Can Radiomics Provide Additional Information in [<sup>18</sup>F]FET-Negative Gliomas?
The purpose of this study was to evaluate the possibility of extracting relevant information from radiomic features even in apparently [<sup>18</sup>F]FET-negative gliomas. A total of 46 patients with a newly diagnosed, histologically verified glioma that was visually classified as [<...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/14/19/4860 |
| _version_ | 1797480158955831296 |
|---|---|
| author | Katharina von Rohr Marcus Unterrainer Adrien Holzgreve Maximilian A. Kirchner Zhicong Li Lena M. Unterrainer Bogdana Suchorska Matthias Brendel Joerg-Christian Tonn Peter Bartenstein Sibylle Ziegler Nathalie L. Albert Lena Kaiser |
| author_facet | Katharina von Rohr Marcus Unterrainer Adrien Holzgreve Maximilian A. Kirchner Zhicong Li Lena M. Unterrainer Bogdana Suchorska Matthias Brendel Joerg-Christian Tonn Peter Bartenstein Sibylle Ziegler Nathalie L. Albert Lena Kaiser |
| author_sort | Katharina von Rohr |
| collection | DOAJ |
| description | The purpose of this study was to evaluate the possibility of extracting relevant information from radiomic features even in apparently [<sup>18</sup>F]FET-negative gliomas. A total of 46 patients with a newly diagnosed, histologically verified glioma that was visually classified as [<sup>18</sup>F]FET-negative were included. Tumor volumes were defined using routine T2/FLAIR MRI data and applied to extract information from dynamic [<sup>18</sup>F]FET PET data, i.e., early and late tumor-to-background (TBR<sub>5–15</sub>, TBR<sub>20–40</sub>) and time-to-peak (TTP) images. Radiomic features of healthy background were calculated from the tumor volume of interest mirrored in the contralateral hemisphere. The ability to distinguish tumors from healthy tissue was assessed using the Wilcoxon test and logistic regression. A total of 5, 15, and 69% of features derived from TBR<sub>20–40</sub>, TBR<sub>5–15</sub>, and TTP images, respectively, were significantly different. A high number of significantly different TTP features was even found in isometabolic gliomas (after exclusion of photopenic gliomas) with visually normal [<sup>18</sup>F]FET uptake in static images. However, the differences did not reach satisfactory predictability for machine-learning-based identification of tumor tissue. In conclusion, radiomic features derived from dynamic [<sup>18</sup>F]FET PET data may extract additional information even in [<sup>18</sup>F]FET-negative gliomas, which should be investigated in larger cohorts and correlated with histological and outcome features in future studies. |
| first_indexed | 2024-03-09T21:55:54Z |
| format | Article |
| id | doaj.art-8e0269bba99f470d844bd1da12ce2d85 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-09T21:55:54Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-8e0269bba99f470d844bd1da12ce2d852023-11-23T19:57:48ZengMDPI AGCancers2072-66942022-10-011419486010.3390/cancers14194860Can Radiomics Provide Additional Information in [<sup>18</sup>F]FET-Negative Gliomas?Katharina von Rohr0Marcus Unterrainer1Adrien Holzgreve2Maximilian A. Kirchner3Zhicong Li4Lena M. Unterrainer5Bogdana Suchorska6Matthias Brendel7Joerg-Christian Tonn8Peter Bartenstein9Sibylle Ziegler10Nathalie L. Albert11Lena Kaiser12Department of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Radiology, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Neurosurgery, Sana Hospital, 47055 Duisburg, GermanyDepartment of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Neurosurgery, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyDepartment of Nuclear Medicine, University Hospital, LMU Munich, 81377 Munich, GermanyThe purpose of this study was to evaluate the possibility of extracting relevant information from radiomic features even in apparently [<sup>18</sup>F]FET-negative gliomas. A total of 46 patients with a newly diagnosed, histologically verified glioma that was visually classified as [<sup>18</sup>F]FET-negative were included. Tumor volumes were defined using routine T2/FLAIR MRI data and applied to extract information from dynamic [<sup>18</sup>F]FET PET data, i.e., early and late tumor-to-background (TBR<sub>5–15</sub>, TBR<sub>20–40</sub>) and time-to-peak (TTP) images. Radiomic features of healthy background were calculated from the tumor volume of interest mirrored in the contralateral hemisphere. The ability to distinguish tumors from healthy tissue was assessed using the Wilcoxon test and logistic regression. A total of 5, 15, and 69% of features derived from TBR<sub>20–40</sub>, TBR<sub>5–15</sub>, and TTP images, respectively, were significantly different. A high number of significantly different TTP features was even found in isometabolic gliomas (after exclusion of photopenic gliomas) with visually normal [<sup>18</sup>F]FET uptake in static images. However, the differences did not reach satisfactory predictability for machine-learning-based identification of tumor tissue. In conclusion, radiomic features derived from dynamic [<sup>18</sup>F]FET PET data may extract additional information even in [<sup>18</sup>F]FET-negative gliomas, which should be investigated in larger cohorts and correlated with histological and outcome features in future studies.https://www.mdpi.com/2072-6694/14/19/4860amino acid PETFET PETgliomaFET negativephotopenicradiomics |
| spellingShingle | Katharina von Rohr Marcus Unterrainer Adrien Holzgreve Maximilian A. Kirchner Zhicong Li Lena M. Unterrainer Bogdana Suchorska Matthias Brendel Joerg-Christian Tonn Peter Bartenstein Sibylle Ziegler Nathalie L. Albert Lena Kaiser Can Radiomics Provide Additional Information in [<sup>18</sup>F]FET-Negative Gliomas? Cancers amino acid PET FET PET glioma FET negative photopenic radiomics |
| title | Can Radiomics Provide Additional Information in [<sup>18</sup>F]FET-Negative Gliomas? |
| title_full | Can Radiomics Provide Additional Information in [<sup>18</sup>F]FET-Negative Gliomas? |
| title_fullStr | Can Radiomics Provide Additional Information in [<sup>18</sup>F]FET-Negative Gliomas? |
| title_full_unstemmed | Can Radiomics Provide Additional Information in [<sup>18</sup>F]FET-Negative Gliomas? |
| title_short | Can Radiomics Provide Additional Information in [<sup>18</sup>F]FET-Negative Gliomas? |
| title_sort | can radiomics provide additional information in sup 18 sup f fet negative gliomas |
| topic | amino acid PET FET PET glioma FET negative photopenic radiomics |
| url | https://www.mdpi.com/2072-6694/14/19/4860 |
| work_keys_str_mv | AT katharinavonrohr canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT marcusunterrainer canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT adrienholzgreve canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT maximilianakirchner canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT zhicongli canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT lenamunterrainer canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT bogdanasuchorska canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT matthiasbrendel canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT joergchristiantonn canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT peterbartenstein canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT sibylleziegler canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT nathalielalbert canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas AT lenakaiser canradiomicsprovideadditionalinformationinsup18supffetnegativegliomas |