Deep-learning Method for the Prediction of Three-Dimensional Dose Distribution for Left Breast Cancer Conformal Radiation Therapy

AIMS

An increase in the demand of a new generation of radiotherapy planning systems based on learning approaches has been reported. At this stage, the new approach is able to improve the planning speed while saving a reasonable level of plan quality, compared with available planning systems. We believe that new achievements, such as deep-learning models, will be able to review the issue from a different point of view.

MATERIALS AND METHODS

The data of 120 breast cancer patients were used to train and test the three-dimensional U-Res-Net model. The network input was computed tomography images and patients' contouring, while the patients' dose distribution was addressed as the output of the model proposed. The predicted dose distributions, created by the model for 10 test patients, were then compared with corresponding dose distributions calculated by a reliable treatment planning system. In particular, the dice similarity coefficients for different isodose volumes, dose difference and mean absolute errors (MAE) for all voxels inside the body, Dmean, D98%, D50%, D2%, V95% for planning target volume and organs at risk were calculated and were statistically analysed with the paired-samples t-test.

RESULTS

The average dose difference for all patients and voxels in body was 0.60 ± 2.81%. The MAE varied from 3.85 ± 6.65% to 8.06 ± 10.00%. The average MAE for test cases was 5.71 ± 1.19%. The average dice similarity coefficients for isodose volumes was 0.91 ± 0.03. The three-dimensional gamma passing rates with 3 mm/3% criteria varied from 78.99% to 97.58% for planning target volume and organs at risk, respectively.

CONCLUSIONS

The investigation showed that a deep-learning model can be applied to predict the three-dimensional dose distribution with optimal accuracy and precision for patients with left breast cancer. As further study, the model can be extended to predict dose distribution in other cancers.

Impact of Different Beam Energies on The Incidence of Thyroid Cancer in Breast Cancer Radiotherapy

Purpose: During breast radiotherapy, the organs which are located out of the radiation field such as the thyroid are prone to secondary cancers. The present study aims to evaluate the risk of thyroid cancer in breast cancer radiotherapy in conventional and conformal radiation therapy. Materials and Methods: The data related to the thyroid dose in radiotherapy of breast cancer from the study by Behmadi et al. were used. In their study, the thyroid dose was measured on the Alderson RANDO phantom for four different breast cancer treatment plans and two photon energies. Using the Biological Effects of Ionizing Radiation (BEIR) VII model, the risk of thyroid cancer was estimated in conventional and conformal plans with two photon energies (6 and 15 MV) in breast cancer radiotherapy. Results: The Lifetime Attributable Risk (LAR) for thyroid cancer in the conventional technique was only 7.5% higher than that in the conformal technique. In the conventional treatment technique, LAR for thyroid cancer at 6 MV in all age groups was 17% higher than the 15 MV energy. However, the LAR for thyroid cancer in conformal technique at 15 MV energy was 50% higher than at 6 MV energy. Conclusion: Applying high energy for radiotherapy of breast cancer, in the conventional technique, could reduce the risk of thyroid cancer. But at high energies, the risk of thyroid cancer in the conformal technique is considerably higher than that at low energy. Therefore, it is suggested that the impact of energies be evaluated to reduce the risk of thyroid cancer in breast cancer radiotherapy.

THERMAL AND FAST NEUTRON DOSE EQUIVALENT DISTRIBUTION MEASUREMENT OF 15-MV LINEAR ACCELERATOR USING A CR-39 NUCLEAR TRACK DETECTORS

The main purpose of this study is to measure the contribution of the thermal and fast neutron dose along the central axis of the 15 MV Elekta Precise linac in a tissue equivalent phantom. In order to achieve this purpose, different points were selected in three field sizes of 5 × 5 cm2, 10 × 10 cm2 and 15 × 15 cm2. Fast and thermal neutrons were measured using CR-39 nuclear track detectors with and without thermal neutron converter of 10B, respectively. According to the results, the fast neutron dose equivalent was decreased as the depth increased (field size 5 × 5, 10 × 10 and 15 × 15 cm2 fall from 0.35 to 0.15, 0.5 to 0.3 and 0.5 to 0.3, respectively). Thermal dose equivalent was increased as the depth increased in the tissue equivalent phantom (field size 5 × 5, 10 × 10 and 15 × 15 cm2 rise from 0.1 to 0.4, 0.4 to 0.8 and 0.4 to 0.9, respectively). In conclusion, at depth <3 cm, most existing neutrons are fast and CR-39 films are sensitive to fast neutrons; therefore, they are more appropriate than thermoluminescent dosemeters in measuring neutron dose equivalent.

A Monte Carlo study on dose perturbation due to dental restorations in a 15 MV photon beam

Aim

The main purpose of this study is to evaluate the effect of dose perturbation due to common dental restoration materials in the head and neck radiotherapy with a 15 MV external photon beam.

Setting and Design

Teeth with three dental restorations such as tooth filled with Amalgam, Ni-Cr alloy, and Ceramco were simulated by MCNPX Monte Carlo code. In this simulation, the dental materials were exposed by a 15 MV photon beam from a Siemens Primus linac, inside a water phantom.

Materials and Methods

A Siemens Primus linear accelerator and a phantom including: tooth only, tooth with Amalgam, tooth with Ni-Cr alloy, and tooth with Ceramco were simulated by MCNPX Monte Carlo code, separately. The percentage dose change was evaluated relative to dose in water versus depth for these samples on the beam's central axis. The absolute dose by prescription of 100 cGy dose in water phantom at 3.0 cm depth was calculated for water, tooth, tooth with Amalgam, tooth with Ni-Cr alloy, and tooth with Ceramco.

Results

The maximum percentage dose change is related to tooth with Ni-Cr alloy, tooth, tooth with Ceramco, and tooth with Amalgam with amounts of 7.73%, 6.95%, 4.7%, and 3.06% relative to water at 0.75 cm depth, respectively. When 100.0 cGy dose was prescribed at 3.1 cm, the maximum absolute dose was 201.0% in the presence of tooth with Ni-Cr alloy at 0.75 cm.

Conclusion

Introduction of the compositions of dental restorations can improve the accuracy of dosimetric calculations in treatment planning and protect the healthy tissues surrounding teeth from a considerable overdose.

Evaluation of Breast Cancer Radiation Therapy Techniques in Outfield Organs of Rando Phantom with Thermoluminescence Dosimeter

BACKGROUND

Given the importance of scattered and low doses in secondary cancer caused by radiation treatment, the point dose of critical organs, which were not subjected to radiation treatment in breast cancer radiotherapy, was measured.

OBJECTIVE

The purpose of this study is to evaluate the peripheral dose in two techniques of breast cancer radiotherapy with two energies.

MATERIAL AND METHODS

Eight different plans in two techniques (conventional and conformal) and two photon energies (6 and 15 MeV) were applied to Rando Alderson Phantom's DICOM images. Nine organs were contoured in the treatment planning system and specified on the phantom. To measure the photon dose, forty-eight thermoluminescence dosimeters (MTS700) were positioned in special places on the above nine organs and plans were applied to Rando phantom with Elekta presice linac. To obtain approximately the same dose distribution in the clinical organ volume, a wedge was used on planes with an energy of 6 MeV photon.

RESULTS

Point doses in critical organs with 8 different plans demonstrated that scattering in low-energy photon is greater than high-energy photon. In contrast, neutron contamination in high-energy photon is not negligible. Using the wedge and shield impose greater scattering and neutron contamination on patients with low-and high-energy photon, respectively.

CONCLUSION

Deciding on techniques and energies required for preparing an acceptable treatment plan in terms of scattering and neutron contamination is a key issue that may affect the probability of secondary cancer in a patient.

Determination of task group 43 dosimetric parameters for CSM40 137Cs source for use in brachytherapy

The CSM40 ¹³⁷Cs source model is currently being used in clinical brachytherapy. According to the recommendations of task group No. 43 (TG-43) of the American Association of Physicists in Medicine, dosimetry parameters of brachytherapy sources should be determined by two independent investigators before their clinical use. The aim of this study was to determine the TG-43 dosimetry parameters for a medium-dose-rate CSM40 ¹³⁷Cs source. The determined dosimetric parameters included the air kerma strength, dose rate constant, radial dose function, and anisotropy function. To determine the source's dosimetric parameters, the CSM40 source was stimulated by the Monte Carlo N-Particle MCNP code. The TG-43 parameters were compared with the data of Vijande et al. on this source. The results showed that the dosimetry parameters for this source had good agreement with the results of Vijande et al. The dosimetric parameters of the CSM40 source can be used in treatment-planning systems incorporating this source model. The data can also be used for the quality assurance of treatment-planning systems.

A Monte Carlo study on electron and neutron contamination caused by the presence of hip prosthesis in photon mode of a 15 MV Siemens PRIMUS linac

Several investigators have pointed out that electron and neutron contamination from high‐energy photon beams are clinically important. The aim of this study is to assess electron and neutron contamination production by various prostheses in a high‐energy photon beam of a medical linac. A 15 MV Siemens PRIMUS linac was simulated by MCNPX Monte Carlo (MC) code and the results of percentage depth dose (PDD) and dose profile values were compared with the measured data. Electron and neutron contaminations were calculated on the beam's central axis for Co‐Cr‐Mo, stainless steel, Ti‐alloy, and Ti hip prostheses through MC simulations. Dose increase factor (DIF) was calculated as the ratio of electron (neutron) dose at a point for 10×10 cm2 field size in presence of prosthesis to that at the same point in absence of prosthesis. DIF was estimated at different depths in a water phantom. Our MC‐calculated PDD and dose profile data are in good agreement with the corresponding measured values. Maximum dose increase factor for electron contamination for Co‐Cr‐Mo, stainless steel, Ti‐alloy, and Ti prostheses were equal to 1.18, 1.16, 1.16, and 1.14, respectively. The corresponding values for neutron contamination were respectively equal to: 184.55, 137.33, 40.66, and 43.17. Titanium‐based prostheses are recommended for the orthopedic practice of hip junction replacement. When treatment planning for a patient with hip prosthesis is performed for a high‐energy photon beam, attempt should be made to ensure that the prosthesis is not exposed to primary photons.

PACS numbers: 87.56.bd, 87.55.kh, 87.55.Gh