Image-guided study of inter-fraction and intra-fraction set-up variability and margins in reverse semi-decubitus breast radiotherapy

Artificial intelligence applied to image-guided radiation therapy (IGRT): a systematic review by the Young Group of the Italian Association of Radiotherapy and Clinical Oncology (yAIRO)

INTRODUCTION

The advent of image-guided radiation therapy (IGRT) has recently changed the workflow of radiation treatments by ensuring highly collimated treatments. Artificial intelligence (AI) and radiomics are tools that have shown promising results for diagnosis, treatment optimization and outcome prediction. This review aims to assess the impact of AI and radiomics on modern IGRT modalities in RT.

METHODS

A PubMed/MEDLINE and Embase systematic review was conducted to investigate the impact of radiomics and AI to modern IGRT modalities. The search strategy was "Radiomics" AND "Cone Beam Computed Tomography"; "Radiomics" AND "Magnetic Resonance guided Radiotherapy"; "Radiomics" AND "on board Magnetic Resonance Radiotherapy"; "Artificial Intelligence" AND "Cone Beam Computed Tomography"; "Artificial Intelligence" AND "Magnetic Resonance guided Radiotherapy"; "Artificial Intelligence" AND "on board Magnetic Resonance Radiotherapy" and only original articles up to 01.11.2022 were considered.

RESULTS

A total of 402 studies were obtained using the previously mentioned search strategy on PubMed and Embase. The analysis was performed on a total of 84 papers obtained following the complete selection process. Radiomics application to IGRT was analyzed in 23 papers, while a total 61 papers were focused on the impact of AI on IGRT techniques.

DISCUSSION

AI and radiomics seem to significantly impact IGRT in all the phases of RT workflow, even if the evidence in the literature is based on retrospective data. Further studies are needed to confirm these tools' potential and provide a stronger correlation with clinical outcomes and gold-standard treatment strategies.

Applicability and usage of dose mapping/accumulation in radiotherapy

Dose mapping/accumulation (DMA) is a topic in radiotherapy (RT) for years, but has not yet found its widespread way into clinical RT routine. During the ESTRO Physics workshop 2021 on "commissioning and quality assurance of deformable image registration (DIR) for current and future RT applications", we built a working group on DMA from which we present the results of our discussions in this article. Our aim in this manuscript is to shed light on the current situation of DMA in RT and to highlight the issues that hinder consciously integrating it into clinical RT routine. As a first outcome of our discussions, we present a scheme where representative RT use cases are positioned, considering expected anatomical variations and the impact of dose mapping uncertainties on patient safety, which we have named the DMA landscape (DMAL). This tool is useful for future reference when DMA applications get closer to clinical day-to-day use. Secondly, we discussed current challenges, lightly touching on first-order effects (related to the impact of DIR uncertainties in dose mapping), and focusing in detail on second-order effects often dismissed in the current literature (as resampling and interpolation, quality assurance considerations, and radiobiological issues). Finally, we developed recommendations, and guidelines for vendors and users. Our main point include: Strive for context-driven DIR (by considering their impact on clinical decisions/judgements) rather than perfect DIR; be conscious of the limitations of the implemented DIR algorithm; and consider when dose mapping (with properly quantified uncertainties) is a better alternative than no mapping.

Factors impacting on patient setup analysis and error management during breast cancer radiotherapy

Radiotherapy is required to deliver an accurate dose to the tumor while protecting surrounding normal tissues. Breast cancer radiotherapy involves a number of factors that can influence patient setup and error management, including the immobilization device used, the verification system and the patient's treatment position. The aim of this review is to compile and discuss the setup errors that occur due to the above-mentioned factors. In view of this, a systematic search of the scientific literature in the Medline/PubMed databases was performed over the 1990-2021 time period, with 93 articles found to be relevant for the study. To be accessible to all, this study not only aims to identify factors impacting on patient setup analysis, but also seeks to evaluate the role of each verification device, board immobilization and position in influencing these errors.

Evaluating 3D-printed Bolus Compared to Conventional Bolus Types Used in External Beam Radiation Therapy

BACKGROUND

When treating superficial tumors with external beam radiation therapy, bolus is often used. Bolus increases surface dose, reduces dose to underlying tissue, and improves dose homogeneity.

INTRODUCTION

The conventional bolus types used clinically in practice have some disadvantages. The use of Three-Dimensional (3D) printing has the potential to create more effective boluses. CT data is used for dosimetric calculations for these treatments and often to manufacture the customized 3D-printed bolus.

PURPOSE

The aim of this review is to evaluate the published studies that have compared 3D-printed bolus against conventional bolus types.

METHODS AND RESULTS

A systematic search of several databases and a further appraisal for relevance and eligibility resulted in the 14 articles used in this review. The 14 articles were analyzed based on their comparison of 3D-printed bolus and at least one conventional bolus type.

