Multi-institutional questionnaire-based survey on online adaptive radiotherapy performed using commercial systems in Japan in 2023

In this study, we aimed to conduct a survey on the current clinical practice of, staffing for, commissioning of, and staff training for online adaptive radiotherapy (oART) in the institutions that installed commercial oART systems in Japan, and to share the information with institutions that will implement oART systems in future. A web-based questionnaire, containing 107 questions, was distributed to nine institutions in Japan. Data were collected from November to December 2023. Three institutions each with the MRIdian (ViewRay, Oakwood Village, OH, USA), Unity (Elekta AB, Stockholm, Sweden), and Ethos (Varian Medical Systems, Palo Alto, CA, USA) systems completed the questionnaire. One institution (MRIdian) had not performed oART by the response deadline. Each institution had installed only one oART system. Hypofractionation, and moderate hypofractionation or conventional fractionation were employed in the MRIdian/Unity and Ethos systems, respectively. The elapsed time for the oART process was faster with the Ethos than with the other systems. All institutions added additional staff for oART. Commissioning periods differed among the oART systems owing to provision of beam data from the vendors. Chambers used during commissioning measurements differed among the institutions. Institutional training was provided by all nine institutions. To the best of our knowledge, this was the first survey about oART performed using commercial systems in Japan. We believe that this study will provide useful information to institutions that installed, are installing, or are planning to install oART systems.

Artificial intelligence innovations in neurosurgical oncology: a narrative review

PURPOSE

Artificial Intelligence (AI) has become increasingly integrated clinically within neurosurgical oncology. This report reviews the cutting-edge technologies impacting tumor treatment and outcomes.

METHODS

A rigorous literature search was performed with the aid of a research librarian to identify key articles referencing AI and related topics (machine learning (ML), computer vision (CV), augmented reality (AR), virtual reality (VR), etc.) for neurosurgical care of brain or spinal tumors.

RESULTS

Treatment of central nervous system (CNS) tumors is being improved through advances across AI-such as AL, CV, and AR/VR. AI aided diagnostic and prognostication tools can influence pre-operative patient experience, while automated tumor segmentation and total resection predictions aid surgical planning. Novel intra-operative tools can rapidly provide histopathologic tumor classification to streamline treatment strategies. Post-operative video analysis, paired with rich surgical simulations, can enhance training feedback and regimens.

CONCLUSION

While limited generalizability, bias, and patient data security are current concerns, the advent of federated learning, along with growing data consortiums, provides an avenue for increasingly safe, powerful, and effective AI platforms in the future.

Coverage with evidence development program on stereotactic body radiotherapy in Belgium (2013-2019): a nationwide registry-based prospective study

Background

Although stereotactic body radiotherapy (SBRT) was progressively adopted in clinical practice in Belgium, a reimbursement request in 2011 was not granted because of remaining clinical and economic uncertainty. A coverage with evidence development (CED) program on SBRT started in 2013, with the aim to assess clinical and technical patterns-of-care in Belgium and monitor survival per indication, in view of supporting inclusion in the reimbursement system.

Methods

The Belgian National Institute for Health and Disability Insurance (NIHDI) initiated this prospective observational registry. Participating departments, using SBRT in clinical practice, signed the 'NIHDI convention'. Eligible patients had a primary tumour (PT) or oligometastatic disease (OMD). Patient, tumour, and treatment characteristics were collected through an online module of the Belgian Cancer Registry, prerequisite for financing. Five-year overall survival (5YOS) and 30- and 90-days mortality were primary outcomes, derived from vital status information.

Findings

Between 10/2013 and 12/2019, 20 of the 24 accredited radiotherapy departments participated, 6 were academic. Registered cases per department ranged from 21 to 867. Of 5675 registrations analysed, the majority had good performance status and limited number of lesions. Enrolment of PTs remained stable over time, OMDs almost doubled. Peripheral lung lesions dominated in PTs as in OMDs. Other metastases were (para)spinal, 'non-standard' and hepatic. Thirty- and 90-days mortalities remained below 0.5% [95% CI 0.3%-0.8%] respectively 2.1% [95% CI 1.6%-2.7%]. 5YOS varied by indication, primary prostate patients performing best (85%, 95% CI [76%, 96%]), those with liver metastases worst (19%, 95% CI [15%, 24%]). Better OS was observed in academic departments, department size did not significantly impact survival. OMD survival was better in 2018-19.

Interpretation

CED can be used to define patterns-of-care and real-life outcome of innovative radiotherapy. As the observed survival for different indications was in line with outcome in emerging literature, SBRT was included in the Belgian reimbursement system as of January 2020.

Funding

NIHDI financed participating departments per registered case.

The value of PROMs for predicting erectile dysfunction in prostate cancer patients with Bayesian network

Purpose

This study aims to develop and externally validate a clinically plausible Bayesian network structure to predict one-year erectile dysfunction in prostate cancer patients by combining expert knowledge with evidence from data using clinical and Patient-reported outcome measures (PROMs) data. In addition, compare and contrast structures that stem from PROM information and routine clinical data.

Summary of background

For men with localized prostate cancer, choosing the optimal treatment can be challenging since each option comes with different side effects, such as erectile dysfunction, which negatively impacts their quality of life. Our previous findings demonstrate that logistic regression models are able to identify patients at high risk of erectile dysfunction. However, methods such as Bayesian networks may be more successful, as they intricately represent the causal relations between the variables.

Patients and methods

946 prostate cancer patients from 65 Dutch hospitals were considered to develop the Bayesian network structure. Continuous variables were discretized before analysis based on expert opinions and literature. Patients with missing information and variables with more than 25% of missing information were excluded. Prostate cancer treating physicians first determined the relationships (arcs) between the available variables. The structures were then modified based on algorithmically derived structures using the hill-climbing algorithm. Structural Performance was evaluated based on the area under the curve (AUC) values and calibration plots on the training and test data.

Results

BMI and prostate volume via MRI were excluded from this analysis due to their high percentage of missingness (>45 %). The final cohort was reduced to 505 and 216 after excluding 157 and 68 patients with missing information, respectively. The AUC of the PROM structure was better than the clinical structure in both the train and test data. The structure that combined both sources of information had an AUC value of 0.94 (0.92 - 0.96) and 0.84171 (0.77 91) in the train and test data, respectively.

Conclusion

Bayesian network structures derived from PROM information by complimenting expert knowledge with evidence from the data produce a clinically plausible structure that is more performant than structures from clinical data. Our study supports the growing global recognition of incorporating the patient's perspective in outcomes research for better decision-making and optimal outcomes. However, a structure that combines both sources of information gives a more holistic view of the patient with actionable insights and improved discriminative power.

MR signature matching (MRSIGMA) implementation for true real-time free-breathing volumetric imaging with sub-200 ms latency on an MR-Linac

PURPOSE

Develop a true real-time implementation of MR signature matching (MRSIGMA) for free-breathing 3D MRI with sub-200 ms latency on the Elekta Unity 1.5T MR-Linac.

METHODS

MRSIGMA was implemented on an external computer with a network connection to the MR-Linac. Stack-of-stars with partial kz sampling was used to accelerate data acquisition and ReconSocket was employed for simultaneous data transmission. Movienet network computed the 4D MRI motion dictionary and correlation analysis was used for signature matching. A programmable 4D MRI phantom was utilized to evaluate MRSIGMA with respect to a ground-truth translational motion reference. In vivo validation was performed on patients with pancreatic cancer, where 15 patients were employed to train Movienet and 7 patients to test the real-time implementation of MRSIGMA. Dice coefficients between real-time MRSIGMA and a retrospectively computed 4D reference were used to evaluate motion tracking performance.

RESULTS

Motion dictionary was computed in under 5 s. Signature acquisition and matching presented 173 ms latency on the phantom and 193 ms on patients. MRSIGMA presented a mean error of 1.3-1.6 mm for all phantom experiments, which was below the 2 mm acquisition resolution along the motion direction. The Dice coefficient over time between MRSIGMA and reference contours was 0.88 ± 0.02 (GTV), 0.87 ± 0.02(duodenum-stomach), and 0.78 ± 0.02(small bowel), demonstrating high motion tracking performance for both tumor and organs at risk.

CONCLUSION

The real-time implementation of MRSIGMA enabled true real-time free-breathing 3D MRI with sub-200 ms imaging latency on a clinical MR-Linac system, which can be used for treatment monitoring, adaptive radiotherapy and dose accumulation mapping in tumors affected by respiratory motion.

Robustness of intensity modulated proton treatment of esophageal cancer for anatomical changes and breathing motion

BACKGROUND AND PURPOSE

In this study, we assessed the robustness of intensity modulated proton therapy (IMPT) in esophageal cancer for anatomical variations during treatment.

METHODS

The first sixty esophageal cancer patients, treated clinically with chemoradiotherapy were included. The treatment planning strategy was based on an internal target volume (ITV) approach, where the ITV was created from the clinical target volumes (CTVs) delineated on all phases of a 4DCT. For optimization, a 3 mm isotropic margin was added to the ITV, combined with robust optimization using 5 mm setup and 3 % range uncertainty. Each patient received weekly repeat CTs (reCTs). Robust plan re-evaluation on all reCTs, and a robust dose summation was performed. To assess the factors influencing ITV coverage, a multivariate linear regression analysis was performed. Additionally, clinical adaptations were evaluated.

RESULTS

The target coverage was adequate (ITV V94%>98 % on the robust voxel-wise minimum dose) on most reCTs (91 %), and on the summed dose in 92 % of patients. Significant predictors for ITV coverage in the multivariate analysis were diaphragm baseline shift and water equivalent depth (WED) of the ITV in the beam direction. Underdosage of the ITV mainly occurred in week 1 and 4, leading to treatment adaptation of eight patients, all on the first reCT.

CONCLUSION

Our IMPT treatment of esophageal cancer is robust for anatomical variations. Adaptation appears to be most effective in the first week of treatment. Diaphragm baseline shifts and WED are predictive factors for ITV underdosage, and should be incorporated in an adaptation protocol.

Lung and Liver Stereotactic Body Radiation Therapy During Mechanically Assisted Deep Inspiration Breath-Holds: A Prospective Feasibility Trial

Purpose

Radiation therapy for tumors subject to breathing-related motion during breath-holds (BHs) has the potential to substantially reduce the irradiated volume. Mechanically assisted and noninvasive ventilation (MANIV) could ensure the target repositioning accuracy during each BH while facilitating treatment feasibility through oxygen supplementation and a perfectly replicated mechanical support. However, there is currently no clinical evidence substantiating the use of MANIV-induced BH for moving tumors. The aim of this work was, therefore, to evaluate the technique's performance under real treatment conditions.

Methods and Materials

Patients eligible for lung or liver stereotactic body radiation therapy were prospectively included in a single-arm trial. The primary endpoint corresponded to the treatment feasibility with MANIV. Secondary outcomes comprised intrafraction geometric uncertainties extracted from real-time imaging, tolerance to BH, and treatment time.

Results

Treatment was successfully delivered in 92.9% (13/14) of patients: 1 patient with a liver tumor was excluded because of a mechanically induced gastric insufflation displacing the liver cranially by more than 1 cm. In the left-right/anteroposterior/craniocaudal directions, the recalculated safety margins based on intrafraction positional data were 4.6 mm/5.1 mm/5.6 mm and 4.7 mm/7.3 mm/5.9 mm for lung and liver lesions, respectively. Compared with the free-breathing internal target volume and midposition approaches, the average reduction in the planning target volume with MANIV reached -47.2% ± 15.3%, P < .001, and -29.4% ± 19.2%, P = .007, for intrathoracic tumors and -23.3% ± 12.4%, P < .001, and -9.3% ± 15.3%, P = .073, for upper abdominal tumors, respectively. For 1 liver lesion, large caudal drifts of occasionally more than 1 cm were measured. The total slot time was 53.1 ± 10.6 minutes with a BH comfort level of 80.1% ± 10.6%.

Conclusions

MANIV enables high treatment feasibility within a nonselected population. Accurate intrafraction tumor repositioning is achieved for lung tumors. Because of occasional intra-BH caudal drifts, pretreatment assessment of BH stability for liver lesions is, however, recommended.

Time is NTCP: Should we maximize patient throughput or perform online adaptation on proton therapy systems?

BACKGROUND

Compared to conventional radiotherapy (XT), proton therapy (PT) may improve normal tissue complication probabilities (NTCP). However, PT typically requires higher adaptation rates due to an increased sensitivity to anatomical changes. Systematic online adaptation may address this issue, but it requires additional replanning time, decreasing patient throughput. Therefore, less patients would benefit in such case from PT for a given machine capacity, with results in worse NTCP.

AIM

To investigate the trade-off between PT patient throughput and NTCP gain as a function of the time needed for adaptation.

METHODS

A retrospective database of 14 lung patients with two repeated 4DCTs was used to compare NTCP values between XT and PT for NTCP2ym (2-year mortality), NTCPdysphagia and NTCPpneumonitis. Four scenarios were considered for PT: no adaptation using clinical robustness parameters (4D robust optimization, 3 % range error and PTV-equivalent setup errors); systematic online adaptation with clinical robustness parameters; setup errors reduced to 4 mm and to 2 mm. Dose was accumulated on the planning CT. The number of patients treated with PT depended on the extra time needed for adaptation, assuming an 8-hours capacity (assuming 14 patients a day; thus minimum 34.2 min per treatment session if there is no or instantaneous adaptation).

RESULTS

Baseline NTCP gains (PT against XT without adaptation) equaled 6.9 %, 6.1 %, and 7.7 % for NTCP2ym, NTCPdysphagia and NTCPpneumonitis, respectively. Using instantaneous online adaptation and setup errors of 2 mm, the overall gains were then 10.7 %, 13.6 % and 12.4 %. Taking into account loss of capacity, 13.7 min was the maximum extra-time allowed to complete adaptation and maintain an advantage on all three metrics for the 2-mm setup error scenario.

CONCLUSION

This study highlights the critical importance of keeping short online adaptation times when using systems with limited capacity like PT.

Validation and reproducibility of in vivo dosimetry for pencil beam scanned FLASH proton treatment in mice

PURPOSE

To investigate quality assurance (QA) techniques for in vivo dosimetry and establish its routine uses for proton FLASH small animal experiments with a saturated monitor chamber.

METHODS AND MATERIALS

227 mice were irradiated at FLASH or conventional (CONV) dose rates with a 250 MeV FLASH-capable proton beamline using pencil beam scanning to characterize the proton FLASH effect on abdominal irradiation and examining various endpoints. A 2D strip ionization chamber array (SICA) detector was positioned upstream of collimation and used for in vivo dose monitoring during irradiation. Before each irradiation series, SICA signal was correlated with the isocenter dose at each delivered dose rate. Dose, dose rate, and 2D dose distribution for each mouse were monitored with the SICA detector.

RESULTS

Calibration curves between the upstream SICA detector signal and the delivered dose at isocenter had good linearity with minimal R2 values of 0.991 (FLASH) and 0.985 (CONV), and slopes were consistent for each modality. After reassigning mice, standard deviations were less than 1.85 % (FLASH) and 0.83 % (CONV) for all dose levels, with no individual subject dose falling outside a ± 3.6 % range of the designated dose. FLASH fields had a field-averaged dose rate of 79.0 ± 0.8 Gy/s and mean local average dose rate of 160.6 ± 3.0 Gy/s. In vivo dosimetry allowed for the accurate detection of variation between the delivered and the planned dose.

CONCLUSION

In vivo dosimetry benefits FLASH experiments through enabling real-time dose and dose rate monitoring allowing mouse cohort regrouping when beam fluctuation causes delivered dose to vary from planned dose.

Challenges and opportunities in the development and clinical implementation of artificial intelligence based synthetic computed tomography for magnetic resonance only radiotherapy

Synthetic computed tomography (sCT) generated from magnetic resonance imaging (MRI) can serve as a substitute for planning CT in radiation therapy (RT), thereby removing registration uncertainties associated with multi-modality imaging pairing, reducing costs and patient radiation exposure. CE/FDA-approved sCT solutions are nowadays available for pelvis, brain, and head and neck, while more complex deep learning (DL) algorithms are under investigation for other anatomic sites. The main challenge in achieving a widespread clinical implementation of sCT lies in the absence of consensus on sCT commissioning and quality assurance (QA), resulting in variation of sCT approaches across different hospitals. To address this issue, a group of experts gathered at the ESTRO Physics Workshop 2022 to discuss the integration of sCT solutions into clinics and report the process and its outcomes. This position paper focuses on aspects of sCT development and commissioning, outlining key elements crucial for the safe implementation of an MRI-only RT workflow.

Results of an Artificial Intelligence-Based Image Review System to Detect Patient Misalignment Errors in a Multi-institutional Database of Cone Beam Computed Tomography-Guided Radiation Therapy

PURPOSE

Present knowledge of patient setup and alignment errors in image guided radiation therapy (IGRT) relies on voluntary reporting, which is thought to underestimate error frequencies. A manual retrospective patient-setup misalignment error search is infeasible owing to the bulk of cases to be reviewed. We applied a deep learning-based misalignment error detection algorithm (EDA) to perform a fully automated retrospective error search of clinical IGRT databases and determine an absolute gross patient misalignment error rate.

METHODS AND MATERIALS

The EDA was developed to analyze the registration between planning scans and pretreatment cone beam computed tomography scans, outputting a misalignment score ranging from 0 (most unlikely) to 1 (most likely). The algorithm was trained using simulated translational errors on a data set obtained from 680 patients treated at 2 radiation therapy clinics between 2017 and 2022. A receiver operating characteristic analysis was performed to obtain target thresholds. DICOM Query and Retrieval software was integrated with the EDA to interact with the clinical database and fully automate data retrieval and analysis during a retrospective error search from 2016 to 2017 and from 2021 to 2022 for the 2 institutions, respectively. Registrations were flagged for human review using both a hard-thresholding method and a prediction trending analysis over each individual patient's treatment course. Flagged registrations were manually reviewed and categorized as errors (>1 cm misalignment at the target) or nonerrors.

RESULTS

A total of 17,612 registrations were analyzed by the EDA, resulting in 7.7% flagged events. Three previously reported errors were successfully flagged by the EDA, and 4 previously unreported vertebral body misalignment errors were discovered during case reviews. False positive cases often displayed substantial image artifacts, patient rotation, and soft tissue anatomy changes.

CONCLUSIONS

Our results validated the clinical utility of the EDA for bulk image reviews and highlighted the reliability and safety of IGRT, with an absolute gross patient misalignment error rate of 0.04% ± 0.02% per delivered fraction.

A single-center experience of the upright proton therapy for skull-base chordomas and chondrosarcomas: Updated results

Aim

To access efficacy and safety of the upright proton therapy for the skull-base chordomas and chondrosarcomas.

Materials and methods

The study encompasses single-center experience of proton therapy in chordomas (CA) and chondrosarcomas (CSA) of skull-base localization. We evaluate overall survival, local control and toxicity. Tumor response was assessed in accordance with RANO criteria. Treatment-related toxicity was evaluated with the help of CTCAE v 5.0 scale.

Results

Proton therapy in the upright position was utilized for 51pts (patients) with CA-CSA (40 pts with chordoma and 11pts with chondrosarcoma) at the A. Tsyb Medical Radiological Research Center in 2016-2023. Median tumor volume constituted 30 cm3 (IQR (interquartile range) 15-41 cm3). Median total dose was 70 GyRBE. Median number of fractions was 35. Overall survival (OS) at 1-, 2- and 3-year rates reached 98.0 %, 88.6 % and 82.7 %, respectively. Median follow-up time was 36 months. The 1-, 2- and 3-year local control (LC) rates constituted, respectively, 98 %, 78.6 % and 66.3 %. Prior surgery showed statistically significant association with better prognosis (p = 0.023). Brainstem-to-tumor dose coverage compromise became the major pattern of LC failure (p = 0.03). The late radiation toxicity reactions included temporal lobe necrosis grade 2 in 2 pts, xerostomia grade 1 in 1pt, radiation cataract grade 2 in 1pt and persistent headache grade 2 in 4 pts. Severe late toxicity reactions were observed in 2 cases (4 %): 1 myelitis grade 3 and brainstem damage grade 5 in 1pt.

