A multi-organ cancer study of the classification performance using 2D and 3D image features in radiomics analysis

Abstract

The purpose of this study was to investigate the predictive performance of 2D and 3D image features across multi-organ cancers using multi-modality images in radiomics studies.In this retrospective study, we included 619 patients with three different cancer types (intrahepatic cholangiocarcinoma (ICC), high-grade osteosarcoma (HOS), pancreatic neuroendocrine tumors (pNETs)) and four clinical end points (early recurrence (ER), lymph node metastasis (LNM), 5-year survival and histologic grade). The image features included fifty-eight 2D image features and fiftyeight 3D image features. The 3D image features were extracted based on the 3D tumor volumes. The 2D image features were extracted based on 2D tumor region, which was the layer with the maximum tumor diameter within the 3D tumor volume. The predictive performance of individual 2D and 3D image feature was measured using the area under the receiver operating characteristic curve (AUC) with univariate analysis. Radiomics signatures were further developed using multivariable analysis with 4-fold cross-validation method.Using univariate analysis, we found that more 3D image features showed the statistically predictive capabilities than 2D image features across all the included cancer types. By comparing the predictive performance of radiomics signatures developed by 2D and 3D image features, we observed better prediction performance in radiomics signatures based on 3D image features than those based on 2D image features for patients with ICC and HGO. Meanwhile, the signatures based on 2D and 3D image features performed closely in the pNETs dataset with the clinical end point of the histologic grade. The reason for this inconsistent result might be that the gross tumor volumes of pNETs were generally small. The tumor heterogeneity was mostly presented in the middle several layers within the tumor volume.Both 2D and 3D image features have certain predictive capacities. By contrast, the 3D image features show better or close predictive performance than 2D image features using both univariate analysis and multivariate analysis. In brief, 3D image features are recommended in radiomics studies.

Are radiomics features universally applicable to different organs?

“…They showed that the same radiomics model was effective for predicting survival in two organs, but the results could be invalid because their feature selection approach was biased [20]. Another study attempted to explore the feasibility of applying the same set of radiomics features [21]. However, the goal was not to find common features but to compare the performance of 2D and 3D radiomics in intrahepatic cholangiocarcinoma, osteosarcoma, and pancreatic neuroendocrine tumors.…”

“…This is because tumors in different organs might share common properties. Thus, there is a scientific curiosity in applying radiomics features found in a given organ to other tumors in different organs [20,21]. A seminal study by Aerts et al explored the application of the same radiomics features to two different organs, but this topic was not their primary aim and was thus insufficiently explored.…”

“…Furthermore, the study had issues regarding how the features were selected. A recent study explored the feasibility of applying the same set of radiomics features to intrahepatic cholangiocarcinoma, osteosarcoma, and pancreatic neuroendocrine tumors [21]. This translates to finding a "universal" set of radiomics features that can be applied to potentially different tumor microenvironments, in which they succeeded.…”

Multi‐marker quantitative radiomics for mass characterization in dedicated breast CT imaging

“…This could provide a stronger characterization compared to simply performing the analysis on a single 2D patch collected from each mass, as often performed in 2D radiomic analyses. 67 To test this latter hypothesis, the final radiomic model was used to reclassify the test set masses based only on the signatures extracted from a single patch (coronal view), resulting in a significantly lower performance (AUC = 0.84 vs 0.90). Nevertheless, a fully 3D radiomic approach should also be investigated in future, to allow for the evaluation, with larger image datasets, of the potential advantage of a fully 3D radiomic signature over the current 2D approach.…”

“…Finally, it should be noted that the proposed approach, although performed on a 2D basis, did take advantage of the 3D nature of the images, since superimposition of tissue was still avoided, and the final radiomic score for each mass was obtained by combining different signatures extracted over multiple angles. This could provide a stronger characterization compared to simply performing the analysis on a single 2D patch collected from each mass, as often performed in 2D radiomic analyses 67 . To test this latter hypothesis, the final radiomic model was used to reclassify the test set masses based only on the signatures extracted from a single patch (coronal view), resulting in a significantly lower performance (AUC = 0.84 vs 0.90).…”