Radiomics-enhanced early regression index for predicting treatment response in rectal cancer: a multi-institutional 0.35 T MRI-guided radiotherapy study.

PURPOSE: The accurate prediction of treatment response in locally advanced rectal cancer (LARC) patients undergoing MRI-guided radiotherapy (MRIgRT) is essential for optimising treatment strategies. This multi-institutional study aimed to investigate the potential of radiomics in enhancing the predictive power of a known radiobiological parameter (Early Regression Index, ERITCP) to evaluate treatment response in LARC patients treated with MRIgRT. METHODS: Patients from three international sites were included and divided into training and validation sets. 0.35 T T2*/T1-weighted MR images were acquired during simulation and at each treatment fraction. The biologically effective dose (BED) conversion was used to account for different radiotherapy schemes: gross tumour volume was delineated on the MR images corresponding to specific BED levels and radiomic features were then extracted. Multiple logistic regression models were calculated, combining ERITCP with other radiomic features. The predictive performance of the different models was evaluated on both training and validation sets by calculating the receiver operating characteristic (ROC) curves. RESULTS: A total of 91 patients was enrolled: 58 were used as training, 33 as validation. Overall, pCR was observed in 25 cases. The model showing the highest performance was obtained combining ERITCP at BED = 26 Gy with a radiomic feature (10th percentile of grey level histogram, 10GLH) calculated at BED = 40 Gy. The area under ROC curve (AUC) of this combined model was 0.98 for training set and 0.92 for validation set, significantly higher (p = 0.04) than the AUC value obtained using ERITCP alone (0.94 in training and 0.89 in validation set). CONCLUSION: The integration of the radiomic analysis with ERITCP improves the pCR prediction in LARC patients, offering more precise predictive models to further personalise 0.35 T MRIgRT treatments of LARC patients.

Use of secondary air kerma from dose area product and fluoroscopy time for preventive effective dose estimation in interventional radiology procedures for staff.

INTRODUCTION: interventional radiology workers are potentially exposed to high levels of ionizing radiation, therefore preventive dose estimation is mandatory for the correct risk classification of staff. Effective dose (ED) is a radiation protection quantity strictly related to the secondary air kerma (KS), using appropriate multiplicative conversion factors (ICRP 106). The aim of this work is to evaluate the accuracy ofKSestimated from physically measurable quantities such as dose-area product (DAP) or fluoroscopy time (FT). METHODS: radiological units (n= 4) were characterized in terms of primary beam air kerma and DAP-meter response, consequently defining a DAP-meter correction factor (CF) for each unit.KS, scattered from an anthropomorphic phantom and measured by a digital multimeter, was then compared with the value estimated from DAP and FT. Different combinations of tube voltages, field sizes, current and scattering angles were used to simulate the variation of working conditions. Further measurements were performed to estimate the couch transmission factor for different phantom placements on the operational couch, defining a CF as the mean transmission factor. RESULTS: when no CFs were applied, the measuredKSshowed a median percentage difference of between 33.8% and 115.7% with respect toKSevaluated from DAP, and between -46.3% and 101.8% forKSevaluated from FT. By contrast, when previously defined CFs were applied to the evaluatedKS, the median percentage difference between the measuredKSand the value evaluated from DAP ranged from between -7.94% and 15.0%, and between -66.2% and 17.2% for that evaluated from FT. CONCLUSION: when appropriate CF are applied, the preventive ED estimation from the median DAP value seems to be more conservative and easier to obtain with respect to the one obtained from the FT value. Further measurements should be performed with a personal dosimeter during routine activities to assess the properKSto ED conversion factor.

THUNDER 2: THeragnostic Utilities for Neoplastic DisEases of the Rectum by MRI guided radiotherapy.