Conclusion

Local control was achieved in the majority of patients receiving the scanning-beam upright proton therapy for skull-base CA-CSA. The LC rates after a surgery-radiotherapy combination treatment were higher compared with irradiation alone. Pattern of failure is mostly brainstem-tumor dose compromise. The high OS and LC rates were accompanied by low toxicity incidence. Even in complex case of the skull base CA-CSA upright proton therapy shows promising clinical outcomes.

High-speed bioimpedance-based gating system for radiotherapy: Prototype and proof of principle

PURPOSE

To investigate a novel bioimpedance-based respiratory gating system (BRGS) designed for external beam radiotherapy and to evaluate its technical characteristics in comparison with existing similar systems.

MATERIALS AND METHODS

The BRGS was tested on three healthy volunteers in free breathing and breath-hold patterns under laboratory conditions. Its parameters, including the time delay (TD) between the actual impedance change and the gating signal, temperature drift, root mean square (RMS) noise, and signal-to-noise ratio (SNR), were measured and analyzed.

RESULTS

The gate-on TD and the gate-off TD were found to be 9.0 ± 2.0 ms [mean ± standard deviation (M ± SD)] and 7.2 ± 1.3 ms, respectively. The temperature drift of the BRGS output signal was 0.02 Ω after 30 min of operation. RMS noise averaged 0.14 ± 0.05 Ω (M ± SD) for all subjects and varied from 0.08 to 0.20 Ω with repeated measurements. A significant difference in SNR (p < 0.001) was observed between subjects, ranging from 4 to 15.

CONCLUSION

The evaluated bioimpedance-based gating system showed a high performance in real-time respiratory monitoring and may potentially be used as an external surrogate guidance for respiratory-gated external beam radiotherapy. Direct comparison with commercially available systems, 4D correlation studies, and expansion of the patient sample are goals for future preclinical studies.

Relative profile measurements in 1.5T MR-linacs: investigation of central axis deviations

Objective. In 1.5 T MR-linacs, the absorbed dose central axis (CAX) deviates from the beam's CAX due to inherent profile asymmetry. In addition, a measured CAX deviation may be biased due to potential lateral (to the beam) effective point of measurement (EPOML) shifts of the detector employed. By investigating CAX deviations, the scope of this study is to determine a set ofEPOMLshifts for profile measurements in 1.5 T MR-linacs.Approach. The Semiflex 3D ion chamber and microDiamond detector (PTW, Germany) were considered in the experimental study while three more detectors were included in the Monte Carlo (MC) study. CAX deviations in the crossline and inline profiles were calculated based on inflection points of the 10×10 cm2field, at five centers. In MC simulations, the experimental setup was reproduced. A small water voxel was simulated to calculate CAX deviation without the impact of the detector-specificEPOMLshift.Main results. All measurements were consistent among the five centers. MC-based and experimental measurements were in agreement within uncertainties. Placing the microDiamond in the vertical orientation does not appear to affect the detector'sEPOML, which is on its central longitudinal axis. For the Semiflex 3D in the crossline direction, the CAX deviation was 2.3 mm, i.e. 1 mm larger than the ones measured using the microDiamond and simulated considering the ideal water detector. Thus, anEPOMLshift of 1 mm is recommended for crossline profile measurements under both Semiflex 3D orientations. For the inline profile, anEPOMLshift of -0.5 mm was determined only for the parallel configuration. In the MC study, CAX deviations were found detector- and orientation-dependent. The dead volume is responsible for theEPOMLshift only in the inline profile and under the parallel orientation.Significance. This work contributes to data availability on the correction or mitigation of the magnetic field-induced changes in the detectors' response.

Comprehensive clinical implementation, workflow, and FMEA of bespoke silicone bolus cast from 3D printed molds using open-source resources

BACKGROUND

Bolus materials have been used for decades in radiotherapy. Most frequently, these materials are utilized to bring dose closer to the skin surface to cover superficial targets optimally. While cavity filling, such as nasal cavities, is desirable, traditional commercial bolus is lacking, requiring other solutions. Recently, investigators have worked on utilizing 3D printing technology, including commercially available solutions, which can overcome some challenges with traditional bolus.

PURPOSE

To utilize failure modes and effects analysis (FMEA) to successfully implement a comprehensive 3D printed bolus solution to replace commercial bolus in our clinic using a series of open-source (or free) software products.

METHODS

3D printed molds for bespoke bolus were created by exporting the DICOM structures of the bolus designed in the treatment planning system and manipulated to create a multipart mold for 3D printing. A silicone (Ecoflex 00-30) mixture is poured into the mold and cured to form the bolus. Molds for sheet bolus of five thicknesses were also created. A comprehensive FMEA was performed to guide workflow adjustments and QA steps.

RESULTS

The process map identified 39 and 30 distinct steps for the bespoke and flat sheet bolus workflows, respectively. The corresponding FMEA highlighted 119 and 86 failure modes, with 69 shared between the processes. Misunderstanding of plan intent was a potential cause for most of the highest-scoring failure modes, indicating that physics and dosimetry involvement early in the process is paramount.

CONCLUSION

FMEA informed the design and implementation of QA steps to guarantee a safe and high-quality comprehensive implementation of silicone bolus from 3D printed molds. This approach allows for greater adaptability not afforded by traditional bolus, as well as potential dissemination to other clinics due to the open-source nature of the workflow.

Commissioning of MRI-guided gynaecological brachytherapy using an MR-linac

Purpose. To evaluate the feasibility of use of an 1.5 T magnetic resonance (MR)-linear accelerator MR-linac for imaging in gynaecologic high-dose-rate (HDR) brachytherapy.Method. Commissioning measurements for MR images quality control, geometric distortion, dwell position accuracy, applicator reconstruction and end-to-end test for a tandem-and-ring applicator were performed following the recommendations of American Brachytherapy Society, International Commission on Radiation Units and Measurements and Report of the Brachytherapy Working Group of the Spanish Society of Medical Physics. The values for MR-based IGABT were compared to the corresponding values with computed tomography (CT).Results. Measured distorsions for the MR images were less than 0.50 mm compared to the CT images. The differences between 3D displacements for all dwell positions were 0.66 mm and 0.62 mm for the tandem and ring, respectively. The maximum difference is 0.64 mm for the distances from the applicator tip obtained using the films. The CT and MR dose differences for the right and left 'A' points were 0.9% and -0.7%, respectively. Similar results were observed in terms of dose distribution for CT and Mr The gamma passing rate was 99.3% and 99.5%, respectively.Conclusion. The use of MR images from an MR-linac used in a radiotherapy service for gynaecological brachytherapy was proved to be feasible, safe and precise as the geometrical differences were less than 1 mm, and the dosimetric differences were less than 1% when comparing to the use of CT images for the same purpose.

Technical note: A software tool to extract complexity metrics from radiotherapy treatment plans

BACKGROUND

Complexity metrics are mathematical quantities designed to quantify aspects of radiotherapy treatment plans that may affect both their deliverability and dosimetric accuracy. Despite numerous studies investigating their utility, there remains a notable absence of shared tools for their extraction.

PURPOSE

This study introduces UCoMX (Universal Complexity Metrics Extractor), a software package designed for the extraction of complexity metrics from the DICOM-RT plan files of radiotherapy treatments.

METHODS

UCoMX is developed around two extraction engines: VCoMX (VMAT Complexity Metrics Extractor) for VMAT/IMRT plans, and TCoMX (Tomotherapy Complexity Metrics Extractor) tailored for Helical Tomotherapy plans. The software, built using Matlab, is freely available in both Matlab-based and stand-alone versions. More than 90 complexity metrics, drawn from relevant literature, are implemented in the package: 43 for VMAT/IMRT and 51 for Helical Tomotherapy.

RESULTS

The package is designed to read DICOM-RT plan files generated by most commercially available Treatment Planning Systems (TPSs), across various treatment units. A reference dataset containing VMAT, IMRT, and Helical Tomotherapy plans is provided to serve as a reference for comparing UCoMX with other in-house systems available at other centers.

CONCLUSION

UCoMX offers a straightforward solution for extracting complexity metrics from radiotherapy plans. Its versatility is enhanced through different versions, including Matlab-based and stand-alone, and its compatibility with a wide range of commercially available TPSs and treatment units. UCoMX presents a free, user-friendly tool empowering researchers to compute the complexity of treatment plans efficiently.

Semi-automated vertex placement for lattice radiotherapy and dosimetric verification using 3D polymer gel dosimetry

PURPOSE

To evaluate the feasibility of an open-source, semi-automated, and reproducible vertex placement tool to improve the efficiency of lattice radiotherapy (LRT) planning. We used polymer gel dosimetry with a Cone Beam CT (CBCT) readout to commission this LRT technique.

MATERIAL AND METHODS

We generated a volumetric modulated arc therapy (VMAT)-based LRT plan on a 2 L NIPAM polymer gel dosimeter using our Eclipse Acuros version 15.6 AcurosXB beam model, and also recalculated the plan with a pre-clinical Acuros v18.0 dose calculation algorithm with the enhanced leaf modelling (ELM). With the assistance of the MAAS-SFRThelper software, a lattice vertex diameter of 1.5 cm and center-to-center spacing of 3 cm were used to place the spheres in a hexagonal, closed packed structure. The verification plan included four gantry arcs with 15°, 345°, 75°, 105° collimator angles. The spheres were prescribed 20 Gy to 50% of their combined volume. The 6 MV Flattening Filter Free beam energy was used to deliver the verification plan. The dosimetric accuracy of the LRT delivery was evaluated with 1D dose profiles, 2D isodose maps, and a 3D global gamma analysis.

RESULTS

Qualitative comparisons between the 1D dose profiles of the Eclipse plan and measured gel showed good consistency at the prescription dose mark. The average diameter measured 13.3 ± 0.2 mm (gel for v15.6), 12.6 mm (v15.6 plan), 13.1 ± 0.2 mm (gel for v18.0), and 12.3 mm (v18.0 plan). 3D gamma analysis showed that all gamma pass percent were > 95% except at 1% and 2% at the 1 mm distance to agreement criteria.

