Stereotactic Magnetic Resonance-Guided Adaptive and Non-Adaptive Radiotherapy on Combination MR-Linear Accelerators: Current Practice and Future Directions

Magnetic Resonance-Guided Cancer Therapy Radiomics and Machine Learning Models for Response Prediction

Magnetic resonance imaging (MRI) is known for its accurate soft tissue delineation of tumors and normal tissues. This development has significantly impacted the imaging and treatment of cancers. Radiomics is the process of extracting high-dimensional features from medical images. Several studies have shown that these extracted features may be used to build machine-learning models for the prediction of treatment outcomes of cancer patients. Various feature selection techniques and machine models interrogate the relevant radiomics features for predicting cancer treatment outcomes. This study aims to provide an overview of MRI radiomics features used in predicting clinical treatment outcomes with machine learning techniques. The review includes examples from different disease sites. It will also discuss the impact of magnetic field strength, sample size, and other characteristics on outcome prediction performance.

Structure-specific rigid dose accumulation dosimetric analysis of ablative stereotactic MRI-guided adaptive radiation therapy in ultracentral lung lesions

BACKGROUND

Definitive local therapy with stereotactic ablative radiation therapy (SABR) for ultracentral lung lesions is associated with a high risk of toxicity, including treatment related death. Stereotactic MR-guided adaptive radiation therapy (SMART) can overcome many of the challenges associated with SABR treatment of ultracentral lesions.

METHODS

We retrospectively identified 14 consecutive patients who received SMART to ultracentral lung lesions from 10/2019 to 01/2021. Patients had a median distance from the proximal bronchial tree (PBT) of 0.38 cm. Tumors were most often lung primary (64.3%) and HILUS group A (85.7%). A structure-specific rigid registration approach was used for cumulative dose analysis. Kaplan-Meier log-rank analysis was used for clinical outcome data and the Wilcoxon Signed Rank test was used for dosimetric data.

RESULTS

Here we show that SMART dosimetric improvements in favor of delivered plans over predicted non-adapted plans for PBT, with improvements in proximal bronchial tree DMax of 5.7 Gy (p = 0.002) and gross tumor 100% prescription coverage of 7.3% (p = 0.002). The mean estimated follow-up is 17.2 months and 2-year local control and local failure free survival rates are 92.9% and 85.7%, respectively. There are no grade ≥ 3 toxicities.

CONCLUSIONS

SMART has dosimetric advantages and excellent clinical outcomes for ultracentral lung tumors. Daily plan adaptation reliably improves target coverage while simultaneously reducing doses to the proximal airways. These results further characterize the therapeutic window improvements for SMART. Structure-specific rigid dose accumulation dosimetric analysis provides insights that elucidate the dosimetric advantages of SMART more so than per fractional analysis alone.

Deep learning application for abdominal organs segmentation on 0.35 T MR-Linac images

Introduction

Linear accelerator (linac) incorporating a magnetic resonance (MR) imaging device providing enhanced soft tissue contrast is particularly suited for abdominal radiation therapy. In particular, accurate segmentation for abdominal tumors and organs at risk (OARs) required for the treatment planning is becoming possible. Currently, this segmentation is performed manually by radiation oncologists. This process is very time consuming and subject to inter and intra operator variabilities. In this work, deep learning based automatic segmentation solutions were investigated for abdominal OARs on 0.35 T MR-images.

Methods

One hundred and twenty one sets of abdominal MR images and their corresponding ground truth segmentations were collected and used for this work. The OARs of interest included the liver, the kidneys, the spinal cord, the stomach and the duodenum. Several UNet based models have been trained in 2D (the Classical UNet, the ResAttention UNet, the EfficientNet UNet, and the nnUNet). The best model was then trained with a 3D strategy in order to investigate possible improvements. Geometrical metrics such as Dice Similarity Coefficient (DSC), Intersection over Union (IoU), Hausdorff Distance (HD) and analysis of the calculated volumes (thanks to Bland-Altman plot) were performed to evaluate the results.

