Deep learning-based detection and identification of brain tumor biomarkers in quantitative MR-images
The infiltrative nature of malignant gliomas results in active tumor spreading into the peritumoral edema, which is not visible in conventional magnetic resonance imaging (cMRI) even after contrast injection. MR relaxometry (qMRI) measures relaxation rates dependent on tissue properties and can offe...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IOP Publishing
2023-01-01
|
Series: | Machine Learning: Science and Technology |
Subjects: | |
Online Access: | https://doi.org/10.1088/2632-2153/acf095 |
_version_ | 1797693088244695040 |
---|---|
author | Iulian Emil Tampu Neda Haj-Hosseini Ida Blystad Anders Eklund |
author_facet | Iulian Emil Tampu Neda Haj-Hosseini Ida Blystad Anders Eklund |
author_sort | Iulian Emil Tampu |
collection | DOAJ |
description | The infiltrative nature of malignant gliomas results in active tumor spreading into the peritumoral edema, which is not visible in conventional magnetic resonance imaging (cMRI) even after contrast injection. MR relaxometry (qMRI) measures relaxation rates dependent on tissue properties and can offer additional contrast mechanisms to highlight the non-enhancing infiltrative tumor. To investigate if qMRI data provides additional information compared to cMRI sequences when considering deep learning-based brain tumor detection and segmentation, preoperative conventional (T1w per- and post-contrast, T2w and FLAIR) and quantitative (pre- and post-contrast R _1 , R _2 and proton density) MR data was obtained from 23 patients with typical radiological findings suggestive of a high-grade glioma. 2D deep learning models were trained on transversal slices ( n = 528) for tumor detection and segmentation using either cMRI or qMRI. Moreover, trends in quantitative R _1 and R _2 rates of regions identified as relevant for tumor detection by model explainability methods were qualitatively analyzed. Tumor detection and segmentation performance for models trained with a combination of qMRI pre- and post-contrast was the highest (detection Matthews correlation coefficient (MCC) = 0.72, segmentation dice similarity coefficient (DSC) = 0.90), however, the difference compared to cMRI was not statistically significant. Overall analysis of the relevant regions identified using model explainability showed no differences between models trained on cMRI or qMRI. When looking at the individual cases, relaxation rates of brain regions outside the annotation and identified as relevant for tumor detection exhibited changes after contrast injection similar to region inside the annotation in the majority of cases. In conclusion, models trained on qMRI data obtained similar detection and segmentation performance to those trained on cMRI data, with the advantage of quantitatively measuring brain tissue properties within a similar scan time. When considering individual patients, the analysis of relaxation rates of regions identified by model explainability suggests the presence of infiltrative tumor outside the cMRI-based tumor annotation. |
first_indexed | 2024-03-12T02:38:29Z |
format | Article |
id | doaj.art-a15e9e7ec6804154b87f143818e46e82 |
institution | Directory Open Access Journal |
issn | 2632-2153 |
language | English |
last_indexed | 2024-03-12T02:38:29Z |
publishDate | 2023-01-01 |
publisher | IOP Publishing |
record_format | Article |
series | Machine Learning: Science and Technology |
spelling | doaj.art-a15e9e7ec6804154b87f143818e46e822023-09-04T10:51:34ZengIOP PublishingMachine Learning: Science and Technology2632-21532023-01-014303503810.1088/2632-2153/acf095Deep learning-based detection and identification of brain tumor biomarkers in quantitative MR-imagesIulian Emil Tampu0https://orcid.org/0000-0002-7582-1706Neda Haj-Hosseini1https://orcid.org/0000-0002-0555-8877Ida Blystad2https://orcid.org/0000-0002-8857-5698Anders Eklund3https://orcid.org/0000-0001-7061-7995Department of Biomedical Engineering, Linköping University , Linköping, Sweden; Center for Medical Image Science and Visualization, Linköping University , Linköping, SwedenDepartment of Biomedical Engineering, Linköping University , Linköping, Sweden; Center for Medical Image Science and Visualization, Linköping University , Linköping, SwedenCenter for Medical Image Science and Visualization, Linköping