The role of parametric feature maps to correct different volume of interest sizes: an in vivo liver MRI study
Abstract Background Different volume of interest (VOI) sizes influence radiomic features. This study examined if translating images into feature maps before feature sampling could compensate for these effects in liver magnetic resonance imaging (MRI). Methods T1- and T2-weighted sequences from three...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-09-01
|
| Series: | European Radiology Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41747-023-00362-9 |
| _version_ | 1797453960282374144 |
|---|---|
| author | Laura Jacqueline Jensen Damon Kim Thomas Elgeti Ingo Günter Steffen Lars-Arne Schaafs Bernd Hamm Sebastian Niko Nagel |
| author_facet | Laura Jacqueline Jensen Damon Kim Thomas Elgeti Ingo Günter Steffen Lars-Arne Schaafs Bernd Hamm Sebastian Niko Nagel |
| author_sort | Laura Jacqueline Jensen |
| collection | DOAJ |
| description | Abstract Background Different volume of interest (VOI) sizes influence radiomic features. This study examined if translating images into feature maps before feature sampling could compensate for these effects in liver magnetic resonance imaging (MRI). Methods T1- and T2-weighted sequences from three different scanners (two 3-T scanners, one 1.5-T scanner) of 66 patients with normal abdominal MRI were included retrospectively. Three differently sized VOIs (10, 20, and 30 mm in diameter) were drawn in the liver parenchyma (right lobe), excluding adjacent structures. Ninety-three features were extracted conventionally using PyRadiomics. All images were also converted to 93 parametric feature maps using a pretested software. Agreement between the three VOI sizes was assessed with overall concordance correlation coefficients (OCCCs), while OCCCs > 0.85 were rated reproducible. OCCCs were calculated twice: for the VOI sizes of 10, 20, and 30 mm and for those of 20 and 30 mm. Results When extracted from original images, only 4 out of the 93 features were reproducible across all VOI sizes in T1- and T2-weighted images. When the smallest VOI was excluded, 5 features (T1-weighted) and 7 features (T2-weighted) were reproducible. Extraction from parametric maps increased the number of reproducible features to 9 (T1- and T2-weighted) across all VOIs. Excluding the 10-mm VOI, reproducibility improved to 16 (T1-weighted) and 55 features (T2-weighted). The stability of all other features also increased in feature maps. Conclusions Translating images into parametric maps before feature extraction improves reproducibility across different VOI sizes in normal liver MRI. Relevance statement The size of the segmented VOI influences the feature quantity of radiomics, while software-based conversion of images into parametric feature maps before feature sampling improves reproducibility across different VOI sizes in MRI of normal liver tissue. Key points • Parametric feature maps can compensate for different VOI sizes. • The effect seems dependent on the VOI sizes and the MRI sequence. • Feature maps can visualize features throughout the entire image stack. Graphical Abstract |
| first_indexed | 2024-03-09T15:30:26Z |
| format | Article |
| id | doaj.art-a3fee83ca5734482b0cbffb75aecebdb |
| institution | Directory Open Access Journal |
| issn | 2509-9280 |
| language | English |
| last_indexed | 2024-03-09T15:30:26Z |
| publishDate | 2023-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Radiology Experimental |
| spelling | doaj.art-a3fee83ca5734482b0cbffb75aecebdb2023-11-26T12:17:39ZengSpringerOpenEuropean Radiology Experimental2509-92802023-09-017111110.1186/s41747-023-00362-9The role of parametric feature maps to correct different volume of interest sizes: an in vivo liver MRI studyLaura Jacqueline Jensen0Damon Kim1Thomas Elgeti2Ingo Günter Steffen3Lars-Arne Schaafs4Bernd Hamm5Sebastian Niko Nagel6Charité–Universitätsmedizin Berlin, Department of Radiology, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthCharité–Universitätsmedizin Berlin, Department of Radiology, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthCharité–Universitätsmedizin Berlin, Department of Radiology, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthCharité–Universitätsmedizin Berlin, Department of Radiology, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthCharité–Universitätsmedizin Berlin, Department of Radiology, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthCharité–Universitätsmedizin Berlin, Department of Radiology, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthCharité–Universitätsmedizin Berlin, Department of Radiology, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthAbstract Background Different volume of interest (VOI) sizes influence radiomic features. This study examined if translating images into feature maps before feature sampling could compensate for these effects in liver magnetic resonance imaging (MRI). Methods T1- and T2-weighted sequences from three different scanners (two 3-T scanners, one 1.5-T scanner) of 66 patients with normal abdominal MRI were included retrospectively. Three differently sized VOIs (10, 20, and 30 mm in diameter) were drawn in the liver parenchyma (right lobe), excluding adjacent structures. Ninety-three features were extracted conventionally using PyRadiomics. All images were also converted to 93 parametric feature maps using a pretested software. Agreement between the three VOI sizes was assessed with overall concordance correlation coefficients (OCCCs), while OCCCs > 0.85 were rated reproducible. OCCCs were calculated twice: for the VOI sizes of 10, 20, and 30 mm and for those of 20 and 30 mm. Results When extracted from original images, only 4 out of the 93 features were reproducible across all VOI sizes in T1- and T2-weighted images. When the smallest VOI was excluded, 5 features (T1-weighted) and 7 features (T2-weighted) were reproducible. Extraction from parametric maps increased the number of reproducible features to 9 (T1- and T2-weighted) across all VOIs. Excluding the 10-mm VOI, reproducibility improved to 16 (T1-weighted) and 55 features (T2-weighted). The stability of all other features also increased in feature maps. Conclusions Translating images into parametric maps before feature extraction improves reproducibility across different VOI sizes in normal liver MRI. Relevance statement The size of the segmented VOI influences the feature quantity of radiomics, while software-based conversion of images into parametric feature maps before feature sampling improves reproducibility across different VOI sizes in MRI of normal liver tissue. Key points • Parametric feature maps can compensate for different VOI sizes. • The effect seems dependent on the VOI sizes and the MRI sequence. • Feature maps can visualize features throughout the entire image stack. Graphical Abstracthttps://doi.org/10.1186/s41747-023-00362-9Magnetic resonance imagingLiverRadiomicsReproducibility of resultsSoftware |
| spellingShingle | Laura Jacqueline Jensen Damon Kim Thomas Elgeti Ingo Günter Steffen Lars-Arne Schaafs Bernd Hamm Sebastian Niko Nagel The role of parametric feature maps to correct different volume of interest sizes: an in vivo liver MRI study European Radiology Experimental Magnetic resonance imaging Liver Radiomics Reproducibility of results Software |
| title | The role of parametric feature maps to correct different volume of interest sizes: an in vivo liver MRI study |
| title_full | The role of parametric feature maps to correct different volume of interest sizes: an in vivo liver MRI study |
| title_fullStr | The role of parametric feature maps to correct different volume of interest sizes: an in vivo liver MRI study |
| title_full_unstemmed | The role of parametric feature maps to correct different volume of interest sizes: an in vivo liver MRI study |
| title_short | The role of parametric feature maps to correct different volume of interest sizes: an in vivo liver MRI study |
| title_sort | role of parametric feature maps to correct different volume of interest sizes an in vivo liver mri study |
| topic | Magnetic resonance imaging Liver Radiomics Reproducibility of results Software |
| url | https://doi.org/10.1186/s41747-023-00362-9 |
| work_keys_str_mv | AT laurajacquelinejensen theroleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT damonkim theroleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT thomaselgeti theroleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT ingoguntersteffen theroleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT larsarneschaafs theroleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT berndhamm theroleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT sebastiannikonagel theroleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT laurajacquelinejensen roleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT damonkim roleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT thomaselgeti roleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT ingoguntersteffen roleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT larsarneschaafs roleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT berndhamm roleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy AT sebastiannikonagel roleofparametricfeaturemapstocorrectdifferentvolumeofinterestsizesaninvivolivermristudy |