CONCLUSION

The findings of this review indicated that 3D-printed bolus has a number of advantages. Compared to conventional bolus types, 3D-printed bolus was found to have equivalent or improved dosimetric measures, positional accuracy, fit, and uniformity. 3D-printed bolus was also found to benefit workflow efficiency through both time and cost effectiveness. However, factors such as patient comfort and staff perspectives need to be further explored to support the use of 3Dprinted bolus in routine practice.

Does the protocol-required uniform margin around the CTV adequately account for setup inaccuracies in whole breast irradiation?

Purpose

To use cone-beam computed tomography (CBCT) imaging to determine the impacts of patient characteristics on the magnitude of geometric setup errors and obtain patient-specific planning target volume (PTV) margins from the correlated patient characteristics in whole breast irradiation (WBI).

Methods

Between January 2019 and December 2019, a total of 97 patients who underwent breast-conserving surgery, followed by intensity-modulated radiation therapy in WBI, were scanned with pre-treatment CBCT for the first three treatment fractions and weekly for the subsequent fractions. Setup errors in the left–right (LR), superior–inferior (SI) and anterior–posterior (AP) directions were recorded and analyzed with patient characteristics—including age, tumor location, body mass index (BMI), chest circumference (CC) and breast volume (BV)—to examine the predictors for setup errors and obtain specific PTV margins.

Results

A total of 679 CBCT images from 97 patients were acquired for analysis. The mean setup errors for the whole group were 2.32 ± 1.21 mm, 3.71 ± 2.21 mm and 2.75 ± 1.56 mm in the LR, SI and AP directions, respectively. Patients’ BMI, CC and BV were moderately associated with setup errors, especially in the SI directions (R = 0.40, 0.43 and 0.22, respectively). Setup errors in the SI directions for patients with BMI > 23.8 kg/m², CC > 89 cm and BV > 657 cm³ were 4.56 ± 2.59 mm, 4.77 ± 2.42 mm and 4.30 ± 2.43 mm, respectively, which were significantly greater than those of patients with BMI ≤ 23.8 kg/m², CC ≤ 89 cm and BV ≤ 657 cm³ (P < 0.05). Correspondingly, the calculated PTV margins in patients with BMI > 23.8 kg/m², CC > 89 cm and BV > 657 cm³ were 4.25/7.95/4.93 mm, 4.37/7.66/5.24 mm and 4.22/7.54/5.29 mm in the LR/SI/AP directions, respectively, compared with 3.64/4.64/5.09 mm, 3.31/4.50/4.82 mm and 3.29/5.74/4.73 mm for BMI ≤ 23.8 kg/m², CC ≤ 89 cm and BV ≤ 657 cm³, respectively.

Conclusions

The magnitude of geometric setup errors was moderately correlated with BMI, CC and BV. It was recommended to set patient-specific PTV margins according to patient characteristics in the absence of daily image-guided treatment setup.

Cone-beam CT image quality improvement using Cycle-Deblur consistent adversarial networks (Cycle-Deblur GAN) for chest CT imaging in breast cancer patients

Cone-beam computed tomography (CBCT) integrated with a linear accelerator is widely used to increase the accuracy of radiotherapy and plays an important role in image-guided radiotherapy (IGRT). For comparison with fan-beam computed tomography (FBCT), the image quality of CBCT is indistinct due to X-ray scattering, noise, and artefacts. We proposed a deep learning model, “Cycle-Deblur GAN”, combined with CycleGAN and Deblur-GAN models to improve the image quality of chest CBCT images. The 8706 CBCT and FBCT image pairs were used for training, and 1150 image pairs were used for testing in deep learning. The generated CBCT images from the Cycle-Deblur GAN model demonstrated closer CT values to FBCT in the lung, breast, mediastinum, and sternum compared to the CycleGAN and RED-CNN models. The quantitative evaluations of MAE, PSNR, and SSIM for CBCT generated from the Cycle-Deblur GAN model demonstrated better results than the CycleGAN and RED-CNN models. The Cycle-Deblur GAN model improved image quality and CT-value accuracy and preserved structural details for chest CBCT images.

Design of a new breast vacuum bag to reduce the global and local setup errors and to reduce PTV margin in post-mastectomy radiation therapy

To design a new breast vacuum bag to reduce global and local setup errors in post-mastectomy radiation therapy (PMRT). A total of 24 PMRT patients were immobilized with an old vacuum bag and 26 PMRT patients were immobilized with a new vacuum bag. The registration results were analysed using four regions of interest (ROI): the global ROI [including the whole region of the planning target volume (PTV), G_ROI], the supraclavicular area (S_ROI), the ipsilateral chest wall region (C_ROI) and the ipsilateral arm region (A_ROI). The global and local setup errors of the two groups were compared. The global setup errors of the new vacuum group were significantly smaller than those in the old vacuum group with the exception of yaw axes (P < 0.05). The systematic error (Σ) and random error (σ) ranged from 1.21 to 2.13 mm. In the new vacuum group, the local setup errors in the medial-lateral (ML) direction and roll axes for C_ROI (the Σ and σ ranged from 0.65 to 1.35 mm), and the local setup errors in ML and superior-inferior (SI) directions for S_ROI were significantly smaller than those in the old vacuum group. The total required PTV margins for the chest wall in ML, SI, and anterior-posterior (AP) were 4.40, 3.12 and 3.77 mm respectively. The new vacuum bag can significantly reduce the global setup errors and local setup errors in PMRT. The respiratory motion of the chest wall was negligible, and the 5 mm PTV margin could cover the local setup errors in PMRT using the new vacuum bag with cone beam CT (CBCT) correction.

