Dataset Information

Optimal Statistical Incorporation of Independent Feature Stability Information into Radiomics Studies.

ABSTRACT: Conducting side experiments termed robustness experiments, to identify features that are stable with respect to rescans, annotation, or other confounding effects is an important element in radiomics research. However, the matter of how to include the finding of these experiments into the model building process still needs to be explored. Three different methods for incorporating prior knowledge into a radiomics modelling process were evaluated: the naïve approach (ignoring feature quality), the most common approach consisting of removing unstable features, and a novel approach using data augmentation for information transfer (DAFIT). Multiple experiments were conducted using both synthetic and publicly available real lung imaging patient data. Ignoring additional information from side experiments resulted in significantly overestimated model performances meaning the estimated mean area under the curve achieved with a model was increased. Removing unstable features improved the performance estimation, while slightly decreasing the model performance, i.e. decreasing the area under curve achieved with the model. The proposed approach was superior both in terms of the estimation of the model performance and the actual model performance. Our experiments show that data augmentation can prevent biases in performance estimation and has several advantages over the plain omission of the unstable feature. The actual gain that can be obtained depends on the quality and applicability of the prior information on the features in the given domain. This will be an important topic of future research.

SUBMITTER: Gotz M

PROVIDER: S-EPMC6971266 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Optimal Statistical Incorporation of Independent Feature Stability Information into Radiomics Studies.

Götz Michael M Maier-Hein Klaus H KH

Scientific reports 20200120 1

Conducting side experiments termed robustness experiments, to identify features that are stable with respect to rescans, annotation, or other confounding effects is an important element in radiomics research. However, the matter of how to include the finding of these experiments into the model building process still needs to be explored. Three different methods for incorporating prior knowledge into a radiomics modelling process were evaluated: the naïve approach (ignoring feature quality), the ...[more]

PMID: 31959832

Similar Datasets

Project description:Multiple statistical approaches have been proposed to validate reference genes in qPCR assays. However, conflicting results from these statistical methods pose a major hurdle in the choice of the best reference genes. Recent studies have proposed the use of at least three different methods but there is no consensus on how to interpret conflicting results. Researchers resort to averaging the stability ranks assessed by different approaches or attributing a weighted rank to candidate genes. However, we report here that the suitability of these validation methods can be influenced by the experimental setting. Therefore, averaging the ranks can lead to suboptimal assessment of stable reference genes if the method used is not suitable for analysis. As the respective approaches of these statistical methods are different, a clear understanding of the fundamental assumptions and the parameters that influence the calculation of reference gene stability is necessary. In this study, the stability of 10 candidate reference genes (Actb, Gapdh, Tbp, Sdha, Pgk1, Ppia, Rpl13a, Hsp60, Mrpl10, Rps26) was assessed using four common statistical approaches (GeNorm, NormFinder, Coefficient of Variation or CV analysis and Pairwise ΔCt method) in a longitudinal experimental setting. We used the development of the cerebellum and the spinal cord of mice as a model to assess the suitability of these statistical methods for reference gene validation. GeNorm and the Pairwise ΔCt were found to be ill suited due to a fundamental assumption in their stability calculations. Highly correlated genes were given better stability ranks despite significant overall variation. NormFinder fares better but the presence of highly variable genes influences the ranking of all genes because of the algorithm's construct. CV analysis estimates overall variation, but it fails to consider variation across groups. We thus highlight the assumptions and potential pitfalls of each method using our longitudinal data. Based on our results, we have devised a workflow combining NormFinder, CV analysis along with visual representation of mRNA fold changes and one-way ANOVA for validating reference genes in longitudinal studies. This workflow proves to be more robust than any of these methods used individually.