CONCLUSION

This study presents a novel application of gel dosimetry in verifying the dosimetric accuracy of LRT, achieving excellent 3D gamma results. The treatment planning was facilitated by publicly available software that automatically placed the vertices for consistency and efficiency.

Investigation of linear energy transfer (LET)-dependence behavior and dosimetric response of a flat-panel detector in pencil beam scanning proton therapy

PURPOSE

This study aims to elucidate the dependence of the flat-panel detector's response on the linear energy transfer (LET) and evaluate the practical viability of employing flat-panel detectors in proton dosimetry applications through LET-dependent correction factors.

METHODS

The study assessed the flat-panel detector's response across varying depths using solid water and distinct 100, 150, and 200 MeV proton beams by comparing the flat-panel readings against reference doses measured with an ionization chamber. A Monte Carlo code was used to derive LET values, and an LET-dependent response correction factor was determined based on the ratio of the uncorrected flat-panel dose to the ionization chamber dose. The implications of this under-response correction were validated by applying it to a measurement involving a spread-out Bragg peak (SOBP), followed by a comparative analysis against doses calculated using the Monte Carlo code and MatriXX ONE measurement.

RESULTS

The association between LET and the flat-panel detector's under-response displayed a positive correlation that intensified with increasing LET values. Notably, with a 10 keV/µm LET value, the detector's under-response reached 50 %, while the measurement points in the SOBP demonstrated under-response greater than 20 %. However, post-correction, the adjusted flat-panel profile closely aligned with the Monte Carlo profile, yielding a 2-dimensional 3 %/3mm gamma passing rate of 100 % at various verification depths.

CONCLUSION

This study successfully defined the link between LET and the responsiveness of flat-panel detectors for proton dosimetric measurements and established a foundational framework for integrating flat-panel detectors in clinical proton dosimetry applications.

RobMedNAS: searching robust neural network architectures for medical image synthesis

Investigating U-Net model robustness in medical image synthesis against adversarial perturbations, this study introduces RobMedNAS, a neural architecture search strategy for identifying resilient U-Net configurations. Through retrospective analysis of synthesized CT from MRI data, employing Dice coefficient and mean absolute error metrics across critical anatomical areas, the study evaluates traditional U-Net models and RobMedNAS-optimized models under adversarial attacks. Findings demonstrate RobMedNAS's efficacy in enhancing U-Net resilience without compromising on accuracy, proposing a novel pathway for robust medical image processing.

Stereotactic body radiation therapy for the primary tumor and oligometastases versus the primary tumor alone in patients with metastatic pancreatic cancer

BACKGROUND

Local therapies may benefit patients with oligometastatic cancer. However, there were limited data about pancreatic cancer. Here, we compared the efficacy and safety of stereotactic body radiation therapy (SBRT) to the primary tumor and all oligometastases with SBRT to the primary tumor alone in patients with metastatic pancreatic cancer.

METHODS

A retrospective review of patients with synchronous oligometastatic pancreatic cancer (up to 5 lesions) receiving SBRT to all lesions (including all oligometastases and the primary tumor) were performed. Another comparable group of patients with similar baseline characteristics, including metastatic burden, SBRT doses, and chemotherapy regimens, receiving SBRT to the primary tumor alone were identified. The primary endpoint was overall survival (OS). The secondary endpoints were progression frees survival (PFS), polyprogression free survival (PPFS) and adverse events.

RESULTS

There were 59 and 158 patients receiving SBRT to all lesions and to the primary tumor alone. The median OS of patients with SBRT to all lesions and the primary tumor alone was 10.9 months (95% CI 10.2-11.6 months) and 9.3 months (95% CI 8.8-9.8 months) (P < 0.001). The median PFS of two groups was 6.5 months (95% CI 5.6-7.4 months) and 4.1 months (95% CI 3.8-4.4 months) (P < 0.001). The median PPFS of two groups was 9.8 months (95% CI 8.9-10.7 months) and 7.8 months (95% CI 7.2-8.4 months) (P < 0.001). Additionally, 14 (23.7%) and 32 (20.2%) patients in two groups had grade 3 or 4 treatment-related toxicity.

CONCLUSIONS

SBRT to all oligometastases and the primary tumor in patients with pancreatic cancer may improve survival, which needs prospective verification.

Dosimetric impact of calibration coefficients determined using linear accelerator photon and electron beams for ionization chamber in an on-site dosimetry audit

This study aimed to clarify the dosimetric impact of calibration beam quality for calibration coefficients of the absorbed dose to water for an ionization chamber in an on-site dosimetry audit. Institution-measured doses of 200 photon and 184 electron beams were compared with the measured dose using one year data before and after the calibration of the ionization chamber used. For photon and electron reference dosimetry, the agreements of the institution-measured dose against two measured doses in this audit were evaluated using the calibration coefficients determined using 60Co (${N}_{D,\mathrm{w},{}^{60}\mathrm{Co}}$) and linear accelerator (linac) (${N}_{D,\mathrm{w},Q}$) beams. For electron reference dosimetry, the agreement of two institution-measured doses against the measured dose was evaluated using${N}_{D,\mathrm{w},Q}$. Institution-measured doses were evaluated using direct- and cross-calibration coefficients. For photon reference dosimetry, the mean differences and standard deviation (SD) of institution-measured dose against the measured dose using ${N}_{D,\mathrm{w},{}^{60}\mathrm{Co}}$ and ${N}_{D,\mathrm{w},Q}$ were -0.1% ± 0.4% and -0.3% ± 0.4%, respectively. For electron reference dosimetry, the mean differences and SD of institution-measured dose using the direct-calibration coefficient against the measured dose using ${N}_{D,\mathrm{w},{}^{60}\mathrm{Co}}$ and ${N}_{D,\mathrm{w},Q}$ were 1.3% ± 0.8% and 0.8% ± 0.8%, respectively. Further, the mean differences and SD of institution-measured dose using the cross-calibration coefficient against the measured dose using ${N}_{D,\mathrm{w},Q}$ were -0.1% ± 0.6%. For photon beams, the dosimetric impact of introducing calibration coefficients determined using linac beams was small. For electron beams, it was larger, and the measured dose using ${N}_{D,\mathrm{w},Q}$ was most consistent with the institution-measured dose, which was evaluated using a cross-calibration coefficient.

Development of deep learning-based novel auto-segmentation for the prostatic urethra on planning CT images for prostate cancer radiotherapy

Urinary toxicities are one of the serious complications of radiotherapy for prostate cancer, and dose-volume histogram of prostatic urethra has been associated with such toxicities in previous reports. Previous research has focused on estimating the prostatic urethra, which is difficult to delineate in CT images; however, these studies, which are limited in number, mainly focused on cases undergoing brachytherapy uses low-dose-rate sources and do not involve external beam radiation therapy (EBRT). In this study, we aimed to develop a deep learning-based method of determining the position of the prostatic urethra in patients eligible for EBRT. We used contour data from 430 patients with localized prostate cancer. In all cases, a urethral catheter was placed when planning CT to identify the prostatic urethra. We used 2D and 3D U-Net segmentation models. The input images included the bladder and prostate, while the output images focused on the prostatic urethra. The 2D model determined the prostate's position based on results from both coronal and sagittal directions. Evaluation metrics included the average distance between centerlines. The average centerline distances for the 2D and 3D models were 2.07 ± 0.87 mm and 2.05 ± 0.92 mm, respectively. Increasing the number of cases while maintaining equivalent accuracy as we did in this study suggests the potential for high generalization performance and the feasibility of using deep learning technology for estimating the position of the prostatic urethra.

Surface guided ring gantry radiotherapy in deep inspiration breath hold for breast cancer patients

PURPOSE

This study investigated the use of surface guided radiotherapy (SGRT) in combination with a tomotherapy treatment mode using discrete delivery angles for deep inspiration breath hold (DIBH) treatments of breast cancer (bc). We aimed to assess the feasibility and dosimetric advantages of this approach.

MATERIALS AND METHODS

We evaluated camera occlusion in the Radixact treatment system bore and the stability of DIBH signals during couch movement. The SGRT system's ability to maintain signal and surface image accuracy was analyzed at different depths within the bore. Dosimetric parameters were compared and measured for 20 left-sided bc patients receiving TomoDirect (TD) tangential radiotherapy in both DIBH and free breathing (FB).

RESULTS

The SGRT system maintained surface coverage and precise DIBH-signal at depths up to 40 cm beyond the treatment center. Camera occlusion occurred in the clavicular and neck regions due to the patient's morphology and gantry geometry. Nonetheless, the system accurately detected respiratory motion for all measurements. The DIBH plans significantly (p < 0.001) reduced mean heart and left anterior descending artery (LAD) radiation doses by up to 40%, with a 50% reduction in near-maximum heart and LAD doses, respectively. No significant dosimetric differences between DIBH and FB were observed in other investigated parameters and volumes.

CONCLUSIONS

Camera occlusion and couch movement minimally impacted the real-time surface image accuracy needed for DIBH treatments of bc. DIBH reduced heart and LAD radiation doses significantly compared to FB, indicating the feasibility and dosimetric benefits of combining these modalities.

Technical note: MR image-based synthesis CT for CyberKnife robotic stereotactic radiosurgery

The purpose of this study is to investigate whether deep learning-based sCT images enable accurate dose calculation in CK robotic stereotactic radiosurgery. A U-net convolutional neural network was trained using 2446 MR-CT pairs and used it to translate 551 MR images to sCT images for testing. The sCT of CK patient was encapsulated into a quality assurance (QA) validation phantom for dose verification. The CT value difference between CT and sCT was evaluated using mean absolute error (MAE) and the statistical significance of dose differences between CT and sCT was tested using the Wilcoxon signed rank test. For all CK patients, the MAE value of the whole brain region did not exceed 25 HU. The percentage dose difference between CT and sCT was less than ±0.4% on GTV (D2(Gy), -0.29%, D95(Gy), -0.09%), PTV (D2(Gy), -0.25%, D95(Gy), -0.10%), and brainstem (max dose(Gy), 0.31%). The percentage dose difference between CT and sCT for most regions of interest (ROIs) was no more than ±0.04%. This study extended MR-based sCT prediction to CK robotic stereotactic radiosurgery, expanding the application scenarios of MR-only radiation therapy. The results demonstrated the remarkable accuracy of dose calculation on sCT for patients treated with CK robotic stereotactic radiosurgery.

Artificial intelligence for treatment delivery: image-guided radiotherapy

Radiation therapy (RT) is a highly digitized field relying heavily on computational methods and, as such, has a high affinity for the automation potential afforded by modern artificial intelligence (AI). This is particularly relevant where imaging is concerned and is especially so during image-guided RT (IGRT). With the advent of online adaptive RT (ART) workflows at magnetic resonance (MR) linear accelerators (linacs) and at cone-beam computed tomography (CBCT) linacs, the need for automation is further increased. AI as applied to modern IGRT is thus one area of RT where we can expect important developments in the near future. In this review article, after outlining modern IGRT and online ART workflows, we cover the role of AI in CBCT and MRI correction for dose calculation, auto-segmentation on IGRT imaging, motion management, and response assessment based on in-room imaging.

Robust optimization and assessment of dynamic trajectory and mixed-beam arc radiotherapy: a preliminary study

Objective.Dynamic trajectory radiotherapy (DTRT) and dynamic mixed-beam arc therapy (DYMBARC) exploit non-coplanarity and, for DYMBARC, simultaneously optimized photon and electron beams. Margin concepts to account for set-up uncertainties during delivery are ill-defined for electron fields. We develop robust optimization for DTRT&DYMBARC and compare dosimetric plan quality and robustness for both techniques and both optimization strategies for four cases.Approach.Cases for different treatment sites and clinical target volume (CTV) to planning target volume (PTV) margins,m, were investigated. Dynamic gantry-table-collimator photon paths were optimized to minimize PTV/organ-at-risk (OAR) overlap in beam's-eye-view and minimize potential photon multileaf collimator (MLC) travel. For DYMBARC plans, non-isocentric partial electron arcs or static fields with shortened source-to-surface distance (80 cm) were added. Direct aperture optimization (DAO) was used to simultaneously optimize MLC-based intensity modulation for both photon and electron beams yielding deliverable PTV-based DTRT&DYMBARC plans. Robust-optimized plans used the same paths/arcs/fields. DAO with stochastic programming was used for set-up uncertainties with equal weights in all translational directions and magnitudeδsuch thatm= 0.7δ. Robust analysis considered random errors in all directions with or without an additional systematic error in the worst 3D direction for the adjacent OARs.Main results.Electron contribution was 7%-41% of target dose depending on the case and optimization strategy for DYMBARC. All techniques achieved similar CTV coverage in the nominal (no error) scenario. OAR sparing was overall better in the DYMBARC plans than in the DTRT plans and DYMBARC plans were generally more robust to the considered uncertainties. OAR sparing was better in the PTV-based than in robust-optimized plans for OARs abutting or overlapping with the target volume, but more affected by uncertainties.Significance.Better plan robustness can be achieved with robust optimization than with margins. Combining electron arcs/fields with non-coplanar photon trajectories further improves robustness and OAR sparing.

Turning the attention to time-resolved EPID-images: treatment error classification with transformer multiple instance learning

Objective.The aim of this work was to develop a novel artificial intelligence-assistedin vivodosimetry method using time-resolved (TR) dose verification data to improve quality of external beam radiotherapy.Approach. Although threshold classification methods are commonly used in error classification, they may lead to missing errors due to the loss of information resulting from the compression of multi-dimensional electronic portal imaging device (EPID) data into one or a few numbers. Recent research has investigated the classification of errors on time-integrated (TI)in vivoEPID images, with convolutional neural networks showing promise. However, it has been observed previously that TI approaches may cancel out the error presence onγ-maps during dynamic treatments. To address this limitation, simulated TRγ-maps for each volumetric modulated arc radiotherapy angle were used to detect treatment errors caused by complex patient geometries and beam arrangements. Typically, such images can be interpreted as a set of segments where only set class labels are provided. Inspired by recent weakly supervised approaches on histopathology images, we implemented a transformer based multiple instance learning approach and utilized transfer learning from TI to TRγ-maps.Main results. The proposed algorithm performed well on classification of error type and error magnitude. The accuracy in the test set was up to 0.94 and 0.81 for 11 (error type) and 22 (error magnitude) classes of treatment errors, respectively.Significance. TR dose distributions can enhance treatment delivery decision-making, however manual data analysis is nearly impossible due to the complexity and quantity of this data. Our proposed model efficiently handles data complexity, substantially improving treatment error classification compared to models that leverage TI data.

Insights into the dosimetric and geometric characteristics of stereotactic radiosurgery for multiple brain metastases: A systematic review

BACKGROUND

GammaKnife (GK) and CyberKnife (CK) have been the mainstay stereotactic radiosurgery (SRS) solution for multiple brain metastases (MBM) for several years. Recent technological advancement has seen an increase in single-isocentre C-arm linac-based SRS. This systematic review focuses on dosimetric and geometric insights into contemporary MBM SRS and thereby establish if linac-based SRS has matured to match the mainstay SRS delivery systems.

METHODS

The PubMed, Web of Science and Scopus databases were interrogated which yielded 891 relevant articles that narrowed to 20 articles after removing duplicates and applying the inclusion and exclusion criteria. Primary studies which reported the use of SRS for treatment of MBM SRS and reported the technical aspects including dosimetry were included. The review was limited to English language publications from January 2015 to August 2023. Only full-length papers were included in the final analysis. Opinion papers, commentary pieces, letters to the editor, abstracts, conference proceedings and editorials were excluded. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines were followed. The reporting of conformity indices (CI) and gradient indices, V12Gy, monitor units and the impact of translational and rotational shifts were extracted and analysed.

RESULTS

The single-isocentre technique for MBM dominated recent SRS studies and the most studied delivery platforms were Varian. The C-arm linac-based SRS plan quality and normal brain tissue sparing was comparable to GK and CK and in some cases better. The most used nominal beam energy was 6FFF, and optimised couch and collimator angles could reduce mean normal brain dose by 11.3%. Reduction in volume of the healthy brain receiving a certain dose was dependent on the number and size of the metastases and the relative geometric location. GK and CK required 4.5-8.4 times treatment time compared with linac-based SRS. Rotational shifts caused larger changes in CI in C-arm linac-based single-isocentre SRS.

CONCLUSION

C-arm linac-based SRS produced comparable MBM plan quality and the delivery is notably shorter compared to GK and CK SRS.

Principles of artificial intelligence in radiooncology

PURPOSE

In the rapidly expanding field of artificial intelligence (AI) there is a wealth of literature detailing the myriad applications of AI, particularly in the realm of deep learning. However, a review that elucidates the technical principles of deep learning as relevant to radiation oncology in an easily understandable manner is still notably lacking. This paper aims to fill this gap by providing a comprehensive guide to the principles of deep learning that is specifically tailored toward radiation oncology.

METHODS

In light of the extensive variety of AI methodologies, this review selectively concentrates on the specific domain of deep learning. It emphasizes the principal categories of deep learning models and delineates the methodologies for training these models effectively.

RESULTS

This review initially delineates the distinctions between AI and deep learning as well as between supervised and unsupervised learning. Subsequently, it elucidates the fundamental principles of major deep learning models, encompassing multilayer perceptrons (MLPs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, generative adversarial networks (GANs), diffusion-based generative models, and reinforcement learning. For each category, it presents representative networks alongside their specific applications in radiation oncology. Moreover, the review outlines critical factors essential for training deep learning models, such as data preprocessing, loss functions, optimizers, and other pivotal training parameters including learning rate and batch size.

CONCLUSION

This review provides a comprehensive overview of deep learning principles tailored toward radiation oncology. It aims to enhance the understanding of AI-based research and software applications, thereby bridging the gap between complex technological concepts and clinical practice in radiation oncology.

Deep learning-based dose prediction for magnetic resonance-guided prostate radiotherapy

BACKGROUND

Daily adaptive radiotherapy, as performed with the Elekta Unity MR-Linac, requires choosing between different adaptation methods, namely ATP (Adapt to Position) and ATS (Adapt to Shape), where the latter requires daily re-contouring to obtain a dose plan tailored to the daily anatomy. These steps are inherently resource-intensive, and quickly predicting the dose distribution and the dosimetric evaluation criteria while the patient is on the table could facilitate a fast selection of adaptation method and decrease the treatment times.

PURPOSE

In this work, we aimed to develop a deep-learning-based dose-prediction pipeline for prostate MR-Linac treatments.

METHODS

Two hundred twelve MR-images, structure sets, and dose distributions from 35 prostate patients treated with 6.1 Gy for 7 or 6 fractions at our MR-Linac were included, split into train/test partitions of 152/60 images, respectively. A deep-learning segmentation network was trained to segment the CTV (prostate), bladder, and rectum. A second network was trained to predict the dose distribution based on manually delineated structures. At inference, the predicted segmentations acted as input to the dose prediction network, and the predicted dose was compared to the true (optimized in the treatment planning system) dose distribution.

RESULTS

Median DSC values from the segmentation network were 0.90/0.94/0.87 for CTV/bladder/rectum. Predicted segmentations as input to the dose prediction resulted in mean differences between predicted and true doses of 0.7%/0.7%/1.7% (relative to the prescription dose) for D98%/D95%/D2% for the CTV. For the bladder, the difference was 0.7%/0.3% for Dmean/D2% and for the rectum 0.1/0.2/0.2 pp (percentage points) for V33Gy/V38Gy/V41Gy. In comparison, true segmentations as input resulted in differences of 1.1%/0.9%/1.6% for CTV, 0.5%/0.4% for bladder, and 0.7/0.4/0.3 pp for the rectum. Only D2% for CTV and Dmean/D2% for bladder were found to be statistically significantly better when using true structures instead of predicted structures as input to the dose prediction.

CONCLUSIONS

Small differences in the fulfillment of clinical dose-volume constraints are seen between utilizing deep-learning predicted structures as input to a dose prediction network and manual structures. Overall mean differences <2% indicate that the dose-prediction pipeline is useful as a decision support tool where differences are >2%.

Enhancing the reliability of deep learning-based head and neck tumour segmentation using uncertainty estimation with multi-modal images

Objective.Deep learning shows promise in autosegmentation of head and neck cancer (HNC) primary tumours (GTV-T) and nodal metastases (GTV-N). However, errors such as including non-tumour regions or missing nodal metastases still occur. Conventional methods often make overconfident predictions, compromising reliability. Incorporating uncertainty estimation, which provides calibrated confidence intervals can address this issue. Our aim was to investigate the efficacy of various uncertainty estimation methods in improving segmentation reliability. We evaluated their confidence levels in voxel predictions and ability to reveal potential segmentation errors.Approach.We retrospectively collected data from 567 HNC patients with diverse cancer sites and multi-modality images (CT, PET, T1-, and T2-weighted MRI) along with their clinical GTV-T/N delineations. Using the nnUNet 3D segmentation pipeline, we compared seven uncertainty estimation methods, evaluating them based on segmentation accuracy (Dice similarity coefficient, DSC), confidence calibration (Expected Calibration Error, ECE), and their ability to reveal segmentation errors (Uncertainty-Error overlap using DSC, UE-DSC).Main results.Evaluated on the hold-out test dataset (n= 97), the median DSC scores for GTV-T and GTV-N segmentation across all uncertainty estimation methods had a narrow range, from 0.73 to 0.76 and 0.78 to 0.80, respectively. In contrast, the median ECE exhibited a wider range, from 0.30 to 0.12 for GTV-T and 0.25 to 0.09 for GTV-N. Similarly, the median UE-DSC also ranged broadly, from 0.21 to 0.38 for GTV-T and 0.22 to 0.36 for GTV-N. A probabilistic network-PhiSeg method consistently demonstrated the best performance in terms of ECE and UE-DSC.Significance.Our study highlights the importance of uncertainty estimation in enhancing the reliability of deep learning for autosegmentation of HNC GTV. The results show that while segmentation accuracy can be similar across methods, their reliability, measured by calibration error and uncertainty-error overlap, varies significantly. Used with visualisation maps, these methods may effectively pinpoint uncertainties and potential errors at the voxel level.

MARes-Net: multi-scale attention residual network for jaw cyst image segmentation

Jaw cyst is a fluid-containing cystic lesion that can occur in any part of the jaw and cause facial swelling, dental lesions, jaw fractures, and other associated issues. Due to the diversity and complexity of jaw images, existing deep-learning methods still have challenges in segmentation. To this end, we propose MARes-Net, an innovative multi-scale attentional residual network architecture. Firstly, the residual connection is used to optimize the encoder-decoder process, which effectively solves the gradient disappearance problem and improves the training efficiency and optimization ability. Secondly, the scale-aware feature extraction module (SFEM) significantly enhances the network's perceptual abilities by extending its receptive field across various scales, spaces, and channel dimensions. Thirdly, the multi-scale compression excitation module (MCEM) compresses and excites the feature map, and combines it with contextual information to obtain better model performance capabilities. Furthermore, the introduction of the attention gate module marks a significant advancement in refining the feature map output. Finally, rigorous experimentation conducted on the original jaw cyst dataset provided by Quzhou People's Hospital to verify the validity of MARes-Net architecture. The experimental data showed that precision, recall, IoU and F1-score of MARes-Net reached 93.84%, 93.70%, 86.17%, and 93.21%, respectively. Compared with existing models, our MARes-Net shows its unparalleled capabilities in accurately delineating and localizing anatomical structures in the jaw cyst image segmentation.

Geometric and dosimetric evaluation for breast and regional nodal auto-segmentation structures

The accuracy of artificial intelligence (AI) generated contours for intact-breast and post-mastectomy radiotherapy plans was evaluated. Geometric and dosimetric comparisons were performed between auto-contours (ACs) and manual-contours (MCs) produced by physicians for target structures. Breast and regional nodal structures were manually delineated on 66 breast cancer patients. ACs were retrospectively generated. The characteristics of the breast/post-mastectomy chestwall (CW) and regional nodal structures (axillary [AxN], supraclavicular [SC], internal mammary [IM]) were geometrically evaluated by Dice similarity coefficient (DSC), mean surface distance, and Hausdorff Distance. The structures were also evaluated dosimetrically by superimposing the MC clinically delivered plans onto the ACs to assess the impact of utilizing ACs with target dose (Vx%) evaluation. Positive geometric correlations between volume and DSC for intact-breast, AxN, and CW were observed. Little or anti correlations between volume and DSC for IM and SC were shown. For intact-breast plans, insignificant dosimetric differences between ACs and MCs were observed for AxNV95% (p = 0.17) and SCV95% (p = 0.16), while IMNV90% ACs and MCs were significantly different. The average V95% for intact-breast MCs (98.4%) and ACs (97.1%) were comparable but statistically different (p = 0.02). For post-mastectomy plans, AxNV95% (p = 0.35) and SCV95% (p = 0.08) were consistent between ACs and MCs, while IMNV90% was significantly different. Additionally, 94.1% of AC-breasts met ΔV95% variation <5% when DSC > 0.7. However, only 62.5% AC-CWs achieved the same metrics, despite AC-CWV95% (p = 0.43) being statistically insignificant. The AC intact-breast structure was dosimetrically similar to MCs. The AC AxN and SC may require manual adjustments. Careful review should be performed for AC post-mastectomy CW and IMN before treatment planning. The findings of this study may guide the clinical decision-making process for the utilization of AI-driven ACs for intact-breast and post-mastectomy plans. Before clinical implementation of this auto-segmentation software, an in-depth assessment of agreement with each local facilities MCs is needed.

The effect of time-delayed contrast-enhanced scanning in determining the gross tumor target volume of large-volume brain metastases

BACKGROUND AND PURPOSE

To assess the variation of large-volume brain metastases (BMs) boundaries and shapes using enhanced magnetic resonance (MR) scanning with different delay times and to provide a basis for determining the gross tumor target volume (GTV) for radiotherapy of BMs.

MATERIALS AND METHODS

We prospectively enrolled 155 patients initially diagnosed with BMs (561 lesions > 1 cm). Contrast-enhanced (CE) T1-weighted imaging scans were performed 1, 3, 5, 10, 18, and 20 min after gadolinium-based contrast agent injection and GTVs were determined as GTV-1min, GTV-3min, GTV-5min, GTV-10min, GTV-18min, and GTV-20min, respectively, which were subsequently fused in different phases. Fusion of the six GTVs was defined as GTV-total, which was set as the reference GTV. The volume, shape, and signal intensity of the GTVs and brain white matter (BWM) were compared at different delay times.

RESULTS

GTV-3min, GTV-5min, GTV-10min, GTV-18min, and GTV-20min volumes increased by 2.2 %, 3.8 %, 6.5 %, 9.5 %, and 10.6 %, respectively (P < 0.05) compared with GTV-1min. Compared with GTV-total, GTV-1min, GTV-3min, GTV-5min, GTV-10min, GTV-18min, and GTV-20min volumes reduced by 25.4 %, 22.1 %, 18.7 %, 15.0 %, 11.2 %, and 10.3 %, respectively (P < 0.05). Compared with GTV-total, 29 (51.8 %) fused GTVs had a volume reduction rate < 5 %, 45 (80.4 %) had a Dice similarity coefficient > 0.95, and all contained GTV-10min, GTV-18min or GTV-20min. The signal intensity ratio between the GTV and BWM peaked at 5 min (0.351 ± 0.24).

CONCLUSION

Enhanced MR scans with different delay times show significant differences in the boundaries and shapes of large-volume BMs, and time-delayed multi-phase CE scanning should be used in GTV determination, with time phases ≥ 10 min being mandatory.

Low-field MRI for use in neurological diseases

PURPOSE OF REVIEW

To review recent clinical uses of low-field magnetic resonance imaging (MRI) to guide incorporation into neurological practice.

RECENT FINDINGS

Use of low-field MRI has been demonstrated in applications including tumours, vascular pathologies, multiple sclerosis, brain injury, and paediatrics. Safety, workflow, and image quality have also been evaluated.

SUMMARY

Low-field MRI has the potential to increase access to critical brain imaging for patients who otherwise may not obtain imaging in a timely manner. This includes areas such as the intensive care unit and emergency room, where patients could be imaged at the point of care rather than be transported to the MRI scanner. Such systems are often more affordable than conventional systems, allowing them to be more easily deployed in resource constrained settings. A variety of systems are available on the market or in a research setting and are currently being used to determine clinical uses for these devices. The utility of such devices must be fully evaluated in clinical scenarios before adoption into standard practice can be achieved. This review summarizes recent clinical uses of low-field MR as well as safety, workflows, and image quality to aid practitioners in assessing this new technology.

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

BACKGROUND AND PURPOSE

Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap.

METHODS AND MATERIALS

A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended.

RESULTS

The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated.

CONCLUSION

A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.

Individualized trajectories in postradiotherapy neurocognitive functioning of patients with brain metastases

Background

The increasing incidence of brain metastases (BMs) and improved survival rates underscore the necessity to investigate the effects of treatments on individuals. The aim of this study was to evaluate the individual trajectories of subjective and objective cognitive performance after radiotherapy in patients with BMs.

Methods

The study population consisted of adult patients with BMs referred for radiotherapy. A semi-structured interview and comprehensive neurocognitive assessment (NCA) were used to assess both subjective and objective cognitive performance before, 3 months and ≥ 11 months after radiotherapy. Reliable change indices were used to identify individual, clinically meaningful changes.

Results

Thirty-six patients completed the 3-month follow-up, and 14 patients completed the ≥ 11-months follow-up. Depending on the domain, subjective cognitive decline was reported by 11-22% of patients. In total, 50% of patients reported subjective decline in at least one cognitive domain. Intracranial progression 3 months postradiotherapy was a risk-factor for self-reported deterioration (P = .031). Objective changes were observed across all domains, with a particular vulnerability for decline in memory at 3 months postradiotherapy. The majority of patients (81%) experienced both a deterioration as well as improvement (eg, mixed response) in objective cognitive functioning. Results were similar for the long-term follow-up (3 to ≥11 months). No risk factors for objective cognitive change 3 months postradiotherapy were identified.

