Influence of inter-observer delineation variability on radiomics stability in different tumor sites

Pavic, Matea; Bogowicz, Marta; Würms, Xaver; Glatz, S.; Finazzi, Tobias; Riesterer, Oliver; Roesch, Johannes; Rudofsky, Leonie; Friess, Martina; Veit-Haibach, Patrick; Huellner, Martin W.; Opitz, Isabelle; Weder, Walter; Frauenfelder, Thomas; Gückenberger, Matthias; Tanadini‐Lang, Stephanie

doi:10.1080/0284186x.2018.1445283

Cited by 164 publications

(142 citation statements)

References 27 publications

(33 reference statements)

Supporting

Mentioning

133

Contrasting

Order By: Relevance

“…3). According to the number of robust features, different diseases had discrepant sensitivity to VOI variations, consistent with a previous discovery [18]. This result could be explained from the fact that the tumors in breast cancer are larger with ill-de ned margins, which cause great changes on the feature values across larger variation.…”

Section: Discussionsupporting

confidence: 87%

See 1 more Smart Citation

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

Zhang

Zhong

Zhang

et al. 2019

Preprint

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionsupporting

confidence: 87%

“…Most prior studies have focused solely on the effects of inter-observer variability in manual tumor delineation to identify radiomics features with high robustness [17,18]. In fact, quanti cation of tumor delineation and tolerance assessment of the differences are likely more important in developing standardized research.…”

Section: Introductionmentioning

confidence: 99%

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

Zhang

Zhong

Zhang

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Although Bashir et al investigated GLNDM-based contrast as well, they applied a logarithmic transform to the feature, rendering direct comparison inappropriate. In addition, previous work investigating the influence of delineation variability on stability of CT-based radiomic features found a strong dependence on cancer site, with relatively high stability for lung cancer 35 . Prior to our study we had no expectation that PET-based radiomic stability results would be similar to results of studies from other imaging modalities.…”

Section: Discussionmentioning

confidence: 95%

Impact of contouring variability on oncological PET radiomics features in the lung

Yang

Simpson

Young

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Irreproducible features were also removed from the signatures according to intraclass correlation coefficients (ICCs), which were independently computed using the multiple segmentation dataset to enhance the robustness of the signatures to inter-observer variability in GTVs. Features that yielded ICCs < 0.8 [42] were considered to be irreproducible, and eliminated following the VIF-based feature removal procedure discussed above.…”

Section: Radiomic Signature Constructionmentioning

confidence: 99%

Homological radiomics analysis for prognostic prediction in lung cancer patients

Ninomiya

Arimura

2020

Physica Medica

View full text Add to dashboard Cite

Influence of inter-observer delineation variability on radiomics stability in different tumor sites

Abstract: Inter-observer delineation variability has a relevant influence on radiomics analysis and is strongly influenced by tumor type. This leads to a reduced number of suitable imaging features.

Cited by 164 publications

References 27 publications

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

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

Impact of contouring variability on oncological PET radiomics features in the lung

Homological radiomics analysis for prognostic prediction in lung cancer patients

Contact Info

Product

Resources

About