Feasibility study: spot-scanning proton arc therapy (SPArc) for left-sided whole breast radiotherapy

BACKGROUND

This study investigated the feasibility and potential clinical benefit of utilizing a new proton treatment technique: Spot-scanning proton arc (SPArc) therapy for left-sided whole breast radiotherapy (WBRT) to further reduce radiation dose to healthy tissue and mitigate the probability of normal tissue complications compared to conventional intensity modulated proton therapy (IMPT).

METHODS

Eight patients diagnosed with left-sided breast cancer and treated with breast-preserving surgery followed by whole breast irradiation without regional nodal irradiation were included in this retrospective planning. Two proton treatment plans were generated for each patient: vertical intensity-modulated proton therapy used for clinical treatment (vIMPT, gantry angle 10°-30°) and SPArc for comparison purpose. Both SPArc and vIMPT plans were optimized using the robust optimization of ± 3.5% range and 5 mm setup uncertainties. Root-mean-square deviation dose (RMSD) volume histograms were used for plan robustness evaluation. All dosimetric results were evaluated based on dose-volume histograms (DVH), and the interplay effect was evaluated based on the accumulation of single-fraction 4D dynamic dose on CT50. The treatment beam delivery time was simulated based on a gantry rotation with energy-layer-switching-time (ELST) from 0.2 to 5 s.

RESULTS

The average D1 to the heart and LAD were reduced to 53.63 cGy and 82.25 cGy compared with vIMPT 110.38 cGy (p = 0.001) and 170.38 cGy (p = 0.001), respectively. The average V5Gy and V20Gy of ipsilateral lung was reduced to 16.77% and 3.07% compared to vIMPT 25.56% (p = 0.001) and 4.68% (p = 0.003). Skin3mm mean and maximum dose were reduced to 3999.38 cGy and 4395.63 cGy compared to vIMPT 4104.25 cGy (p = 0.039) and 4411.63 cGy (p = 0.043), respectively. A significant relative risk reduction (RNTCP = NTCP_SPArc/NTCP_vIMPT) for organs at risk (OARs) was obtained with SPArc ranging from 0.61 to 0.86 depending on the clinical endpoint. The RMSD volume histogram (RVH) analysis shows SPArc provided better plan robustness in OARs sparing, including the heart, LAD, ipsilateral lung, and skin. The average estimated treatment beam delivery times were comparable to vIMPT plans when the ELST is about 0.5 s.

CONCLUSION

SPArc technique can further reduce dose delivered to OARs and the probability of normal tissue complications in patients treated for left-sided WBRT.

Prehabilitation for patient positioning: pelvic exercises assist in minimizing inter-fraction sacral slope variability during radiation therapy

Reproducible patient positioning is essential for precision in radiation therapy (RT) delivery. We tested the hypothesis that a structured daily pre-treatment stretching regimen is both feasible and effective for minimizing variability in positioning, as measured by sacral slope angles (SSA). Eight female subjects undergoing pelvic radiotherapy performed a structured daily hip exercise regimen (extension and external rotation) immediately prior to both simulation imaging and daily treatment, throughout their RT course. This exercising cohort was compared to a retrospective review of 20 subjects (17 women and 3 men) undergoing RT, who had usual care. SSA measurements from daily pre-treatment imaging were compared to SSA measurements from the simulation CT. The average variation in SSA among the intervention subjects was 0.91° (± 0.58°), with a range among subjects of 0.57°-1.27°. The average variation for the control subjects was 2.27° (± 1.43°), ranging 1.22°-5.09°. The difference between the two groups was statistically significant (p = 0.0001). There was a statistically significant SSA variation between groups at each week of treatment. There was no significant variation among the intervention subjects between week 1 and later weeks, whereas subjects in the control group demonstrated significant SSA variation between week 1 and later weeks. We demonstrated a significant decrease in the variability of SSA by implementing a simple pre-treatment exercise program, while control subjects exhibited increasing variation in SSA over the course of treatment. We conclude that there is a potential benefit of prehabilitation during pelvic RT; however, a larger randomized control trial is required to confirm the findings.Clinical Trial: This research project was approved by the University of Massachusetts Medical School IRB (IRB ID H00012353) on January 21, 2017. The study is listed on ClinicalTrials.gov, provided by the U.S. National Library of Medicine, found with identifier NCT03242538.