Online Adaptive Procedure Research Articles

A Deep Learning Approach for the Fast Generation of Synthetic Computed Tomography from Low-Dose Cone Beam Computed Tomography Images on a Linear Accelerator Equipped with Artificial Intelligence

Artificial Intelligence (AI) is revolutionising many aspects of radiotherapy (RT), opening scenarios that were unimaginable just a few years ago. The aim of this study is to propose a Deep Leaning (DL) approach able to quickly generate synthetic Computed Tomography (CT) images from low-dose Cone Beam CT (CBCT) acquired on a modern linear accelerator integrating AI. Methods: A total of 53 patients treated in the pelvic region were enrolled and split into training (30), validation (9), and testing (14). A Generative Adversarial Network (GAN) was trained for 200 epochs. The image accuracy was evaluated by calculating the mean and mean absolute error (ME and ME) between sCT and CT. RT treatment plans were calculated on CT and sCT images, and dose accuracy was evaluated considering Dose Volume Histogram (DVH) and gamma analysis. Results: A total of 4507 images were selected for training. The MAE and ME values in the test set were 36 ± 6 HU and 7 ± 6 HU, respectively. Mean gamma passing rates for 1%/1 mm, 2%/2 mm, and 3%/3 mm tolerance criteria were respectively 93.5 ± 3.4%, 98.0 ± 1.3%, and 99.2 ± 0.7%, with no difference between curative and palliative cases. All the DVH parameters analysed were within 1 Gy of the difference between sCT and CT. Conclusion: This study demonstrated that sCT generation using the DL approach is feasible on low-dose CBCT images. The proposed approach can represent a valid tool to speed up the online adaptive procedure and remove CT simulation from the RT workflow.

Feasibility of Conebeam CT-based online adaptive radiotherapy for neoadjuvant treatment of rectal cancer

BackgroundOnline adaptive radiotherapy has the potential to reduce toxicity for patients treated for rectal cancer because smaller planning target volumes (PTV) margins around the entire clinical target volume (CTV) are required. The aim of this study is to describe the first clinical experience of a Conebeam CT (CBCT)-based online adaptive workflow for rectal cancer, evaluating timing of different steps in the workflow, plan quality, target coverage and patient compliance.MethodsTwelve consecutive patients eligible for 5 × 5 Gy pre-operative radiotherapy were treated on a ring-based linear accelerator with a multidisciplinary team present at the treatment machine for each fraction. The accelerator is operated using an integrated software platform for both treatment planning and delivery. In all directions for all CTVs a PTV margin of 5 mm was used, except for the cranial/caudal borders of the total CTV where a margin of 8 mm was applied. A reference plan was generated based on a single planning CT. After aligning the patient the online adaptive procedure started with acquisition of a CBCT. The planning CT scan was registered to the CBCT using deformable registration and a synthetic CT scan was generated. With the support of artificial intelligence, structure guided deformation and the synthetic CT scan contours were adapted by the system to match the anatomy on the CBCT. If necessary, these contours were adjusted before a new plan was generated. A second and third CBCT were acquired to validate the new plan with respect to CTV coverage just before and after treatment delivery, respectively. Treatment was delivered using volumetric modulated arc treatment (VMAT). All steps in this process were defined and timed.ResultsOn average the timeslot needed at the treatment machine was 34 min. The process of acquiring a CBCT, evaluating and adjusting the contours, creating the new plan and verifying the CTV on the CBCT scan took on average 20 min. Including delivery and post treatment verification this was 26 min. Manual adjustments of the target volumes were necessary in 50% of fractions. Plan quality, target coverage and patient compliance were excellent.ConclusionsFirst clinical experience with CBCT-based online adaptive radiotherapy shows it is feasible for rectal cancer.Trial registration Medical Research Involving Human Subjects Act (WMO) does not apply to this study and was retrospectively approved by the Medical Ethics review Committee of the Academic Medical Center (W21_087 # 21.097; Amsterdam University Medical Centers, Location Academic Medical Center, Amsterdam, The Netherlands).

