A Deep Learning-based correction to EPID dosimetry for attenuation and scatter in the Unity MR-Linac system.

PURPOSE: EPID dosimetry in the Unity MR-Linac system allows for reconstruction of absolute dose distributions within the patient geometry. Dose reconstruction is accurate for the parts of the beam arriving at the EPID through the MRI central unattenuated region, free of gradient coils, resulting in a maximum field size of ~10 × 22 cm2 at isocentre. The purpose of this study is to develop a Deep Learning-based method to improve the accuracy of 2D EPID reconstructed dose distributions outside this central region, accounting for the effects of the extra attenuation and scatter. METHODS: A U-Net was trained to correct EPID dose images calculated at the isocenter inside a cylindrical phantom using the corresponding TPS dose images as ground truth for training. The model was evaluated using a 5-fold cross validation procedure. The clinical validity of the U-Net corrected dose images (the so-called DEEPID dose images) was assessed with in vivo verification data of 45 large rectum IMRT fields. The sensitivity of DEEPID to leaf bank position errors (±1.5 mm) and ±5% MU delivery errors was also tested. RESULTS: Compared to the TPS, in vivo 2D DEEPID dose images showed an average γ-pass rate of 90.2% (72.6%-99.4%) outside the central unattenuated region. Without DEEPID correction, this number was 44.5% (4.0%-78.4%). DEEPID correctly detected the introduced delivery errors. CONCLUSIONS: DEEPID allows for accurate dose reconstruction using the entire EPID image, thus enabling dosimetric verification for field sizes up to ~19 × 22 cm2 at isocentre. The method can be used to detect clinically relevant errors.

3D dosimetric verification of unity MR-linac treatments by portal dosimetry.

PURPOSE AND BACKGROUND: 3D dosimetric verification of online adaptive workflows is essential as their complexity is unprecedented in radiation oncology. The aim of this work is to demonstrate the feasibility of back-projection portal dosimetry for 3D dosimetric verification of Unity MR-linac treatments. MATERIAL AND METHODS: An earlier presented 2D back-projection algorithm for the Unity MR-linac geometry was extended for 3D dose reconstruction and comparison against planned dose distributions. 'In-air' as well as in-vivo portal EPID images can be used as input. The method was validated using data from treatments of 5 patients (2 rectal, 2 prostate cancer and one oligo metastasis). 3D pre-treatment verification of the reference plan using 'in-air' EPID images was performed and compared against measured (with the Octavius 4D system) and planned (in the planning CT) dose distributions. In-vivo EPID dose distributions were compared to the TPS for the first three adaptations of all treatments. For all comparisons, dose difference values at the reference point and γ-parameters were reported. RESULTS: The comparison against the OCTAVIUS 4D system (3%, 2 mm, local) showed y-mean = 0.52 ± 0.10 and y-passrate = 91.9%, 95% CI [85.4, 98.4], and ΔDRP = -0.1 ± 1.1%. Pre-treatment verification against TPS data (3%, 2 mm, global) showed y-mean = 0.52 ± 0.04, y-passrate = 93.5%, 95% CI [92.4, 94.6] and ΔDRP = -0.9 ± 1.5%. The averaged y-results for the in-vivo 3D verification were y-mean = 0.52 ± 0.05, y-passrate = 92.5%, 95% CI [90.2, 94.8] and ΔDRP = 0.8 ± 2.1%. CONCLUSION: 3D dosimetric verification of Unity MR-linac treatments using portal dosimetry is feasible, pre-treatment as well as in-vivo.

Two-dimensional EPID dosimetry for an MR-linac: Proof of concept.

PURPOSE: At our institute, in vivo patient dose distributions are reconstructed for all treatments delivered using conventional linacs from electronic portal imaging device (EPID) transit images acquired during treatment using a simple back-projection model. Currently, the clinical implementation of MRI-guided radiotherapy systems, which aims for online and real-time adaptation of the treatment plan, is progressing. In our department, the MR-linac (Unity, Elekta AB, Stockholm, Sweden) is now in clinical use. The aim of this work is to demonstrate the feasibility of two-dimensional (2D) EPID dosimetric verification for the magnetic resonance (MR)-linac by comparing back-projected EPID doses to ionization chamber (IC) array dose distributions. MATERIALS AND METHODS: Our conventional back-projection algorithm was adapted for the MR-linac. The most important changes involve modeling of the attenuation by and scatter from the cryostat. The commissioning process involved the acquisition of square field EPID measurements using various phantom setups (varying SSD, phantom thickness, and field size). Commissioning models were created for gantry 0°, 90°, and 180° and verified by comparing EPID-reconstructed 2D dose distributions to measurements made with the OCTAVIUS 1500 IC array (PTW, Freiburg, Germany) for two prostate and one rectum IMRT plans (25 beams total). The average of the γ parameters (y-mean and y-pass rate) and the dose difference at a reference point were reported. Due to their construction, the attenuation of couch, bridge, and cryostat shows a much stronger dependence on gantry angle in the MR-linac compared to conventional linacs. We present a method to correct for these effects. This method is validated by dose reconstruction of the 25 intensity-modulated radiation therapy beams recorded at a certain gantry angle using the model of another gantry angle, combined with the correction method. RESULTS: For dose verification performed at a gantry angle identical to the commissioned model, the average y-mean and y-pass rate values (3% global dose, 2 mm, 10% isodose) were 0.37 ± 0.07 and 98.1, 95% CI [98.1 ± 2.4], respectively. The average dose difference at the reference point was -0.5% ± 1.8%. Verification at gantry angles different from the commissioned model (i.e., using the gantry angle dependent correction) reported 0.39 ± 0.08 and 97.6, 95% CI [96.9, 98.3] average y-mean and y-pass rate values. The average dose difference at the reference point was -0.1% ± 1.8%. CONCLUSION: The EPID dosimetry back-projection model was successfully adapted for the MR-linac at gantry 0°, 90°, and 180°, accounting for the presence of the MRI housing between phantom (or patient) and the EPID. A method to account for the gantry angle dependence was also tested reporting similar results.