Radiomics Feature Analysis Using Native T1 Mapping for Discriminating Between Cardiac Tumors and Thrombi

Jinwoo Son, Yoo Jin Hong, Sujeong Kim, Kyunghwa Han, Hye Jeong Lee, Jin Hur, Young Jin Kim, Byoung Wook Choi

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)


Rationale and Objectives: Accurate differential diagnosis is essential because cardiac tumors and thrombi have different prognoses and therapeutic approaches. Native T1 map provides an objective T1 time quantifications of cardiac mass without the need for a contrast agent. We examined the diagnostic performance of radiomics features for differentiating cardiac tumors from thrombi using cardiac magnetic resonance imaging T1 mapping technique compared to that of late gadolinium enhancement (LGE) imaging. Materials and Methods: This retrospective study included 22 cardiac tumors and 21 thrombi of 41 patients who underwent cardiac magnetic resonance imaging from December 2013 to May 2018. Fifty-six radiomics features were extracted from native T1 images. The least absolute shrinkage and selection operator method was used for feature selection and rad score extraction. The diagnostic performance of the rad score was compared to that of the native T1 value (mean T1) and LGE ratio. Results: The area under the receiver operating characteristic curve of the rad score was higher than that of the mean T1 and LGE ratio (0.98 vs. 0.86 vs. 0.82, p = 0.001). With the optimal cut-off value, the rad score showed sensitivity, specificity, and accuracy of 95.4%, 95.2%, and 95.2%, respectively. Combination of the rad score and mean T1 showed a significantly higher diagnostic performance than mean T1 (p = 0.019) or LGE ratio (p = 0.022). Conclusion: The rad score derived from native T1 maps can differentiate thrombi from tumors better than the mean T1 or LGE ratio. This is valuable for determining a treatment strategy for cardiac lesions in patients who cannot tolerate contrast agents.

Original languageEnglish
Pages (from-to)S1-S8
JournalAcademic Radiology
Publication statusPublished - 2022 Apr

Bibliographical note

Publisher Copyright:
© 2020 The Association of University Radiologists

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Radiomics Feature Analysis Using Native T1 Mapping for Discriminating Between Cardiac Tumors and Thrombi'. Together they form a unique fingerprint.

Cite this