Results

The nnUNet trained in 3D mode achieved the best performance, with DSC scores for the liver, the kidneys, the spinal cord, the stomach, and the duodenum of 0.96 ± 0.01, 0.91 ± 0.02, 0.91 ± 0.01, 0.83 ± 0.10, and 0.69 ± 0.15, respectively. The matching IoU scores were 0.92 ± 0.01, 0.84 ± 0.04, 0.84 ± 0.02, 0.54 ± 0.16 and 0.72 ± 0.13. The corresponding HD scores were 13.0 ± 6.0 mm, 16.0 ± 6.6 mm, 3.3 ± 0.7 mm, 35.0 ± 33.0 mm, and 42.0 ± 24.0 mm. The analysis of the calculated volumes followed the same behavior.

Discussion

Although the segmentation results for the duodenum were not optimal, these findings imply a potential clinical application of the 3D nnUNet model for the segmentation of abdominal OARs for images from 0.35 T MR-Linac.

A multi-centric evaluation of self-learning GAN based pseudo-CT generation software for low field pelvic magnetic resonance imaging

Purpose/objectives

An artificial intelligence-based pseudo-CT from low-field MR images is proposed and clinically evaluated to unlock the full potential of MRI-guided adaptive radiotherapy for pelvic cancer care.

Materials and method

In collaboration with TheraPanacea (TheraPanacea, Paris, France) a pseudo-CT AI-model was generated using end-to-end ensembled self-supervised GANs endowed with cycle consistency using data from 350 pairs of weakly aligned data of pelvis planning CTs and TrueFisp-(0.35T)MRIs. The image accuracy of the generated pCT were evaluated using a retrospective cohort involving 20 test cases coming from eight different institutions (US: 2, EU: 5, AS: 1) and different CT vendors. Reconstruction performance was assessed using the organs at risk used for treatment. Concerning the dosimetric evaluation, twenty-nine prostate cancer patients treated on the low field MR-Linac (ViewRay) at Montpellier Cancer Institute were selected. Planning CTs were non-rigidly registered to the MRIs for each patient. Treatment plans were optimized on the planning CT with a clinical TPS fulfilling all clinical criteria and recalculated on the warped CT (wCT) and the pCT. Three different algorithms were used: AAA, AcurosXB and MonteCarlo. Dose distributions were compared using the global gamma passing rates and dose metrics.

Results

The observed average scaled (between maximum and minimum HU values of the CT) difference between the pCT and the planning CT was 33.20 with significant discrepancies across organs. Femoral heads were the most reliably reconstructed (4.51 and 4.77) while anal canal and rectum were the less precise ones (63.08 and 53.13). Mean gamma passing rates for 1%1mm, 2%/2mm, and 3%/3mm tolerance criteria and 10% threshold were greater than 96%, 99% and 99%, respectively, regardless the algorithm used. Dose metrics analysis showed a good agreement between the pCT and the wCT. The mean relative difference were within 1% for the target volumes (CTV and PTV) and 2% for the OARs.

Conclusion

This study demonstrated the feasibility of generating clinically acceptable an artificial intelligence-based pseudo CT for low field MR in pelvis with consistent image accuracy and dosimetric results.

Treatment of Central Nervous System Tumors on Combination MR-Linear Accelerators: Review of Current Practice and Future Directions

