Technical note: Flat panel proton radiography with a patient specific imaging field for accurate WEPL assessment

BACKGROUND

Proton radiography (PR) uses highly energetic proton beams to create images where energy loss is the main contrast mechanism. Water-equivalent path length (WEPL) measurements using flat panel PR (FP-PR) have potential for in vivo range verification. However, an accurate WEPL measurement via FP-PR requires irradiation with multiple energy layers, imposing high imaging doses.

PURPOSE

A FP-PR method is proposed for accurate WEPL determination based on a patient-specific imaging field with a reduced number of energies (n) to minimize imaging dose.

METHODS

Patient-specific FP-PRs were simulated and measured for a head and neck (HN) phantom. An energy selection algorithm estimated spot-wise the lowest energy required to cross the anatomy (Emin) using a water-equivalent thickness map. Starting from Emin, n was restricted to certain values (n = 26, 24, 22, …, 2 for simulations, n = 10 for measurements), resulting in patient-specific FP-PRs. A reference FP-PR with a complete set of energies was compared against patient-specific FP-PRs covering the whole anatomy via mean absolute WEPL differences (MAD), to evaluate the impact of the developed algorithm. WEPL accuracy of patient-specific FP-PRs was assessed using mean relative WEPL errors (MRE) with respect to measured multi-layer ionization chamber PRs (MLIC-PR) in the base of skull, brain, and neck regions.

RESULTS

MADs ranged from 2.1 mm (n = 26) to 21.0 mm (n = 2) for simulated FP-PRs, and 7.2 mm for measured FP-PRs (n = 10). WEPL differences below 1 mm were observed across the whole anatomy, except at the phantom surfaces. Measured patient-specific FP-PRs showed good agreement against MLIC-PRs, with MREs of 1.3 ± 2.0%, -0.1 ± 1.0%, and -0.1 ± 0.4% in the three regions of the phantom.

CONCLUSION

A method to obtain accurate WEPL measurements using FP-PR with a reduced number of energies selected for the individual patient anatomy was established in silico and validated experimentally. Patient-specific FP-PRs could provide means of in vivo range verification.

Deep learning-based 4D-synthetic CTs from sparse-view CBCTs for dose calculations in adaptive proton therapy

BACKGROUND

Time-resolved 4D cone beam-computed tomography (4D-CBCT) allows a daily assessment of patient anatomy and respiratory motion. However, 4D-CBCTs suffer from imaging artifacts that affect the CT number accuracy and prevent accurate proton dose calculations. Deep learning can be used to correct CT numbers and generate synthetic CTs (sCTs) that can enable CBCT-based proton dose calculations.

PURPOSE

In this work, sparse view 4D-CBCTs were converted into 4D-sCT utilizing a deep convolutional neural network (DCNN). 4D-sCTs were evaluated in terms of image quality and dosimetric accuracy to determine if accurate proton dose calculations for adaptive proton therapy workflows of lung cancer patients are feasible.

METHODS

A dataset of 45 thoracic cancer patients was utilized to train and evaluate a DCNN to generate 4D-sCTs, based on sparse view 4D-CBCTs reconstructed from projections acquired with a 3D acquisition protocol. Mean absolute error (MAE) and mean error were used as metrics to evaluate the image quality of single phases and average 4D-sCTs against 4D-CTs acquired on the same day. The dosimetric accuracy was checked globally (gamma analysis) and locally for target volumes and organs-at-risk (OARs) (lung, heart, and esophagus). Furthermore, 4D-sCTs were also compared to 3D-sCTs. To evaluate CT number accuracy, proton radiography simulations in 4D-sCT and 4D-CTs were compared in terms of range errors. The clinical suitability of 4D-sCTs was demonstrated by performing a 4D dose reconstruction using patient specific treatment delivery log files and breathing signals.

RESULTS

4D-sCTs resulted in average MAEs of 48.1 ± 6.5 HU (single phase) and 37.7 ± 6.2 HU (average). The global dosimetric evaluation showed gamma pass ratios of 92.3% ± 3.2% (single phase) and 94.4% ± 2.1% (average). The clinical target volume showed high agreement in D₉₈ between 4D-CT and 4D-sCT, with differences below 2.4% for all patients. Larger dose differences were observed in mean doses of OARs (up to 8.4%). The comparison with 3D-sCTs showed no substantial image quality and dosimetric differences for the 4D-sCT average. Individual 4D-sCT phases showed slightly lower dosimetric accuracy. The range error evaluation revealed that lung tissues cause range errors about three times higher than the other tissues.

CONCLUSION

In this study, we have investigated the accuracy of deep learning-based 4D-sCTs for daily dose calculations in adaptive proton therapy. Despite image quality differences between 4D-sCTs and 3D-sCTs, comparable dosimetric accuracy was observed globally and locally. Further improvement of 3D and 4D lung sCTs could be achieved by increasing CT number accuracy in lung tissues.

Clinical suitability of deep learning based synthetic CTs for adaptive proton therapy of lung cancer

Purpose

Adaptive proton therapy (APT) of lung cancer patients requires frequent volumetric imaging of diagnostic quality. Cone‐beam CT (CBCT) can provide these daily images, but x‐ray scattering limits CBCT‐image quality and hampers dose calculation accuracy. The purpose of this study was to generate CBCT‐based synthetic CTs using a deep convolutional neural network (DCNN) and investigate image quality and clinical suitability for proton dose calculations in lung cancer patients.

Methods

A dataset of 33 thoracic cancer patients, containing CBCTs, same‐day repeat CTs (rCT), planning‐CTs (pCTs), and clinical proton treatment plans, was used to train and evaluate a DCNN with and without a pCT‐based correction method. Mean absolute error (MAE), mean error (ME), peak signal‐to‐noise ratio, and structural similarity were used to quantify image quality. The evaluation of clinical suitability was based on recalculation of clinical proton treatment plans. Gamma pass ratios, mean dose to target volumes and organs at risk, and normal tissue complication probabilities (NTCP) were calculated. Furthermore, proton radiography simulations were performed to assess the HU‐accuracy of sCTs in terms of range errors.

Results

On average, sCTs without correction resulted in a MAE of 34 ± 6 HU and ME of 4 ± 8 HU. The correction reduced the MAE to 31 ± 4HU (ME to 2 ± 4HU). Average 3%/3 mm gamma pass ratios increased from 93.7% to 96.8%, when the correction was applied. The patient specific correction reduced mean proton range errors from 1.5 to 1.1 mm. Relative mean target dose differences between sCTs and rCT were below ± 0.5% for all patients and both synthetic CTs (with/without correction). NTCP values showed high agreement between sCTs and rCT (<2%).

Conclusion

CBCT‐based sCTs can enable accurate proton dose calculations for APT of lung cancer patients. The patient specific correction method increased the image quality and dosimetric accuracy but had only a limited influence on clinically relevant parameters.

Optimizing calibration settings for accurate water equivalent path length assessment using flat panel proton radiography

OBJECTIVE

Proton range uncertainties can compromise the effectiveness of proton therapy treatments. Water equivalent path length (WEPL) assessment by flat panel detector proton radiography (FP-PR) can provide means of range uncertainty detection. Since WEPL accuracy intrinsically relies on the FP-PR calibration parameters, the purpose of this study is to establish an optimal calibration procedure that ensures high accuracy of WEPL measurements. To that end, several calibration settings were investigated.

APPROACH

FP-PR calibration datasets were obtained simulating PR fields with different proton energies, directed towards water-equivalent material slabs of increasing thickness. The parameters investigated were the spacing between energy layers (ΔE) and the increment in thickness of the water-equivalent material slabs (ΔX) used for calibration. 30 calibrations were simulated, as a result of combining ΔE = 9, 7, 5, 3, 1 MeV and ΔX = 10, 8, 5, 3, 2, 1 mm. FP-PRs through a CIRS electron density phantom were simulated, and WEPL images corresponding to each calibration were obtained. Ground truth WEPL values were provided by range probing multi-layer ionization chamber simulations on each insert of the phantom. Relative WEPL errors between FP-PR simulations and ground truth were calculated for each insert. Mean relative WEPL errors and standard deviations across all inserts were computed for WEPL images obtained with each calibration.

MAIN RESULTS

Large mean and standard deviations were found in WEPL images obtained with large ΔEvalues (ΔE = 9 or 7 MeV), for any ΔX. WEPL images obtained with ΔE ≤ 5 MeV and ΔX ≤ 5 mm resulted in a WEPL accuracy with mean values within ±0.5% and standard deviations around 1%.

SIGNIFICANCE

An optimal FP calibration in the framework of this study was established, characterized by 3 MeV ≤ ΔE ≤ 5 MeV and 2 mm ≤ ΔX ≤ 5 mm. Within these boundaries, highly accurate WEPL acquisitions using FP-PR are feasible and practical, holding the potential to assist future online range verification quality control procedures.

