Modeling dose uncertainty in cone-beam computed tomography: Predictive approach for deep learning-based synthetic computed tomography generation
Background and purpose:: Cone-beam computed tomography (CBCT) is essential in image-guided radiotherapy (RT) for patient positioning and daily dose calculation. However, CT numbers in CBCT fluctuate and differ from those in computed tomography (CT), requiring synthetic CT (sCT) generation to improve...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Physics and Imaging in Radiation Oncology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405631625000090 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582080891977728 |
|---|---|
| author | Cédric Hémon Lucía Cubero Valentin Boussot Romane-Alize Martin Blanche Texier Joël Castelli Renaud de Crevoisier Anaïs Barateau Caroline Lafond Jean-Claude Nunes |
| author_facet | Cédric Hémon Lucía Cubero Valentin Boussot Romane-Alize Martin Blanche Texier Joël Castelli Renaud de Crevoisier Anaïs Barateau Caroline Lafond Jean-Claude Nunes |
| author_sort | Cédric Hémon |
| collection | DOAJ |
| description | Background and purpose:: Cone-beam computed tomography (CBCT) is essential in image-guided radiotherapy (RT) for patient positioning and daily dose calculation. However, CT numbers in CBCT fluctuate and differ from those in computed tomography (CT), requiring synthetic CT (sCT) generation to improve dose calculation accuracy. CBCT-to-sCT synthesis remains a challenging and uncertain task in clinical practice. This study aims to introduce a voxel-wise uncertainty estimator correlated with the error between sCT and CT. Material and Methods:: Eighty-five head and neck (H&N) patients treated with photon RT from a single center were selected for developing and validating our uncertainty estimation method. To test the method’s robustness on out-of-distribution images, three additional patients from different centers were included. Our proposed uncertainty estimation method builds on established conventional techniques. Additionally, to explore potential error scenarios, we generated several ‘plausible’ sCTs representing variations in sCT generation caused by CBCT quality differences. This allowed us to quantify dose uncertainties. Results:: The effectiveness of uncertainty maps was evaluated by correlating them with the absolute error map between sCT and CT, yielding a Pearson correlation coefficient between 0.65 and 0.72. Dose uncertainty was determined on the dose-volume histogram (DVH). For all patients except one, the reference CT DVH was included in the uncertainty interval defined by the sCT-derived DVH. Conclusions:: Our proposed methods effectively predict uncertainty maps that aid in evaluating sCT quality. This approach also provides a novel method for estimating dose uncertainty by defining a confidence interval around the CT DVH using the estimated sCT uncertainty. |
| format | Article |
| id | doaj-art-2358aebf05e347af9ef9aa65c2fe0fe5 |
| institution | Kabale University |
| issn | 2405-6316 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Physics and Imaging in Radiation Oncology |
| spelling | doaj-art-2358aebf05e347af9ef9aa65c2fe0fe52025-01-30T05:14:33ZengElsevierPhysics and Imaging in Radiation Oncology2405-63162025-01-0133100704Modeling dose uncertainty in cone-beam computed tomography: Predictive approach for deep learning-based synthetic computed tomography generationCédric Hémon0Lucía Cubero1Valentin Boussot2Romane-Alize Martin3Blanche Texier4Joël Castelli5Renaud de Crevoisier6Anaïs Barateau7Caroline Lafond8Jean-Claude Nunes9Corresponding author.; Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceUniv. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceUniv. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceUniv. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceUniv. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceUniv. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceUniv. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceUniv. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceUniv. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceUniv. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, FranceBackground and purpose:: Cone-beam computed tomography (CBCT) is essential in image-guided radiotherapy (RT) for patient positioning and daily dose calculation. However, CT numbers in CBCT fluctuate and differ from those in computed tomography (CT), requiring synthetic CT (sCT) generation to improve dose calculation accuracy. CBCT-to-sCT synthesis remains a challenging and uncertain task in clinical practice. This study aims to introduce a voxel-wise uncertainty estimator correlated with the error between sCT and CT. Material and Methods:: Eighty-five head and neck (H&N) patients treated with photon RT from a single center were selected for developing and validating our uncertainty estimation method. To test the method’s robustness on out-of-distribution images, three additional patients from different centers were included. Our proposed uncertainty estimation method builds on established conventional techniques. Additionally, to explore potential error scenarios, we generated several ‘plausible’ sCTs representing variations in sCT generation caused by CBCT quality differences. This allowed us to quantify dose uncertainties. Results:: The effectiveness of uncertainty maps was evaluated by correlating them with the absolute error map between sCT and CT, yielding a Pearson correlation coefficient between 0.65 and 0.72. Dose uncertainty was determined on the dose-volume histogram (DVH). For all patients except one, the reference CT DVH was included in the uncertainty interval defined by the sCT-derived DVH. Conclusions:: Our proposed methods effectively predict uncertainty maps that aid in evaluating sCT quality. This approach also provides a novel method for estimating dose uncertainty by defining a confidence interval around the CT DVH using the estimated sCT uncertainty.http://www.sciencedirect.com/science/article/pii/S2405631625000090CBCT-to-CT generationUncertainty estimationDose uncertaintyHead and Neck |
| spellingShingle | Cédric Hémon Lucía Cubero Valentin Boussot Romane-Alize Martin Blanche Texier Joël Castelli Renaud de Crevoisier Anaïs Barateau Caroline Lafond Jean-Claude Nunes Modeling dose uncertainty in cone-beam computed tomography: Predictive approach for deep learning-based synthetic computed tomography generation Physics and Imaging in Radiation Oncology CBCT-to-CT generation Uncertainty estimation Dose uncertainty Head and Neck |
| title | Modeling dose uncertainty in cone-beam computed tomography: Predictive approach for deep learning-based synthetic computed tomography generation |
| title_full | Modeling dose uncertainty in cone-beam computed tomography: Predictive approach for deep learning-based synthetic computed tomography generation |
| title_fullStr | Modeling dose uncertainty in cone-beam computed tomography: Predictive approach for deep learning-based synthetic computed tomography generation |
| title_full_unstemmed | Modeling dose uncertainty in cone-beam computed tomography: Predictive approach for deep learning-based synthetic computed tomography generation |
| title_short | Modeling dose uncertainty in cone-beam computed tomography: Predictive approach for deep learning-based synthetic computed tomography generation |
| title_sort | modeling dose uncertainty in cone beam computed tomography predictive approach for deep learning based synthetic computed tomography generation |
| topic | CBCT-to-CT generation Uncertainty estimation Dose uncertainty Head and Neck |
| url | http://www.sciencedirect.com/science/article/pii/S2405631625000090 |
| work_keys_str_mv | AT cedrichemon modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration AT luciacubero modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration AT valentinboussot modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration AT romanealizemartin modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration AT blanchetexier modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration AT joelcastelli modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration AT renauddecrevoisier modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration AT anaisbarateau modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration AT carolinelafond modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration AT jeanclaudenunes modelingdoseuncertaintyinconebeamcomputedtomographypredictiveapproachfordeeplearningbasedsyntheticcomputedtomographygeneration |