Development of an Online Adaptive Procedure for MRI-Guided Liver SBRT

Development of an Online Adaptive Procedure for MRI-Guided Liver SBRT

Enhanced model-order reduction approach via online adaptation for parametrized nonlinear structural problems

With regard to the parameterized projection-based reduced-order model, it is significant to consider the computational efficiency as well as its capability for the parametric variation. The proposed approach is based on the online adaptive procedure to improve the accuracy and stability of the reduced-order model. Achieving efficient computation in online adaptation, a matrix version of the discrete empirical interpolation method is employed to approximate the nonlinear finite element matrix, independently. The proposed approach is applied to analysis of a structure with geometric and material nonlinearities. As a result, the computational efficiency during the offline/online steps of the proposed approach is significantly improved, compared to other existing approaches. Moreover, within the present numerical examinations, it is found that the proposed approach is capable of accurately addressing broad parametric variations by using only ten percent of the number of data used in the conventional ROM from the preliminary computation.

A direct adaptive neural control for maximum power point tracking of photovoltaic system

This paper represents a novel direct adaptive neural control (DANC) method for maximum power point tracking (MPPT) of photovoltaic (PV) systems. A DC/DC buck converter to regulate the output power of the photovoltaic system is considered. The direct adaptive neural control scheme operates on MPP and improves the performance of solar energy conversion efficiency. The online adaptation procedure is based on learning law of the δ rule and only the system output error is required. The prime contributions of this study are a simple and effective solution for MPPT, the fast learning and the straightforward digital implementation. The performance of direct adaptive neural controller on photovoltaic sources with different characteristics is assessed. The simulation results confirm the feasibility and effectiveness of the DANC. The proposed MPPT control system is compared to the conventional perturbation and observation (P&O) method.

Introducing an on-line adaptive procedure for prostate image guided intensity modulate proton therapy

With on-line image guidance (IG), prostate shifts relative to the bony anatomy can be corrected by realigning the patient with respect to the treatment fields. In image guided intensity modulated proton therapy (IG-IMPT), because the proton range is more sensitive to the material it travels through, the realignment may introduce large dose variations. This effect is studied in this work and an on-line adaptive procedure is proposed to restore the planned dose to the target. A 2D anthropomorphic phantom was constructed from a real prostate patient's CT image. Two-field laterally opposing spot 3D-modulation and 24-field full arc distal edge tracking (DET) plans were generated with a prescription of 70 Gy to the planning target volume. For the simulated delivery, we considered two types of procedures: the non-adaptive procedure and the on-line adaptive procedure. In the non-adaptive procedure, only patient realignment to match the prostate location in the planning CT was performed. In the on-line adaptive procedure, on top of the patient realignment, the kinetic energy for each individual proton pencil beam was re-determined from the on-line CT image acquired after the realignment and subsequently used for delivery. Dose distributions were re-calculated for individual fractions for different plans and different delivery procedures. The results show, without adaptive, that both the 3D-modulation and the DET plans experienced delivered dose degradation by having large cold or hot spots in the prostate. The DET plan had worse dose degradation than the 3D-modulation plan. The adaptive procedure effectively restored the planned dose distribution in the DET plan, with delivered prostate D98%, D50% and D2% values less than 1% from the prescription. In the 3D-modulation plan, in certain cases the adaptive procedure was not effective to reduce the delivered dose degradation and yield similar results as the non-adaptive procedure. In conclusion, based on this 2D phantom study, by updating the proton pencil beam energy from the on-line image after realignment, this on-line adaptive procedure is necessary and effective for the DET-based IG-IMPT. Without dose re-calculation and re-optimization, it could be easily incorporated into the clinical workflow.

A real-time stage Muskingum forecasting model for a site without rating curve

An adaptive model for on-line stage forecasting is proposed for river reaches where significant lateral inflow contributions occur. The model is based on the Muskingum method and requires the estimation of four parameters if the downstream rating curve is unknown; otherwise only two parameters have to be determined. As the choice of the forecast lead time is linked to wave travel time along the reach, to increase the lead time, a schematization of two connected river reaches is also investigated. The variability of lateral inflow is accounted for through an on-line adaptive procedure. Calibration and validation of the model were carried out by applying it to different flood events observed in two equipped river reaches of the upper-middle Tiber basin in central Italy, characterized by a significant contributing drainage area. Even if the rating curve is unknown at the downstream section, the forecast stage hydrographs were found in good agreement with those observed. Errors in peak stage and time to peak along with the persistence coefficient values show that the model has potential as a practical tool for on-line flood risk management.