ABSTRACT
BACKGROUND AND PURPOSE: Brain tumors are in general treated with a maximal safe resection followed by radiotherapy of remaining tumor including the resection cavity (RC) and chemotherapy. Anatomical changes of the RC during radiotherapy can have impact on the coverage of the target volume. The aim of the current study was to quantify the potential changes of the RC and to identify risk factors for RC changes. MATERIALS AND METHODS: Sixteen patients treated with pencil beam scanning proton therapy between October 2019 and April 2020 were retrospectively analyzed. The RC was delineated on pre-treatment computed tomography (CT) and magnetic resonance imaging, and weekly CT-scans during treatment. Isotropic expansions were applied to the pre-treatment RC (1-5 mm). The percentage of volume of the RC during treatment within the expanded pre-treatment volumes was quantified. Potential risk factors (volume of RC, time interval surgery-radiotherapy and relationship of RC to the ventricles) were evaluated using Spearman's rank correlation coefficient. RESULTS: The average variation in relative RC volume during treatment was 26.1% (SD 34.6%). An expansion of 4 mm was required to cover > 95% of the RC volume in > 90% of patients. There was a significant relationship between the absolute volume of the pre-treatment RC and the volume changes during treatment (Spearman's ρ = - 0.644; p = 0.007). CONCLUSION: RCs are dynamic after surgery. Potentially, an additional margin in brain cancer patients with an RC should be considered, to avoid insufficient target coverage. Future research on local recurrence patterns is recommended.
Subject(s)
Brain Neoplasms , Radiotherapy, Intensity-Modulated , Humans , Retrospective Studies , Combined Modality Therapy , Tomography, X-Ray Computed , Radiotherapy Planning, Computer-Assisted , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/radiotherapy , Brain Neoplasms/surgery , Brain/diagnostic imaging , Brain/surgery , Radiotherapy DosageABSTRACT
Rising incidence and mortality of cancer have led to an incremental amount of research in the field. To learn from preexisting data, it has become important to capture maximum information related to disease type, stage, treatment, and outcomes. Medical imaging reports are rich in this kind of information but are only present as free text. The extraction of information from such unstructured text reports is labor-intensive. The use of Natural Language Processing (NLP) tools to extract information from radiology reports can make it less time-consuming as well as more effective. In this study, we have developed and compared different models for the classification of lung carcinoma reports using clinical concepts. This study was approved by the institutional ethics committee as a retrospective study with a waiver of informed consent. A clinical concept-based classification pipeline for lung carcinoma radiology reports was developed using rule-based as well as machine learning models and compared. The machine learning models used were XGBoost and two more deep learning model architectures with bidirectional long short-term neural networks. A corpus consisting of 1700 radiology reports including computed tomography (CT) and positron emission tomography/computed tomography (PET/CT) reports were used for development and testing. Five hundred one radiology reports from MIMIC-III Clinical Database version 1.4 was used for external validation. The pipeline achieved an overall F1 score of 0.94 on the internal set and 0.74 on external validation with the rule-based algorithm using expert input giving the best performance. Among the machine learning models, the Bi-LSTM_dropout model performed better than the ML model using XGBoost and the Bi-LSTM_simple model on internal set, whereas on external validation, the Bi-LSTM_simple model performed relatively better than other 2. This pipeline can be used for clinical concept-based classification of radiology reports related to lung carcinoma from a huge corpus and also for automated annotation of these reports.
Subject(s)
Carcinoma , Radiology , Humans , Retrospective Studies , Positron Emission Tomography Computed Tomography , Natural Language Processing , LungABSTRACT
OBJECTIVE: As preservation of cognitive functioning increasingly becomes important in the light of ameliorated survival after intracranial tumor treatments, identification of eloquent brain areas would enable optimization of these treatments. METHODS: This cohort study enrolled adult intracranial tumor patients who received neuropsychological assessments pre-irradiation, estimating processing speed, verbal fluency and memory. Anatomical magnetic resonance imaging scans were used for multivariate voxel-wise lesion-symptom predictions of the test scores (corrected for age, gender, educational level, histological subtype, surgery, and tumor volume). Potential effects of histological and molecular subtype and corresponding WHO grades on the risk of cognitive impairment were investigated using Chi square tests. P-values were adjusted for multiple comparisons (p < .001 and p < .05 for voxel- and cluster-level, resp.). RESULTS: A cohort of 179 intracranial tumor patients was included [aged 19-85 years, median age (SD) = 58.46 (14.62), 50% females]. In this cohort, test-specific impairment was detected in 20-30% of patients. Higher WHO grade was associated with lower processing speed, cognitive flexibility and delayed memory in gliomas, while no acute surgery-effects were found. No grading, nor surgery effects were found in meningiomas. The voxel-wise analyses showed that tumor locations in left temporal areas and right temporo-parietal areas were related to verbal memory and processing speed, respectively. INTERPRETATION: Patients with intracranial tumors affecting the left temporal areas and right temporo-parietal areas might specifically be vulnerable for lower verbal memory and processing speed. These specific patients at-risk might benefit from early-stage interventions. Furthermore, based on future validation studies, imaging-informed surgical and radiotherapy planning could further be improved.
