Search

Artificial intelligence (AI) has great potential to transform the clinical workflow of radiotherapy. Since the introduction of deep neural networks (DNNs), many AI-based methods have been proposed to address challenges in different aspects of radiotherapy. Commercial vendors have started to release AI-based tools that can be readily integrated to the established clinical workflow. To show the recent progress in AI-aided radiotherapy, we have reviewed AI-based studies in five major aspects of radiotherapy, including image reconstruction, image registration, image segmentation, image synthesis, and automatic treatment planning. In each section, we summarized and categorized the recently published methods, followed by a discussion of the challenges, concerns, and future development. Given the rapid development of AI-aided radiotherapy, the efficiency and effectiveness of radiotherapy in the future could be substantially improved through intelligent automation of various aspects of radiotherapy.

Purpose Emerging evidence suggests cardiac substructures are highly radiosensitive during radiation therapy for cancer treatment. However, variability in substructure position after tumor localization has not been well characterized. This study quantifies inter-fraction displacement and planning organ at risk volumes (PRVs) of substructures by leveraging the excellent soft tissue contrast of magnetic resonance imaging (MRI). Methods Eighteen retrospectively evaluated patients underwent radiotherapy for intrathoracic tumors with a 0.35 T MRI-guided linear accelerator. Imaging was acquired at a 17–25 s breath-hold (resolution 1.5 × 1.5 × 3 mm3). Three to four daily MRIs per patient (n = 71) were rigidly registered to the planning MRI-simulation based on tumor matching. Deep learning or atlas-based segmentation propagated 13 substructures (e.g., chambers, coronary arteries, great vessels) to daily MRIs and were verified by two radiation oncologists. Daily centroid displacements from MRI-simulation were quantified and PRVs were calculated. Results Across substructures, inter-fraction displacements for 14% in the left–right, 18% in the anterior-posterior, and 21% of fractions in the superior-inferior were > 5 mm. Due to lack of breath-hold compliance, ~4% of all structures shifted > 10 mm in any axis. For the chambers, median displacements were 1.8, 1.9, and 2.2 mm in the left–right, anterior-posterior, and superior-inferior axis, respectively. Great vessels demonstrated larger displacements (> 3 mm) in the superior-inferior axis (43% of shifts) and were only 25% (left–right) and 29% (anterior-posterior) elsewhere. PRVs from 3 to 5 mm were determined as anisotropic substructure-specific margins. Conclusions This exploratory work derived substructure-specific safety margins to ensure highly effective cardiac sparing. Findings require validation in a larger cohort for robust margin derivation and for applications in prospective clinical trials.

Purpose To evaluate the dosimetric and image‐guided radiation therapy (IGRT) performance of a novel generative adversarial network (GAN) generated synthetic CT (synCT) in the brain and compare its performance for clinical use including conventional brain radiotherapy, cranial stereotactic radiosurgery (SRS), planar, and volumetric IGRT. Methods and Materials SynCT images for 12 brain cancer patients (6 SRS, 6 conventional) were generated from T1‐weighted postgadolinium magnetic resonance (MR) images by applying a GAN model with a residual network (ResNet) generator and a convolutional neural network (CNN) with 5 convolutional layers as the discriminator that classified input images as real or synthetic. Following rigid registration, clinical structures and treatment plans derived from simulation CT (simCT) images were transferred to synCTs. Dose was recalculated for 15 simCT/synCT plan pairs using fixed monitor units. Two‐dimensional (2D) gamma analysis (2%/2 mm, 1%/1 mm) was performed to compare dose distributions at isocenter. Dose–volume histogram (DVH) metrics (D95%, D99%, D0.2cc, and D0.035cc) were assessed for the targets and organ at risks (OARs). IGRT performance was evaluated via volumetric registration between cone beam CT (CBCT) to synCT/simCT and planar registration between KV images to synCT/simCT digital reconstructed radiographs (DRRs). Results Average gamma passing rates at 1%/1mm and 2%/2mm were 99.0 ± 1.5% and 99.9 ± 0.2%, respectively. Excellent agreement in DVH metrics was observed (mean difference ≤0.10 ± 0.04 Gy for targets, 0.13 ± 0.04 Gy for OARs). The population averaged mean difference in CBCT‐synCT registrations were 0.05). An outlier with a large resection cavity exhibited the worst‐case scenario. Conclusion Brain GAN synCTs demonstrated excellent performance for dosimetric and IGRT endpoints, offering potential use in high precision brain cancer therapy.

Purpose Rising evidence suggests that cardiac substructures are highly radiosensitive. However, they are not routinely considered in treatment planning as they are not readily visualized on treatment planning CTs (TPCTs). This work integrated the soft tissue contrast provided by low‐field MRIs acquired on an MR‐linac via image registration to further enable cardiac substructure sparing on TPCTs. Methods Sixteen upper thoracic patients treated at various breathing states (7 end‐exhalation, 7 end‐inhalation, 2 free‐breathing) on a 0.35T MR‐linac were retrospectively evaluated. A hybrid MR/CT atlas and a deep learning three‐dimensional (3D) U‐Net propagated 13 substructures to TPCTs. Radiation oncologists revised contours using registered MRIs. Clinical treatment plans were re‐optimized and evaluated for beam arrangement modifications to reduce substructure doses. Dosimetric assessment included mean and maximum (0.03cc) dose, left ventricular volume receiving 5Gy (LV‐V5), and other clinical endpoints. As metrics of plan complexity, total MU and treatment time were evaluated between approaches. Results Cardiac sparing plans reduced the mean heart dose (mean reduction 0.7 ± 0.6, range 0.1 to 2.5 Gy). Re‐optimized plans reduced left anterior descending artery (LADA) mean and LADA0.03cc (0.0–63.9% and 0.0 to 17.3 Gy, respectively). LV0.03cc was reduced by >1.5 Gy for 10 patients while 6 cases had large reductions (>7%) in LV‐V5. Left atrial mean dose was equivalent/reduced in all sparing plans (mean reduction 0.9 ± 1.2 Gy). The left main coronary artery was better spared in all cases for mean dose and D0.03cc. One patient exhibited >10 Gy reduction in D0.03cc to four substructures. There was no statistical difference in treatment time and MU, or clinical endpoints to the planning target volume, lung, esophagus, or spinal cord after re‐optimization. Four patients benefited from new beam arrangements, leading to further dose reductions. Conclusions By introducing 0.35T MRIs acquired on an MR‐linac to verify cardiac substructure segmentations for CT‐based treatment planning, an opportunity was presented for more effective sparing with limited increase in plan complexity. Validation in a larger cohort with appropriate margins offers potential to reduce radiation‐related cardiotoxicities.

Radiation dose to the heart and cardiac substructures has been linked to cardiotoxicities. Because cardiac substructures are poorly visualized on treatment-planning computed tomography (CT) scans, we used the superior soft-tissue contrast of magnetic resonance (MR) imaging to optimize a hybrid MR/CT atlas for substructure dose assessment using CT.Thirty-one patients with left-sided breast cancer underwent a T2-weighted MR imaging scan and noncontrast simulation CT scans. A radiation oncologist delineated 13 substructures (chambers, great vessels, coronary arteries, etc) using MR/CT information via cardiac-confined rigid registration. Ground-truth contours for 20 patients were inputted into an intensity-based deformable registration atlas and applied to 11 validation patients. Automatic segmentations involved using majority vote and Simultaneous Truth and Performance Level Estimation (STAPLE) strategies with 1 to 15 atlas matches. Performance was evaluated via Dice similarity coefficient (DSC), mean distance to agreement, and centroid displacement. Three physicians evaluated segmentation performance via consensus scoring by using a 5-point scale. Dosimetric assessment included measurements of mean heart dose, left ventricular volume receiving 5 Gy, and left anterior descending artery mean and maximum doses.Atlas approaches performed similarly well, with 7 of 13 substructures (heart, chambers, ascending aorta, and pulmonary artery) having DSC0.75 when averaged over 11 validation patients. Coronary artery segmentations were not successful with the atlas-based approach (mean DSC0.3). The STAPLE method with 10 matches yielded the highest DSC and the lowest mean distance to agreement for all high-performing substructures (omitting coronary arteries). For the STAPLE method with 10 matches,50% of all validation contours had centroid displacements3.0 mm, with the largest shifts in the coronary arteries. Atlas-generated contours had no statistical difference from ground truth for left anterior descending artery maximum dose, mean heart dose, and left ventricular volume receiving 5 Gy (P .05). Qualitative contour grading showed that 8 substructures required minor modifications.The hybrid MR/CT atlas provided reliable segmentations of chambers, heart, and great vessels for patients undergoing noncontrast CT, suggesting potential widespread applicability for routine treatment planning.

Purpose: Patient tolerability of magnetic resonance (MR)–guided radiation treatment delivery is limited by the need for repeated deep inspiratory breath holds (DIBHs). This volunteer study assessed the feasibility of continuous positive airway pressure (CPAP) with and without DIBH for respiratory motion management during radiation treatment with an MR-linear accelerator (MR-linac). Methods and Materials: MR imaging safety was first addressed by placing the CPAP device in an MR-safe closet and configuring a tube circuit via waveguide to the magnet bore. Reproducibility and linearity of the final configuration were assessed. Six healthy volunteers underwent thoracic imaging in a 0.35T MR-linac, with one free breathing (FB) and 2 DIBH acquisitions being obtained at 5 pressures from 0 to 15 cm-H2O. Lung and heart volumes and positions were recorded; repeatability was assessed by comparing 2 consecutive DIBH scans. Blinded reviewers graded images for motion artifact using a 3-point grading scale. Participants completed comfort and perception surveys before and after imaging sessions. Results: Compared with FB alone, FB-10, FB-12, and FB-15 cm H2O significantly increased lung volumes (+23%, +34%, +44%; all P

Purpose: Whole-heart dose metrics are not as strongly linked to late cardiac morbidities as radiation doses to individual cardiac substructures. Our aim was to characterize the excursion and dosimetric variation throughout respiration of sensitive cardiac substructures for future robust safety margin design. Methods and Materials: Eleven patients with cancer treatments in the thorax underwent 4-phase noncontrast 4-dimensional computed tomography (4DCT) with T2-weighted magnetic resonance imaging in end-exhale. The end-exhale phase of the 4DCT was rigidly registered with the magnetic resonance imaging and refined with an assisted alignment surrounding the heart from which 13 substructures (chambers, great vessels, coronary arteries, etc) were contoured by a radiation oncologist on the 4DCT. Contours were deformed to the other respiratory phases via an intensity-based deformable registration for radiation oncologist verification. Measurements of centroid and volume were evaluated between phases. Mean and maximum dose to substructures were evaluated across respiratory phases for the breast (n = 8) and thoracic cancer (n = 3) cohorts. Results: Paired t tests revealed reasonable maintenance of geometric and anatomic properties (P < .05 for 4/39 volume comparisons). Maximum displacements >5 mm were found for 24.8%, 8.5%, and 64.5% of the cases in the left-right, anterior-posterior, and superior-inferior axes, respectively. Vector displacements were largest for the inferior vena cava and the right coronary artery, with displacements up to 17.9 mm. In breast, the left anterior descending artery Dmean varied 3.03 ± 1.75 Gy (range, 0.53-5.18 Gy) throughout respiration whereas lung showed patient-specific results. Across all patients, whole heart metrics were insensitive to breathing phase (mean and maximum dose variations

Purpose This work characterizes a novel exponential 4DCT reconstruction algorithm (EXPO), in phantom and patient, to determine its impact on image quality as compared to the standard cosine‐squared weighted 4DCT reconstruction. Methods A motion platform translated objects in the superior–inferior (S‐I) direction at varied breathing rates (8–20 bpm) and couch pitches (0.06–0.1) to evaluate interplay between parameters. Ten‐phase 4DCTs were acquired and data were reconstructed with cosine squared and EXPO weighting. To quantify the magnitude of image blur, objects were translated in the anterior–posterior (A‐P) and S‐I directions for full‐width half maximum (FWHM) analysis between both 4DCT algorithms and a static case. 4DCT sinogram data for 10 patients were retrospectively reconstructed using both weighting factors. Image subtractions elucidated intensity and boundary differences. Subjective image quality grading (presence of image artifacts, noise, spatial resolution (i.e., lung/liver boundary sharpness), and overall image quality) was conducted yielding 200 evaluations. Results After taking static object size into account, the FWHM of EXPO reconstructions in the A‐P direction was 3.3 ± 1.7 mm (range: 0–4.9) as compared to cosine squared 9.8 ± 4.0 mm (range: 2.6–14.4). The FWHM of objects translated in the S‐I direction reconstructed with EXPO agreed better with the static FWHM than the cosine‐squared reconstructions. Slower breathing periods, faster couch pitches, and intermediate 4DCT phases had the largest reductions of blurring with EXPO. 18 of 60 comparisons of artifacts were improved with EXPO reconstruction, whereas no appreciable changes were observed in image quality scores. In 18 of 20 cases, EXPO provided sharper images although the reduced projections also increased baseline noise. Conclusion Exponential weighted 4DCT offers potential for reducing image blur (i.e., improving image sharpness) in 4DCT with a tendency to reduce artifacts. Future work will involve evaluating the impact on treatment planning including delineation ability and dose calculation.

Model‐based iterative reconstruction (MBIR) reduces CT imaging dose while maintaining image quality. However, MBIR reduces noise while preserving edges which may impact intensity‐based tasks such as auto‐segmentation. This work evaluates the sensitivity of an auto‐contouring prostate atlas across multiple MBIR reconstruction protocols and benchmarks the results against filtered back projection (FBP). Images were created from raw projection data for 11 prostate cancer cases using FBP and nine different MBIR reconstructions (3 protocols/3 noise reduction levels) yielding 10 reconstructions/patient. Five bony structures, bladder, rectum, prostate, and seminal vesicles (SVs) were segmented using an auto‐segmentation pipeline that renders 3D binary masks for analysis. Performance was evaluated for volume percent difference (VPD) and Dice similarity coefficient (DSC), using FBP as the gold standard. Nonparametric Friedman tests plus post hoc all pairwise comparisons were employed to test for significant differences (P

Recent advancements in synthetic computed tomography (synCT) from magnetic resonance (MR) imaging data have made MRI-only treatment planning feasible in the brain, although synCT performance for image guided radiation therapy (IGRT) is not well understood. This work compares geometric equivalence of digitally reconstructed radiographs (DRRs) from CTs and synCTs for brain cancer patients and quantifies performance for partial brain IGRT.Ten brain cancer patients (12 lesions, 7 postsurgical) underwent MR-SIM and CT-SIM. SynCTs were generated by combining ultra-short echo time, T1, T2, and fluid attenuation inversion recovery datasets using voxel-based weighted summation. SynCT and CT DRRs were compared using patient-specific thresholding and assessed via overlap index, Dice similarity coefficient, and Jaccard index. Planar IGRT images for 22 fractions were evaluated to quantify differences between CT-generated DRRs and synCT-generated DRRs in 6 quadrants. Previously validated software was implemented to perform 2-dimensional (2D)-2D rigid registrations using normalized mutual information. Absolute (planar image/DRR registration) and relative (differences between synCT and CT DRR registrations) shifts were calculated for each axis and 3-dimensional vector difference. A total of 1490 rigid registrations were assessed.DRR agreements in anteroposterior and lateral views for overlap index, Dice similarity coefficient, and Jaccard index were0.95. Normalized mutual information results were equivalent in 75% of quadrants. Rotational registration results were negligible (0.07°). Statistically significant differences between CT and synCT registrations were observed in 9/18 matched quadrants/axes (P.05). The population average absolute shifts were 0.77 ± 0.58 and 0.76 ± 0.59 mm for CT and synCT, respectively, for all axes/quadrants. Three-dimensional vectors were2 mm in 77.7 ± 10.8% and 76.5 ± 7.2% of CT and synCT registrations, respectively. SynCT DRRs were sensitive in postsurgical cases (vector displacements2 mm in affected quadrants).DRR synCT geometry was robust. Although statistically significant differences were observed between CT and synCT registrations, results were not clinically significant. Future work will address synCT generation in postsurgical settings.