Portal Imaging Research Articles

Defining the Planning Tumor Volume by analyzing Setup of Head & Neck (H&N) Carcinoma in Radiotherapy

Aim: To find out the setup error of Head and Neck patients treated with Intensity modulated radiation therapy (IMRT) on CLINAC-IX at Center for Nuclear medicine and Radiotherapy (CENAR) Quetta by using inbuilt electronic portal imaging device (EPID) to obtain the setup margin for clinical investigation. Methods: A total of 35 patients of head & neck carcinoma were treated with Intensity modulated radiation therapy (IMRT) total dose of 69.96Gy in 33 fractions at CENAR from 1st January 2021 to 31st December 2022 were consider this retrospective study. PTV margin for different directions (Vertical, lateral &Longitudinal) were analyzed by Van Herk’s formula Results: Data analyzed for calculating the mean displacement in X (Lateral), Y (Longitudinal) and Z (Vertical) directions, from where the mean systematic and random errors derived. These shifts (displacements) used for calculation of the final PTV margins by using Van Herk’s formula. The calculated mean (±SD) systematic errors in the Z (Vertical), X (Lateral) and Y (Longitudinal) and directions were 0.10cm, 0.06cm, and 0.07cm and the mean(±SD) random errors were 0.01cm, 0.004cm and 0.01cm respectively. Conclusion: In our study, less than3 mm is an optimal margin for GTV- PTV for head and neck cancer patients. The reduction in setup margin helps in prognosis of treatment results, reduce radiation related complication in normal tissue and reduce the local recurrence. Imaging guidance techniques is effective tool for setup margin. Keywords: Electronic Portal Imaging Device, Van Herk Equation, Systematic Error, Random Error, Head & Neck Carcinoma,

Study of the prediction of gamma passing rate in dosimetric verification of intensity-modulated radiotherapy using machine learning models based on plan complexity.

To predict the gamma passing rate (GPR) in dosimetric verification of intensity-modulated radiotherapy (IMRT) using three machine learning models based on plan complexity and find the best prediction model by comparing and evaluating the prediction ability of the regression and classification models of three classical algorithms: artificial neural network (ANN), support vector machine (SVM) and random forest (RF). 269 clinical IMRT plans were chosen retrospectively and the GPRs of a total of 2340 fields by the 2%/2mm standard at the threshold of 10% were collected for dosimetric verification using electronic portal imaging device (EPID). Subsequently, the plan complexity feature values of each field were extracted and calculated, and a total of 6 machine learning models (classification and regression models for three algorithms) were trained to learn the relation between 21 plan complexity features and GPRs. Each model was optimized by tuning the hyperparameters and ten-fold cross validation. Finally, the GPRs predicted by the model were compared with measured values to verify the accuracy of the model, and the evaluation indicators were applied to evaluate each model to find the algorithm with the best prediction performance. The RF algorithm had the optimal prediction effect on GPR, and its mean absolute error (MAE) on the test set was 1.81%, root mean squared error (RMSE) was 2.14%, and correlation coefficient (CC) was 0.72; SVM was the second and ANN was the worst. Among the classification models, the RF algorithm also had the optimal prediction performance with the highest area under the curve (AUC) value of 0.80, specificity and sensitivity of 0.80 and 0.68 respectively, followed by SVM and the worst ANN. All the three classic algorithms, ANN, SVM, and RF, could realize the prediction and classification of GPR. The RF model based on plan complexity had the optimal prediction performance which could save valuable time for quality control workers to improve quality control efficiency.

Development and multi-institutional evaluation of a new phantom for verifying beam-positioning errors at off-isocenter positions

PurposeSingle-isocenter stereotactic radiotherapy for multiple brain metastases requires highly accurate treatment delivery at off-isocenter positions (off-iso). This study aimed to verify the beam-positioning errors at off-iso using a newly developed phantom tested at multiple institutions. MethodsThe off-iso phantom comprised five stainless-steel balls with a 3-mm diameter placed at the center and at four peripheral positions on a diagonal line. Each ball was placed 3.5 cm apart along each of the three axes. Two patterns of the phantom setup were defined as 0° and 90° phantom rotations to evaluate the beam-positioning error, which is the distance between the center of the ball and the irradiated field on the electronic portal imaging device. Furthermore, the reproducibility of the beam-positioning errors was verified by evaluating their standard deviation (SD) at a single institution, which included five measurements for two treatment machines. The errors were evaluated at multiple institutions using eight treatment machines. ResultsThe measurement time from setup to image acquisition was approximately 20 min for two patterns. The SD of the beam-positioning errors in the reproducibility tests was 0.41 mm. In the multi-institutional evaluation, the beam-positioning error at the isocenter position was within 1.00 mm of the AAPM-RSS tolerance, with the exception of two linacs. The largest beam-positioning error (1.36 mm) was observed 7.5 cm away from the isocenter in three directions at a gantry angle of 180°. ConclusionsThe developed phantom can be applied as a new tool for establishing beam-positioning errors in single-isocenter stereotactic radiotherapy at off-isocenter positions.