BACKGROUND: Neoadjuvant chemoradiation therapy (nCRT) is the standard treatment modality in locally advanced rectal cancer (LARC). Since response to radiotherapy (RT) is dose dependent in rectal cancer, dose escalation may lead to higher complete response rates. The possibility to predict patients who will achieve complete response (CR) is fundamental. Recently, an early tumour regression index (ERI) was introduced to predict pathological CR (pCR) after nCRT in LARC patients. The primary endpoints will be the increase of CR rate and the evaluation of feasibility of delta radiomics-based predictive MRI guided Radiotherapy (MRgRT) model. METHODS: Patients affected by LARC cT2-3, N0-2 or cT4 for anal sphincter involvement N0-2a, M0 without high risk features will be enrolled in the trial. Neoadjuvant CRT will be administered using MRgRT. The initial RT treatment will consist in delivering 55 Gy in 25 fractions on Gross Tumor Volume (GTV) plus the corresponding mesorectum and 45 Gy in 25 fractions on the drainage nodes. Chemotherapy with 5-fluoracil (5-FU) or oral capecitabine will be administered continuously. A 0.35 Tesla MRI will be acquired at simulation and every day during MRgRT. At fraction 10, ERI will be calculated: if ERI will be inferior than 13.1, the patient will continue the original treatment; if ERI will be higher than 13.1 the treatment plan will be reoptimized, intensifying the dose to the residual tumor at the 11th fraction to reach 60.1 Gy. At the end of nCRT instrumental examinations are to be performed in order to restage patients. In case of stable disease or progression, the patient will undergo surgery. In case of major or complete clinical response, conservative approaches may be chosen. Patients will be followed up to evaluate toxicity and quality of life. The number of cases to be enrolled will be 63: all the patients will be treated at Fondazione Policlinico Universitario A. Gemelli IRCCS in Rome. DISCUSSION: This clinical trial investigates the impact of RT dose escalation in poor responder LARC patients identified using ERI, with the aim of increasing the probability of CR and consequently an organ preservation benefit in this group of patients. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT04815694 (25/03/2021).

Radiomics-based prediction of two-year clinical outcome in locally advanced cervical cancer patients undergoing neoadjuvant chemoradiotherapy.

PURPOSE: The aim of this study is to determine if radiomics features extracted from staging magnetic resonance (MR) images could predict 2-year long-term clinical outcome in patients with locally advanced cervical cancer (LACC) after neoadjuvant chemoradiotherapy (NACRT). MATERIALS AND METHODS: We retrospectively enrolled patients with LACC diagnosis who underwent NACRT followed by radical surgery in two different institutions. Radiomics features were extracted from pre-treatment 1.5 T T2w MR images. The predictive performance of each feature was quantified in terms of Wilcoxon-Mann-Whitney test. Among the significant features, Pearson correlation coefficient (PCC) was calculated to quantify the correlation among the different predictors. A logistic regression model was calculated considering the two most significant features at the univariate analysis showing the lowest PCC value. The predictive performance of the model created was quantified out using the area under the receiver operating characteristic curve (AUC). RESULTS: A total of 175 patients were retrospectively enrolled (142 for the training cohort and 33 for the validation one). 1896 radiomic feature were extracted, 91 of which showed significance (p < 0.05) at the univariate analysis. The radiomic model showing the highest predictive value combined the features calculated starting from the gray level co-occurrence-based features. This model achieved an AUC of 0.73 in the training set and 0.91 in the validation set. CONCLUSIONS: The proposed radiomic model showed promising performances in predicting 2-year overall survival before NACRT. Nevertheless, the observed results should be tested in larger studies with consistent external validation cohorts, to confirm their potential clinical use.

Does restaging MRI radiomics analysis improve pathological complete response prediction in rectal cancer patients? A prognostic model development.

PURPOSE: Our study investigated the contribution that the application of radiomics analysis on post-treatment magnetic resonance imaging can add to the assessments performed by an experienced disease-specific multidisciplinary tumor board (MTB) for the prediction of pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC). MATERIALS AND METHODS: This analysis included consecutively retrospective LARC patients who obtained a complete or near-complete response after nCRT and/or a pCR after surgery between January 2010 and September 2019. A three-step radiomics features selection was performed and three models were generated: a radiomics model (rRM), a multidisciplinary tumor board model (yMTB) and a combined model (CM). The predictive performance of models was quantified using the receiver operating characteristic (ROC) curve, evaluating the area under curve (AUC). RESULTS: The analysis involved 144 LARC patients; a total of 232 radiomics features were extracted from the MR images acquired post-nCRT. The yMTB, rRM and CM predicted pCR with an AUC of 0.82, 0.73 and 0.84, respectively. ROC comparison was not significant (p = 0.6) between yMTB and CM. CONCLUSION: Radiomics analysis showed good performance in identifying complete responders, which increased when combined with standard clinical evaluation; this increase was not statistically significant but did improve the prediction of clinical response.

