Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma.
<h4>Background</h4>Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ~60% of cases. Further, CE-MRI...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2015-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0141506 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849331955547504640 |
|---|---|
| author | Leland S Hu Shuluo Ning Jennifer M Eschbacher Nathan Gaw Amylou C Dueck Kris A Smith Peter Nakaji Jonathan Plasencia Sara Ranjbar Stephen J Price Nhan Tran Joseph Loftus Robert Jenkins Brian P O'Neill William Elmquist Leslie C Baxter Fei Gao David Frakes John P Karis Christine Zwart Kristin R Swanson Jann Sarkaria Teresa Wu J Ross Mitchell Jing Li |
| author_facet | Leland S Hu Shuluo Ning Jennifer M Eschbacher Nathan Gaw Amylou C Dueck Kris A Smith Peter Nakaji Jonathan Plasencia Sara Ranjbar Stephen J Price Nhan Tran Joseph Loftus Robert Jenkins Brian P O'Neill William Elmquist Leslie C Baxter Fei Gao David Frakes John P Karis Christine Zwart Kristin R Swanson Jann Sarkaria Teresa Wu J Ross Mitchell Jing Li |
| author_sort | Leland S Hu |
| collection | DOAJ |
| description | <h4>Background</h4>Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ~60% of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM.<h4>Methods</h4>We recruited primary GBM patients undergoing image-guided biopsies and acquired pre-operative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs <80% tumor nuclei) for corresponding samples. In a training set, we used three texture analysis algorithms and three ML methods to identify MRI-texture features that optimized model accuracy to distinguish tumor content. We confirmed model accuracy in a separate validation set.<h4>Results</h4>We collected 82 biopsies from 18 GBMs throughout ENH and BAT. The MRI-based model achieved 85% cross-validated accuracy to diagnose high- vs low-tumor in the training set (60 biopsies, 11 patients). The model achieved 81.8% accuracy in the validation set (22 biopsies, 7 patients).<h4>Conclusion</h4>Multi-parametric MRI and texture analysis can help characterize and visualize GBM's spatial histologic heterogeneity to identify regional tumor-rich biopsy targets. |
| format | Article |
| id | doaj-art-320cfd61fa854bedb91d16d8e4075cd4 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2015-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-320cfd61fa854bedb91d16d8e4075cd42025-08-20T03:46:21ZengPublic Library of Science (PLoS)PLoS ONE1932-62032015-01-011011e014150610.1371/journal.pone.0141506Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma.Leland S HuShuluo NingJennifer M EschbacherNathan GawAmylou C DueckKris A SmithPeter NakajiJonathan PlasenciaSara RanjbarStephen J PriceNhan TranJoseph LoftusRobert JenkinsBrian P O'NeillWilliam ElmquistLeslie C BaxterFei GaoDavid FrakesJohn P KarisChristine ZwartKristin R SwansonJann SarkariaTeresa WuJ Ross MitchellJing Li<h4>Background</h4>Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ~60% of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM.<h4>Methods</h4>We recruited primary GBM patients undergoing image-guided biopsies and acquired pre-operative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs <80% tumor nuclei) for corresponding samples. In a training set, we used three texture analysis algorithms and three ML methods to identify MRI-texture features that optimized model accuracy to distinguish tumor content. We confirmed model accuracy in a separate validation set.<h4>Results</h4>We collected 82 biopsies from 18 GBMs throughout ENH and BAT. The MRI-based model achieved 85% cross-validated accuracy to diagnose high- vs low-tumor in the training set (60 biopsies, 11 patients). The model achieved 81.8% accuracy in the validation set (22 biopsies, 7 patients).<h4>Conclusion</h4>Multi-parametric MRI and texture analysis can help characterize and visualize GBM's spatial histologic heterogeneity to identify regional tumor-rich biopsy targets.https://doi.org/10.1371/journal.pone.0141506 |
| spellingShingle | Leland S Hu Shuluo Ning Jennifer M Eschbacher Nathan Gaw Amylou C Dueck Kris A Smith Peter Nakaji Jonathan Plasencia Sara Ranjbar Stephen J Price Nhan Tran Joseph Loftus Robert Jenkins Brian P O'Neill William Elmquist Leslie C Baxter Fei Gao David Frakes John P Karis Christine Zwart Kristin R Swanson Jann Sarkaria Teresa Wu J Ross Mitchell Jing Li Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma. PLoS ONE |
| title | Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma. |
| title_full | Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma. |
| title_fullStr | Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma. |
| title_full_unstemmed | Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma. |
| title_short | Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma. |
| title_sort | multi parametric mri and texture analysis to visualize spatial histologic heterogeneity and tumor extent in glioblastoma |
| url | https://doi.org/10.1371/journal.pone.0141506 |
| work_keys_str_mv | AT lelandshu multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT shuluoning multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT jennifermeschbacher multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT nathangaw multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT amyloucdueck multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT krisasmith multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT peternakaji multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT jonathanplasencia multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT sararanjbar multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT stephenjprice multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT nhantran multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT josephloftus multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT robertjenkins multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT brianponeill multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT williamelmquist multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT lesliecbaxter multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT feigao multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT davidfrakes multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT johnpkaris multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT christinezwart multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT kristinrswanson multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT jannsarkaria multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT teresawu multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT jrossmitchell multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma AT jingli multiparametricmriandtextureanalysistovisualizespatialhistologicheterogeneityandtumorextentinglioblastoma |