Subject(s)
Brain Neoplasms , Glioma , Meningeal Neoplasms , Female , Humans , Adult , Male , Cohort Studies , Brain Neoplasms/complications , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/pathology , Glioma/pathology , Neuropsychological Tests , Magnetic Resonance Imaging/methodsABSTRACT
PURPOSE: Reduced temporal muscle thickness (TMT) has recently been postulated as a prognostic imaging marker and an objective tool to assess patients frailty in glioblastoma. Our aim is to investigate the correlation of TMT and systemic muscle loss to confirm that TMT is an adequate surrogate marker of sarcopenia in newly diagnosed glioblastoma patients. METHODS: TMT was assessed on preoperative MR-images and skeletal muscle area (SMA) was assessed at the third lumbar vertebra on preoperative abdominal CT-scans. Previous published TMT sex-specific cut-off values were used to classify patients as 'patient at risk of sarcopenia' or 'patient with normal muscle status'. Correlation between TMT and SMA was assessed using Spearman's rank correlation coefficient. RESULTS: Sixteen percent of the 245 included patients were identified as at risk of sarcopenia. The mean SMA of glioblastoma patients at risk of sarcopenia (124.3 cm2, SD 30.8 cm2) was significantly lower than the mean SMA of patients with normal muscle status (146.3 cm2, SD 31.1 cm2, P < .001). We found a moderate association between TMT and SMA in the patients with normal muscle status (Spearman's rho 0.521, P < .001), and a strong association in the patients at risk of sarcopenia (Spearman's rho 0.678, P < .001). CONCLUSION: Our results confirm the use of TMT as a surrogate marker of total body skeletal muscle mass in glioblastoma, especially in frail patients at risk of sarcopenia. TMT can be used to identify patients with muscle loss early in the disease process, which enables the implementation of adequate intervention strategies.
Subject(s)
Glioblastoma , Sarcopenia , Male , Female , Humans , Glioblastoma/complications , Glioblastoma/diagnostic imaging , Glioblastoma/pathology , Sarcopenia/diagnostic imaging , Sarcopenia/etiology , Temporal Muscle/pathology , Tomography, X-Ray Computed , Muscle, Skeletal/diagnostic imaging , Muscle, Skeletal/pathologyABSTRACT
BACKGROUND: Dose-guided adaptive radiation therapy (DGART) is the systematic evaluation and adaptation of the dose delivery during treatment for an individual patient. The aim of this study is to define quantitative action levels for DGART by evaluating changes in 3D dose metrics in breast cancer and correlate them with clinical expert evaluation. MATERIAL AND METHODS: Twenty-three breast cancer treatment plans were evaluated, that were clinically adapted based on institutional IGRT guidelines. Reasons for adaptation were variation in seroma, hematoma, edema, positioning or problems using voluntary deep inspiration breath hold. Sixteen patients received a uniform dose to the breast (clinical target volume 1; CTV1). Six patients were treated with a simultaneous integrated boost to CTV2. The original plan was copied to the CT during treatment (re-CT) or to the stitched cone-beam CT (CBCT). Clinical expert evaluation of the re-calculated dose distribution and extraction of dose-volume histogram (DVH) parameters were performed. The extreme scenarios were evaluated, assuming all treatment fractions were given to the original planning CT (pCT), re-CT or CBCT. Reported results are mean ± SD. RESULTS: DVH results showed a mean dose (Dmean) difference between pCT and re-CT of -0.4 ± 1.4% (CTV1) and -1.4 ± 2.1% (CTV2). The difference in V95% was -2.6 ± 4.4% (CTV1) and -9.8 ± 8.3% (CTV2). Clinical evaluation and DVH evaluation resulted in a recommended adaptation in 17/23 or 16/23 plans, respectively. Applying thresholds on the DVH parameters: Dmean CTV, V95% CTV, Dmax, mean lung dose, volume exceeding 107% (uniform dose) or 90% (SIB) of the prescribed dose enabled the identification of patients with an assumed clinically relevant dose difference, with a sensitivity of 0.89 and specificity of 1.0. Re-calculation on CBCT imaging identified the same plans for adaptation as re-CT imaging. CONCLUSIONS: Clinical expert evaluation can be related to quantitative DVH parameters on re-CT or CBCT imaging to select patients for DGART.