Difference between planned and delivered radiotherapy dose to the internal mammary nodes in high-risk breast cancer patients.

Chest wall movement during radiotherapy can impact the delivered dose to the internal mammary nodes (IMN) in high-risk breast cancer patients. Using portal imaging and dose reconstruction we aimed to examine the delivered IMN dose coverage. Cine MV images were recorded for 39 breast cancer patients treated with daily image-guided radiotherapy (IGRT) in deep-inspiration breath-hold (DIBH). On the final frame of each cine MV recording the chest wall was matched with the Digitally Reconstructed Radiograph (DRR) from the treatment plan. The geometrical chest wall error was determined in the imager-plane perpendicular to the cranio-caudal direction, rounded to integer millimeters, and binned. For each 1mm bin, an isocenter-shifted treatment plan was recalculated assuming that the projected error observed in the cine MV image was caused by anterior-posterior chest wall movement in the IMN region. A weighted plan sum yielded the IMN clinical target volume receiving at least 90% dose (V90_CTVn_IMN). The mean number of cine MV observations per patient was 36 (range 26-55). Most patients (67%) had on average a posterior chest wall position at treatment compared to planned. This translated into a change in the delivered median V90_CTVn_IMN of -0.7% (range, -11.9-2.9%; p<0.001). The V90_CTVn_IMN reduction wasgreater than9% in three patients. No clinically relevant differences were found for the mean lung dose or mean heart dose. Using cine MV images, we found that the delivered V90_CTVn_IMN was significantly lower than planned. In 8% of the patients, the V90_CTVn_IMN reduction exceeded 9%.

AAPM Task Group Report 307: Use of EPIDs for Patient-Specific IMRT and VMAT QA.

Electronic portal imaging devices (EPIDs) have been widely utilized for patient-specific quality assurance (PSQA) and their use for transit dosimetry applications is emerging. Yet there are no specific guidelines on the potential uses, limitations, and correct utilization of EPIDs for these purposes. The American Association of Physicists in Medicine (AAPM) Task Group 307 (TG-307) provides a comprehensive review of the physics, modeling, algorithms and clinical experience with EPID-based pre-treatment and transit dosimetry techniques. This review also includes the limitations and challenges in the clinical implementation of EPIDs, including recommendations for commissioning, calibration and validation, routine QA, tolerance levels for gamma analysis and risk-based analysis. Characteristics of the currently available EPID systems and EPID-based PSQA techniques are reviewed. The details of the physics, modeling, and algorithms for both pre-treatment and transit dosimetry methods are discussed, including clinical experience with different EPID dosimetry systems. Commissioning, calibration, and validation, tolerance levels and recommended tests, are reviewed, and analyzed. Risk-based analysis for EPID dosimetry is also addressed. Clinical experience, commissioning methods and tolerances for EPID-based PSQA system are described for pre-treatment and transit dosimetry applications. The sensitivity, specificity, and clinical results for EPID dosimetry techniques are presented as well as examples of patient-related and machine-related error detection by these dosimetry solutions. Limitations and challenges in clinical implementation of EPIDs for dosimetric purposes are discussed and acceptance and rejection criteria are outlined. Potential causes of and evaluations of pre-treatment and transit dosimetry failures are discussed. Guidelines and recommendations developed in this report are based on the extensive published data on EPID QA along with the clinical experience of the TG-307 members. TG-307 focused on the commercially available EPID-based dosimetric tools and provides guidance for medical physicists in the clinical implementation of EPID-based patient-specific pre-treatment and transit dosimetry QA solutions including intensity modulated radiation therapy (IMRT) and volumetric modulated arc therapy (VMAT) treatments.

Seeing beyond the tumor: computed tomography image-based radiomic analysis helps identify ovarian clear cell carcinoma subtype in epithelial ovarian cancer.

To develop and validate a model that can preoperatively identify the ovarian clear cell carcinoma (OCCC) subtype in epithelial ovarian cancer (EOC) using CT imaging radiomics and clinical data. We retrospectively analyzed data from 282 patients with EOC (training set = 225, testing set = 57) who underwent pre-surgery CT examinations. Patients were categorized into OCCC or other EOC subtypes based on postoperative pathology. Seven clinical characteristics (age, cancer antigen [CA]-125, CA-199, endometriosis, venous thromboembolism, hypercalcemia, stage) were collected. Primary tumors were manually delineated on portal venous-phase images, and 1218 radiomic features were extracted. The F-test-based feature selection method and logistic regression algorithm were used to build the radiomic signature, clinical model, and integrated model. To explore the effects of integrated model-assisted diagnosis, five radiologists independently interpreted images in the testing set and reevaluated cases two weeks later with knowledge of the integrated model's output. The diagnostic performances of the predictive models, radiologists, and radiologists aided by the integrated model were evaluated. The integrated model containing the radiomic signature (constructed by four wavelet radiomic features) and three clinical characteristics (CA-125, endometriosis, and hypercalcinemia), showed better diagnostic performance (AUC = 0.863 [0.762-0.964]) than the clinical model (AUC = 0.792 [0.630-0.953], p = 0.295) and the radiomic signature alone (AUC = 0.781 [0.636-0.926], p = 0.185). The diagnostic sensitivities of the radiologists were significantly improved when using the integrated model (p = 0.023-0.041), while the specificities and accuracies were maintained (p = 0.074-1.000). Our integrated model shows great potential to facilitate the early identification of the OCCC subtype in EOC, which may enhance subtype-specific therapy and clinical management.

Image-guided radiation therapy (IGRT) in prostate cancer in México, survey of SOMERA (Sociedad Mexicana de Radioterapeutas/Mexican Society of Radiation Oncologists) with recommendations on its implementation and process.

Prostate cancer is one of the main tumors worldwide, its treatment is multidisciplinary, includes radiotherapy in all stages: curative, radical, adjuvant, salvage and palliative. Technological advances in planning systems, image acquisition and treatment equipment have allowed the delivery of higher doses limiting toxicity in healthy tissues, distributing radiation optimally and ensuring reproducibility of conditions. Image-guided radiotherapy (IGRT) is not standard in guidelines, only recommended with heterogeneity in its own process. A survey was conducted to members of the Mexican Society of Radiation Oncologists (SOMERA), to know the current status and make recommendations about its implementation and use, taking into account existing resources. Responses of 541 patients were evaluated, 85% belonged to the intermediate-high risk group, 65% received adjuvant or salvage radiotherapy (RT), 80% received intensity-modulated radiation therapy (IMRT) using doses up to 80 Gy/2 Gy. Cone beam computed tomography (CBCT) was performed on 506 (93.5%), (100% IMRT) and 90% at a periodicity of 3-5/week. 3D treatment with 42% portal images 1/week. Online correction strategies (36% changes before treatment), following a diet and bladder and rectal control. Evidence and recommendations are reviewed. IGRT should be performed in patients with prostate cancer. In Mexico, despite limitations in the distribution of human and technological resources, it is routinely applied. More information is still needed on clinical evidence of its benefits and the process should be implemented according to infrastructure, following institutional guidelines, recommending to report the initial experience that helps to standardize national conduct.

The role of EPID in vivo dosimetry in the risk management of stereotactic lung treatments.

In this work we report our experience with the use of in vivo dosimetry (IVD) in the risk management of stereotactic lung treatments. Acommercial software based on the electronic portal imaging device (EPID) signal was used to reconstruct the actual planning target volume (PTV) dose of stereotactic lung treatments. The study was designed in two phases: i)in the observational phase, the IVD results of 41consecutive patients were reviewed and out-of-tolerance cases were studied for root cause analysis; ii)in the active phase, the IVD results of 52patients were analyzed and corrective actions were taken when needed. Moreover, proactive preventions were further introduced to reduce the risk of future failures. The error occurrence rate was analyzed to evaluate the effectiveness of proactive actions. Atotal of 330fractions were analyzed. In the first phase, 13errors were identified. In the active phase, 12errors were detected, 5of which needed corrective actions; in 4patients the actions taken corrected the error. Several preventions and barriers were introduced to reduce the risk of future failures: the planning checklist was updated, the procedure for vacuum pillows was improved, and use of the respiratory compression belt was optimized. Adecrease in the failure rate was observed, showing the effectiveness of procedural adjustment. The use of IVD allowed the quality of lung stereotactic body radiation therapy (SBRT) treatments to be improved. Patient-specific and procedural corrective actions were successfully taken as part of risk management, leading to an overall improvement in the dosimetric accuracy.