Project description:ObjectivesTo compare image quality of deep learning reconstruction (AiCE) for radiomics feature extraction with filtered back projection (FBP), hybrid iterative reconstruction (AIDR 3D), and model-based iterative reconstruction (FIRST).MethodsEffects of image reconstruction on radiomics features were investigated using a phantom that realistically mimicked a 65-year-old patient's abdomen with hepatic metastases. The phantom was scanned at 18 doses from 0.2 to 4 mGy, with 20 repeated scans per dose. Images were reconstructed with FBP, AIDR 3D, FIRST, and AiCE. Ninety-three radiomics features were extracted from 24 regions of interest, which were evenly distributed across three tissue classes: normal liver, metastatic core, and metastatic rim. Features were analyzed in terms of their consistent characterization of tissues within the same image (intraclass correlation coefficient ≥ 0.75), discriminative power (Kruskal-Wallis test p value < 0.05), and repeatability (overall concordance correlation coefficient ≥ 0.75).ResultsThe median fraction of consistent features across all doses was 6%, 8%, 6%, and 22% with FBP, AIDR 3D, FIRST, and AiCE, respectively. Adequate discriminative power was achieved by 48%, 82%, 84%, and 92% of features, and 52%, 20%, 17%, and 39% of features were repeatable, respectively. Only 5% of features combined consistency, discriminative power, and repeatability with FBP, AIDR 3D, and FIRST versus 13% with AiCE at doses above 1 mGy and 17% at doses ≥ 3 mGy. AiCE was the only reconstruction technique that enabled extraction of higher-order features.ConclusionsAiCE more than doubled the yield of radiomics features at doses typically used clinically. Inconsistent tissue characterization within CT images contributes significantly to the poor stability of radiomics features.Key points• Image quality of CT images reconstructed with filtered back projection and iterative methods is inadequate for the majority of radiomics features due to inconsistent tissue characterization, low discriminative power, or low repeatability. • Deep learning reconstruction enhances image quality for radiomics and more than doubled the feature yield at doses that are typically used in clinical CT imaging. • Image reconstruction algorithms can optimize image quality for more reliable quantification of tissues in CT images.

Project description:Few studies have reported the reproducibility and stability of ultrasound (US) images based radiomics features obtained from automatic segmentation in oncology. The purpose of this study is to study the accuracy of automatic segmentation algorithms based on multiple U-net models and their effects on radiomics features from US images for patients with ovarian cancer. A total of 469 US images from 127 patients were collected and randomly divided into three groups: training sets (353 images), validation sets (23 images), and test sets (93 images) for automatic segmentation models building. Manual segmentation of target volumes was delineated as ground truth. Automatic segmentations were conducted with U-net, U-net++, U-net with Resnet as the backbone (U-net with Resnet), and CE-Net. A python 3.7.0 and package Pyradiomics 2.2.0 were used to extract radiomic features from the segmented target volumes. The accuracy of automatic segmentations was evaluated by Jaccard similarity coefficient (JSC), dice similarity coefficient (DSC), and average surface distance (ASD). The reliability of radiomics features were evaluated by Pearson correlation and intraclass correlation coefficients (ICC). CE-Net and U-net with Resnet outperformed U-net and U-net++ in accuracy performance by achieving a DSC, JSC, and ASD of 0.87, 0.79, 8.54, and 0.86, 0.78, 10.00, respectively. A total of 97 features were extracted from the delineated target volumes. The average Pearson correlation was 0.86 (95% CI, 0.83-0.89), 0.87 (95% CI, 0.84-0.90), 0.88 (95% CI, 0.86-0.91), and 0.90 (95% CI, 0.88-0.92) for U-net++, U-net, U-net with Resnet, and CE-Net, respectively. The average ICC was 0.84 (95% CI, 0.81-0.87), 0.85 (95% CI, 0.82-0.88), 0.88 (95% CI, 0.85-0.90), and 0.89 (95% CI, 0.86-0.91) for U-net++, U-net, U-net with Resnet, and CE-Net, respectively. CE-Net based segmentation achieved the best radiomics reliability. In conclusion, U-net based automatic segmentation was accurate enough to delineate the target volumes on US images for patients with ovarian cancer. Radiomics features extracted from automatic segmented targets showed good reproducibility and for reliability further radiomics investigations.

Dataset Information

Optimal Statistical Incorporation of Independent Feature Stability Information into Radiomics Studies.

Publications

Optimal Statistical Incorporation of Independent Feature Stability Information into Radiomics Studies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets