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

Abstract

BackgroundManual 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.MethodsThis 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).ResultsThe 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.ConclusionsDifferences 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.

Convolutional neural networks for PET functional volume fully automatic segmentation: development and validation in a multi-center setting

“…Such measures can subsequently be used to build models predictive of outcome or for assessing changes in tumors before, during, and after treatment in order to better evaluate response to therapy [7,37,38]. It has been shown in all image modalities including PET that the choice of the segmentation method in this step of the radiomics workflow can significantly affect the extracted features [21,31,42,46,51]. In addition, it is recognized that in the absence of fully automated segmentation, this step is a crucial bottleneck and time-consuming step of any radiomics study, preventing such a process to be expanded to very large datasets [23].…”

Effect of grey-level discretization on texture feature on different weighted MRI images of diverse disease groups

“…Moreover, radiomics parameters can also be influenced by the applied segmentation method, including manual, semi-automatic or automatic delineation of the ROI or VOI. The accuracy of the calculated radiomics data may be affected by how the external tissue areas are excluded from the selected VOI, which ensures that pathological and intact tissue areas do not mix nor overlap during the evaluation [38][39][40]. In this work, we aimed to investigate the effect of three different discretization methods and their impact on the parameters obtained for texture calculation in a cohort of 71 patients with clinical brain studies employing MRI.…”

Evaluation of a multiparametric MRI radiomic-based approach for stratification of equivocal PI-RADS 3 and upgraded PI-RADS 4 prostatic lesions

“…Another aspect to highlight is that also delineations of prostatic lesions are prone to inter-observer variability. In fact, it should be considered that we delineated only the prostatic lesion for feature extraction, and it is well-recognized that small volumes might lead to uncertainties in feature extraction [60][61][62][63] .…”