3Din vivodose verification in prostate proton therapy with deep learning-based proton-acoustic imaging

3D protoacoustic radiography: A proof of principle study

We propose protoacoustic radiography (PAR), an imaging modality combining proton excitation and acoustic detection for three-dimensional (3D) imaging from a single proton projection. PAR avoids the effect of multiple Coulomb scattering in imaging by detecting ultrasound. Proton-induced acoustic waves propagate spherically, enabling 3D imaging from a single projection. Additionally, the distinctive feature of proton beams-concentrating energy deposition primarily at the Bragg peak-allows for precise depth-selectivity through proton energy tuning. We performed PAR using clinical proton machines, and our results demonstrate the capability of PAR to reconstruct targets at various depths (between ∼20 and 23 cm) with an axial resolution of 1.3 mm by fully leveraging the Bragg peak and by tuning the kinetic energy of the proton beam. PAR offers opportunities for precise structural determination with protons both in biomedicine and nondestructive testing.

X-ray-induced acoustic computed tomography: 3D X-ray absorption imaging from a single view

Computed tomography (CT) scanners are essential for modern imaging but require around 600 projections from various angles. We present x-ray-induced acoustic computed tomography (XACT), a method that uses radiation-induced acoustic waves for three-dimensional (3D) x-ray imaging. These spherical acoustic waves travel through tissue at 1.5 × 103 meters per second, much slower than x-rays, allowing ultrasound detectors to capture them and generate 3D images without mechanical scanning. We validate this theory by performing 3D numerical reconstructions of a human breast from a single x-ray projection and experimentally determining 3D structures of objects at different depths. Achieving resolutions of 0.4 millimeters in the XZ plane and 3.5 millimeters in the XY plane at a depth of 16 millimeters, XACT demonstrates the ability to produce 3D images from one x-ray projection, reducing radiation exposure and enabling gantry-free imaging. XACT shows great promise for biomedical and nondestructive testing applications, potentially replacing conventional CT.

The emerging role of Artificial Intelligence in proton therapy: A review

Artificial intelligence (AI) has made a tremendous impact in the space of healthcare, and proton therapy is not an exception. Proton therapy has witnessed growing popularity in oncology over recent decades, and researchers are increasingly looking to develop AI and machine learning tools to aid in various steps of the treatment planning and delivery processes. This review delves into the emergent role of AI in proton therapy, evaluating its development, advantages, intended clinical contexts, and areas of application. Through the analysis of 76 studies, we aim to underscore the importance of AI applications in advancing proton therapy and to highlight their prospective influence on clinical practices.

Accurate patient alignment without unnecessary imaging using patient-specific 3D CT images synthesized from 2D kV images

BACKGROUND

In radiotherapy, 2D orthogonally projected kV images are used for patient alignment when 3D-on-board imaging (OBI) is unavailable. However, tumor visibility is constrained due to the projection of patient's anatomy onto a 2D plane, potentially leading to substantial setup errors. In treatment room with 3D-OBI such as cone beam CT (CBCT), the field of view (FOV) of CBCT is limited with unnecessarily high imaging dose. A solution to this dilemma is to reconstruct 3D CT from kV images obtained at the treatment position.

METHODS

We propose a dual-models framework built with hierarchical ViT blocks. Unlike a proof-of-concept approach, our framework considers kV images acquired by 2D imaging devices in the treatment room as the solo input and can synthesize accurate, full-size 3D CT within milliseconds.

RESULTS

We demonstrate the feasibility of the proposed approach on 10 patients with head and neck (H&N) cancer using image quality (MAE: < 45HU), dosimetric accuracy (Gamma passing rate ((2%/2 mm/10%): > 97%) and patient position uncertainty (shift error: < 0.4 mm).

CONCLUSIONS

The proposed framework can generate accurate 3D CT faithfully mirroring patient position effectively, thus substantially improving patient setup accuracy, keeping imaging dose minimal, and maintaining treatment veracity.

Proton spot dose estimation based on positron activity distributions with neural network

BACKGROUND

Positron emission tomography (PET) has been investigated for its ability to reconstruct proton-induced positron activity distributions in proton therapy. This technique holds potential for range verification in clinical practice. Recently, deep learning-based dose estimation from positron activity distributions shows promise for in vivo proton dose monitoring and guided proton therapy.

PURPOSE

This study evaluates the effectiveness of three classical neural network models, recurrent neural network (RNN), U-Net, and Transformer, for proton dose estimating. It also investigates the characteristics of these models, providing valuable insights for selecting the appropriate model in clinical practice.