Subject(s)
Breast Neoplasms/radiotherapy , Decision Support Techniques , Imaging, Three-Dimensional/methods , Organs at Risk/radiation effects , Radiotherapy Planning, Computer-Assisted/methods , Cone-Beam Computed Tomography/methods , Female , Humans , Image Processing, Computer-Assisted/methods , Radiotherapy Dosage , Radiotherapy, Intensity-Modulated/methods , Retrospective StudiesABSTRACT
PURPOSE: Multiple imaging techniques are nowadays available for clinical in-vivo visualization of tumour biology. FDG PET/CT identifies increased tumour metabolism, hypoxia PET visualizes tumour oxygenation and dynamic contrast-enhanced (DCE) CT characterizes vasculature and morphology. We explored the relationships among these biological features in patients with non-small-cell lung cancer (NSCLC) at both the patient level and the tumour subvolume level. METHODS: A group of 14 NSCLC patients from two ongoing clinical trials (NCT01024829 and NCT01210378) were scanned using FDG PET/CT, HX4 PET/CT and DCE CT prior to chemoradiotherapy. Standardized uptake values (SUV) in the primary tumour were calculated for the FDG and hypoxia HX4 PET/CT scans. For hypoxia imaging, the hypoxic volume, fraction and tumour-to-blood ratio (TBR) were also defined. Blood flow and blood volume were obtained from DCE CT imaging. A tumour subvolume analysis was used to quantify the spatial overlap between subvolumes. RESULTS: At the patient level, negative correlations were observed between blood flow and the hypoxia parameters (TBR >1.2): hypoxic volume (-0.65, p = 0.014), hypoxic fraction (-0.60, p = 0.025) and TBR (-0.56, p = 0.042). At the tumour subvolume level, hypoxic and metabolically active subvolumes showed an overlap of 53 ± 36 %. Overlap between hypoxic sub-volumes and those with high blood flow and blood volume was smaller: 15 ± 17 % and 28 ± 28 %, respectively. Half of the patients showed a spatial mismatch (overlap <5 %) between increased blood flow and hypoxia. CONCLUSION: The biological imaging features defined in NSCLC tumours showed large interpatient and intratumour variability. There was overlap between hypoxic and metabolically active subvolumes in the majority of tumours, there was spatial mismatch between regions with high blood flow and those with increased hypoxia.
Subject(s)
Carcinoma, Non-Small-Cell Lung/diagnostic imaging , Lung Neoplasms/diagnostic imaging , Multimodal Imaging , Oxygen/metabolism , Positron-Emission Tomography , Tomography, X-Ray Computed , Carcinoma, Non-Small-Cell Lung/metabolism , Carcinoma, Non-Small-Cell Lung/pathology , Cell Hypoxia , Female , Fluorodeoxyglucose F18 , Humans , Lung Neoplasms/metabolism , Lung Neoplasms/pathology , Male , Nitroimidazoles , Oxygen Consumption , Radiopharmaceuticals , TriazolesABSTRACT
BACKGROUND AND PURPOSE: Increased tumour hypoxia is associated with a worse overall survival in patients with head and neck squamous cell carcinoma (HNSCC). The aims of this study were to evaluate treatment-associated changes in [18F]HX4-PET, hypoxia-related blood biomarkers, and their interdependence. MATERIAL AND METHODS: [18F]HX4-PET/CT scans of 20 patients with HNSCC were acquired at baseline and after ±20Gy of radiotherapy. Within the gross-tumour-volumes (GTV; primary and lymph nodes), mean and maximum standardized uptake values, the hypoxic fraction (HF) and volume (HV) were calculated. Also, the changes in spatial uptake pattern were evaluated using [18F]HX4-PET/CT imaging. For all patients, the plasma concentration of CAIX, osteopontin and VEGF was assessed. RESULTS: At baseline, tumour hypoxia was detected in 69 % (22/32) of the GTVs. During therapy, we observed a significant decrease in all image parameters. The HF decreased from 21.7 ± 19.8 % (baseline) to 3.6 ± 10.0 % (during treatment; P < 0.001). Only two patients had a HV > 1 cm3 during treatment, which was located for >98 % within the baseline HV. During treatment, no significant changes in plasma CAIX or VEGF were observed, while osteopontin was increased. CONCLUSIONS: [18F]HX4-PET/CT imaging allows monitoring changes in hypoxia during (chemo)radiotherapy whereas the blood biomarkers were not able to detect a treatment-associated decrease in hypoxia.
Subject(s)
Biomarkers, Tumor/blood , Head and Neck Neoplasms/radiotherapy , Imidazoles , Positron-Emission Tomography/methods , Triazoles , Tumor Hypoxia/radiation effects , Aged , Female , Head and Neck Neoplasms/blood , Head and Neck Neoplasms/diagnosis , Humans , Male , Middle Aged , Radiopharmaceuticals , Reproducibility of Results , Sensitivity and Specificity , Treatment OutcomeABSTRACT
PURPOSE: Hypoxia is an important factor influencing tumor progression and treatment efficacy. The aim of this study was to investigate the repeatability of hypoxia PET imaging with [(18)F]HX4 in patients with head and neck and lung cancer. METHODS: Nine patients with lung cancer and ten with head and neck cancer were included in the analysis (NCT01075399). Two sequential pretreatment [(18)F]HX4 PET/CT scans were acquired within 1 week. The maximal and mean standardized uptake values (SUVmax and SUVmean) were defined and the tumor-to-background ratios (TBR) were calculated. In addition, hypoxic volumes were determined as the volume of the tumor with a TBR >1.2 (HV1.2). Bland Altman analysis of the uptake parameters was performed and coefficients of repeatability were calculated. To evaluate the spatial repeatability of the uptake, the PET/CT images were registered and a voxel-wise comparison of the uptake was performed, providing a correlation coefficient. RESULTS: All parameters of [(18)F]HX4 uptake were significantly correlated between scans: SUVmax (r = 0.958, p < 0.001), SUVmean (r = 0.946, p < 0.001), TBRmax (r = 0.962, p < 0.001) and HV1.2 (r = 0.995, p < 0.001). The relative coefficients of repeatability were 15 % (SUVmean), 17 % (SUVmax) and 17 % (TBRmax). Voxel-wise analysis of the spatial uptake pattern within the tumors provided an average correlation of 0.65 ± 0.14. CONCLUSION: Repeated hypoxia PET scans with [(18)F]HX4 provide reproducible and spatially stable results in patients with head and neck cancer and patients with lung cancer. [(18)F]HX4 PET imaging can be used to assess the hypoxic status of tumors and has the potential to aid hypoxia-targeted treatments.
Subject(s)
Head and Neck Neoplasms/diagnostic imaging , Head and Neck Neoplasms/pathology , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/pathology , Nitroimidazoles , Positron-Emission Tomography , Triazoles , Aged , Biological Transport , Cell Hypoxia , Female , Head and Neck Neoplasms/metabolism , Humans , Lung Neoplasms/metabolism , Male , Middle Aged , Nitroimidazoles/metabolism , Prospective Studies , Reproducibility of Results , Triazoles/metabolismABSTRACT
BACKGROUND: To investigate the effect of hypoxia tracer properties on positron emission tomography (PET) image quality for three tracers [18F]-fluoromisonidazole (FMISO), [18F]-fluoroazomycinarabinoside (FAZA) and [18F]-flortanidazole (HX4), using mathematical simulations based on microscopic tumor tissue sections. MATERIAL AND METHODS: Oxygen distribution and tracer binding was mathematically simulated on immunohistochemically stained cross-sections of tumor xenografts. Tracer diffusion properties were determined based on available literature. Blood activity and clearance over a four-hour period post-injection (p.i.) were derived from clinical dynamic PET scans of patients suffering from head and neck or bronchial cancer. Simulations were performed both for average patient blood activities and for individual patients, and image contrast between normoxic and hypoxic tissue areas was determined over this four-hour period p.i. RESULTS: On average, HX4 showed a six-fold higher clearance than FMISO and an almost three-fold higher clearance than FAZA based on the clinical PET data. The absolute variation in clearance was significantly higher for HX4 than for FMISO (standard deviations of 5.75 *10-5 s-1 vs. 1.55 *10-5 s-1). The absolute tracer activity in these scans at four hours p.i. was highest for FMISO and lowest for HX4. Simulated contrast at four hours p.i. was highest for HX4 (2.39), while FMISO and FAZA were comparable (1.67 and 1.75, respectively). Variations in contrast of 7-11% were observed for each tracer depending on the vascularization patterns of the chosen tissue. Higher variations in clearance for HX4 resulted in an increased inter-patient variance in simulated contrast at four hours p.i. CONCLUSIONS: In line with recent experimental and clinical data, the results suggest that HX4 is a promising new tracer that provides high image contrast four hours p.i., though inter-patient variance can be very high. Nevertheless, the widely used tracer FMISO provides a robust and reproducible signal four hours p.i., but with a lower contrast. The simulations revealed tracer clearance to be the key factor in determining image contrast.
Subject(s)
Imidazoles/pharmacokinetics , Misonidazole/analogs & derivatives , Models, Theoretical , Nitroimidazoles/pharmacokinetics , Positron-Emission Tomography/methods , Radiopharmaceuticals/pharmacokinetics , Triazoles/pharmacokinetics , Humans , Hypoxia/diagnostic imaging , Misonidazole/pharmacokineticsABSTRACT
BACKGROUND: Tumour hypoxia and a high tumour metabolism increase radioresistance in patients with head and neck squamous cell carcinoma (HNSCC). The aim of this study was to evaluate the correlation between hypoxia ([(18)F]HX4 PET) and glucose metabolism ([(18)F]FDG PET) molecular imaging. MATERIAL AND METHODS: [(18)F]HX4 and [(18)F]FDG PET/CT images of 20 HNSCC patients were acquired prior to (chemo)radiotherapy, in an immobilisation mask, with a median time interval of seven days (NCT01347281). Gross tumour volumes of the primary lesions (GTVprim) and pathological lymph nodes (GTVln) were included in the analysis. [(18)F]FDG PET/CT images were rigidly registered to the [(18)F]HX4 PET/CT images. The maximum and mean standardised uptake values (SUVmax, SUVmean) within both GTVs were determined. In addition, the overlap was compared between the [(18)F]HX4 high volume ([(18)F]HX4 HV) with a tumour-to-muscle ratio > 1.4 and the [(18)F]FDG high volume ([(18)F]FDG HV) with an SUV > 50% of the SUVmax. We report the mean ± standard deviation. RESULTS: PET/CT scans including 20 GTVprim and 12 GTVln were analysed. There was a significant correlation between several [(18)F]FDG and [(18)F]HX4 parameters, the most pronounced being the correlation between [(18)F]FDG HV and [(18)F]HX4 HV (R = 0.93, p < 0.001). The fraction of the GTVprim with a high HX4 uptake (9 ± 10%) was on average smaller than the FDG high fraction (51 ± 26%; p < 0.001). In 65% (13/20) of the patients, the GTVprim was hypoxic. In four of these patients the [(18)F]HX4 HV was located within the [(18)F]FDG HV, whereas for the remaining nine GTVprim a partial mismatch was observed. In these nine tumours 25 ± 21% (range 5-64%) of the HX4 HV was located outside the FDG HV. CONCLUSIONS: There is a correlation between [(18)F]HX4 and [(18)F]FDG uptake parameters on a global tumour level. In the majority of lesions a partial mismatch between the [(18)F]HX4 and [(18)F]FDG high uptake volumes was observed, therefore [(18)F]FDG PET imaging cannot be used as a surrogate for hypoxia. [(18)F]HX4 PET provides complementary information to [(18)F]FDG PET imaging.
Subject(s)
Carcinoma, Squamous Cell/diagnostic imaging , Fluorodeoxyglucose F18/pharmacokinetics , Head and Neck Neoplasms/diagnostic imaging , Hypoxia/diagnostic imaging , Imidazoles/pharmacokinetics , Positron-Emission Tomography/methods , Radiopharmaceuticals/pharmacokinetics , Triazoles/pharmacokinetics , Aged , Female , Humans , Image Interpretation, Computer-Assisted , Male , Middle Aged , Squamous Cell Carcinoma of Head and NeckABSTRACT
BACKGROUND: Trials are vital in informing routine clinical care; however, current designs have major deficiencies. An overview of the various challenges that face modern clinical research and the methods that can be exploited to solve these challenges, in the context of personalised cancer treatment in the 21st century is provided. AIM: The purpose of this manuscript, without intending to be comprehensive, is to spark thought whilst presenting and discussing two important and complementary alternatives to traditional evidence-based medicine, specifically rapid learning health care and cohort multiple randomised controlled trial design. Rapid learning health care is an approach that proposes to extract and apply knowledge from routine clinical care data rather than exclusively depending on clinical trial evidence, (please watch the animation: http://youtu.be/ZDJFOxpwqEA). The cohort multiple randomised controlled trial design is a pragmatic method which has been proposed to help overcome the weaknesses of conventional randomised trials, taking advantage of the standardised follow-up approaches more and more used in routine patient care. This approach is particularly useful when the new intervention is a priori attractive for the patient (i.e. proton therapy, patient decision aids or expensive medications), when the outcomes are easily collected, and when there is no need of a placebo arm. DISCUSSION: Truly personalised cancer treatment is the goal in modern radiotherapy. However, personalised cancer treatment is also an immense challenge. The vast variety of both cancer patients and treatment options makes it extremely difficult to determine which decisions are optimal for the individual patient. Nevertheless, rapid learning health care and cohort multiple randomised controlled trial design are two approaches (among others) that can help meet this challenge.
Subject(s)
Evidence-Based Medicine/methods , Neoplasms/radiotherapy , Precision Medicine/methods , Randomized Controlled Trials as Topic , HumansABSTRACT
Radiation therapy (RT) plays a fundamental role in the treatment of malignant and benign brain tumors. Current state-of-the-art photon- and proton-based RT combines more conformal dose distribution of target volumes and accurate dose delivery while limiting the adverse radiation effects. PubMed was systematically searched from from 2000 to October 2023 to identify studies reporting outcomes related to treatment of central nervous system (CNS)/skull base tumors with PT in adults. Several studies have demonstrated that proton therapy (PT) provides a reduced dose to healthy brain parenchyma compared with photon-based (xRT) radiation techniques. However, whether dosimetric advantages translate into superior clinical outcomes for different adult brain tumors remains an open question. This review aims at critically reviewing the recent studies on PT in adult patients with brain tumors, including glioma, meningiomas, and chordomas, to explore its potential benefits compared with xRT.
ABSTRACT
BACKGROUND: Deterioration of neurocognitive function in adult patients with a primary brain tumor is the most concerning side effect of radiotherapy. This study aimed to develop and evaluate normal-tissue complication probability (NTCP) models using clinical and dose-volume measures for 6-month, 1-year, and 2-year Neurocognitive Decline (ND) postradiotherapy. METHODS: A total of 219 patients with a primary brain tumor treated with radical photon and/or proton radiotherapy (RT) between 2019 and 2022 were included. Controlled oral word association test, Hopkins verbal learning test-revised, and trail making test were used to objectively measure ND. A comprehensive set of potential clinical and dose-volume measures on several brain structures were considered for statistical modeling. Clinical, dose-volume and combined models were constructed and internally tested in terms of discrimination (area under the curve, AUC), calibration (mean absolute error, MAE), and net benefit. RESULTS: Fifty percent, 44.5%, and 42.7% of the patients developed ND at 6-month, 1-year, and 2-year time points, respectively. The following predictors were included in the combined model for 6-month ND: age at radiotherapyâ >â 56 years (ORâ =â 5.71), overweight (ORâ =â 0.49), obesity (ORâ =â 0.35), chemotherapy (ORâ =â 2.23), brain V20 Gyâ ≥â 20% (ORâ =â 3.53), brainstem volumeâ ≥â 26 cc (ORâ =â 0.39), and hypothalamus volumeâ ≥â 0.5 cc (ORâ =â 0.4). Decision curve analysis showed that the combined models had the highest net benefits at 6-month (AUCâ =â 0.79, MAEâ =â 0.021), 1-year (AUCâ =â 0.72, MAEâ =â 0.027), and 2-year (AUCâ =â 0.69, MAEâ =â 0.038) time points. CONCLUSIONS: The proposed NTCP models use easy-to-obtain predictors to identify patients at high risk of ND after brain RT. These models can potentially provide a base for RT-related decisions and post-therapy neurocognitive rehabilitation interventions.
Subject(s)
Brain Neoplasms , Cranial Irradiation , Humans , Male , Female , Brain Neoplasms/radiotherapy , Middle Aged , Cranial Irradiation/adverse effects , Adult , Aged , Radiation Injuries/etiology , Radiation Injuries/diagnosis , Follow-Up Studies , Prognosis , Neurocognitive Disorders/etiology , Cognitive Dysfunction/etiology , Risk FactorsABSTRACT
This retrospective study examined bone flap displacement during radiotherapy in 25 post-operative brain tumour patients. Though never exceeding 2.5 mm, the sheer frequency of displacement highlights the need for future research on larger populations to validate its presence and assess the potential clinical impact on planning tumour volume margins.
ABSTRACT
Purpose: Artificial intelligence applications in radiation oncology have been the focus of study in the last decade. The introduction of automated and intelligent solutions for routine clinical tasks, such as treatment planning and quality assurance, has the potential to increase safety and efficiency of radiotherapy. In this work, we present a multi-institutional study across three different institutions internationally on a Bayesian network (BN)-based initial plan review assistive tool that alerts radiotherapy professionals for potential erroneous or suboptimal treatment plans. Methods: Clinical data were collected from the oncology information systems in three institutes in Europe (Maastro clinic - 8753 patients treated between 2012 and 2020) and the United States of America (University of Vermont Medical Center [UVMMC] - 2733 patients, University of Washington [UW] - 6180 patients, treated between 2018 and 2021). We trained the BN model to detect potential errors in radiotherapy treatment plans using different combinations of institutional data and performed single-site and cross-site validation with simulated plans with embedded errors. The simulated errors consisted of three different categories: i) patient setup, ii) treatment planning and iii) prescription. We also compared the strategy of using only diagnostic parameters or all variables as evidence for the BN. We evaluated the model performance utilizing the area under the receiver-operating characteristic curve (AUC). Results: The best network performance was observed when the BN model is trained and validated using the dataset in the same center. In particular, the testing and validation using UVMMC data has achieved an AUC of 0.92 with all parameters used as evidence. In cross-validation studies, we observed that the BN model performed better when it was trained and validated in institutes with similar technology and treatment protocols (for instance, when testing on UVMMC data, the model trained on UW data achieved an AUC of 0.84, compared with an AUC of 0.64 for the model trained on Maastro data). Also, combining training data from larger clinics (UW and Maastro clinic) and using it on smaller clinics (UVMMC) leads to satisfactory performance with an AUC of 0.85. Lastly, we found that in general the BN model performed better when all variables are considered as evidence. Conclusion: We have developed and validated a Bayesian network model to assist initial treatment plan review using multi-institutional data with different technology and clinical practices. The model has shown good performance even when trained on data from clinics with divergent profiles, suggesting that the model is able to adapt to different data distributions.
ABSTRACT
PURPOSE: Atlas-based and deep-learning contouring (DLC) are methods for automatic segmentation of organs-at-risk (OARs). The European Particle Therapy Network (EPTN) published a consensus-based atlas for delineation of OARs in neuro-oncology. In this study, geometric and dosimetric evaluation of automatically-segmented neuro-oncological OARs was performed using CT- and MR-models following the EPTN-contouring atlas. METHODS: Image and contouring data from 76 neuro-oncological patients were included. Two atlas-based models (CT-atlas and MR-atlas) and one DLC-model (MR-DLC) were created. Manual contours on registered CT-MR-images were used as ground-truth. Results were analyzed in terms of geometrical (volumetric Dice similarity coefficient (vDSC), surface DSC (sDSC), added path length (APL), and mean slice-wise Hausdorff distance (MSHD)) and dosimetrical accuracy. Distance-to-tumor analysis was performed to analyze to which extent the location of the OAR relative to planning target volume (PTV) has dosimetric impact, using Wilcoxon rank-sum tests. RESULTS: CT-atlas outperformed MR-atlas for 22/26 OARs. MR-DLC outperformed MR-atlas for all OARs. Highest median (95 %CI) vDSC and sDSC were found for the brainstem in MR-DLC: 0.92 (0.88-0.95) and 0.84 (0.77-0.89) respectively, as well as lowest MSHD: 0.27 (0.22-0.39)cm. Median dose differences (ΔD) were within ± 1 Gy for 24/26(92 %) OARs for all three models. Distance-to-tumor showed a significant correlation for ΔDmax,0.03cc-parameters when splitting the data in ≤ 4 cm and > 4 cm OAR-distance (p < 0.001). CONCLUSION: MR-based DLC and CT-based atlas-contouring enable high-quality segmentation. It was shown that a combination of both CT- and MR-autocontouring models results in the best quality.
Subject(s)
Neoplasms , Organs at Risk , Humans , Radiometry , Radiotherapy Planning, Computer-Assisted/methods , Tomography, X-Ray Computed/methodsABSTRACT
Purpose: Although an increasing body of literature suggests a relationship between brain irradiation and deterioration of neurocognitive function, it remains as the standard therapeutic and prophylactic modality in patients with brain tumors. This review was aimed to abstract and evaluate the prediction models for radiation-induced neurocognitive decline in patients with primary or secondary brain tumors. Methods: MEDLINE was searched on October 31, 2021 for publications containing relevant truncation and MeSH terms related to "radiotherapy," "brain," "prediction model," and "neurocognitive impairments." Risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool. Results: Of 3,580 studies reviewed, 23 prediction models were identified. Age, tumor location, education level, baseline neurocognitive score, and radiation dose to the hippocampus were the most common predictors in the models. The Hopkins verbal learning (n = 7) and the trail making tests (n = 4) were the most frequent outcome assessment tools. All studies used regression (n = 14 linear, n = 8 logistic, and n = 4 Cox) as machine learning method. All models were judged to have a high risk of bias mainly due to issues in the analysis. Conclusion: Existing models have limited quality and are at high risk of bias. Following recommendations are outlined in this review to improve future models: developing cognitive assessment instruments taking into account the peculiar traits of the different brain tumors and radiation modalities; adherence to model development and validation guidelines; careful choice of candidate predictors according to the literature and domain expert consensus; and considering radiation dose to brain substructures as they can provide important information on specific neurocognitive impairments.
ABSTRACT
PURPOSE: Image guided radiotherapy (IGRT) strategies allow detecting and monitoring anatomical changes during external beam radiotherapy (EBRT). However, assessing the dosimetric impact of anatomical changes is not straightforward. In current IGRT strategies dose volume histograms (DVH) are not available due to lack of contours and dose recalculations on the cone-beam CT (CBCT) scan. This study investigates the feasibility of using automatically calculated DVH parameters in CBCTs using an independent dose calculation engine and propagated contours. METHOD: A prospective study (NCT03385031) of thirty-one breast cancer patients who received additional CBCT imaging (N = 70) was performed. Manual and automatically propagated contours were generated for all CBCTs and an automatic dose recalculation was performed. Differences between planned and CBCT-derived DVH parameters (mean and maximum dose to targets, 95% volume coverage to targets and mean heart dose (MHD)) were calculated using the dose verification system with manual and propagated contours and, in both cases, benchmarked against DVH differences quantified in the TPS using manually contoured CBCTs. RESULTS: Differences in DVH parameters between the TPS and dose verification system with propagated contours were -1.3% to 0.7% (95% CI) for mean dose to the target volume, -0.3 to 0.2 Gy (95% CI) in MHD and -3.9% to 2.9% (95% CI) in target volume coverage. CONCLUSION: The use of an independent fully automatic dose verification system with contour propagation showed to be feasible and sufficiently reliable to recalculate CBCT based DVHs during breast EBRT. Volume coverage parameters, i.e. V95%, proved to be especially sensitive to contouring differences.
Subject(s)
Radiotherapy, Image-Guided , Radiotherapy, Intensity-Modulated , Cone-Beam Computed Tomography/methods , Humans , Prospective Studies , Radiotherapy Dosage , Radiotherapy Planning, Computer-Assisted/methods , Radiotherapy, Image-Guided/methods , Radiotherapy, Intensity-Modulated/methodsABSTRACT
Ten new organs at risk (OARs) were recently introduced in the updated European Particle Therapy Network neurological contouring atlas. Despite the use of the illustrated atlas and descriptive text, interindividual contouring variations may persist. To further facilitate the contouring of these OARs, educational films were developed and published on www.cancerdata.org.
ABSTRACT
Mobile health data capture applications (mHDA's) may improve communication between healthcare providers and patients. However, there is limited literature about the use of mHDA's facilitating clinical trials. In this study, the effectiveness of an application, supporting follow-up visits of cancer trial participants was investigated. Twenty participants were provided with an e-questionnaire via the mHDA. Participants rated the usability of the application as high performing (mean Systems Usability Scale 87 points). The research team rated the mHDA as highly applicable and efficient in preparing visits. Anamnesis, physical examination and agreement on further policy were performed within an average of 31 min.