Magnetic resonance image guidance in external beam radiation therapy planning and delivery

Revolutionizing radiation therapy: the role of AI in clinical practice

This review provides an overview of the application of artificial intelligence (AI) in radiation therapy (RT) from a radiation oncologist's perspective. Over the years, advances in diagnostic imaging have significantly improved the efficiency and effectiveness of radiotherapy. The introduction of AI has further optimized the segmentation of tumors and organs at risk, thereby saving considerable time for radiation oncologists. AI has also been utilized in treatment planning and optimization, reducing the planning time from several days to minutes or even seconds. Knowledge-based treatment planning and deep learning techniques have been employed to produce treatment plans comparable to those generated by humans. Additionally, AI has potential applications in quality control and assurance of treatment plans, optimization of image-guided RT and monitoring of mobile tumors during treatment. Prognostic evaluation and prediction using AI have been increasingly explored, with radiomics being a prominent area of research. The future of AI in radiation oncology offers the potential to establish treatment standardization by minimizing inter-observer differences in segmentation and improving dose adequacy evaluation. RT standardization through AI may have global implications, providing world-standard treatment even in resource-limited settings. However, there are challenges in accumulating big data, including patient background information and correlating treatment plans with disease outcomes. Although challenges remain, ongoing research and the integration of AI technology hold promise for further advancements in radiation oncology.

Real-time marker-less tumor tracking with TOF PET: in silico feasibility study

Purpose. Although positron emission tomography (PET) can provide a functional image of static tumors for RT guidance, it’s conventionally very challenging for PET to track a moving tumor in real-time with a multiple frame/s sampling rate. In this study, we developed a novel method to enable PET based three-dimension (3D) real-time marker-less tumor tracking (RMTT) and demonstrated its feasibility with a simulation study. Methods. For each line-of-response (LOR) acquired, its positron-electron annihilation position is calculated based on the time difference between the two gamma interactions detected by the TOF PET detectors. The accumulation of these annihilation positions from data acquired within a single sampling frame forms a coarsely measured 3D distribution of positron-emitter radiotracer uptakes of the lung tumor and other organs and tissues (background). With clinically relevant tumor size and sufficient differential radiotracer uptake concentrations between the tumor and background, the high-uptake tumor can be differentiated from the surrounding low-uptake background in the measured distribution of radiotracer uptakes. With a volume-of-interest (VOI) that closely encloses the tumor, the count-weighted centroid of the annihilation positions within the VOI can be calculated as the tumor position. All these data processes can be conducted online. The feasibility of the new method was investigated with a simulated cardiac-torso digital phantom and stationary dual-panel TOF PET detectors to track a 28 mm diameter lung tumor with a 4:1 tumor-to-background 18FDG activity concentration ratio. Results. The initial study shows TOF PET based RMTT can achieve <2.0 mm tumor tracking accuracy with 5 frame s−1 sampling rate under the simulated conditions. In comparison, using reconstructed PET images to track a similar size tumor would require >30 s acquisition time to achieve the same tracking accuracy. Conclusion. With the demonstrated feasibility, the new method may enable TOF PET based RMTT for practical RT applications.

Technical Note: Toward implementation of MR-guided radiation therapy for Laryngeal cancer with healthy volunteer imaging and a custom MR-CT larynx phantom

PURPOSE

Internal motion of the larynx can cause normal tissue toxicity and/or tumor underdosage during radiotherapy. MR-guided radiation therapy (MRgRT) provides improved soft-tissue contrast for patient setup, and real-time gating of radiation based on cine imaging of tumor motion, potentially making it an advantageous modality for laryngeal treatments. However, there are potential concerns regarding the small target size, proximity to heterogeneous tissue interfaces in the airway that may cause dosimetric errors in the presence of the magnetic field, and uncertainty about the ability of MR-linear accelerator (MR-Linac) systems to visualize and track laryngeal motion. To date, there have been no reports of the use of MRgRT for laryngeal treatments.

METHODS

A healthy volunteer was imaged on a ViewRay MRIdian MR-Linac. Organs-at-risk and a laryngeal pseudo target were contoured and used to generate a stereotactic body radiotherapy plan. A custom phantom was created using 3D-printing based on structures delineated on the volunteer images to construct an enclosure containing the target and airway anatomy, with a gap for radiochromic film, and filled with gelatin . The treatment plan was mapped onto the phantom and delivered dose assessed on radiochromic film with global normalization and a 10% dose threshold. A cine MR of the volunteer was acquired to assess the magnitude of larynx motion with speaking and swallowing, and system's ability to gate radiation.

RESULTS

A clinically acceptable laryngeal treatment plan and larynx phantom that was MR and CT-visible were successfully created. The delivered dose had good agreement with the treatment plan with a gamma passing rate of 96.5% (3%/2mm). The MR-Linac was able to visualize, track, and gate larynx motion.

CONCLUSIONS

The MRgRT workflow for laryngeal treatments was assessed and performed in preparation for clinical implementation on the MR-Linac, demonstrating that it is feasible to treat laryngeal cancer patients on the MR-Linac. This article is protected by copyright. All rights reserved.