Age-related morphometrics of normal adrenal glands based on deep learning-aided segmentation

Objective.This study aims to evaluate the morphometrics of normal adrenal glands in adult patients semiautomatically using a deep learning-based segmentation model.Materials and Methods.A total of 520 abdominal CT image series with normal findings, from January 1, 2016, to March 14, 2019, were retrospectively collected for the training of the adrenal segmentation model. Then, 1043 portal venous phase image series of inpatient contrast-enhanced abdominal CT examinations with normal adrenal glands were included for analysis and grouped by every 10-year gap. A 3D U-Net-based segmentation model was used to predict bilateral adrenal labels followed by manual modification of labels as appropriate. Quantitative parameters (volume, CT value, and diameters) of the bilateral adrenal glands were then analyzed.Results.In the study cohort aged 18–77 years old (554 males and 489 females), the left adrenal gland was significantly larger than the right adrenal gland [all patients, 2867.79 (2317.11–3499.89) mm3 vs. 2452.84 (1983.50–2935.18) mm3, P < 0.001]. Male patients showed a greater volume of bilateral adrenal glands than females in all age groups (all patients, left: 3237.83 ± 930.21 mm3 vs. 2646.49 ± 766.42 mm3, P < 0.001; right: 2731.69 ± 789.19 mm3 vs. 2266.18 ± 632.97 mm3, P = 0.001). Bilateral adrenal volume in male patients showed an increasing then decreasing trend as age increased that peaked at 38–47 years old (left: 3416.01 ± 886.21 mm3, right: 2855.04 ± 774.57 mm3).Conclusions.The semiautomated measurement revealed that the adrenal volume differs as age increases. Male patients aged 38–47 years old have a peaked adrenal volume.

Preoperative prediction of vessel invasion in locally advanced gastric cancer based on computed tomography radiomics and machine learning.

Vessel invasion (VI) is an important factor affecting the prognosis of gastric cancer (GC), and the accurate determination of preoperative VI for locally advanced GC is of great clinical significance. Traditional methods for the evaluation of VI require postoperative pathological examination. Noninvasive preoperative evaluation of VI is therefore crucial to determine the best treatment strategy. To determine the value of preoperative prediction of gastric VI based on portal venous phase computed tomography (CT) radiomic features and machine-learning models, a retrospective analysis of 296 patients with locally advanced GC confirmed through pathological examination was performed. They were divided into two groups, VI+ (n=213) and VI- (n=83), based on pathological results. Using pyradiomics to extract two-dimensional radiomic features of the portal venous stage of locally advanced GC, data were divided into training (n=207) and validation sets (n=89), with a ratio of 7:3, and three feature selection methods were cascaded and merged. Finally, least absolute shrinkage and selection operator (LASSO) regression was used for feature screening to obtain the optimal feature subset. Four current representative machine-learning algorithms were used to construct the prediction model, the receiver operating characteristic curve was constructed to evaluate the predictive performance of the model, and the area under the curve (AUC), accuracy, sensitivity, and specificity were calculated. The differentiation degree, and the Lauren's and CA199 classifications were independent risk factors for locally advanced GC VI. Pyradiomics extracted 864 quantitative features of portal vein images of locally advanced GC. After filtering out low variance features using R, 236 features remained. Next, 18 features were screened using the LASSO algorithm. Extreme gradient boosting (XGBoost), logistic regression, Gaussian naive Bayes, and support vector machine models were constructed based on the 18 best features screened out of the portal venous CT images of advanced GC and three independent risk factors of GC VI in clinical features predicted the training set AUC values of 0.914, 0.897, 0.880, and 0.814, respectively. The predicted validation set AUC values were 0.870, 0.877, 0.859, and 0.773, respectively. The DeLong test results indicated no statistically significant difference in AUC values between the XGBoost and logistic regression models in the training and validation sets. The four machine-learning models showed high predictive performance. The logistic regression model had the highest AUC value in the validation set (0.877), and the accuracy and F1 score were 77 and 87.6%, respectively. CT radiomic features and machine-learning models based on the portal venous phase can be used as a noninvasive imaging method for the preoperative prediction of VI in locally advanced GC. The logistic regression model exhibited the highest diagnostic performance.

