Radiomics Feature Stability in True and Virtual Non-Contrast Reconstructions from Cardiac Photon-Counting Detector CT Datasets

Overview

Journal Diagnostics (Basel)

Specialty Radiology

Date 2024 Nov 27

PMID 39594149

Authors

Luca Canalini

Elif G Becker

Franka Risch

Stefanie Bette

Simon Hellbrueck

Judith Becker

Katharina Rippel

Christian Scheurig-Muenkler

Thomas Kroencke

Josua A Decker

Affiliations

Soon will be listed here.

Abstract

: Virtual non-contrast (VNC) series reconstructed from contrast-enhanced cardiac scans acquired with photon counting detector CT (PCD-CT) systems have the potential to replace true non-contrast (TNC) series. However, a quantitative comparison of the image characteristics of TNC and VNC data is necessary to determine to what extent they are interchangeable. This work quantitatively evaluates the image similarity between VNC and TNC reconstructions by measuring the stability of multi-class radiomics features extracted in intra-patient TNC and VNC reconstructions. : TNC and VNC series of 84 patients were retrospectively collected. For each patient, the myocardium and epicardial adipose tissue (EAT) were semi-automatically segmented in both VNC and TNC reconstructions, and 105 radiomics features were extracted in each mask. Intra-feature correlation scores were computed using the intraclass correlation coefficient (ICC). Stable features were defined with an ICC higher than 0.75. : In the myocardium, 41 stable features were identified, and the three with the highest ICC were glrlm_GrayLevelVariance with ICC3 of 0.98 [0.97, 0.99], ngtdm_Strength with ICC3 of 0.97 [0.95, 0.98], firstorder_Variance with ICC3 of 0.96 [0.94, 0.98]. For the epicardial fat, 40 stable features were found, and the three highest ranked are firstorder_Median with ICC3 of 0.96 [0.93, 0.97], firstorder_RootMeanSquared with ICC3 of 0.95 [0.92, 0.97], firstorder_Mean with ICC3 of 0.95 [0.92, 0.97]. A total of 24 features (22.8%; 24/105) showed stability in both anatomical structures. : The significant differences in the correlation of radiomics features in VNC and TNC volumes of the myocardium and epicardial fat suggested that the two reconstructions may differ more than initially assumed. This indicates that they may not be interchangeable, and such differences could have clinical implications. Therefore, care should be given when selecting VNC as a substitute for TNC in radiomics research to ensure accurate and reliable analysis. Moreover, the observed variations may impact clinical workflows, where precise tissue characterization is critical for diagnosis and treatment planning.

References

Emrich T, Aquino G, Schoepf U, Braun F, Risch F, Bette S . Coronary Computed Tomography Angiography-Based Calcium Scoring: In Vitro and In Vivo Validation of a Novel Virtual Noniodine Reconstruction Algorithm on a Clinical, First-Generation Dual-Source Photon Counting-Detector System. Invest Radiol. 2022; 57(8):536-543. DOI: 10.1097/RLI.0000000000000868. View

Wasserthal J, Breit H, Meyer M, Pradella M, Hinck D, Sauter A . TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images. Radiol Artif Intell. 2023; 5(5):e230024. PMC: 10546353. DOI: 10.1148/ryai.230024. View

Vecsey-Nagy M, Varga-Szemes A, Emrich T, Zsarnoczay E, Nagy N, Fink N . Calcium scoring on coronary computed angiography tomography with photon-counting detector technology: Predictors of performance. J Cardiovasc Comput Tomogr. 2023; 17(5):328-335. DOI: 10.1016/j.jcct.2023.08.004. View

Moss A, Williams M, Newby D, Nicol E . The Updated NICE Guidelines: Cardiac CT as the First-Line Test for Coronary Artery Disease. Curr Cardiovasc Imaging Rep. 2017; 10(5):15. PMC: 5368205. DOI: 10.1007/s12410-017-9412-6. View

Lubner M, Smith A, Sandrasegaran K, Sahani D, Pickhardt P . CT Texture Analysis: Definitions, Applications, Biologic Correlates, and Challenges. Radiographics. 2017; 37(5):1483-1503. DOI: 10.1148/rg.2017170056. View

Henglin M, Stein G, Hushcha P, Snoek J, Wiltschko A, Cheng S . Machine Learning Approaches in Cardiovascular Imaging. Circ Cardiovasc Imaging. 2017; 10(10). PMC: 5718356. DOI: 10.1161/CIRCIMAGING.117.005614. View