A field strength independent MR radiomics model to predict pathological complete response in locally advanced rectal cancer.

PURPOSE: Aim of this study was to develop a generalised radiomics model for predicting pathological complete response after neoadjuvant chemo-radiotherapy in locally advanced rectal cancer patients using pre-CRT T2-weighted images acquired at a 1.5 T and a 3 T scanner. METHODS: In two institutions, 195 patients were scanned: 136 patients were scanned on a 1.5 T MR scanner, 59 patients on a 3 T MR scanner. Gross tumour volumes were delineated on the MR images and 496 radiomic features were extracted, applying the intensity-based (IB) filter. Features were standardised with Z-score normalisation and an initial feature selection was carried out using Wilcoxon-Mann-Whitney test: The most significant features at 1.5 T and 3 T were selected as main features. Several logistic regression models combining the main features with a third one selected by those resulting significant were elaborated and evaluated in terms of area under curve (AUC). A tenfold cross-validation was repeated 300 times to evaluate the model robustness. RESULTS: Three features were selected: maximum fractal dimension with IB = 0-50, energy and grey-level non-uniformity calculated on the run-length matrix with IB = 0-50. The AUC of the model applied to the whole dataset after cross-validation was 0.72, while values of 0.70 and 0.83 were obtained when 1.5 T and 3 T patients were considered, respectively. CONCLUSIONS: The model elaborated showed good performance, even when data from patients scanned on 1.5 T and 3 T were merged. This shows that magnetic field intensity variability can be overcome by means of selecting appropriate image features.

Characterization of an inorganic scintillator for small-field dosimetry in MR-guided radiotherapy.

INTRODUCTION: Aim of this study is to dosimetrically characterize a new inorganic scintillator designed for magnetic resonance-guided radiotherapy (MRgRT) in the presence of 0.35 tesla magnetic field (B). METHODS: The detector was characterized in terms of signal to noise ratio (SNR), reproducibility, dose linearity, angular response, and dependence by energy, field size, and B orientation using a 6 MV magnetic resonance (MR)-Linac and a water tank. Field size dependence was investigated by measuring the output factor (OF) at 1.5 cm. The results were compared with those measured using other detectors (ion chamber and synthetic diamond) and those calculated using a Monte Carlo (MC) algorithm. Energy dependence was investigated by acquiring a percentage depth dose (PDD) curve at two field sizes (3.32 × 3.32 and 9.96 × 9.96 cm2 ) and repeating the OF measurements at 5 and 10 cm depths. RESULTS: The mean SNR was 116.3 ± 0.6. Detector repeatability was within 1%, angular dependence was <2% and its response variation based on the orientation with respect to the B lines was <1%. The detector has a temporal resolution of 10 Hz and it showed a linear response (R2  = 1) in the dose range investigated. All the OF values measured at 1.5 cm depth using the scintillator are in accordance within 1% with those measured with other detectors and are calculated using the MC algorithm. PDD values are in accordance with MC algorithm only for 3.32 × 3.32 cm2 field. Numerical models can be applied to compensate for energy dependence in case of larger fields. CONCLUSION: The inorganic scintillator in the present form can represent a valuable detector for small-field dosimetry and periodic quality controls at MR-Linacs such as dose stability, OFs, and dose linearity. In particular, the detector can be effectively used for small-field dosimetry at 1.5 cm depth and for PDD measurements if the field dimension of 3.32 × 3.32 cm2 is not exceeded.

Quantitative analysis of MRI-guided radiotherapy treatment process time for tumor real-time gating efficiency.