University , Linköping, Sweden; Department of Radiology and Department of Health, Medicine and Caring Sciences, Linköping University , Linköping, SwedenDepartment of Biomedical Engineering, Linköping University , Linköping, Sweden; Center for Medical Image Science and Visualization, Linköping University , Linköping, Sweden; Division of Statistics & Machine Learning, Department of Computer and Information Science, Linköping University , Linköping, SwedenThe infiltrative nature of malignant gliomas results in active tumor spreading into the peritumoral edema, which is not visible in conventional magnetic resonance imaging (cMRI) even after contrast injection. MR relaxometry (qMRI) measures relaxation rates dependent on tissue properties and can offer additional contrast mechanisms to highlight the non-enhancing infiltrative tumor. To investigate if qMRI data provides additional information compared to cMRI sequences when considering deep learning-based brain tumor detection and segmentation, preoperative conventional (T1w per- and post-contrast, T2w and FLAIR) and quantitative (pre- and post-contrast R _1 , R _2 and proton density) MR data was obtained from 23 patients with typical radiological findings suggestive of a high-grade glioma. 2D deep learning models were trained on transversal slices ( n = 528) for tumor detection and segmentation using either cMRI or qMRI. Moreover, trends in quantitative R _1 and R _2 rates of regions identified as relevant for tumor detection by model explainability methods were qualitatively analyzed. Tumor detection and segmentation performance for models trained with a combination of qMRI pre- and post-contrast was the highest (detection Matthews correlation coefficient (MCC) = 0.72, segmentation dice similarity coefficient (DSC) = 0.90), however, the difference compared to cMRI was not statistically significant. Overall analysis of the relevant regions identified using model explainability showed no differences between models trained on cMRI or qMRI. When looking at the individual cases, relaxation rates of brain regions outside the annotation and identified as relevant for tumor detection exhibited changes after contrast injection similar to region inside the annotation in the majority of cases. In conclusion, models trained on qMRI data obtained similar detection and segmentation performance to those trained on cMRI data, with the advantage of quantitatively measuring brain tissue properties within a similar scan time. When considering individual patients, the analysis of relaxation rates of regions identified by model explainability suggests the presence of infiltrative tumor outside the cMRI-based tumor annotation.https://doi.org/10.1088/2632-2153/acf095quantitative MRIbrain tumordeep learningmodel explainability |
spellingShingle | Iulian Emil Tampu Neda Haj-Hosseini Ida Blystad Anders Eklund Deep learning-based detection and identification of brain tumor biomarkers in quantitative MR-images Machine Learning: Science and Technology quantitative MRI brain tumor deep learning model explainability |
title | Deep learning-based detection and identification of brain tumor biomarkers in quantitative MR-images |
title_full | Deep learning-based detection and identification of brain tumor biomarkers in quantitative MR-images |
title_fullStr | Deep learning-based detection and identification of brain tumor biomarkers in quantitative MR-images |
title_full_unstemmed | Deep learning-based detection and identification of brain tumor biomarkers in quantitative MR-images |
title_short | Deep learning-based detection and identification of brain tumor biomarkers in quantitative MR-images |
title_sort | deep learning based detection and identification of brain tumor biomarkers in quantitative mr images |
topic | quantitative MRI brain tumor deep learning model explainability |
url | https://doi.org/10.1088/2632-2153/acf095 |
work_keys_str_mv | AT iulianemiltampu deeplearningbaseddetectionandidentificationofbraintumorbiomarkersinquantitativemrimages AT nedahajhosseini deeplearningbaseddetectionandidentificationofbraintumorbiomarkersinquantitativemrimages AT idablystad deeplearningbaseddetectionandidentificationofbraintumorbiomarkersinquantitativemrimages AT anderseklund deeplearningbaseddetectionandidentificationofbraintumorbiomarkersinquantitativemrimages |