METHODS

Proton dose calculations for spot beams were simulated using Geant4. Computed tomography (CT) images from four head cases were utilized, with three for training neural networks and the remaining one for testing. The neural networks were trained with one-dimensional (1D) positron activity distributions as inputs and generated 1D dose distributions as outputs. The impact of the number of training samples on the networks was examined, and their dose prediction performance in both homogeneous brain and heterogeneous nasopharynx sites was evaluated. Additionally, the effect of positron activity distribution uncertainty on dose prediction performance was investigated. To quantitatively evaluate the models, mean relative error (MRE) and absolute range error (ARE) were used as evaluation metrics.

RESULTS

The U-Net exhibited a notable advantage in range verification with a smaller number of training samples, achieving approximately 75% of AREs below 0.5 mm using only 500 training samples. The networks performed better in the homogeneous brain site compared to the heterogeneous nasopharyngeal site. In the homogeneous brain site, all networks exhibited small AREs, with approximately 90% of the AREs below 0.5 mm. The Transformer exhibited the best overall dose distribution prediction, with approximately 92% of MREs below 3%. In the heterogeneous nasopharyngeal site, all networks demonstrated acceptable AREs, with approximately 88% of AREs below 3 mm. The Transformer maintained the best overall dose distribution prediction, with approximately 85% of MREs below 5%. The performance of all three networks in dose prediction declined as the uncertainty of positron activity distribution increased, and the Transformer consistently outperformed the other networks in all cases.

CONCLUSIONS

Both the U-Net and the Transformer have certain advantages in the proton dose estimation task. The U-Net proves well suited for range verification with a small training sample size, while the Transformer outperforms others at dose-guided proton therapy.

Patient-specific deep learning for 3D protoacoustic image reconstruction and dose verification in proton therapy

BACKGROUND

Protoacoustic (PA) imaging has the potential to provide real-time 3D dose verification of proton therapy. However, PA images are susceptible to severe distortion due to limited angle acquisition. Our previous studies showed the potential of using deep learning to enhance PA images. As the model was trained using a limited number of patients' data, its efficacy was limited when applied to individual patients.

PURPOSE

In this study, we developed a patient-specific deep learning method for protoacoustic imaging to improve the reconstruction quality of protoacoustic imaging and the accuracy of dose verification for individual patients.

METHODS

Our method consists of two stages: in the first stage, a group model is trained from a diverse training set containing all patients, where a novel deep learning network is employed to directly reconstruct the initial pressure maps from the radiofrequency (RF) signals; in the second stage, we apply transfer learning on the pre-trained group model using patient-specific dataset derived from a novel data augmentation method to tune it into a patient-specific model. Raw PA signals were simulated based on computed tomography (CT) images and the pressure map derived from the planned dose. The reconstructed PA images were evaluated against the ground truth by using the root mean squared errors (RMSE), structural similarity index measure (SSIM) and gamma index on 10 specific prostate cancer patients. The significance level was evaluated by t-test with the p-value threshold of 0.05 compared with the results from the group model.

RESULTS

The patient-specific model achieved an average RMSE of 0.014 (p < 0.05 ${{{p}}}<{0.05}$ ), and an average SSIM of 0.981 (p < 0.05 ${{{p}}}<{0.05}$ ), out-performing the group model. Qualitative results also demonstrated that our patient-specific approach acquired better imaging quality with more details reconstructed when comparing with the group model. Dose verification achieved an average RMSE of 0.011 (p < 0.05 ${{{p}}}<{0.05}$ ), and an average SSIM of 0.995 (p < 0.05 ${{{p}}}<{0.05}$ ). Gamma index evaluation demonstrated a high agreement (97.4% [p < 0.05 ${{{p}}}<{0.05}$ ] and 97.9% [p < 0.05 ${{{p}}}<{0.05}$ ] for 1%/3  and 1%/5 mm) between the predicted and the ground truth dose maps. Our approach approximately took 6 s to reconstruct PA images for each patient, demonstrating its feasibility for online 3D dose verification for prostate proton therapy.

CONCLUSIONS

Our method demonstrated the feasibility of achieving 3D high-precision PA-based dose verification using patient-specific deep-learning approaches, which can potentially be used to guide the treatment to mitigate the impact of range uncertainty and improve the precision. Further studies are needed to validate the clinical impact of the technique.

4Din vivodosimetry for a FLASH electron beam using radiation-induced acoustic imaging

Objective. The primary goal of this research is to demonstrate the feasibility of radiation-induced acoustic imaging (RAI) as a volumetric dosimetry tool for ultra-high dose rate FLASH electron radiotherapy (FLASH-RT) in real time. This technology aims to improve patient outcomes by accurate measurements ofin vivodose delivery to target tumor volumes.Approach. The study utilized the FLASH-capable eRT6 LINAC to deliver electron beams under various doses (1.2 Gy pulse-1to 4.95 Gy pulse-1) and instantaneous dose rates (1.55 × 105Gy s-1to 2.75 × 106Gy s-1), for imaging the beam in water and in a rabbit cadaver with RAI. A custom 256-element matrix ultrasound array was employed for real-time, volumetric (4D) imaging of individual pulses. This allowed for the exploration of dose linearity by varying the dose per pulse and analyzing the results through signal processing and image reconstruction in RAI.Main Results. By varying the dose per pulse through changes in source-to-surface distance, a direct correlation was established between the peak-to-peak amplitudes of pressure waves captured by the RAI system and the radiochromic film dose measurements. This correlation demonstrated dose rate linearity, including in the FLASH regime, without any saturation even at an instantaneous dose rate up to 2.75 × 106Gy s-1. Further, the use of the 2D matrix array enabled 4D tracking of FLASH electron beam dose distributions on animal tissue for the first time.Significance. This research successfully shows that 4Din vivodosimetry is feasible during FLASH-RT using a RAI system. It allows for precise spatial (∼mm) and temporal (25 frames s-1) monitoring of individual FLASH beamlets during delivery. This advancement is crucial for the clinical translation of FLASH-RT as enhancing the accuracy of dose delivery to the target volume the safety and efficacy of radiotherapeutic procedures will be improved.

Hybrid-supervised deep learning for domain transfer 3D protoacoustic image reconstruction

Objective. Protoacoustic imaging showed great promise in providing real-time 3D dose verification of proton therapy. However, the limited acquisition angle in protoacoustic imaging induces severe artifacts, which impairs its accuracy for dose verification. In this study, we developed a hybrid-supervised deep learning method for protoacoustic imaging to address the limited view issue.Approach. We proposed a Recon-Enhance two-stage deep learning method. In the Recon-stage, a transformer-based network was developed to reconstruct initial pressure maps from raw acoustic signals. The network is trained in a hybrid-supervised approach, where it is first trained using supervision by the iteratively reconstructed pressure map and then fine-tuned using transfer learning and self-supervision based on the data fidelity constraint. In the enhance-stage, a 3D U-net is applied to further enhance the image quality with supervision from the ground truth pressure map. The final protoacoustic images are then converted to dose for proton verification.Main results. The results evaluated on a dataset of 126 prostate cancer patients achieved an average root mean squared errors (RMSE) of 0.0292, and an average structural similarity index measure (SSIM) of 0.9618, out-performing related start-of-the-art methods. Qualitative results also demonstrated that our approach addressed the limit-view issue with more details reconstructed. Dose verification achieved an average RMSE of 0.018, and an average SSIM of 0.9891. Gamma index evaluation demonstrated a high agreement (94.7% and 95.7% for 1%/3 mm and 1%/5 mm) between the predicted and the ground truth dose maps. Notably, the processing time was reduced to 6 s, demonstrating its feasibility for online 3D dose verification for prostate proton therapy.Significance. Our study achieved start-of-the-art performance in the challenging task of direct reconstruction from radiofrequency signals, demonstrating the great promise of PA imaging as a highly efficient and accurate tool forinvivo3D proton dose verification to minimize the range uncertainties of proton therapy to improve its precision and outcomes.

Discrete Wavelet Transformation for the Sensitive Detection of Ultrashort Radiation Pulse with Radiation-induced Acoustics

Radiation-induced acoustics (RIA) shows promise in advancing radiological imaging and radiotherapy dosimetry methods. However, RIA signals often require extensive averaging to achieve reasonable signal-to-noise ratios, which increases patient radiation exposure and limits real-time applications. Therefore, this paper proposes a discrete wavelet transform (DWT) based filtering approach to denoise the RIA signals and avoid extensive averaging. The algorithm was benchmarked against low-pass filters and tested on various types of RIA sources, including low-energy X-rays, high-energy X-rays, and protons. The proposed method significantly reduced the required averages (1000 times less averaging for low-energy X-ray RIA, 32 times less averaging for high-energy X-ray RIA, and 4 times less averaging for proton RIA) and demonstrated robustness in filtering signals from different sources of radiation. The coif5 wavelet in conjunction with the sqtwolog threshold selection algorithm yielded the best results. The proposed DWT filtering method enables high-quality, automated, and robust filtering of RIA signals, with a performance similar to low-pass filtering, aiding in the clinical translation of radiation-based acoustic imaging for radiology and radiation oncology.

