Skip to main content

ORIGINAL RESEARCH article

Front. Oncol.
Sec. Cancer Imaging and Image-directed Interventions
Volume 14 - 2024 | doi: 10.3389/fonc.2024.1444115
This article is part of the Research Topic Towards Precision Oncology: Assessing the Role of Radiomics and Artificial Intelligence View all 9 articles

Comparison of Diagnostic Accuracy of Radiomics Parameter Maps and Standard Reconstruction for Detection of Liver Lesions in Computed Tomography

Provisionally accepted
Alexander Hertel Alexander Hertel *Mustafa Kuru Mustafa Kuru Fabian Tollens Fabian Tollens Hishan Tharmaseelan Hishan Tharmaseelan Dominik Nörenberg Dominik Nörenberg Nils Rathmann Nils Rathmann Stefan O. Schoenberg Stefan O. Schoenberg Matthias Froelich Matthias Froelich
  • Department of Radiology and Nuclear Medicine, University Hospital Mannheim, Mannheim, Germany

The final, formatted version of the article will be published soon.

    Backround: The liver is a frequent location of metastatic disease in various malignant tumour entities.Computed tomography (CT) is the most frequently employed modality for initial diagnosis.However, liver metastases may only be delineated vaguely on CT. Calculating radiomics features in feature maps can unravel textures not visible to the human eye on a standard CT reconstruction (SCTR). This study aimed to investigate the comparative diagnostic accuracy of radiomics feature maps and SCTR for liver metastases. Materials and Methods: Forty-seven patients with hepatic metastatic colorectal cancer were retrospectively enrolled.Whole-liver maps of original radiomics features were generated. A representative feature was selected for each feature class based on the visualization of example lesions from five patients. These maps and the conventional CT image data were viewed and evaluated by four readers regarding liver parenchyma, number of lesions, visual Contrast of lesions and diagnostic confidence. T-tests and chi²-tests were performed with a cut-off for p<0.05 for significance to compare the feature maps with SCRT, and the data was visualized as boxplots. Results: Regarding the number of lesions detected, SCTR showed superior performance compared to radiomics maps. However, the feature map for firstorderRootMeanSquared was ranked superior in terms of very high visual Contrast in 57.4 % of cases, compared to 41.0 % in standard reconstructions (p<0.001). All other radiomics maps ranked significantly lower in visual Contrast when compared to SCTR. For diagnostic confidence, firstorderRootMeanSquared reached very high ratings in 47.9 % compared to 62.8 % for SCTR (p < 0.001). The conventional CT images showed superior results in all categories for the other features investigated. Conclusion: Application of firstorderRootMeanSquared feature maps may help visualize faintly demarcated liver lesions by increasing visual Contrast. However, reading of SCTR remains necessary for diagnostic confidence.

    Keywords: Radiomics, Radiomics-Maps, Lesion detectability, liver metastases, colorectal cancer

    Received: 05 Jun 2024; Accepted: 29 Aug 2024.

    Copyright: © 2024 Hertel, Kuru, Tollens, Tharmaseelan, Nörenberg, Rathmann, Schoenberg and Froelich. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Alexander Hertel, Department of Radiology and Nuclear Medicine, University Hospital Mannheim, Mannheim, Germany

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.