Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools
Radiotherapy commonly utilizes cone beam computed tomography (CBCT) for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Computer Assisted Surgery |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/24699322.2024.2327981 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850064606531158016 |
|---|---|
| author | Matteo Rossi Gabriele Belotti Luca Mainardi Guido Baroni Pietro Cerveri |
| author_facet | Matteo Rossi Gabriele Belotti Luca Mainardi Guido Baroni Pietro Cerveri |
| author_sort | Matteo Rossi |
| collection | DOAJ |
| description | Radiotherapy commonly utilizes cone beam computed tomography (CBCT) for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radiation artifacts, and variability in pixel intensity hinder the direct use of raw CBCT for dose recalculation during treatment. To address this issue, reliable correction techniques are necessary to remove artifacts and remap pixel intensity into Hounsfield Units (HU) values. This study proposes a deep-learning framework for calibrating CBCT images acquired with narrow field of view (FOV) systems and demonstrates its potential use in proton treatment planning updates. Cycle-consistent generative adversarial networks (cGAN) processes raw CBCT to reduce scatter and remap HU. Monte Carlo simulation is used to generate CBCT scans, enabling the possibility to focus solely on the algorithm’s ability to reduce artifacts and cupping effects without considering intra-patient longitudinal variability and producing a fair comparison between planning CT (pCT) and calibrated CBCT dosimetry. To showcase the viability of the approach using real-world data, experiments were also conducted using real CBCT. Tests were performed on a publicly available dataset of 40 patients who received ablative radiation therapy for pancreatic cancer. The simulated CBCT calibration led to a difference in proton dosimetry of less than 2%, compared to the planning CT. The potential toxicity effect on the organs at risk decreased from about 50% (uncalibrated) up the 2% (calibrated). The gamma pass rate at 3%/2 mm produced an improvement of about 37% in replicating the prescribed dose before and after calibration (53.78% vs 90.26%). Real data also confirmed this with slightly inferior performances for the same criteria (65.36% vs 87.20%). These results may confirm that generative artificial intelligence brings the use of narrow FOV CBCT scans incrementally closer to clinical translation in proton therapy planning updates. |
| format | Article |
| id | doaj-art-908e7d5e865e4100892716bc5f6fe802 |
| institution | DOAJ |
| issn | 2469-9322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Computer Assisted Surgery |
| spelling | doaj-art-908e7d5e865e4100892716bc5f6fe8022025-08-20T02:49:16ZengTaylor & Francis GroupComputer Assisted Surgery2469-93222024-12-0129110.1080/24699322.2024.2327981Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence toolsMatteo Rossi0Gabriele Belotti1Luca Mainardi2Guido Baroni3Pietro Cerveri4Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, ItalyDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, ItalyDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, ItalyDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, ItalyDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, ItalyRadiotherapy commonly utilizes cone beam computed tomography (CBCT) for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radiation artifacts, and variability in pixel intensity hinder the direct use of raw CBCT for dose recalculation during treatment. To address this issue, reliable correction techniques are necessary to remove artifacts and remap pixel intensity into Hounsfield Units (HU) values. This study proposes a deep-learning framework for calibrating CBCT images acquired with narrow field of view (FOV) systems and demonstrates its potential use in proton treatment planning updates. Cycle-consistent generative adversarial networks (cGAN) processes raw CBCT to reduce scatter and remap HU. Monte Carlo simulation is used to generate CBCT scans, enabling the possibility to focus solely on the algorithm’s ability to reduce artifacts and cupping effects without considering intra-patient longitudinal variability and producing a fair comparison between planning CT (pCT) and calibrated CBCT dosimetry. To showcase the viability of the approach using real-world data, experiments were also conducted using real CBCT. Tests were performed on a publicly available dataset of 40 patients who received ablative radiation therapy for pancreatic cancer. The simulated CBCT calibration led to a difference in proton dosimetry of less than 2%, compared to the planning CT. The potential toxicity effect on the organs at risk decreased from about 50% (uncalibrated) up the 2% (calibrated). The gamma pass rate at 3%/2 mm produced an improvement of about 37% in replicating the prescribed dose before and after calibration (53.78% vs 90.26%). Real data also confirmed this with slightly inferior performances for the same criteria (65.36% vs 87.20%). These results may confirm that generative artificial intelligence brings the use of narrow FOV CBCT scans incrementally closer to clinical translation in proton therapy planning updates.https://www.tandfonline.com/doi/10.1080/24699322.2024.2327981Deep learningimage-to-image translationdosimetrycycleGANCBCTCT |
| spellingShingle | Matteo Rossi Gabriele Belotti Luca Mainardi Guido Baroni Pietro Cerveri Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools Computer Assisted Surgery Deep learning image-to-image translation dosimetry cycleGAN CBCT CT |
| title | Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools |
| title_full | Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools |
| title_fullStr | Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools |
| title_full_unstemmed | Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools |
| title_short | Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools |
| title_sort | feasibility of proton dosimetry overriding planning ct with daily cbct elaborated through generative artificial intelligence tools |
| topic | Deep learning image-to-image translation dosimetry cycleGAN CBCT CT |
| url | https://www.tandfonline.com/doi/10.1080/24699322.2024.2327981 |
| work_keys_str_mv | AT matteorossi feasibilityofprotondosimetryoverridingplanningctwithdailycbctelaboratedthroughgenerativeartificialintelligencetools AT gabrielebelotti feasibilityofprotondosimetryoverridingplanningctwithdailycbctelaboratedthroughgenerativeartificialintelligencetools AT lucamainardi feasibilityofprotondosimetryoverridingplanningctwithdailycbctelaboratedthroughgenerativeartificialintelligencetools AT guidobaroni feasibilityofprotondosimetryoverridingplanningctwithdailycbctelaboratedthroughgenerativeartificialintelligencetools AT pietrocerveri feasibilityofprotondosimetryoverridingplanningctwithdailycbctelaboratedthroughgenerativeartificialintelligencetools |