Scapicchio C, Gabelloni M, Barucci A, Cioni D, Saba L, Neri E . A deep look into radiomics. Radiol Med. 2021; 126(10):1296-1311. PMC: 8520512. DOI: 10.1007/s11547-021-01389-x. View

Bobak C, Barr P, OMalley A . Estimation of an inter-rater intra-class correlation coefficient that overcomes common assumption violations in the assessment of health measurement scales. BMC Med Res Methodol. 2018; 18(1):93. PMC: 6134634. DOI: 10.1186/s12874-018-0550-6. View

Ayx I, Tharmaseelan H, Hertel A, Norenberg D, Overhoff D, Rotkopf L . Myocardial Radiomics Texture Features Associated with Increased Coronary Calcium Score-First Results of a Photon-Counting CT. Diagnostics (Basel). 2022; 12(7). PMC: 9320412. DOI: 10.3390/diagnostics12071663. View

10.

Kocak B, Baessler B, Bakas S, Cuocolo R, Fedorov A, Maier-Hein L . CheckList for EvaluAtion of Radiomics research (CLEAR): a step-by-step reporting guideline for authors and reviewers endorsed by ESR and EuSoMII. Insights Imaging. 2023; 14(1):75. PMC: 10160267. DOI: 10.1186/s13244-023-01415-8. View

11.

Risch F, Schwarz F, Braun F, Bette S, Becker J, Scheurig-Muenkler C . Assessment of epicardial adipose tissue on virtual non-contrast images derived from photon-counting detector coronary CTA datasets. Eur Radiol. 2022; 33(4):2450-2460. PMC: 10017616. DOI: 10.1007/s00330-022-09257-6. View

12.

Dunning C, Rajendran K, Fletcher J, McCollough C, Leng S . Impact of improved spatial resolution on radiomic features using photon-counting-detector CT. Proc SPIE Int Soc Opt Eng. 2022; 12032. PMC: 9171727. DOI: 10.1117/12.2612229. View

13.

Newby D, Adamson P, Berry C, Boon N, Dweck M, Flather M . Coronary CT Angiography and 5-Year Risk of Myocardial Infarction. N Engl J Med. 2018; 379(10):924-933. DOI: 10.1056/NEJMoa1805971. View

14.

Bette S, Risch F, Canalini L, Becker J, Leithner E, Huber A . Diagnostic performance of photon-counting detector CT for differentiation between adrenal adenomas and metastases. Eur Radiol. 2024; 34(9):5944-5953. PMC: 11364581. DOI: 10.1007/s00330-024-10675-x. View

15.

Wolf E, Muller L, Schoepf U, Fink N, Griffith 3rd J, Zsarnoczay E . Photon-counting detector CT-based virtual monoenergetic reconstructions: repeatability and reproducibility of radiomics features of an organic phantom and human myocardium. Eur Radiol Exp. 2023; 7(1):59. PMC: 10597903. DOI: 10.1186/s41747-023-00371-8. View

16.

Xue C, Yuan J, Lo G, Chang A, Poon D, Wong O . Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review. Quant Imaging Med Surg. 2021; 11(10):4431-4460. PMC: 8408801. DOI: 10.21037/qims-21-86. View

17.

Kumar V, Gu Y, Basu S, Berglund A, Eschrich S, Schabath M . Radiomics: the process and the challenges. Magn Reson Imaging. 2012; 30(9):1234-48. PMC: 3563280. DOI: 10.1016/j.mri.2012.06.010. View

18.

Shrout P, Fleiss J . Intraclass correlations: uses in assessing rater reliability. Psychol Bull. 1979; 86(2):420-8. DOI: 10.1037//0033-2909.86.2.420. View

19.

Decker J, Bette S, Scheurig-Muenkler C, Jehs B, Risch F, Woznicki P . Virtual Non-Contrast Reconstructions of Photon-Counting Detector CT Angiography Datasets as Substitutes for True Non-Contrast Acquisitions in Patients after EVAR-Performance of a Novel Calcium-Preserving Reconstruction Algorithm. Diagnostics (Basel). 2022; 12(3). PMC: 8946873. DOI: 10.3390/diagnostics12030558. View

20.

Cundari G, Galea N, Mergen V, Alkadhi H, Eberhard M . Myocardial extracellular volume quantification with computed tomography-current status and future outlook. Insights Imaging. 2023; 14(1):156. PMC: 10519917. DOI: 10.1186/s13244-023-01506-6. View