X-ray-induced acoustic computed tomography and its applications in biomedicine

Significance

X-ray-induced acoustic computed tomography (XACT) offers a promising approach to biomedical imaging, leveraging X-ray absorption contrast. It overcomes the shortages of traditional X-ray, allowing for more advanced medical imaging.

Aim

The review focuses on the significance and draws onto the potential applications of XACT to demonstrate it as an innovative imaging technique.

Approach

This review navigates the expanding landscape of XACT imaging within the biomedical sphere. Integral topics addressed encompass the refinement of imaging systems and the advancement in image reconstruction algorithms. The review particularly emphasizes XACT's significant biomedical applications.

Results

Key uses, such as breast imaging, bone density maps for osteoporosis, and X-ray molecular imaging, are highlighted to demonstrate the capability of XACT. A unique niche for XACT imaging is its application in in vivo dosimetry during radiotherapy, which has been validated on patients.

Conclusions

Because of its unique property, XACT has great potential in biomedicine and non-destructive testing. We conclude by casting light on potential future avenues in this promising domain.

Radiation-induced acoustic signal denoising using a supervised deep learning framework for imaging and therapy monitoring

Radiation-induced acoustic (RA) imaging is a promising technique for visualizing the invisible radiation energy deposition in tissues, enabling new imaging modalities and real-time therapy monitoring. However, RA imaging signal often suffers from poor signal-to-noise ratios (SNRs), thus requiring measuring hundreds or even thousands of frames for averaging to achieve satisfactory quality. This repetitive measurement increases ionizing radiation dose and degrades the temporal resolution of RA imaging, limiting its clinical utility. In this study, we developed a general deep inception convolutional neural network (GDI-CNN) to denoise RA signals to substantially reduce the number of frames needed for averaging. The network employs convolutions with multiple dilations in each inception block, allowing it to encode and decode signal features with varying temporal characteristics. This design generalizes GDI-CNN to denoise acoustic signals resulting from different radiation sources. The performance of the proposed method was evaluated using experimental data of x-ray-induced acoustic, protoacoustic, and electroacoustic signals both qualitatively and quantitatively. Results demonstrated the effectiveness of GDI-CNN: it achieved x-ray-induced acoustic image quality comparable to 750-frame-averaged results using only 10-frame-averaged measurements, reducing the imaging dose of x-ray-acoustic computed tomography (XACT) by 98.7%; it realized proton range accuracy parallel to 1500-frame-averaged results using only 20-frame-averaged measurements, improving the range verification frequency in proton therapy from 0.5 to 37.5 Hz; it reached electroacoustic image quality comparable to 750-frame-averaged results using only a single frame signal, increasing the electric field monitoring frequency from 1 fps to 1k fps. Compared to lowpass filter-based denoising, the proposed method demonstrated considerably lower mean-squared-errors, higher peak-SNR, and higher structural similarities with respect to the corresponding high-frame-averaged measurements. The proposed deep learning-based denoising framework is a generalized method for few-frame-averaged acoustic signal denoising, which significantly improves the RA imaging's clinical utilities for low-dose imaging and real-time therapy monitoring.

Single pulse protoacoustic range verification using a clinical synchrocyclotron

Objective.Proton therapy as the next generation radiation-based cancer therapy offers dominant advantages over conventional radiation therapy due to the utilization of the Bragg peak; however, range uncertainty in beam delivery substantially mitigates the advantages of proton therapy. This work reports using protoacoustic measurements to determine the location of proton Bragg peak deposition within a water phantom in real time during beam delivery.Approach.In protoacoustics, proton beams have a definitive range, depositing a majority of the dose at the Bragg peak; this dose is then converted to heat. The resulting thermoelastic expansion generates a 3D acoustic wave, which can be detected by acoustic detectors to localize the Bragg peak.Main results.Protoacoustic measurements were performed with a synchrocyclotron proton machine over the exhaustive energy range from 45.5 to 227.15 MeV in clinic. It was found that the amplitude of the acoustic waves is proportional to proton dose deposition, and therefore encodes dosimetric information. With the guidance of protoacoustics, each individual proton beam (7 pC/pulse) can be directly visualized with sub-millimeter (<0.7 mm) resolution using single beam pulse for the first time.Significance.The ability to localize the Bragg peak in real-time and obtain acoustic signals proportional to dose within tumors could enable precision proton therapy and hope to progress towardsin vivomeasurements.