Uncertainty quantification in multi-parametric MRI-based meningioma radiotherapy target segmentation
PurposeThis work investigates the use of a spherical projection-based U-Net (SPU-Net) segmentation model to improve meningioma segmentation performance and allow for uncertainty quantification.MethodsA total of 76 supratentorial meningioma patients treated with radiotherapy were studied. Gross tumor...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1474590/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583716469211136 |
|---|---|
| author | Lana Wang Zhenyu Yang Zhenyu Yang Dominic LaBella Zachary Reitman John Ginn Jingtong Zhao Justus Adamson Kyle Lafata Kyle Lafata Kyle Lafata Evan Calabrese John Kirkpatrick Chunhao Wang |
| author_facet | Lana Wang Zhenyu Yang Zhenyu Yang Dominic LaBella Zachary Reitman John Ginn Jingtong Zhao Justus Adamson Kyle Lafata Kyle Lafata Kyle Lafata Evan Calabrese John Kirkpatrick Chunhao Wang |
| author_sort | Lana Wang |
| collection | DOAJ |
| description | PurposeThis work investigates the use of a spherical projection-based U-Net (SPU-Net) segmentation model to improve meningioma segmentation performance and allow for uncertainty quantification.MethodsA total of 76 supratentorial meningioma patients treated with radiotherapy were studied. Gross tumor volumes (GTVs) were contoured by a single experienced radiation oncologist on high-resolution contrast-enhanced T1 MRI scans (T1ce), and both T1 and T1ce images were utilized for segmentation. SPU-Net, an adaptation of U-Net incorporating spherical image projection to map 2D images onto a spherical surface, was proposed. As an equivalence of a nonlinear image transform, projections enhance locoregional details while maintaining the global field of view. By employing multiple projection centers, SPU-Net generates various GTV segmentation predictions, the variance indicating the model’s uncertainty. This uncertainty is quantified on a pixel-wise basis using entropy calculations and aggregated through Otsu’s method for a final segmentation.Results/conclusionThe SPU-Net model poses an advantage over traditional U-Net models by providing a quantitative method of displaying segmentation uncertainty. Regarding segmentation performance, SPU-Net demonstrated comparable results to a traditional U-Net in sensitivity (0.758 vs. 0.746), Dice similarity coefficient (0.760 vs. 0.742), reduced mean Hausdorff distance (mHD) (0.612 cm vs 0.744 cm), and reduced 95% Hausdorff distance (HD95) (2.682 cm vs 2.912 cm). SPU-Net not only is comparable to U-Net in segmentation performance but also offers a significant advantage by providing uncertainty quantification. The added SPU-Net uncertainty mapping revealed low uncertainty in accurate segments (e.g., within GTV or healthy tissue) and higher uncertainty in problematic areas (e.g., GTV boundaries, dural tail), providing valuable insights for potential manual corrections. This advancement is particularly valuable given the complex extra-axial nature of meningiomas and involvement with dural tissue. The capability to quantify uncertainty makes SPU-Net a more advanced and informative tool for segmentation, without sacrificing performance. |
| format | Article |
| id | doaj-art-5c47420981b3458ea82a3e077259b896 |
| institution | Kabale University |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-5c47420981b3458ea82a3e077259b8962025-01-28T06:41:19ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-01-011510.3389/fonc.2025.14745901474590Uncertainty quantification in multi-parametric MRI-based meningioma radiotherapy target segmentationLana Wang0Zhenyu Yang1Zhenyu Yang2Dominic LaBella3Zachary Reitman4John Ginn5Jingtong Zhao6Justus Adamson7Kyle Lafata8Kyle Lafata9Kyle Lafata10Evan Calabrese11John Kirkpatrick12Chunhao Wang13Department of Radiation Oncology, Duke University, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University, Durham, NC, United StatesMedical Physics Graduate Program, Duke Kunshan University, Kunshan, Jiangsu, ChinaDepartment of Radiation Oncology, Duke University, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University, Durham, NC, United StatesDepartment of Radiology, Duke University, Durham, NC, United StatesDepartment of Electrical Engineering, Duke University, Durham, NC, United StatesDepartment of Radiology, Duke University, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University, Durham, NC, United StatesPurposeThis work investigates the use of a spherical projection-based U-Net (SPU-Net) segmentation model to improve