Quality assurance and safety of hippocampal avoidance prophylactic cranial irradiation in the multicenter randomized phase III trial (NCT01780675)

ObjectiveNCT01780675, a multicenter randomized phase III trial of prophylactic cranial irradiation (PCI) versus PCI with hippocampal sparing in small cell lung cancer (SCLC) investigated neurocognitive decline and safety. As part of quality assurance, we evaluated if hippocampal avoidance (HA)-PCI was performed according to the NCT01780675 trial protocol instructions, and performed a safety analysis to study the incidence and location of brain metastases for patients treated with HA-PCI. MethodsThis retrospective analysis evaluated the quality of the irradiation given in the randomized controlled trial (RCT) comparing SCLC patients receiving PCI with or without hippocampal avoidance, using intensity modulated radiotherapy (IMRT) or volumetric modulated arc therapy (VMAT). The dose distribution for each patient receiving HA-PCI was retrieved and analyzed to evaluate if the treatment dose constraints were met. A questionnaire was sent out to all participating sites, and data on radiotherapy technique, pre-treatment dummy runs, phantom measurements and treatment electronic portal imaging device (EPID) dosimetry were collected and analyzed. As part of the safety analysis, the follow-up magnetic resonance imaging (MRI) or computerized tomography (CT) scans on which cranial disease progression was first diagnosed were collected and matched to the radiotherapy planning dose distribution. The matched scans were reviewed to analyze the location of the brain metastases in relation to the prescribed dose. ResultsA total of 168 patients were randomized in the NCT01780675 trial in 10 centers in the Netherlands and Belgium from April 2013 until March 2018. Eighty two patients receiving HA-PCI without evidence of brain metastases were analyzed. All patients were treated with 25 Gy in 10 fractions. Dummy runs and phantom measurements were performed in all institutions prior to enrolling patients into the study. The radiotherapy (RT) plans showed a median mean bilateral hippocampal dose of 8.0 Gy, range 5.4–11.4 (constraint ≤ 8.5 Gy). In six patients (7.3%) there was a protocol violation of the mean dose in one or both hippocampi. In four of these six patients (4.9%) the mean dose to both hippocampi exceeded the constraint, in 1 patient (1.2%) only the left and in 1 patient (1.2%) only the right hippocampal mean dose was violated (average median dose left and right 8.9 Gy). All patients met the trial dose constraint of V115%PTV ≤ 1%; however the DmaxPTV constraint of ≤ 28.75 Gy was violated in 22.0% of the patients. The safety analysis showed that 14 patients (17.1%) developed cranial progression. No solitary brain metastases in the underdosed region were found. Two out of 11 patients with multiple brain metastasis developed metastasis in the underdosed region(s). ConclusionsThe radiotherapy quality within the HA-PCI trial is performed according to the protocol guidelines. The dose constraints to the hippocampi are met in the vast majority of cases. In all patients, the volume of the brain for which a higher dose was accepted, is according to the trial. However, within this volume there are small areas with higher doses than advised.

An integrated 3D printed radioluminescent-based phantom for quality assurance on a robotic-arm linac

Objective. To develop, characterize and improve upon a high-resolution 3D printed radioluminescence-based imaging phantom for quality assurance (QA) of a robotic arm linear accelerator. Approach. A phantom was constructed which consisted of a scintillating sheet, fiducial markers, a low-cost complementary metal-oxide semiconductor camera and a 3D printed light–tight enclosure. The camera, equipped with a 12 mm lens, was angled 45 degrees from the horizontal axis with a direct line of sight of the scintillating sheet. A perspective image transformation with optical distortion correction was employed to obtain beam’s eye view images for different collimators. Beam profiles, Iris™ field size, multileaf collimator leaf positioning and central laser-radiation field coincidence QA tests were performed and compared against data obtained with gafchromic film. The phantom’s short-term stability, sensitivity to changes in output, field size and leaf positioning were also assessed. Main Results. The limiting resolution of the optical system was measured to be ∼0.26 mm. Field size, as measured by the radioluminescence system for Iris apertures, agreed to within 0.2 mm of the values measured using film. The imaging system was sensitive to field size changes well below 0.2 mm and output changes as small as 1 monitor unit (MU). For the optical setup, the mean leaf deviation error for banks X1 and X2 was 0.21 and 0.17 mm at 800 mm source to axis distance, whereas the mean difference for the film dataset was 0.16 mm and 0.22 mm for banks X1 and X2, respectively. The optical system was able to detect leaf positioning errors as small as 0.2 mm. Compared with film data, excellent agreement was seen for relative central axis beam profiles for 10 mm and 5 mm beams. Significance. The phantom presented here is an alternative to film and electronic portal imager devices, due to its low-cost, portability, and high spatial and temporal resolution.

