Back to the list
Congress: ECR24
Poster Number: C-11624
Type: EPOS Radiologist (scientific)
Authorblock: A. Hertel1, F. Haag1, F. Tollens1, S. O. Schönberg1, M. Frölich1, S. Waldeck2, D. P. Overhoff1; 1Mannheim/DE, 2Koblenz/DE
Disclosures:
Alexander Hertel: Nothing to disclose
Florian Haag: Nothing to disclose
Fabian Tollens: Nothing to disclose
Stefan Oswald Schönberg: Nothing to disclose
Matthias Frölich: Nothing to disclose
Stephan Waldeck: Nothing to disclose
Daniel Pasqual Overhoff: Nothing to disclose
Keywords: Artificial Intelligence, Computer applications, Urinary Tract / Bladder, CT, CT-Quantitative, Computer Applications-Detection, diagnosis, Calcifications / Calculi
Purpose The aim of this study is to investigate the potential of using the radiomics profile of different monoenergetic reconstructions of photon-counting Computed Tomography (PCCT) scans to differentiate various types of kidney stones. Urolithiasis is a common disease that is associated with severe pain and a high level of suffering for patients. There are different therapeutic approaches depending on the size, localisation and composition of the stones. The study seeks to explore the relationship between radiomics features and the underlying composition...
Read more Methods and materials In this study, we scanned 135 different types of kidney stones, including Xanthine, Brushite, Carbonateapatite, Cystine, and others, using a PCCT. An infrared spectroscopy of the stones was carried out in advance to analyse the exact composition and establish the ground truth. Monoenergetic reconstructions of the CT-scans were created using the Syngo Via software (version VB60A_HF02) from Siemens from 40 to 190 keV. The stones were segmented using the MITK-Workbench software (v2022.10), and radiomics features were then extracted using a...
Read more Results Especially in the monoenergetic reconstructions with low kev values (40 and 70kev) a differentiation of the different kidney stone types is possible based on the mean HU Values. Using a random forest classifier, an accuracy of 78% could be demonstrated with regard to the differentiation of the various kidney stone types based on the extracted Radiomics Parameters. Original_NGTDM_Strength was identified in the random forest feature importance analysis as the most important parameter for differentiating between the various types of kidney...
Read more Conclusion Radiomics evaluations of monoenergetic reconstructions of PCCT scans can help differentiate and characterize renal stones noninvasively, potentially optimizing therapy. The workflow presented here can also be extended to other fields, such as oncological issues. PCCT technology can potentially pave the way for radiomics analyses in clinical routine due to its high spatial resolution, lower radiation exposure compared to conventional scanners and excellent radiomics feature stability.
Read more References Bartoletti R, Cai T, Mondaini N, et al (2007) Epidemiology and Risk Factors in Urolithiasis. Urol Int 79:3–7. https://doi.org/10.1159/000104434Sakhaee K, Maalouf NM, Sinnott B (2012) Kidney Stones 2012: Pathogenesis, Diagnosis, and Management. The Journal of Clinical Endocrinology & Metabolism 97:1847–1860. https://doi.org/10.1210/jc.2011-3492Hertel A, Tharmaseelan H, Rotkopf LT, Nörenberg D, Riffel P, Nikolaou K, Weiss J, Bamberg F, Schoenberg SO, Froelich MF, Ayx I. Phantom-based radiomics feature test-retest stability analysis on photon-counting detector CT. Eur Radiol. 2023 Jul;33(7):4905-4914. doi: 10.1007/s00330-023-09460-z. Epub 2023...
Read more
GALLERY