A systematic review and meta-analysis of liver tumor position variability during SBRT using various motion management and IGRT strategies

PURPOSE

To suggest PTV margins for liver SBRT with different motion management strategies based on a systematic review and meta-analysis.

METHODS

In accordance with Preferred-Reporting-Items-for-Systematic-Reviews-and-Meta-Analyses (PRISMA), a systematic review in PubMed, Embase and Medline databases was performed for liver tumor position variability. From an initial 533 studies published before October 2020, 36 studies were categorized as 18 free-breathing (FB; n_patients = 401), 9 abdominal compression (AC; n_patients = 145) and 9 breath-hold (BH; n_patients = 126). A meta-analysis was performed on inter- and intra-fraction position variability to report weighted-mean with 95% confidence interval (CI₉₅) in superior-inferior (SI), left-right (LR) and anterior-posterior (AP) directions. Furthermore, weighted-mean ITV margins were computed for FB (n_studies = 15, n_patients = 373) and AC (n_studies = 6, n_patients = 97) and PTV margins were computed for FB (n_studies = 6, n_patients = 95), AC (n_studies = 7, n_patients = 106) and BH (n_studies = 8, n_patients = 133).

RESULTS

The FB weighted-mean intra-fraction variability, ITV margins and weighted-standard-deviation in mm were SI-9.7, CI₉₅ = 9.3-10.1, 13.5 ± 4.9; LR-5.4, CI₉₅ = 5.3-5.6, 7.3 ± 7.9; and AP-4.2, CI₉₅ = 4.0-4.4, 6.3 ± 7.6. The inter-fraction-based results were SI-4.7, CI₉₅ = 4.3-5.1, 5.7 ± 1.7; LR-1.4, CI₉₅ = 1.1-1.6, 3.6 ± 2.7; and AP-2.8, CI₉₅ = 2.5-3.1, 4.8 ± 2.1. For AC intra-fraction results in mm were SI-1.8, CI₉₅ = 1.6-2.0, 2.6 ± 1.2; LR-0.7, CI₉₅ = 0.6-0.8, 1.7 ± 1.5; and AP-0.9, CI₉₅ = 0.8-1.0, 1.9 ± 1.7. The inter-fraction results were SI-2.6, CI₉₅ = 2.3-3.0, 5.2 ± 2.9; LR-1.9, CI₉₅ = 1.7-2.1, 4.0 ± 2.2; and AP-2.9, CI₉₅ = 2.5-3.2, 5.8 ± 2.7. For BH the inter-fraction variability, and the weighted-mean PTV margins and weighted-standard-deviation in mm were SI-2.4, CI₉₅ = 2.1-2.7, 5.6 ± 2.9; LR-1.8, CI₉₅ = 1.3-2.2, 5.5 ± 1.7; and AP-1.4; CI₉₅ = 1.2-1.7, 6.1 ± 2.1.

CONCLUSION

Our meta-analysis suggests a symmetric weighted-mean PTV margin of 6 mm might be appropriate for BH. For AC and FB, asymmetric PTV margins (weighted-mean margin of 4 mm (AP), 6 mm (SI/LR)) might be appropriate. For FB, if larger (>ITV margin) intra-fraction variability observed, the additional intra- and inter-fraction variability should be accounted in the PTV margin.

The rationale for MR-only delineation and planning: retrospective CT–MR registration and target volume analysis for prostate radiotherapy

Aim:

Magnetic resonance imaging (MRI) is indispensable for treatment planning in prostate radiotherapy (PR). Registration of MRI when compared to planning CT (pCT) is prone to uncertainty and this is rarely reported. In this study, we have compared three different types of registration methods to justify the direct use of MRI in PR.

Methods and materials:

Thirty patients treated for PR were retrospectively selected for this study and all underwent both CT and MRI. The MR scans were registered to the pCT using markers, focused and unfocussed methods and their registration are REGM, REGF, and REGNF, respectively. Registration comparison is done using the translational differences of three axes from the centre-of-mass values of gross tumour volume (GTV) generated using MRI.

Results:

The average difference in all three axes (x, y, z) is (1, 2·5, 2·3 mm) and (1, 3, 2·3 mm) for REGF-REFNF and REGF-REGM, respectively. MR-based GTV Volume is less in comparison to CT-based GTV and it is significantly different (p < 0·001).

Findings:

Image registration uncertainty is unavoidable for a regular CT–MR workflow. Additional planning target volume margin ranging from 2 to 3mm could be avoided if MR-only workflow is employed. This reduction in the margin is beneficial for small tumours treated with hypofractionation.

Use of magnetic resonance imaging-guided radiotherapy for breast cancer: a scoping review protocol

BACKGROUND

In recent years, we have seen the incorporation of magnetic resonance imaging (MRI) simulators into radiotherapy centres and the emergence of the new technology of MR linacs. However, the significant health care resources associated with this advanced technology impact immediate widespread use and availability. There are currently limited studies to demonstrate the clinical effectiveness and inform decision-making on the use of MRI in radiotherapy. The objective of this scoping review is to identify and map the existing evidence surrounding the clinical implementation of MRI-guided radiotherapy in patients with breast cancer. It also aims to identify challenges and knowledge gaps in the literature.