Conclusions

Our study revealed that the majority of patients with BMs will show a mixed cognitive response following radiotherapy, reflecting the complex impact. This underscores the importance of patient-tailored NCAs 3 months postradiotherapy to guide optimal rehabilitation strategies.

Evaluating intra-fractional tumor motion in lung stereotactic radiotherapy with deep inspiration breath-hold

PURPOSE

To evaluate the intra-fractional tumor motion in lung stereotactic body radiotherapy (SBRT) with deep inspiration breath-hold (DIBH), and to investigate the adequacy of the current planning target volume (PTV) margins.

METHODS

Twenty-eight lung SBRT patients with DIBH were selected in this study. Among the lesions, twenty-three were at right or left lower lobe, two at right middle lobe, and three at right or left upper lobe. Post-treatment gated cone-beam computed tomography (CBCT) was acquired to quantify the intra-fractional tumor shift at each treatment. These obtained shifts were then used to calculate the required PTV margin, which was compared with the current applied margin of 5 mm margin in anterior-posterior (AP) and right-left (RL) directions and 8 mm in superior-inferior (SI) direction. The beam delivery time was prolonged with DIBH. The actual beam delivery time with DIBH (Tbeam_DIBH) was compared with the beam delivery time without DIBH (Tbeam_wo_DIBH) for the corresponding SBRT plan.

RESULTS

A total of 113 treatments were analyzed. At six treatments (5.3%), the shifts exceeded the tolerance defined by the current PTV margin. The average shifts were 0.0 ± 1.9 mm, 0.1±1.5 mm, and -0.5 ± 3.7 mm in AP, RL, and SI directions, respectively. The required PTV margins were determined to be 4.5, 3.9, and 7.4 mm in AP, RL, and SI directions, respectively. The average Tbeam_wo_DIBH and Tbeam_DIBH were 2.4 ± 0.4 min and 3.6 ± 1.5 min, respectively. The average treatment slot for lung SBRT with DIBH was 25.3 ± 7.9 min.

CONCLUSION

Intra-fractional tumor motion is the predominant source of treatment uncertainties in CBCT-guided lung SBRT with DIBH. The required PTV margin should be determined based on data specific to each institute, considering different techniques and populations. Our data indicate that our current applied PTV margin is adequate, and it is possible to reduce further in the RL direction. The time increase of Tbeam_DIBH, relative to the treatment slot, is not clinically significant.

Clinical implementation and evaluation of deep learning-assisted automatic radiotherapy treatment planning for lung cancer

PURPOSE

The purpose of the study is to investigate the clinical application of deep learning (DL)-assisted automatic radiotherapy planning for lung cancer.

METHODS

A DL model was developed for predicting patient-specific doses, trained and validated on a dataset of 235 patients with diverse target volumes and prescriptions. The model was integrated into clinical workflow with DL-predicted objective functions. The automatic plans were retrospectively designed for additional 50 treated manual volumetric modulated arc therapy (VMAT) plans. A comparison was made between automatic and manual plans in terms of dosimetric indexes, monitor units (MUs) and planning time. Plan quality metric (PQM) encompassing these indexes was evaluated, with higher PQM values indicating superior plan quality. Qualitative evaluations of two plans were conducted by four reviewers.

RESULTS

The PQM score was 40.7 ± 13.1 for manual plans and 40.8 ± 13.5 for automatic plans (P = 0.75). Compared to manual plans, the targets coverage and homogeneity of automatic plans demonstrated no significant difference. Manual plans exhibited better sparing for lung in V5 (difference: 1.8 ± 4.2 %, P = 0.02), whereas automatic plans showed enhanced sparing for heart in V30 (difference: 1.4 ± 4.7 %, P = 0.02) and for spinal cord in Dmax (difference: 0.7 ± 4.7 Gy, P = 0.04). The planning time and MUs of automatic plans were significantly reduced by 70.5 ± 20.0 min and 97.4 ± 82.1. Automatic plans were deemed acceptable in 88 % of the reviews (176/200).

CONCLUSIONS

The DL-assisted approach for lung cancer notably decreased planning time and MUs, while demonstrating comparable or superior quality relative to manual plans. It has the potential to provide benefit to lung cancer patients.

Improving 3D dose prediction for breast radiotherapy using novel glowing masks and gradient-weighted loss functions

BACKGROUND

The quality of treatment plans for breast cancer can vary greatly. This variation could be reduced by using dose prediction to automate treatment planning. Our work investigates novel methods for training deep-learning models that are capable of producing high-quality dose predictions for breast cancer treatment planning.

PURPOSE

The goal of this work was to compare the performance impact of two novel techniques for deep learning dose prediction models for tangent field treatments for breast cancer. The first technique, a "glowing" mask algorithm, encodes the distance from a contour into each voxel in a mask. The second, a gradient-weighted mean squared error (MSE) loss function, emphasizes the error in high-dose gradient regions in the predicted image.

METHODS

Four 3D U-Net deep learning models were trained using the planning CT and contours of the heart, lung, and tumor bed as inputs. The dataset consisted of 305 treatment plans split into 213/46/46 training/validation/test sets using a 70/15/15% split. We compared the impact of novel "glowing" anatomical mask inputs and a novel gradient-weighted MSE loss function to their standard counterparts, binary anatomical masks, and MSE loss, using an ablation study methodology. To assess performance, we examined the mean error and mean absolute error (ME/MAE) in dose across all within-body voxels, the error in mean dose to heart, ipsilateral lung, and tumor bed, dice similarity coefficient (DSC) across isodose volumes defined by 0%-100% prescribed dose thresholds, and gamma analysis (3%/3 mm).

RESULTS

The combination of novel glowing masks and gradient weighted loss function yielded the best-performing model in this study. This model resulted in a mean ME of 0.40%, MAE of 2.70%, an error in mean dose to heart and lung of -0.10 and 0.01 Gy, and an error in mean dose to the tumor bed of -0.01%. The median DSC at 50/95/100% isodose levels were 0.91/0.87/0.82. The mean 3D gamma pass rate (3%/3 mm) was 93%.

CONCLUSIONS

This study found the combination of novel anatomical mask inputs and loss function for dose prediction resulted in superior performance to their standard counterparts. These results have important implications for the field of radiotherapy dose prediction, as the methods used here can be easily incorporated into many other dose prediction models for other treatment sites. Additionally, this dose prediction model for breast radiotherapy has sufficient performance to be used in an automated planning pipeline for tangent field radiotherapy and has the major benefit of not requiring a PTV for accurate dose prediction.

Robustness evaluation of pencil beam scanning proton therapy treatment planning: A systematic review

Compared to conventional radiotherapy using X-rays, proton therapy, in principle, allows better conformity of the dose distribution to target volumes, at the cost of greater sensitivity to physical, anatomical, and positioning uncertainties. Robust planning, both in terms of plan optimization and evaluation, has gained high visibility in publications on the subject and is part of clinical practice in many centers. However, there is currently no consensus on the methods and parameters to be used for robust optimization or robustness evaluation. We propose to overcome this deficiency by following the modified Delphi consensus method. This method first requires a systematic review of the literature. We performed this review using the PubMed and Web Of Science databases, via two different experts. Potential conflicts were resolved by a third expert. We then explored the different methods before focusing on clinical studies that evaluate robustness on a significant number of patients. Many robustness assessment methods are proposed in the literature. Some are more successful than others and their implementation varies between centers. Moreover, they are not all statistically or mathematically equivalent. The most sophisticated and rigorous methods have seen more limited application due to the difficulty of their implementation and their lack of widespread availability.

Self-reported checklists and quality scoring tools in radiomics: a meta-research

OBJECTIVE

To evaluate the use of reporting checklists and quality scoring tools for self-reporting purposes in radiomics literature.

METHODS

Literature search was conducted in PubMed (date, April 23, 2023). The radiomics literature was sampled at random after a sample size calculation with a priori power analysis. A systematic assessment for self-reporting, including the use of documentation such as completed checklists or quality scoring tools, was conducted in original research papers. These eligible papers underwent independent evaluation by a panel of nine readers, with three readers assigned to each paper. Automatic annotation was used to assist in this process. Then, a detailed item-by-item confirmation analysis was carried out on papers with checklist documentation, with independent evaluation of two readers.

RESULTS

The sample size calculation yielded 117 papers. Most of the included papers were retrospective (94%; 110/117), single-center (68%; 80/117), based on their private data (89%; 104/117), and lacked external validation (79%; 93/117). Only seven papers (6%) had at least one self-reported document (Radiomics Quality Score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD), or Checklist for Artificial Intelligence in Medical Imaging (CLAIM)), with a statistically significant binomial test (p < 0.001). Median rate of confirmed items for all three documents was 81% (interquartile range, 6). For quality scoring tools, documented scores were higher than suggested scores, with a mean difference of - 7.2 (standard deviation, 6.8).

CONCLUSION

Radiomic publications often lack self-reported checklists or quality scoring tools. Even when such documents are provided, it is essential to be cautious, as the accuracy of the reported items or scores may be questionable.

CLINICAL RELEVANCE STATEMENT

Current state of radiomic literature reveals a notable absence of self-reporting with documentation and inaccurate reporting practices. This critical observation may serve as a catalyst for motivating the radiomics community to adopt and utilize such tools appropriately, thereby fostering rigor, transparency, and reproducibility of their research, moving the field forward.

KEY POINTS

• In radiomics literature, there has been a notable absence of self-reporting with documentation. • Even if such documents are provided, it is critical to exercise caution because the accuracy of the reported items or scores may be questionable. • Radiomics community needs to be motivated to adopt and appropriately utilize the reporting checklists and quality scoring tools.

Treatment Planning Methods for Dose Painting by Numbers Treatment in Gamma Knife Radiosurgery

Purpose

Dose painting radiation therapy delivers a nonuniform dose to tumors to account for heterogeneous radiosensitivity. With recent and ongoing development of Gamma Knife machines making large-volume brain tumor treatments more practical, it is increasingly feasible to deliver dose painting treatments. The increased prescription complexity means automated treatment planning is greatly beneficial, and the impact of dose painting on stereotactic radiosurgery (SRS) plan quality has not yet been studied. This research investigates the plan quality achievable for Gamma Knife SRS dose painting treatments when using optimization techniques and automated isocenter placement in treatment planning.