Range probing as a quality control tool for CBCT-based synthetic CTs: In vivo application for head and neck cancer patients

Purpose

Cone‐beam CT (CBCT)‐based synthetic CTs (sCT) produced with a deep convolutional neural network (DCNN) show high image quality, suggesting their potential usability in adaptive proton therapy workflows. However, the nature of such workflows involving DCNNs prevents the user from having direct control over their output. Therefore, quality control (QC) tools that monitor the sCTs and detect failures or outliers in the generated images are needed.

This work evaluates the potential of using a range‐probing (RP)‐based QC tool to verify sCTs generated by a DCNN. Such a RP QC tool experimentally assesses the CT number accuracy in sCTs.

Methods

A RP QC dataset consisting of repeat CTs (rCT), CBCTs, and RP acquisitions of seven head and neck cancer patients was retrospectively assessed. CBCT‐based sCTs were generated using a DCNN. The CT number accuracy in the sCTs was evaluated by computing relative range errors between measured RP fields and RP field simulations based on rCT and sCT images.

Results

Mean relative range errors showed agreement between measured and simulated RP fields, ranging from −1.2% to 1.5% in rCTs, and from −0.7% to 2.7% in sCTs.

Conclusions

The agreement between measured and simulated RP fields suggests the suitability of sCTs for proton dose calculations. This outcome brings sCTs generated by DCNNs closer toward clinical implementation within adaptive proton therapy treatment workflows. The proposed RP QC tool allows for CT number accuracy assessment in sCTs and can provide means of in vivo range verification.

Technical Note: First report on an in vivo range probing quality control procedure for scanned proton beam therapy in head and neck cancer patients

PURPOSE

The capability of proton therapy to provide highly conformal dose distributions is impaired by range uncertainties. The aim of this work is to apply range probing (RP), a form of a proton radiography-based quality control (QC) procedure for range accuracy assessment in head and neck cancer (HNC) patients in a clinical setting.

METHODS AND MATERIALS

This study included seven HNC patients. RP acquisition was performed using a multi-layer ionization chamber (MLIC). Per patient, two RP frames were acquired within the first two weeks of treatment, on days when a repeated CT scan was obtained. Per RP frame, integral depth dose (IDD) curves of 81 spots around the treatment isocenter were acquired. Range errors are determined as a discrepancy between calculated IDDs in the treatment planning system and measured residual ranges by the MLIC. Range errors are presented relative to the water equivalent path length of individual proton spots. In addition to reporting results for complete measurement frames, an analysis, excluding range error contributions due to anatomical changes, is presented.

RESULTS

Discrepancies between measured and calculated ranges are smaller when performing RP calculations on the day-specific patient anatomy rather than the planning CT. The patient-specific range evaluation shows an agreement between calculated and measured ranges for spots in anatomically consistent areas within 3% (1.5 standard deviation).

CONCLUSIONS

The results of an RP-based QC procedure implemented in the clinical practice for HNC patients have been demonstrated. The agreement of measured and simulated proton ranges confirms the 3% uncertainty margin for robust optimization. Anatomical variations show a predominant effect on range accuracy, motivating efforts towards the implementation of adaptive radiotherapy.

Classification of various sources of error in range assessment using proton radiography and neural networks in head and neck cancer patients

This study evaluates the suitability of convolutional neural networks (CNN) to automatically process proton radiography (PR) based images. CNNs are used to classify PR images impaired by several sources of error affecting the proton range, more precisely setup and calibration curve errors. PR simulations were performed in 40 head and neck cancer patients, at three different anatomical locations (fields A, B and C, centered for head and neck, neck and base of skull coverage). Field sizes were 26x26cm2 for field A and 4.5x4.5cm2 for fields B and C. Range shift maps were obtained by comparing an unperturbed reference PR against a PR where one or more sources of error affected the proton range. CT calibration curve errors in soft, bone and fat tissues and setup errors in the anterior-posterior and inferior-superior directions were simulated individually and in combination. A CNN was trained for each type of PR field, leading to 3 CNNs trained with a mixture of range shift maps arising from one or more sources of range error. To test the full/partial/wrong agreement between predicted and actual sources of range error in the range shift maps, exact, partial and wrong match percentages were computed for an independent test dataset containing range shift maps arising from isolated or combined errors, retrospectively. The CNN corresponding to field A showed superior capability to detect isolated and combined errors, with exact matches of 92% and 71% respectively. Field B showed exact matches of 80% and 54%, and field C resulted in exact matches of 77% and 41%. The suitability of CNNs to classify PR based images containing different sources of error affecting the proton range was demonstrated. This procedure enables the detection of setup and calibration curve errors when they appear individually or in combination, providing valuable information for the interpretation of PR images.