meningioma segmentation performance and allow for uncertainty quantification.MethodsA total of 76 supratentorial meningioma patients treated with radiotherapy were studied. Gross tumor volumes (GTVs) were contoured by a single experienced radiation oncologist on high-resolution contrast-enhanced T1 MRI scans (T1ce), and both T1 and T1ce images were utilized for segmentation. SPU-Net, an adaptation of U-Net incorporating spherical image projection to map 2D images onto a spherical surface, was proposed. As an equivalence of a nonlinear image transform, projections enhance locoregional details while maintaining the global field of view. By employing multiple projection centers, SPU-Net generates various GTV segmentation predictions, the variance indicating the model’s uncertainty. This uncertainty is quantified on a pixel-wise basis using entropy calculations and aggregated through Otsu’s method for a final segmentation.Results/conclusionThe SPU-Net model poses an advantage over traditional U-Net models by providing a quantitative method of displaying segmentation uncertainty. Regarding segmentation performance, SPU-Net demonstrated comparable results to a traditional U-Net in sensitivity (0.758 vs. 0.746), Dice similarity coefficient (0.760 vs. 0.742), reduced mean Hausdorff distance (mHD) (0.612 cm vs 0.744 cm), and reduced 95% Hausdorff distance (HD95) (2.682 cm vs 2.912 cm). SPU-Net not only is comparable to U-Net in segmentation performance but also offers a significant advantage by providing uncertainty quantification. The added SPU-Net uncertainty mapping revealed low uncertainty in accurate segments (e.g., within GTV or healthy tissue) and higher uncertainty in problematic areas (e.g., GTV boundaries, dural tail), providing valuable insights for potential manual corrections. This advancement is particularly valuable given the complex extra-axial nature of meningiomas and involvement with dural tissue. The capability to quantify uncertainty makes SPU-Net a more advanced and informative tool for segmentation, without sacrificing performance.https://www.frontiersin.org/articles/10.3389/fonc.2025.1474590/fullmeningiomauncertainty quantificationradiation therapydeep learningauto-segmentation |
| spellingShingle | Lana Wang Zhenyu Yang Zhenyu Yang Dominic LaBella Zachary Reitman John Ginn Jingtong Zhao Justus Adamson Kyle Lafata Kyle Lafata Kyle Lafata Evan Calabrese John Kirkpatrick Chunhao Wang Uncertainty quantification in multi-parametric MRI-based meningioma radiotherapy target segmentation Frontiers in Oncology meningioma uncertainty quantification radiation therapy deep learning auto-segmentation |
| title | Uncertainty quantification in multi-parametric MRI-based meningioma radiotherapy target segmentation |
| title_full | Uncertainty quantification in multi-parametric MRI-based meningioma radiotherapy target segmentation |
| title_fullStr | Uncertainty quantification in multi-parametric MRI-based meningioma radiotherapy target segmentation |
| title_full_unstemmed | Uncertainty quantification in multi-parametric MRI-based meningioma radiotherapy target segmentation |
| title_short | Uncertainty quantification in multi-parametric MRI-based meningioma radiotherapy target segmentation |
| title_sort | uncertainty quantification in multi parametric mri based meningioma radiotherapy target segmentation |
| topic | meningioma uncertainty quantification radiation therapy deep learning auto-segmentation |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1474590/full |
| work_keys_str_mv | AT lanawang uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT zhenyuyang uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT zhenyuyang uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT dominiclabella uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT zacharyreitman uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT johnginn uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT jingtongzhao uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT justusadamson uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT kylelafata uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT kylelafata uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT kylelafata uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT evancalabrese uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT johnkirkpatrick uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation AT chunhaowang uncertaintyquantificationinmultiparametricmribasedmeningiomaradiotherapytargetsegmentation |