Methods and Materials

Dose painting prescription functions with varying parameters were applied to convert voxel image intensities to prescriptions for 10 sample cases. To study achievable plan quality and optimization, clinically placed isocenters were used with each dose painting prescription and optimized using a semi-infinite linear programming formulation. To study automated isocenter placement, a grassfire sphere-packing algorithm and a clinically available Leksell gamma plan isocenter fill algorithm were used. Plan quality for each optimized treatment plan was measured with dose painting SRS metrics.

Results

Optimization can be used to find high quality dose painting plans, and plan quality is affected by the dose painting prescription method. Polynomial function prescriptions show more achievable plan quality than sigmoid function prescriptions even with high mean dose boost. Automated isocenter placement is shown as a feasible method for dose painting SRS treatment, and increasing the number of isocenters improves plan quality. The computational solve time for optimization is within 5 minutes in most cases, which is suitable for clinical planning.

Conclusions

The impact of dose painting prescription method on achievable plan quality is quantified in this study. Optimization and automated isocenter placement are shown as possible treatment planning methods to obtain high quality plans.

Radiomics in esophagogastric junction cancer: A scoping review of current status and advances

PURPOSE

This scoping review aimed to understand the advances in radiomics in esophagogastric junction (EGJ) cancer and assess the current status of radiomics in EGJ cancer.

METHODS

We conducted systematic searches of PubMed, Embase, and Web of Science databases from January 18, 2012, to January 15, 2023, to identify radiomics articles related to EGJ cancer. Two researchers independently screened the literature, extracted data, and assessed the quality of the studies using the Radiomics Quality Score (RQS) and the METhodological RadiomICs Score (METRICS) tool, respectively.

RESULTS

A total of 120 articles were retrieved from the three databases, and after screening, only six papers met the inclusion criteria. These studies investigated the role of radiomics in differentiating adenocarcinoma from squamous carcinoma, diagnosing T-stage, evaluating HER2 overexpression, predicting response to neoadjuvant therapy, and prognosis in EGJ cancer. The median score percentage of RQS was 34.7% (range from 22.2% to 38.9%). The median score percentage of METRICS was 71.2% (range from 58.2% to 84.9%).

CONCLUSION

Although there is a considerable difference between the RQS and METRICS scores of the included literature, we believe that the research value of radiomics in EGJ cancer has been revealed. In the future, while actively exploring more diagnostic, prognostic, and biological correlation studies in EGJ cancer, greater emphasis should be placed on the standardization and clinical application of radiomics.

Optimization of treatment workflow for 0.35T MR-Linac system

PURPOSE

This study presents a novel and comprehensive framework for evaluating magnetic resonance guided radiotherapy (MRgRT) workflow by integrating the Failure Modes and Effects Analysis (FMEA) approach with Time-Driven Activity-Based Costing (TDABC). We assess the workflow for safety, quality, and economic implications, providing a holistic understanding of the MRgRT implementation. The aim is to offer valuable insights to healthcare practitioners and administrators, facilitating informed decision-making regarding the 0.35T MRIdian MR-Linac system's clinical workflow.

METHODS

For FMEA, a multidisciplinary team followed the TG-100 methodology to assess the MRgRT workflow's potential failure modes. Following the mitigation of primary failure modes and workflow optimization, a treatment process was established for TDABC analysis. The TDABC was applied to both MRgRT and computed tomography guided RT (CTgRT) for typical five-fraction stereotactic body RT (SBRT) treatments, assessing total workflow and costs associated between the two treatment workflows.

RESULTS

A total of 279 failure modes were identified, with 31 categorized as high-risk, 55 as medium-risk, and the rest as low-risk. The top 20% risk priority numbers (RPN) were determined for each radiation oncology care team member. Total MRgRT and CTgRT costs were assessed. Implementing technological advancements, such as real-time multi leaf collimator (MLC) tracking with volumetric modulated arc therapy (VMAT), auto-segmentation, and increasing the Linac dose rate, led to significant cost savings for MRgRT.

CONCLUSION

In this study, we integrated FMEA with TDABC to comprehensively evaluate the workflow and the associated costs of MRgRT compared to conventional CTgRT for five-fraction SBRT treatments. FMEA analysis identified critical failure modes, offering insights to enhance patient safety. TDABC analysis revealed that while MRgRT provides unique advantages, it may involve higher costs. Our findings underscore the importance of exploring cost-effective strategies and key technological advancements to ensure the widespread adoption and financial sustainability of MRgRT in clinical practice.

Development and validation of an MR-driven dose-of-the-day procedure for online adaptive radiotherapy in upper gastrointestinal cancer patients

Objective.To develop and validate a dose-of-the-day (DOTD) treatment plan verification procedure for liver and pancreas cancer patients treated with an magnetic resonance (MR)-Linac system.Approach.DOTD was implemented as an automated process that uses 3D datasets collected during treatment delivery. Particularly, the DOTD pipeline's input included the adapt-to-shape (ATS) plan-i.e. 3D-MR dataset acquired at beginning of online session, anatomical contours, dose distribution-and 3D-MR dataset acquired during beam-on (BON). The DOTD automated analysis included (a) ATS-to-BON image intensity-based deformable image registration (DIR), (b) ATS-to-BON contours mapping via DIR, (c) BON-to-ATS contours copying through rigid registration, (d) determining ATS-to-BON dosimetric differences, and (e) PDF report generation. The DIR process was validated by two expert reviewers. ATS-plans were recomputed on BON datasets to assess dose differences. DOTD analysis was performed retrospectively for 75 treatment fractions (12-liver and 5-pancreas patients).Main results.The accuracy of DOTD process relied on DIR and mapped contours quality. Most DIR-generated contours (99.6%) were clinically acceptable. DICE correlated with depreciation of DIR-based region of interest mapping process. The ATS-BON plan difference was found negligible (<1%). The duodenum and large bowel exhibited highest variations, 24% and 39% from fractional values, for 5-fraction liver and pancreas. For liver 1-fraction, a 62% variation was observed for duodenum.Significance.The DOTD methodology provides an automated approach to quantify 3D dosimetric differences between online plans and their delivery. This analysis offers promise as a valuable tool for plan quality assessment and decision-making in the verification stage of the online workflow.

Electromagnetic Modulation of Cell Behavior: Unraveling the Positive Impacts in a Comprehensive Review

There are numerous effective procedures for cell signaling, in which humans directly transmit detectable signals to cells to govern their essential behaviors. From a biomedical perspective, the cellular response to the combined influence of electrical and magnetic fields holds significant promise in various domains, such as cancer treatment, targeted drug delivery, gene therapy, and wound healing. Among these modern cell signaling methods, electromagnetic fields (EMFs) play a pivotal role; however, there remains a paucity of knowledge concerning the effects of EMFs across all wavelengths. It's worth noting that most wavelengths are incompatible with human cells, and as such, this study excludes them from consideration. In this review, we aim to comprehensively explore the most effective and current EMFs, along with their therapeutic impacts on various cell types. Specifically, we delve into the influence of alternating electromagnetic fields (AEMFs) on diverse cell behaviors, encompassing proliferation, differentiation, biomineralization, cell death, and cell migration. Our findings underscore the substantial potential of these pivotal cellular behaviors in advancing the treatment of numerous diseases. Moreover, AEMFs wield a significant role in the realms of biomaterials and tissue engineering, given their capacity to decisively influence biomaterials, facilitate non-invasive procedures, ensure biocompatibility, and exhibit substantial efficacy. It is worth mentioning that AEMFs often serve as a last-resort treatment option for various diseases. Much about electromagnetic fields remains a mystery to the scientific community, and we have yet to unravel the precise mechanisms through which wavelengths control cellular fate. Consequently, our understanding and knowledge in this domain predominantly stem from repeated experiments yielding similar effects. In the ensuing sections of this article, we delve deeper into our extended experiments and research.

Deep Learning for Automatic Gross Tumor Volumes Contouring in Esophageal Cancer Based on Contrast-Enhanced Computed Tomography Images: A Multi-Institutional Study

PURPOSE

To develop and externally validate an automatic artificial intelligence (AI) tool for delineating gross tumor volume (GTV) in patients with esophageal squamous cell carcinoma (ESCC), which can assist in neo-adjuvant or radical radiation therapy treatment planning.

METHODS AND MATERIALS

In this multi-institutional study, contrast-enhanced CT images from 580 eligible ESCC patients were retrospectively collected. The GTV contours delineated by 2 experts via consensus were used as ground truth. A 3-dimensional deep learning model was developed for GTV contouring in the training cohort and internally and externally validated in 3 validation cohorts. The AI tool was compared against 12 board-certified experts in 25 patients randomly selected from the external validation cohort to evaluate its assistance in improving contouring performance and reducing variation. Contouring performance was measured using dice similarity coefficient (DSC) and average surface distance. Additionally, our previously established radiomics model for predicting pathologic complete response was used to compare AI-generated and ground truth contours, to assess the potential of the AI contouring tool in radiomics analysis.

RESULTS

The AI tool demonstrated good GTV contouring performance in multicenter validation cohorts, with median DSC values of 0.865, 0.876, and 0.866 and median average surface distance values of 0.939, 0.789, and 0.875 mm, respectively. Furthermore, the AI tool significantly improved contouring performance for half of 12 board-certified experts (DSC values, 0.794-0.835 vs 0.856-0.881, P = .003-0.048), reduced the intra- and interobserver variations by 37.4% and 55.2%, respectively, and saved contouring time by 77.6%. In the radiomics analysis, 88.7% of radiomic features from ground truth and AI-generated contours demonstrated stable reproducibility, and similar pathologic complete response prediction performance for these contours (P = .430) was observed.

CONCLUSIONS

Our AI contouring tool can improve GTV contouring performance and facilitate radiomics analysis in ESCC patients, which indicates its potential for GTV contouring during radiation therapy treatment planning and radiomics studies.