Radiomics models based on multisequence MRI for predicting PD-1/PD-L1 expression in hepatocellular carcinoma

The purpose of this study was to explore the effectiveness of radiomics based on multisequence MRI in predicting the expression of PD-1/PD-L1 in hepatocellular carcinoma (HCC). One hundred and eight patients with HCC who underwent contrast-enhanced MRI 2 weeks before surgical resection were enrolled in this retrospective study. Corresponding paraffin sections were collected for immunohistochemistry to detect the expression of PD-1 and PD-L1. All patients were randomly divided into a training cohort and a validation cohort at a ratio of 7:3. Univariate and multivariate analyses were used to select potential clinical characteristics related to PD-1 and PD-L1 expression. Radiomics features were extracted from the axial fat-suppression T2-weighted imaging (FS-T2WI) images and the arterial phase and portal venous phase images from the axial dynamic contrast-enhanced MRI, and the corresponding feature sets were generated. The least absolute shrinkage and selection operator (LASSO) was used to select the optimal radiomics features for analysis. Logistic regression analysis was performed to construct single-sequence and multisequence radiomics and radiomic-clinical models. The predictive performance was judged by the area under the receiver operating characteristic curve (AUC) in the training and validation cohorts. In the whole cohort, PD-1 expression was positive in 43 patients, and PD-L1 expression was positive in 34 patients. The presence of satellite nodules served as an independent predictor of PD-L1 expression. The AUC values of the FS-T2WI, arterial phase, portal venous phase and multisequence models in predicting the expression of PD-1 were 0.696, 0.843, 0.863, and 0.946 in the training group and 0.669, 0.792, 0.800 and 0.815 in the validation group, respectively. The AUC values of the FS-T2WI, arterial phase, portal venous phase, multisequence and radiomic-clinical models in predicting PD-L1 expression were 0.731, 0.800, 0.800, 0.831 and 0.898 in the training group and 0.621, 0.743, 0.771, 0.810 and 0.779 in the validation group, respectively. The combined models showed better predictive performance. The results of this study suggest that a radiomics model based on multisequence MRI has the potential to predict the preoperative expression of PD-1 and PD-L1 in HCC, which could become an imaging biomarker for immune checkpoint inhibitor (ICI)-based treatment.

Evaluation of the dataset quality in gamma passing rate predictions using machine learning methods.

Gamma passing rate (GPR) predictions using machine learning methods have been explored for treatment verification of radiotherapy plans. However, these methods presented datasets with unbalanced number of plans having different treatment conditions (heterogeneous datasets), such as anatomical sites or dose per fractions, leading to lower model interpretability and prediction performance. We investigated the impact of the dataset composition on GPR binary classification (pass/fail) using random forest (RF), XG-boost, and neural network (NN) models. 945 plans were used to create one reference dataset (randomly assembled) and 24 customized datasets that considered four heterogeneity factors independently (anatomical region, number of arcs, dose per fraction, and treatment unit). 309 predictor features were extracted and calculated from plan parameters, modulation complexity metrics, and radiomic analysis (leave-trajectory maps, 3D dose distributions, and portal dosimetry images). The models' performances were measured using the area under the curve from the receiver operating characteristic (ROC-AUC). Radiomics features for reference models increased ROC-AUC values up to 13%, 15%, and 5% for RF, XG-Boost, and NN, respectively. The datasets with higher heterogeneous conditions presented the lower ROC-AUC values (RF: 0.72 ± 0.11, XG-Boost: 0.67 ± 0.1, NN: 0.89 ± 0.05) compared to models with less heterogeneous treatment conditions (RF: 0.88 ± 0.06, XG-Boost: 0.89 ± 0.07, NN: 0.98 ± 0.01). The ten most important features for each heterogeneity dataset group demonstrated their correlation with the treatments' physical aspects and GPR prediction. Improvements in data generalization and model performances can be associated with datasets having similar treatment conditions. This analysis might be implemented to evaluate the dataset quality and model consistency of further ML applications in radiotherapy. Dataset heterogeneities decrease ML model performance and reliability.

The use of in-vivo dosimetry to identify head and neck cancer patients needing adaptive radiotherapy

Background and purposeHead and neck cancer (HNC) patients experiencing anatomical changes during their radiotherapy (RT) course may benefit from adaptive RT (ART). We investigated the sensitivity of an electronic portal imaging device (EPID)-based in-vivo dosimetry (EIVD) system to detect patients that require ART and identified its limitations. Materials and methodsA retrospective study was conducted for 182 HNC patients: laryngeal cancer without elective lymph nodes (group A), postoperative RT (group B) and primary RT including elective lymph nodes (group C). The effect of anatomical changes on the dose distribution and volumetric changes was quantified. The receiver operating characteristic curve was used to obtain the optimal cut-off value for the gamma passing rate (%GP) with a dose difference of 3% and a distance to agreement of 3 mm. ResultsFifty HNC patients receiving ART were analyzed: 1 in group A, 10 in group B and 39 in group C. Failed fractions (FFs) occurred in 1/1, 6/10 and 23/39 cases before ART in group A, B and C respectively. In the four cases in group B without FFs, only minor dosimetric changes were observed. One of the cases in group C without FFs had significant dosimetric changes (false negative). Three cases received ART because of clinical reasons that cannot be detected by EIVD. The optimal cut-off value for the %GP was 95%/95.2% for old/new generation machines respectively. ConclusionEIVD combined with 3D imaging techniques can be synergistic in the detection of anatomical changes in HNC patients who benefit from ART.

Quantitative imaging predicts pancreatic fatty infiltration on routine CT examination

PurposeThe purpose of this study was to assess the performance of quantitative computed tomography (CT) imaging for detecting pancreatic fatty infiltration, using the results of histopathological analysis as reference. Materials and methodsSixty patients who underwent pancreatic surgery for a pancreatic tumor between 2016 and 2019 were retrospectively included. There were 33 women and 27 men with a mean age of 56 ± 12 (SD) years (age range: 18–79 years). Patients with dilatation of the main pancreatic duct, chronic pancreatitis, or preoperative treatment were excluded to prevent any bias in the radiological-pathological correlation. Pancreatic fatty infiltration was recorded at pathology. Pancreatic surface lobularity, pancreatic attenuation, visceral fat area, and subcutaneous fat area were derived from preoperative CT images. The performance for the prediction of fatty infiltration was assessed using area under receiver operating characteristic curve (AUC) and backward binary logistic regression analysis. Results were validated in a separate cohort of 34 patients (17 women; mean age, 50 ± 14 [SD] years; age range: 18–73). ResultsA total of 28/60 (47%) and 17/34 (50%) patients had pancreatic fatty infiltration in the derivation and validation cohorts, respectively. In the derivation cohort, patients with pancreatic fatty infiltration had a significantly higher PSL (P < 0.001) and a lower pancreatic attenuation on both precontrast and portal venous phase images (P = 0.011 and 0.003, respectively), and higher subcutaneous fat area and visceral fat area (P = 0.010 and 0.007, respectively). Multivariable analysis identified pancreatic surface lobularity > 7.6 and pancreatic attenuation on portal venous phase images < 83.5 Hounsfield units as independently associated with fatty infiltration. The combination of these variables resulted in an AUC of 0.85 (95% CI: 0.74–0.95) and 0.83 (95% CI: 0.67–0.99) in the derivation and validation cohorts, respectively. ConclusionCT-based quantitative imaging accurately predicts pancreatic fatty infiltration.

Technical note: Comprehensive evaluations of gantry and couch rotation isocentricities for implementing proton stereotactic radiosurgery.

Mechanical accuracy should be verified before implementing a proton stereotactic radiosurgery (SRS) program. Linear accelerator (Linac)-based SRS systems often use electronic portal imaging devices (EPIDs) to verify beam isocentricity. Because proton therapy systems do not have EPID, beam isocentricity tests of proton SRS may still rely on films, which are not efficient. To validate that our proton SRS system meets mechanical precision requirements and to present an efficient method to evaluate the couch and gantry's rotational isocentricity for our proton SRS system. A dedicated applicator to hold brass aperture for proton SRS system was designed. The mechanical precision of the system was tested using a metal ball and film for 11 combinations of gantry and couch angles. A more efficient quality assurance (QA) procedure was developed, which used a scintillator device to replace the film. The couch rotational isocentricity tests were performed using orthogonal kV x-rays with the couch rotated isocentrically to five positions (0°, 315°, 270°, 225°, and 180°). At each couch position, the distance between the metal ball in kV images and the imaging isocenter was measured. The gantry isocentricity tests were performed using a cone-shaped scintillator and proton beams at five gantry angles (0°, 45°, 90°, 135°, and 180°), and the isocenter position and the distance of each beam path to the isocenter were obtained. Daily QA procedure was performed for 1month to test the robustness and reproducibility of the procedure. The gantry and couch rotational isocentricity exhibited sub-mm precision, with most measurements within ±0.5mm. The 1-month QA results showed that the procedure was robust and highly reproducible to within ±0.2mm. The gantry isocentricity test using the cone-shaped scintillator was accurate and sensitive to variations of ±0.2mm. The QA procedure was efficient enough to be completed within 30min. The 1-month isocentricity position variations were within 0.5mm, which demonstrating that the overall proton SRS system was stable and precise. The proton SRS Winston-Lutz QA procedure using a cone-shaped scintillator was efficient and robust. We were able to verify radiation delivery could be performed with sub-mm mechanical precision.

Radiotherapy delivery error detection with electronic portal imaging device (EPID)-based in vivo dosimetry.

Radiotherapy delivery error detection with electronic portal imaging device (EPID)-based in vivo dosimetry.

Computed Tomography-based Radiomics Evaluation of Postoperative Local Recurrence of Pancreatic Ductal Adenocarcinoma.

To develop and validate an effective model for identifying patients with postoperative local disease recurrence of pancreatic ductal adenocarcinoma (PDAC). A total of 153 patients who had undergone surgical resection of PDAC with regular postoperative follow-up were consecutively enrolled and randomly divided into training (n=108) and validation (n=45) cohorts. The postoperative soft-tissue biopsy results or clinical follow-up results served as the reference diagnostic criteria. Radiomics analysis of the postoperative soft-tissue was performed on a commercially available prototype software using portal vein phase image. Three models were built to characterize postoperative soft tissue: computed tomography (CT)-based radiomics, clinicoradiological, and their combination. The area under the receiver operating characteristic curves (AUC) was used to evaluate the differential diagnostic performance. A nomogram was used to select the final model with best performance. One radiologist's diagnostic choices that were made with and without the nomogram's assistance were evaluated. A seven-feature-combined radiomics signature was constructed as a predictor of postoperative local recurrence. The nomogram model combining the radiomics signature with postoperative CA 19-9 elevation showed the best performance (training cohort, AUC=0.791 [95%CI: 0.707, 0.876]; validation cohort, AUC=0.742 [95%CI: 0.590, 0.894]). In the validation cohort, the AUC for differential diagnosis was significantly improved for the combined model relative to that for postoperative CA 19-9 elevation (AUC=0.742 vs. 0.533, p < 0.001). The calibration curve and decision curve analysis demonstrated the clinical usefulness of the proposed nomogram. The diagnostic performance of the radiologist was not significantly improve by using the proposed nomogram (AUC=0.742 vs. 0.670, p=0.17). The combined model using CT radiomic features and CA 19-9 elevation effectively characterized postoperative soft tissue and potentially may improve treatment strategies and facilitate personalized treatment for PDAC after surgical resection.

Comparison of two pre-treatment verification methods for arc – IMRT plans

In radiotherapy, the application of the IMRT arc technique, a special technique of external beam irradiation, while providing greater ballistic accuracy and personalization of treatment, as well as better speed of execution, requires special attention to the development of the treatment plan and its verification.Therefore, tools and methods of physical-health analysis that allow verification of the accuracy of the delivery of the radiant beam in the stages prior to treatment are essential. At the unit of Medical Physics at Dimiccoli Hospital Barletta, a prospective experimental study was conducted based on the comparison of two different methods of pre-treatment verification in patients treated for prostate cancer with the aim of increasing the performance of the treatment workflow.A comparative evaluation of gamma analysis results on images acquired with a 2D flat panel detector EPID (Electronic Portal Imaging Device) on the one hand and a 2D ionizing chambers detector on the other hand was conducted. The study sample included 38 patients undergoing radiotherapy with IMRT between December 2021 and October 2022, and each subject was studied and verified with both methods.The results of gamma analysis conducted with the two methods of pre-treatment verification of patients with prostate cancer are superimposable. In addition, with EPID we have a significant saving of machine time and thus allows an increase in the number of patients undergoing daily radiotherapy.In light of internationally accepted dosimetric and radiation protection accuracy standards according to Decree 101/2020, pre-treatment verification of dose distributions, using a 2D flat panel detection system (EPID), was found to be in line with waiting list reduction goals.