METHODS

We will perform a comprehensive search in MEDLINE and EMBASE databases from January 2010 onwards. Grey literature sources will include the WHO International Clinical Trials Registry Platform. We will include systematic reviews, randomised and non-randomised controlled studies published in English. Literature should examine the use of magnetic resonance imaging-guided radiotherapy in adults with breast cancer, regardless of cancer stage or severity. Two reviewers will independently screen all titles, abstracts and full-text reports. Data will be extracted and summarised using qualitative (e.g. content and thematic analysis) methods and presented in tables.

DISCUSSION

The results from this review will consolidate the evidence surrounding MRI-guided radiotherapy for breast cancer, contributing to the development and optimisation of patient selection, simulation, planning, treatment delivery, quality assurance and research, to help improve patient outcomes, cancer care and treatment for women with breast cancer.

SYSTEMATIC REVIEW REGISTRATION

The protocol is available on Open Science Framework at DOI https://doi.org/10.17605/OSF.IO/8TEV6.

Time Analysis of Online Adaptive Magnetic Resonance-Guided Radiation Therapy Workflow According to Anatomical Sites

PURPOSE

To document time analysis of detailed workflow steps for the online adaptive magnetic resonance-guided radiation therapy treatments (MRgRT) with the ViewRay MRIdian system and to identify the barriers to and solutions for shorter treatment times.

METHODS AND MATERIALS

A total of 154 patients were treated with the ViewRay MRIdian system between September 2018 and October 2019. The time process of MRgRT workflow steps of 962 fractions for 166 treatment sites was analyzed in terms of patient and online adaptive treatment (ART) characteristics.

RESULTS

Overall, 774 of 962 fractions were treated with online ART, and 83.2% of adaptive fractions were completed in less than 60 minutes. Sixty-three percent, 50.3%, and 4.2% of fractions were completed in less than 50 minutes, 45 minutes, and 30 minutes, respectively. Eight-point-three percent and 3% of fractions were completed in more than 70 minutes and 80 minutes, respectively. The median time (t_med) for ART workflow steps were as follows: (1) setup t_med: 5.0 minutes, (2) low-resolution scanning t_med: 1 minute, (3) high-resolution scanning t_med: 3 minutes, (4) online contouring t_med: 9 minutes, (5) reoptimization with online quality assurance t_med: 5 minutes, (6) real targeting t_med: 3 minutes, (7) beam delivery with gating t_med: 17 minutes, and (8) net total treatment time t_med: 45 minutes. The shortest and longest t_mean rates of net total treatment time were 41.59 minutes and 64.43 minutes for upper-lung-lobe-located thoracic tumors and ultracentrally located thoracic tumors, respectively.

CONCLUSIONS

To our knowledge, this is the first broad treatment-time analysis for online ART in the literature. Although treatment times are long due to human- and technology-related limitations, benefits offered by MRgRT might be clinically important. In the future, implementation of artificial intelligence segmentation, an increase in dose rate, and faster multileaf collimator and gantry speeds may lead to achieving shorter MRgRT treatments.

Image-guided radiotherapy for prostate cancer

Intensity-modulated radiotherapy (IMRT) has become the standard radiotherapy technology utilized for the treatment of prostate cancer, as it permits the delivery of highly conformal radiation dose distributions. Image-guided radiotherapy (IGRT) is an essential companion to IMRT that allows the treatment team to account for daily changes in target anatomy and positioning. In the present review, we will discuss the different sources of geometric uncertainty and review the rationale behind using IGRT in the treatment of prostate cancer. We will then describe commonly employed IGRT techniques and review their benefits and drawbacks. Additionally, we will review the evidence suggesting a potential clinical benefit to utilizing IGRT.

Survey on deep learning for radiotherapy

More than 50% of cancer patients are treated with radiotherapy, either exclusively or in combination with other methods. The planning and delivery of radiotherapy treatment is a complex process, but can now be greatly facilitated by artificial intelligence technology. Deep learning is the fastest-growing field in artificial intelligence and has been successfully used in recent years in many domains, including medicine. In this article, we first explain the concept of deep learning, addressing it in the broader context of machine learning. The most common network architectures are presented, with a more specific focus on convolutional neural networks. We then present a review of the published works on deep learning methods that can be applied to radiotherapy, which are classified into seven categories related to the patient workflow, and can provide some insights of potential future applications. We have attempted to make this paper accessible to both radiotherapy and deep learning communities, and hope that it will inspire new collaborations between these two communities to develop dedicated radiotherapy applications.

The role of imaging in the clinical practice of radiation oncology for pancreatic cancer

Advances in technology have enabled the delivery of high doses of radiation therapy for pancreatic ductal adenocarcinoma (PDAC) with low rates of toxicity. Although the role of radiation for pancreatic cancer continues to evolve, encouraging results with newer techniques indicate that radiation may benefit selected patient populations. Imaging has been central to the modern successes of radiation therapy for PDAC. Here, we review the role of diagnostic imaging, imaging-based planning, and image guidance in radiation oncology practice for PDAC.