Magnetic resonance imaging (MRI) provides excellent visualization of central nervous system (CNS) tumors due to its superior soft tissue contrast. Magnetic resonance-guided radiotherapy (MRgRT) has historically been limited to use in the initial treatment planning stage due to cost and feasibility. MRI-guided linear accelerators (MRLs) allow clinicians to visualize tumors and organs at risk (OARs) directly before and during treatment, a process known as online MRgRT. This novel system permits adaptive treatment planning based on anatomical changes to ensure accurate dose delivery to the tumor while minimizing unnecessary toxicity to healthy tissue. These advancements are critical to treatment adaptation in the brain and spinal cord, where both preliminary MRI and daily CT guidance have typically had limited benefit. In this narrative review, we investigate the application of online MRgRT in the treatment of various CNS malignancies and any relevant ongoing clinical trials. Imaging of glioblastoma patients has shown significant changes in the gross tumor volume over a standard course of chemoradiotherapy. The use of adaptive online MRgRT in these patients demonstrated reduced target volumes with cavity shrinkage and a resulting reduction in radiation dose to uninvolved tissue. Dosimetric feasibility studies have shown MRL-guided stereotactic radiotherapy (SRT) for intracranial and spine tumors to have potential dosimetric advantages and reduced morbidity compared with conventional linear accelerators. Similarly, dosimetric feasibility studies have shown promise in hippocampal avoidance whole brain radiotherapy (HA-WBRT). Next, we explore the potential of MRL-based multiparametric MRI (mpMRI) and genomically informed radiotherapy to treat CNS disease with cutting-edge precision. Lastly, we explore the challenges of treating CNS malignancies and special limitations MRL systems face.

Accurate, repeatable, and geometrically precise diffusion-weighted imaging on a 0.35 T magnetic resonance imaging-guided linear accelerator

Background and purpose

Diffusion weighted imaging (DWI) allows for the interrogation of tissue cellularity, which is a surrogate for cellular proliferation. Previous attempts to incorporate DWI into the workflow of a 0.35 T MR-linac (MRL) have lacked quantitative accuracy. In this study, accuracy, repeatability, and geometric precision of apparent diffusion coefficient (ADC) maps produced using an echo planar imaging (EPI)-based DWI protocol on the MRL system is illustrated, and in vivo potential for longitudinal patient imaging is demonstrated.

Materials and methods

Accuracy and repeatability were assessed by measuring ADC values in a diffusion phantom at three timepoints and comparing to reference ADC values. System-dependent geometric distortion was quantified by measuring the distance between 93 pairs of phantom features on ADC maps acquired on a 0.35 T MRL and a 3.0 T diagnostic scanner and comparing to spatially precise CT images. Additionally, for five sarcoma patients receiving radiotherapy on the MRL, same-day in vivo ADC maps were acquired on both systems, one of which at multiple timepoints.

Results

Phantom ADC quantification was accurate on the 0.35 T MRL with significant discrepancies only seen at high ADC. Average geometric distortions were 0.35 (±0.02) mm and 0.85 (±0.02) mm in the central slice and 0.66 (±0.04) mm and 2.14 (±0.07) mm at 5.4 cm off-center for the MRL and diagnostic system, respectively. In the sarcoma patients, a mean pretreatment ADC of 910x10-6 (±100x10-6) mm2/s was measured on the MRL.

Conclusions

The acquisition of accurate, repeatable, and geometrically precise ADC maps is possible at 0.35 T with an EPI approach.

Inter-Breath-Hold Geometric and Dosimetric Variations in Organs at Risk during Pancreatic Stereotactic Body Radiotherapy: Implications for Adaptive Radiation Therapy

Pancreatic cancer is the fourth leading cause of cancer-related death, with nearly 60,000 cases each year and less than a 10% 5-year overall survival rate. Radiation therapy (RT) is highly beneficial as a local-regional anticancer treatment. As anatomical variation is of great concern, motion management techniques, such as DIBH, are commonly used to minimize OARs toxicities; however, the variability between DIBHs has not been well studied. Here, we present an unprecedented systematic analysis of patients' anatomical reproducibility over multiple DIBH motion-management technique uses for pancreatic cancer RT. We used data from 20 patients; four DIBH scans were available for each patient to design 80 SBRT plans. Our results demonstrated that (i) there is considerable variation in OAR geometry and dose between same-subject DIBH scans; (ii) the RT plan designed for one scan may not be directly applicable to another scan; (iii) the RT treatment designed using a DIBH simulation CT results in different dosimetry in the DIBH treatment delivery; and (iv) this confirms the importance of adaptive radiation therapy (ART), such as MR-Linacs, for pancreatic RT delivery. The ART treatment delivery technique can account for anatomical variation between referenced and scheduled plans, and thus avoid toxicities of OARs because of anatomical variations between DIBH patient setups.