indexes before and after discussion was conducted using the Wilcoxon test for paired samples. A p-value less than 0.05 was considered to indicate statistical significance.ResultsThe indexes were not improved in case 1, for which the inter-observer agreement was considered good after the first comparison (DSC = 0.83 ± 0.06). In case 2, the second comparison showed homogenization of the CTV delineation with a significant improvement in CV (81.4 ± 11.7 vs. 88.6 ± 10.26, respectively, p = 0.048), VO (0.41 ± 0.09 vs. 0.47 ± 0.07, respectively; p = 0.009) and DSC (0.58 ± 0.09 vs. 0.63 ± 0.07, respectively; p = 0.0098). In case 3, VR and AV were significantly improved: VR: 1.71(± 0.6) vs. 1.34(± 0.46), respectively, p = 0.0034; AV: 46.58(± 14.50) vs. 38.08(± 15.10), respectively, p = 0.0024. DSC was not improved, but it was already superior to 0.6 in the first comparison.ConclusionOur prospective work showed that a collaborative discussion about clinical cases and the choice of shared guidelines within an established framework improved the homogeneity of CTV delineation among the senior radiation oncologists in our region.

Project description:PurposeBrain metastases are almost universally lethal with short median survival times. Despite this, they are often potentially curable, with therapy failing only because of local relapse. One key reason relapse occurs is because treatment planning did not delineate metastasis margins sufficiently or accurately, allowing residual tumor to regrow. The aim of this study was to determine the extent to which multimodal magnetic resonance imaging (MRI), with a simple and automated analysis pipeline, could improve upon current clinical practice of single-modality, independent-observer tumor delineation.Methods and materialsWe used a single rat model of brain metastasis (ENU1564 breast carcinoma cells in BD-IX rats), with and without radiation therapy. Multimodal MRI data were acquired using sequences either in current clinical use or in clinical trial and included postgadolinium T1-weighted images and maps of blood flow, blood volume, T1 and T2 relaxation times, and apparent diffusion coefficient.ResultsIn all cases, independent observers underestimated the true size of metastases from single-modality gadolinium-enhanced MRI (85 ± 36 μL vs 131 ± 40 μL histologic measurement), although multimodal MRI more accurately delineated tumor volume (132 ± 41 μL). Multimodal MRI offered increased sensitivity compared with independent observer for detecting metastasis (0.82 vs 0.61, respectively), with only a slight decrease in specificity (0.86 vs 0.98). Blood flow maps conferred the greatest improvements in margin detection for late-stage metastases after radiation therapy. Gadolinium-enhanced T1-weighted images conferred the greatest increase in accuracy of detection for smaller metastases.ConclusionsThese findings suggest that multimodal MRI of brain metastases could significantly improve the visualization of brain metastasis margins, beyond current clinical practice, with the potential to decrease relapse rates and increase patient survival. This finding now needs validation in additional tumor models or clinical cohorts.

Dataset Information

The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups.

Background

Methods

Results

Conclusions

Publications

The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets