"sCT-Feasibility" - a feasibility study for deep learning-based MRI-only brain radiotherapy.

BACKGROUND: Radiotherapy (RT) is an important treatment modality for patients with brain malignancies. Traditionally, computed tomography (CT) images are used for RT treatment planning whereas magnetic resonance imaging (MRI) images are used for tumor delineation. Therefore, MRI and CT need to be registered, which is an error prone process. The purpose of this clinical study is to investigate the clinical feasibility of a deep learning-based MRI-only workflow for brain radiotherapy, that eliminates the registration uncertainty through calculation of a synthetic CT (sCT) from MRI data. METHODS: A total of 54 patients with an indication for radiation treatment of the brain and stereotactic mask immobilization will be recruited. All study patients will receive standard therapy and imaging including both CT and MRI. All patients will receive dedicated RT-MRI scans in treatment position. An sCT will be reconstructed from an acquired MRI DIXON-sequence using a commercially available deep learning solution on which subsequent radiotherapy planning will be performed. Through multiple quality assurance (QA) measures and reviews during the course of the study, the feasibility of an MRI-only workflow and comparative parameters between sCT and standard CT workflow will be investigated holistically. These QA measures include feasibility and quality of image guidance (IGRT) at the linear accelerator using sCT derived digitally reconstructed radiographs in addition to potential dosimetric deviations between the CT and sCT plan. The aim of this clinical study is to establish a brain MRI-only workflow as well as to identify risks and QA mechanisms to ensure a safe integration of deep learning-based sCT into radiotherapy planning and delivery. DISCUSSION: Compared to CT, MRI offers a superior soft tissue contrast without additional radiation dose to the patients. However, up to now, even though the dosimetrical equivalence of CT and sCT has been shown in several retrospective studies, MRI-only workflows have still not been widely adopted. The present study aims to determine feasibility and safety of deep learning-based MRI-only radiotherapy in a holistic manner incorporating the whole radiotherapy workflow. TRIAL REGISTRATION: NCT06106997.

Quality requirements for MRI simulation in cranial stereotactic radiotherapy: a guideline from the German Taskforce "Imaging in Stereotactic Radiotherapy".

Accurate Magnetic Resonance Imaging (MRI) simulation is fundamental for high-precision stereotactic radiosurgery and fractionated stereotactic radiotherapy, collectively referred to as stereotactic radiotherapy (SRT), to deliver doses of high biological effectiveness to well-defined cranial targets. Multiple MRI hardware related factors as well as scanner configuration and sequence protocol parameters can affect the imaging accuracy and need to be optimized for the special purpose of radiotherapy treatment planning. MRI simulation for SRT is possible for different organizational environments including patient referral for imaging as well as dedicated MRI simulation in the radiotherapy department but require radiotherapy-optimized MRI protocols and defined quality standards to ensure geometrically accurate images that form an impeccable foundation for treatment planning. For this guideline, an interdisciplinary panel including experts from the working group for radiosurgery and stereotactic radiotherapy of the German Society for Radiation Oncology (DEGRO), the working group for physics and technology in stereotactic radiotherapy of the German Society for Medical Physics (DGMP), the German Society of Neurosurgery (DGNC), the German Society of Neuroradiology (DGNR) and the German Chapter of the International Society for Magnetic Resonance in Medicine (DS-ISMRM) have defined minimum MRI quality requirements as well as advanced MRI simulation options for cranial SRT.

Toward a deep learning-based magnetic resonance imaging only workflow for postimplant dosimetry in I-125 seed brachytherapy for prostate cancer.

BACKGROUND AND PURPOSE: The current standard imaging-technique for creating postplans in seed prostate brachytherapy is computed tomography (CT), that is associated with additional radiation exposure and poor soft tissue contrast. To establish a magnetic resonance imaging (MRI) only workflow combining improved tissue contrast and high seed detectability, a deep learning-approach for automatic seed segmentation on MRI-scans was developed. MATERIAL AND METHODS: Patients treated with I-125 seed brachytherapy received a postplan-CT and a 1.5 T MRI-scan on nominal day 30 after implantation. For MRI-based seed visualization, DIXON-sequences were acquired and deep learning-based quantitative susceptibility maps (QSM) were generated from 3D-gradient-echo-sequences from 20 patients. Seed segmentations created on CT served as ground truth. For automatic seed segmentation on MRI, a 3D nnU-net model was trained using QSM and DIXON, both solely and combined. RESULTS: Of the implanted seeds 94.8 ± 2.4% were detected with deep learning automatic segmentation entrained on both QSM and DIXON data. Models trained on the individual sequence data-sets performed worse with detection rates of 87.5 ± 2.6% or 88.6 ± 7.5% for QSM and DIXON respectively. The seed centers identified on CT versus QSM and DIXON were on average 1.8 ± 1.3 mm apart. Postimplant dosimetry for evaluation of positioning inaccuracies revealed only small variations of up to 0.4 ± 4.26 Gy in D90 (dose 90% of the prostate receives) between the standard CT-approach and our MRI-only workflow. CONCLUSION: The proposed deep learning-based MRI-only workflow provided a promisingly accurate and robust seed localization and thus has the potential to compete with current state-of-the-art CT-based postimplant dosimetry in the future.

Benchmarking ChatGPT-4 on a radiation oncology in-training exam and Red Journal Gray Zone cases: potentials and challenges for ai-assisted medical education and decision making in radiation oncology.

Purpose: The potential of large language models in medicine for education and decision-making purposes has been demonstrated as they have achieved decent scores on medical exams such as the United States Medical Licensing Exam (USMLE) and the MedQA exam. This work aims to evaluate the performance of ChatGPT-4 in the specialized field of radiation oncology. Methods: The 38th American College of Radiology (ACR) radiation oncology in-training (TXIT) exam and the 2022 Red Journal Gray Zone cases are used to benchmark the performance of ChatGPT-4. The TXIT exam contains 300 questions covering various topics of radiation oncology. The 2022 Gray Zone collection contains 15 complex clinical cases. Results: For the TXIT exam, ChatGPT-3.5 and ChatGPT-4 have achieved the scores of 62.05% and 78.77%, respectively, highlighting the advantage of the latest ChatGPT-4 model. Based on the TXIT exam, ChatGPT-4's strong and weak areas in radiation oncology are identified to some extent. Specifically, ChatGPT-4 demonstrates better knowledge of statistics, CNS & eye, pediatrics, biology, and physics than knowledge of bone & soft tissue and gynecology, as per the ACR knowledge domain. Regarding clinical care paths, ChatGPT-4 performs better in diagnosis, prognosis, and toxicity than brachytherapy and dosimetry. It lacks proficiency in in-depth details of clinical trials. For the Gray Zone cases, ChatGPT-4 is able to suggest a personalized treatment approach to each case with high correctness and comprehensiveness. Importantly, it provides novel treatment aspects for many cases, which are not suggested by any human experts. Conclusion: Both evaluations demonstrate the potential of ChatGPT-4 in medical education for the general public and cancer patients, as well as the potential to aid clinical decision-making, while acknowledging its limitations in certain domains. Owing to the risk of hallucinations, it is essential to verify the content generated by models such as ChatGPT for accuracy.

Synthetic CTs for MRI-only brain RT treatment: integration of immobilization systems.

PURPOSE: Auxiliary devices such as immobilization systems should be considered in synthetic CT (sCT)-based treatment planning (TP) for MRI-only brain radiotherapy (RT). A method for auxiliary device definition in the sCT is introduced, and its dosimetric impact on the sCT-based TP is addressed. METHODS: T1-VIBE DIXON was acquired in an RT setup. Ten datasets were retrospectively used for sCT generation. Silicone markers were used to determine the auxiliary devices' relative position. An auxiliary structure template (AST) was created in the TP system and placed manually on the MRI. Various RT mask characteristics were simulated in the sCT and investigated by recalculating the CT-based clinical plan on the sCT. The influence of auxiliary devices was investigated by creating static fields aimed at artificial planning target volumes (PTVs) in the CT and recalculated in the sCT. The dose covering 50% of the PTV (D50) deviation percentage between CT-based/recalculated plan (∆D50[%]) was evaluated. RESULTS: Defining an optimal RT mask yielded a ∆D50[%] of 0.2 ± 1.03% for the PTV and between -1.6 ± 3.4% and 1.1 ± 2.0% for OARs. Evaluating each static field, the largest ∆D50[%] was delivered by AST positioning inaccuracy (max: 3.5 ± 2.4%), followed by the RT table (max: 3.6 ± 1.2%) and the RT mask (max: 3.0 ± 0.8% [anterior], 1.6 ± 0.4% [rest]). No correlation between ∆D50[%] and beam depth was found for the sum of opposing beams, except for (45°â€¯+ 315°). CONCLUSION: This study evaluated the integration of auxiliary devices and their dosimetric influence on sCT-based TP. The AST can be easily integrated into the sCT-based TP. Further, we found that the dosimetric impact was within an acceptable range for an MRI-only workflow.

Usability of magnetic resonance images acquired at a novel low-field 0.55 T scanner for brain radiotherapy treatment planning.

Background and Purpose: Low-field magnetic resonance imaging (MRI) may offer specific advantages over high-field MRI, e.g. lower susceptibility-dependent distortions and simpler installation. The study aim was to evaluate if a novel 0.55 T MRI scanner provides sufficient image accuracy and quality for radiotherapy (RT) treatment planning. Material and methods: The geometric accuracy of images acquired at a low-field MRI scanner was evaluated in phantom measurements regarding gradient non-linearity-related distortions. Patient-induced B0-susceptibility changes were investigated via B0-field-mapping in ten volunteers. Patients were positioned in RT-setup using a 3D-printed insert for the head/neck-coil that was tested for sufficient signal-to-noise-ratio (SNR). The suitability of the MRI-system for detection of metastases was evaluated in eleven patients. In comparison to diagnostic images, acquired at ≥1.5 T, three physicians evaluated the detectability of metastases by counting them in low- and high-field-images, respectively. Results: The phantom measurements showed a high imaging fidelity after 3D-distortion-correction with (1.2 ± 0.9) mm geometric distortion in 10 cm radius from isocentre. At the edges remaining distortions were greater than at 1.5 T. The mean susceptibility-induced distortions in the head were (0.05 ± 0.05) mm and maximum 0.69 mm. SNR analysis showed that optimised positioning of RT-patients without signal loss in the head/neck-coil was possible with the RT-insert. No significant differences (p = 0.48) in detectability of metastases were found. Conclusion: The 0.55 T MRI system provided sufficiently geometrically accurate and high-resolution images that can be used for RT-planning for brain metastases. Hence, modern low-field MRI may contribute to simply access MRI for RT-planning after further investigations.

End-to-end testing for stereotactic radiotherapy including the development of a Multi-Modality phantom.

PURPOSE: A new insert for a commercially available end-to-end test phantom was designed and in-house manufactured by 3D printing. Subsequently, the insert was tested for different stereotactic radiation therapy workflows (SRS, SBRT, FSRT, and Multimet) also in comparison to the original insert. MATERIAL AND METHODS: Workflows contained imaging (MR, CT), treatment planning, positioning, and irradiation. Positioning accuracy was evaluated for non-coplanar x-ray, kV- and MV-CBCT systems, as well as surface guided radiation therapy. Dosimetric accuracy of the irradiation was measured with an ionization chamber at four different linear accelerators including dynamic tumor tracking for SBRT. RESULTS: CT parameters of the insert were within the specification. For MR images, the new insert allowed quantitative analysis of the MR distortion. Positioning accuracy of the phantom with the new insert using the imaging systems of the different linacs was < 1 mm/degree also for MV-CBCT and a non-coplanar imaging system which caused > 3 mm deviation with the original insert. Deviation of point dose values was <3% for SRS, FSRT, and SBRT for both inserts. For the Multimet plans deviations exceeded 10% because the ionization chamber was not positioned in each metastasis, but in the center of phantom and treatment plan. CONCLUSION: The in-house manufactured insert performed well in all steps of four stereotactic treatment end-to-end tests. Advantages over the commercially available alternative were seen for quantitative analysis of deformation correction in MR images, applicability for non-coplanar x-ray imaging, and dynamic tumor tracking.

Feasibility of artificial-intelligence-based synthetic computed tomography in a magnetic resonance-only radiotherapy workflow for brain radiotherapy: Two-way dose validation and 2D/2D kV-image-based positioning.

Background and purpose: Magnetic Resonance Imaging (MRI)-only workflow eliminates the MRI-computed tomography (CT) registration inaccuracy, which degrades radiotherapy (RT) treatment accuracy. For an MRI-only workflow MRI sequences need to be converted to synthetic-CT (sCT). The purpose of this study was to evaluate a commercially available artificial intelligence (AI)-based sCT generation for dose calculation and 2D/2D kV-image daily positioning for brain RT workflow. Materials and methods: T1-VIBE DIXON was acquired at the 1.5 T MRI for 26 patients in RT setup for sCTs generation. For each patient, a volumetric modulated arc therapy (VMAT) plan was optimized on the CT, then recalculated on the sCT; and vice versa. sCT-based digitally reconstructed radiographs (DRRs) were fused with stereoscopic X-ray images recorded as image guidance for clinical treatments. Dosimetric differences between planned/recalculated doses and the differences between the calculated and recorded clinical couch shift/rotation were evaluated. Results: Mean ΔD50 between planned/recalculated doses for target volumes ranged between -0.2 % and 0.2 %; mean ΔD50 and ΔD0.01ccm were -0.6 % and 1.6 % and -1.4 % and 1.0 % for organ-at-risks, respectively. Differences were tested for clinical equivalence using intervals ±2 % (dose), ±1mm (translation), and ±1° (rotation). Dose equivalence was found using ±2 % interval (p < 0.001). The median differences between lat./long./vert. couch shift between CT-based/sCT-based DRRs were 0.3 mm/0.2 mm/0.3 mm (p < 0.05); median differences between lat./long./vert. couch rotation were -1.5°/0.1°/0.1° (after improvement of RT setup: -0.4°/-0.1°/-0.4°, p < 0.05). Conclusions: This in-silico study showed that the AI-based sCT provided equivalent results to the CT for dose calculation and daily stereoscopic X-ray positioning when using an optimal RT setup during MRI acquisition.

Permanent LDR prostate brachytherapy: Comprehensive characterization of seed-dynamics within the prostate on a seed-only level.

PURPOSE: Seed brachytherapy is a well-established treatment modality for prostate cancer. However, there is still a lack of profound characterizations of seed motions within the prostate. We assessed these dynamics between day 0 and day 30 of brachytherapy. METHODS: We considered 45 patients with 2408 implanted seeds, and performed a 1:1 assignment between their positions on post-plan CT (nominal day 30) and intraoperative ultrasound (day 0). Geometric seed arrangement changes were measured for each patient and the entire collective. The impact of seed strand-lengths and implant regions was investigated. Correlations with patient characteristics were evaluated. We determined corresponding dosimetric effects by calculating common dose metrics. RESULTS: We found a median seed displacement of 4.3 mm [interquartile range: 3.1-6.9 mm], occurring preferentially in superior-inferior direction. Single and double strands moved significantly stronger than strands of higher lengths. Seed dynamics was more pronounced in base (5.6 mm [3.7-10.7 mm]) and apex (6.5 mm [4.1-15.0 mm]) than in the mid-gland (3.8 mm [2.7-5.0 mm]), and less pronounced in peripheral (4.3 mm [3.0-6.7 mm]) than in urethra-near (5.5 mm [3.5-10.7 mm]) regions. Correlations of seed dynamics with prostate volume changes and the number of implanted seeds and needles were found. D90 (dose that 90% of the prostate receives) varied by a median of 3 Gy [-6 to 15 Gy] between treatment plan and post-plan, but >40 Gy for individual patients. CONCLUSIONS: Reducing seed dynamics is important to ensure a high treatment quality. For this, strands containing ≥3 seeds may be useful, implantations in base-, apex-, and urethra-near zone should be avoided, and the number of needles and seeds may be minimized where possible.

Deep learning-based quantitative susceptibility mapping (QSM) in the presence of fat using synthetically generated multi-echo phase training data.

PURPOSE: To enable a fast and automatic deep learning-based QSM reconstruction of tissues with diverse chemical shifts, relevant to most regions outside the brain. METHODS: A UNET was trained to reconstruct susceptibility maps using synthetically generated, unwrapped, multi-echo phase data as input. The RMS error with respect to synthetic validation data was computed. The method was tested on two in vivo knee and two pelvis data sets. Comparisons were made to a conventional fat-water separation pipeline by applying a commonly used graph-cut algorithm, both without and with an extended mask for background field removal (FWS-CONV-QSM and FWS-MASK-CONV-QSM, respectively). Several regions of interest were segmented and compared. Furthermore, the approach was tested on a prostate cancer patient receiving low-dose-rate brachytherapy, to detect and localize the seeds by MRI. RESULTS: The RMS error was 0.292 ppm with FWS-CONV-QSM and 0.123 ppm for the UNET approach. Susceptibility maps were reconstructed much faster (< 10 s) and completely automatically (no background masking needed) by the UNET compared with the other applied techniques (5 min 51 s and 22 min 44 s for CONV-QSM and FWS-MASK-CONV-QSM, respectively. Background artifacts, fat-water swaps, and hypointense artifacts between I-125 seeds of a patient receiving low-dose brachytherapy in the prostate were largely reduced in the UNET approach. CONCLUSIONS: Deep learning-based QSM reconstruction, trained solely with synthetic data, is well-suited to rapidly reconstructing high-quality susceptibility maps in the presence of fat without needing masking for background field removal.