PURPOSE: Magnetic Resonance-guided radiotherapy (MRgRT) systems allow continuous monitoring of therapy volumes during treatment delivery and personalized respiratory gating approaches. Treatment length may therefore be significantly affected by patient's compliance and breathing control. We quantitatively analyzed treatment process time efficiency (TE ) using data obtained from real-world patient treatment logs to optimize MRgRT delivery settings. METHODS: Data corresponding to the first 100 patients treated with a low T hybrid MRI-Linac system, both in free breathing (FB) and in breath hold inspiration (BHI) were collected. TE has been computed as the percentage difference of the actual single fraction's total treatment time and the predicted treatment process time, as computed by the TPS during plan optimization. Differences between the scheduled and actual treatment room occupancy time were also evaluated. Finally, possible correlations with planning, delivery and clinical parameters with TE were also investigated. RESULTS: Nine hundred and nineteen treatment fractions were evaluated. TE difference between BHI and FB patients' groups was statistically significant and the mean TE were 42.4%, and -0.5% respectively. No correlation was found with TE for BHI and FB groups. Planning, delivering and clinical parameters classified BHI and FB groups, but no correlation with TE was found. CONCLUSION: The use of BHI gating technique can increase the treatment process time significantly. BHI technique could be not always an adequate delivery technique to optimize the treatment process time. Further gating techniques should be considered to improve the use of MRgRT.

On the accuracy of bulk synthetic CT for MR-guided online adaptive radiotherapy.

PURPOSE: MR-guided radiotherapy (MRgRT) relies on the daily assignment of a relative electron density (RED) map to allow the fraction specific dose calculation. One approach to assign the RED map consists of segmenting the daily magnetic resonance image into five different density levels and assigning a RED bulk value to each level to generate a synthetic CT (sCT). The aim of this study is to evaluate the dose calculation accuracy of this approach for applications in MRgRT. METHODS: A planning CT (pCT) was acquired for 26 patients with abdominal and pelvic lesions and segmented in five levels similar to an online approach: air, lung, fat, soft tissue and bone. For each patient, the median RED value was calculated for fat, soft tissue and bone. Two sCTs were generated assigning different bulk values to the segmented levels on pCT: The sCTICRU uses the RED values recommended by ICRU46, and the sCTtailor uses the median patient-specific RED values. The same treatment plan was calculated on two the sCTs and the pCT. The dose calculation accuracy was investigated in terms of gamma analysis and dose volume histogram parameters. RESULTS: Good agreement was found between dose calculated on sCTs and pCT (gamma passing rate 1%/1 mm equal to 91.2% ± 6.9% for sCTICRU and 93.7% ± 5.3% b or sCTtailor). The mean difference in estimating V95 (PTV) was equal to 0.2% using sCTtailor and 1.2% using sCTICRU, respect to pCT values CONCLUSIONS: The bulk sCT guarantees a high level of dose calculation accuracy also in presence of magnetic field, making this approach suitable to MRgRT. This accuracy can be improved by using patient-specific RED values.

Evaluation of a simplified optimizer for MR-guided adaptive RT in case of pancreatic cancer.

PURPOSE: Magnetic resonance-guided adaptive radiotherapy (MRgART) is considered a promising resource for pancreatic cancer, as it allows to online modify the dose distribution according to daily anatomy. This study aims to compare the dosimetric performance of a simplified optimizer implemented on a MR-Linac treatment planning system (TPS) with those obtained using an advanced optimizer implemented on a conventional Linac. METHODS: Twenty patients affected by locally advanced pancreatic cancer (LAPC) were considered. Gross tumor volume (GTV) and surrounding organ at risks (OARs) were contoured on the average 4DCT scan. Planning target volume was generated from GTV by adding an isotropic 3 mm margin and excluding overlap areas with OARs. Treatment plans were generated by using the simple optimizer for the MR-Linac in intensity-modulated radiation therapy (IMRT) and the advanced optimizer for conventional Linac in IMRT and volumetric modulated arc therapy (VMAT) technique. Prescription dose was 40 Gy in five fractions. The dosimetric comparison was performed on target coverage, dosimetric indicators, and low dose diffusion. RESULTS: The simplified optimizer of MR-Linac generated clinically acceptable plans in 80% and optimal plans in 55% of cases. The number of clinically acceptable plans obtained using the advanced optimizer of the conventional Linac with IMRT was the same of MR-Linac, but the percentage of optimal plans was higher (65%). Using the VMAT technique, it is possible to obtain clinically acceptable plan in 95% and optimal plans in 90% of cases. The advanced optimizer combined with VMAT technique ensures higher target dose homogeneity and minor diffusion of low doses, but its actual optimization time is not suitable for MRgART. CONCLUSION: Simplified optimization solutions implemented in the MR-Linac TPS allows to elaborate in most of cases treatment plans dosimetrically comparable with those obtained by using an advanced optimizer. A superior treatment plan quality is possible using the VMAT technique that could represent a breakthrough for the MRgART if the modern advancements will lead to shorter optimization times.

A new frontier of image guidance: Organs at risk avoidance with MRI-guided respiratory-gated intensity modulated radiotherapy: Technical note and report of a case.

The case of a 50-year-old man affected by a rhabdomiosarcoma metastatic lesion in the left flank Is reported. The patient was addressed to 50.4 Gy radiotherapy with concomitant chemotherapy in order to locally control the lesion. A Tri-60-Co magnetic resonance hybrid radiotherapy unit was used for treatment delivery and a respiratory gating protocol was applied for the different breathing phases (Free Breathing, Deep Inspiration Breath Hold and Final Expiration Breath Hold). Three intensity modulated radiation therapy (IMRT) plans were calculated and Final Expiration Breath Hold plan was finally selected due to the absence of PTV coverage differences and better organs at risk sparing (i.e. kidneys). This case report suggests that organs at risk avoidance with MRI-guided respiratory-gated Radiotherapy is feasible and particularly advantageous whenever sparing the organs at risk is of utmost dosimetric or clinical importance.

Delta radiomics for rectal cancer response prediction with hybrid 0.35 T magnetic resonance-guided radiotherapy (MRgRT): a hypothesis-generating study for an innovative personalized medicine approach.

The aim of this study was to evaluate the variation of radiomics features, defined as "delta radiomics", in patients undergoing neoadjuvant radiochemotherapy (RCT) for rectal cancer treated with hybrid magnetic resonance (MR)-guided radiotherapy (MRgRT). The delta radiomics features were then correlated with clinical complete response (cCR) outcome, to investigate their predictive power. A total of 16 patients were enrolled, and 5 patients (31%) showed cCR at restaging examinations. T2*/T1 MR images acquired with a hybrid 0.35 T MRgRT unit were considered for this analysis. An imaging acquisition protocol of 6 MR scans per patient was performed: the first MR was acquired at first simulation (t0) and the remaining ones at fractions 5, 10, 15, 20 and 25. Radiomics features were extracted from the gross tumour volume (GTV), and each feature was correlated with the corresponding delivered dose. The variations of each feature during treatment were quantified, and the ratio between the values calculated at different dose levels and the one extracted at t0 was calculated too. The Wilcoxon-Mann-Whitney test was performed to identify the features whose variation can be predictive of cCR, assessed with a MR acquired 6 weeks after RCT and digital examination. The most predictive feature ratios in cCR prediction were the L_least and glnu ones, calculated at the second week of treatment (22 Gy) with a p value = 0.001. Delta radiomics approach showed promising results and the quantitative analysis of images throughout MRgRT treatment can successfully predict cCR offering an innovative personalized medicine approach to rectal cancer treatment.

Fractal-based radiomic approach to predict complete pathological response after chemo-radiotherapy in rectal cancer.

The aim of this study was to propose a methodology to investigate the tumour heterogeneity and evaluate its ability to predict pathologically complete response (pCR) after chemo-radiotherapy (CRT) in locally advanced rectal cancer (LARC). This approach consisted in normalising the pixel intensities of the tumour and identifying the different sub-regions using an intensity-based thresholding. The spatial organisation of these subpopulations was quantified using the fractal dimension (FD). This approach was implemented in a radiomic workflow and applied to 198 T2-weighted pre-treatment magnetic resonance (MR) images of LARC patients. Three types of features were extracted from the gross tumour volume (GTV): morphological, statistical and fractal features. Feature selection was performed using the Wilcoxon test and a logistic regression model was calculated to predict the pCR probability after CRT. The model was elaborated considering the patients treated in two institutions: Fondazione Policlinico Universitario "Agostino Gemelli" of Rome (173 cases, training set) and University Medical Centre of Maastricht (25 cases, validation set). The results obtained showed that the fractal parameters of the subpopulations have the highest performance in predicting pCR. The predictive model elaborated had an area under the curve (AUC) equal to 0.77 ± 0.07. The model reliability was confirmed by the validation set (AUC = 0.79 ± 0.09). This study suggests that the fractal analysis can play an important role in radiomics, providing valuable information not only about the GTV structure, but also about its inner subpopulations.

Sum signal dosimetry: A new approach for high dose quality assurance with Gafchromic EBT3.

Gafchromic EBT3 film dosimetry in radiosurgery (RS) and hypofractionated radiotherapy (HRT) is complicated by the limited film accuracy at high fractional doses. The aim of this study is to develop and evaluate sum signal (SS) film dosimetry to increase dose resolution at high fractional doses, thus allowing for use of EBT3 for dose distribution verification of RS/HRT treatments. To characterize EBT3 dose-response, a calibration was performed in the dose range 0.44-26.43 Gy. Red (RC) and green (GC) channel net optical densities were linearly added to produce the SS. Dose resolution and overall accuracy of the dosimetric protocol were estimated and compared for SS,RC, and GC. A homemade Matlab software was developed to compare, in terms of gamma analysis, dose distributions delivered by a Cyberknife on EBT3 films to dose distributions calculated by the treatment planning system. The new SS and conventional single channel (SC) methods were compared, using 3%/1 and 4%/1 mm acceptance criteria, for 20 patient plans. Our analysis shows that the SS dose-response curve is characterized by a steeper trend in comparison with SC, with SS providing a higher dose resolution in the whole dose range investigated. Gamma analysis confirms that the percentage of points satisfying the agreement criteria is significantly higher for SS compared to SC: 95.03% vs. 88.41% (P = 0.014) for 3%/1 mm acceptance criteria and 97.24% vs. 93.58% (P = 0.048) for 4%/1 mm acceptance criteria. This study demonstrates that the SS approach is a new and effective method to improve dosimetric accuracy in the framework of the RS-HRT patient-specific quality assurance protocol.

Evaluation of the extent of resection of intracranial tumors with virtual intraoperative MRI: a case series.

OBJECTIVE: Intraoperative MRI (iMRI) is the gold-standard technique for intraoperative evaluation of the extent of resection in brain tumor surgery. Unfortunately, it is currently available at only a few neurosurgical centers. A commercially available software, Virtual iMRI Cranial, provides an elastic fusion between preoperative MRI and intraoperative CT (iCT). The aim of this study was to evaluate the accuracy of this software in determining the presence of residual tumor. METHODS: Virtual iMRI was performed in patients who underwent iCT after intracranial tumor resection. The results of the software in terms of presence or absence of tumor residual were then compared with postoperative MRI performed within 48 hours after surgery to evaluate the diagnostic accuracy of virtual iMRI. RESULTS: Sixty-six patients were included in the present study. The virtual iMRI findings were concordant with the postoperative MRI data in 35 cases (53%) in the detection of tumor residual (p = 0.006). No false-negative findings (i.e., presence of residual on postoperative MRI and absence of residual on virtual iMRI) were encountered. Virtual iMRI had a sensitivity of 1 (95% CI 0.86-1), specificity of 0.26 (95% CI 0.14-0.42), positive predictive value of 0.44 (95% CI 0.3-0.58), and negative predictive value of 1 (95% CI 0.72-1). Subgroup analysis revealed that the virtual iMRI findings were concordant with postoperative MRI findings in all cases (n = 9) of lower-grade glioma (LGG) with a sensitivity of 1 (95% CI 0.59-1) and a specificity of 1 (95% CI 0.16-1) (p = 0.003); a statistically significant association was also found for grade 4 gliomas with a sensitivity of 1 (95% CI 0.69-1) and a specificity of 0.33 (95% CI 0.08-0.7) (p = 0.046) (19 patients). No significant association was found when considering meningiomas or metastases. CONCLUSIONS: The commercially available virtual iMRI can predict the presence or absence of tumor residual with high sensitivity. The diagnostic accuracy of this method was higher in LGGs and much lower for meningiomas or metastases; these findings must be evaluated in prospective studies in a larger population.

Real-time motion management in MRI-guided radiotherapy: Current status and AI-enabled prospects.

MRI-guided radiotherapy (MRIgRT) is a highly complex treatment modality, allowing adaptation to anatomical changes occurring from one treatment day to the other (inter-fractional), but also to motion occurring during a treatment fraction (intra-fractional). In this vision paper, we describe the different steps of intra-fractional motion management during MRIgRT, from imaging to beam adaptation, and the solutions currently available both clinically and at a research level. Furthermore, considering the latest developments in the literature, a workflow is foreseen in which motion-induced over- and/or under-dosage is compensated in 3D, with minimal impact to the radiotherapy treatment time. Considering the time constraints of real-time adaptation, a particular focus is put on artificial intelligence (AI) solutions as a fast and accurate alternative to conventional algorithms.

Auto-segmentation of pelvic organs at risk on 0.35T MRI using 2D and 3D Generative Adversarial Network models.

PURPOSE: Manual recontouring of targets and Organs At Risk (OARs) is a time-consuming and operator-dependent task. We explored the potential of Generative Adversarial Networks (GAN) to auto-segment the rectum, bladder and femoral heads on 0.35T MRIs to accelerate the online MRI-guided-Radiotherapy (MRIgRT) workflow. METHODS: 3D planning MRIs from 60 prostate cancer patients treated with 0.35T MR-Linac were collected. A 3D GAN architecture and its equivalent 2D version were trained, validated and tested on 40, 10 and 10 patients respectively. The volumetric Dice Similarity Coefficient (DSC) and 95th percentile Hausdorff Distance (HD95th) were computed against expert drawn ground-truth delineations. The networks were also validated on an independent external dataset of 16 patients. RESULTS: In the internal test set, the 3D and 2D GANs showed DSC/HD95th of 0.83/9.72 mm and 0.81/10.65 mm for the rectum, 0.92/5.91 mm and 0.85/15.72 mm for the bladder, and 0.94/3.62 mm and 0.90/9.49 mm for the femoral heads. In the external test set, the performance was 0.74/31.13 mm and 0.72/25.07 mm for the rectum, 0.92/9.46 mm and 0.88/11.28 mm for the bladder, and 0.89/7.00 mm and 0.88/10.06 mm for the femoral heads. The 3D and 2D GANs required on average 1.44 s and 6.59 s respectively to generate the OARs' volumetric segmentation for a single patient. CONCLUSIONS: The proposed 3D GAN auto-segments pelvic OARs with high accuracy on 0.35T, in both the internal and the external test sets, outperforming its 2D equivalent in both segmentation robustness and volume generation time.

Impact of bias field correction on 0.35 T pelvic MR images: evaluation on generative adversarial network-based OARs' auto-segmentation and visual grading assessment.

Purpose: Magnetic resonance imaging (MRI)-guided radiotherapy enables adaptive treatment plans based on daily anatomical changes and accurate organ visualization. However, the bias field artifact can compromise image quality, affecting diagnostic accuracy and quantitative analyses. This study aims to assess the impact of bias field correction on 0.35 T pelvis MRIs by evaluating clinical anatomy visualization and generative adversarial network (GAN) auto-segmentation performance. Materials and methods: 3D simulation MRIs from 60 prostate cancer patients treated on MR-Linac (0.35 T) were collected and preprocessed with the N4ITK algorithm for bias field correction. A 3D GAN architecture was trained, validated, and tested on 40, 10, and 10 patients, respectively, to auto-segment the organs at risk (OARs) rectum and bladder. The GAN was trained and evaluated either with the original or the bias-corrected MRIs. The Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD95th) were computed for the segmented volumes of each patient. The Wilcoxon signed-rank test assessed the statistical difference of the metrics within OARs, both with and without bias field correction. Five radiation oncologists blindly scored 22 randomly chosen patients in terms of overall image quality and visibility of boundaries (prostate, rectum, bladder, seminal vesicles) of the original and bias-corrected MRIs. Bennett's S score and Fleiss' kappa were used to assess the pairwise interrater agreement and the interrater agreement among all the observers, respectively. Results: In the test set, the GAN trained and evaluated on original and bias-corrected MRIs showed DSC/HD95th of 0.92/5.63 mm and 0.92/5.91 mm for the bladder and 0.84/10.61 mm and 0.83/9.71 mm for the rectum. No statistical differences in the distribution of the evaluation metrics were found neither for the bladder (DSC: p = 0.07; HD95th: p = 0.35) nor for the rectum (DSC: p = 0.32; HD95th: p = 0.63). From the clinical visual grading assessment, the bias-corrected MRI resulted mostly in either no change or an improvement of the image quality and visualization of the organs' boundaries compared with the original MRI. Conclusion: The bias field correction did not improve the anatomy visualization from a clinical point of view and the OARs' auto-segmentation outputs generated by the GAN.

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.

Patient-specific transfer learning for auto-segmentation in adaptive 0.35 T MRgRT of prostate cancer: a bi-centric evaluation.

BACKGROUND: Online adaptive radiation therapy (RT) using hybrid magnetic resonance linear accelerators (MR-Linacs) can administer a tailored radiation dose at each treatment fraction. Daily MR imaging followed by organ and target segmentation adjustments allow to capture anatomical changes, improve target volume coverage, and reduce the risk of side effects. The introduction of automatic segmentation techniques could help to further improve the online adaptive workflow by shortening the re-contouring time and reducing intra- and inter-observer variability. In fractionated RT, prior knowledge, such as planning images and manual expert contours, is usually available before irradiation, but not used by current artificial intelligence-based autocontouring approaches. PURPOSE: The goal of this study was to train convolutional neural networks (CNNs) for automatic segmentation of bladder, rectum (organs at risk, OARs), and clinical target volume (CTV) for prostate cancer patients treated at 0.35 T MR-Linacs. Furthermore, we tested the CNNs generalization on data from independent facilities and compared them with the MR-Linac treatment planning system (TPS) propagated structures currently used in clinics. Finally, expert planning delineations were utilized for patient- (PS) and facility-specific (FS) transfer learning to improve auto-segmentation of CTV and OARs on fraction images. METHODS: In this study, data from fractionated treatments at 0.35 T MR-Linacs were leveraged to develop a 3D U-Net-based automatic segmentation. Cohort C1 had 73 planning images and cohort C2 had 19 planning and 240 fraction images. The baseline models (BMs) were trained solely on C1 planning data using 53 MRIs for training and 10 for validation. To assess their accuracy, the models were tested on three data subsets: (i) 10 C1 planning images not used for training, (ii) 19 C2 planning, and (iii) 240 C2 fraction images. BMs also served as a starting point for FS and PS transfer learning, where the planning images from C2 were used for network parameter fine tuning. The segmentation output of the different trained models was compared against expert ground truth by means of geometric metrics. Moreover, a trained physician graded the network segmentations as well as the segmentations propagated by the clinical TPS. RESULTS: The BMs showed dice similarity coefficients (DSC) of 0.88(4) and 0.93(3) for the rectum and the bladder, respectively, independent of the facility. CTV segmentation with the BM was the best for intermediate- and high-risk cancer patients from C1 with DSC=0.84(5) and worst for C2 with DSC=0.74(7). The PS transfer learning brought a significant improvement in the CTV segmentation, yielding DSC=0.72(4) for post-prostatectomy and low-risk patients and DSC=0.88(5) for intermediate- and high-risk patients. The FS training did not improve the segmentation accuracy considerably. The physician's assessment of the TPS-propagated versus network-generated structures showed a clear advantage of the latter. CONCLUSIONS: The obtained results showed that the presented segmentation technique has potential to improve automatic segmentation for MR-guided RT.