Explore the vast range of titles available.

The UK National Health Service has also noted that use of AI in contouring could increase capacity, reduce waiting lists, and allow more focus on patient-facing tasks amid ongoing workforce pressures and staff shortages.4 We initiated the Radiation Planning Assistant (RPA) project to use automated contouring and treatment planning to support treatment planners and oncologists in low-income and middle-income countries (LMICs) by allowing them to scale their efforts and treat more patients safely and efficiently. The RPA team has taken an open science approach to the research behind the initiative and has followed appropriate industry standards for software development (eg, International Organization for Standardization and US Food and Drug Administration [FDA]). Oncologists at Ocean Road Cancer Institute in Dar es Salaam, Tanzania, recently showed that RPA tools could generate clinically acceptable treatment plans for nearly 100% of their own patients.6 Risk is minimised by following international standards, minimalist design to reduce user error, and automated quality assurance to identify outlier results.

To evaluate the uncertainty of radiomics features from contrast-enhanced breath-hold helical CT scans of non-small cell lung cancer for both manual and semi-automatic segmentation due to intra-observer, inter-observer, and inter-software reliability. Three radiation oncologists manually delineated lung tumors twice from 10 CT scans using two software tools (3D-Slicer and MIM Maestro). Additionally, three observers without formal clinical training were instructed to use two semi-automatic segmentation tools, Lesion Sizing Toolkit (LSTK) and GrowCut, to delineate the same tumor volumes. The accuracy of the semi-automatic contours was assessed by comparison with physician manual contours using Dice similarity coefficients and Hausdorff distances. Eighty-three radiomics features were calculated for each delineated tumor contour. Informative features were identified based on their dynamic range and correlation to other features. Feature reliability was then evaluated using intra-class correlation coefficients (ICC). Feature range was used to evaluate the uncertainty of the segmentation methods. From the initial set of 83 features, 40 radiomics features were found to be informative, and these 40 features were used in the subsequent analyses. For both intra-observer and inter-observer reliability, LSTK had higher reliability than GrowCut and the two manual segmentation tools. All observers achieved consistently high ICC values when using LSTK, but the ICC value varied greatly for each observer when using GrowCut and the manual segmentation tools. For inter-software reliability, features were not reproducible across the software tools for either manual or semi-automatic segmentation methods. Additionally, no feature category was found to be more reproducible than another feature category. Feature ranges of LSTK contours were smaller than those of manual contours for all features. Radiomics features extracted from LSTK contours were highly reliable across and among observers. With semi-automatic segmentation tools, observers without formal clinical training were comparable to physicians in evaluating tumor segmentation.

Radiomics studies require many patients in order to power them, thus patients are often combined from different institutions and using different imaging protocols. Various studies have shown that imaging protocols affect radiomics feature values. We examined whether using data from cohorts with controlled imaging protocols improved patient outcome models. We retrospectively reviewed 726 CT and 686 PET images from head and neck cancer patients, who were divided into training or independent testing cohorts. For each patient, radiomics features with different preprocessing were calculated and two clinical variables-HPV status and tumor volume-were also included. A Cox proportional hazards model was built on the training data by using bootstrapped Lasso regression to predict overall survival. The effect of controlled imaging protocols on model performance was evaluated by subsetting the original training and independent testing cohorts to include only patients whose images were obtained using the same imaging protocol and vendor. Tumor volume, HPV status, and two radiomics covariates were selected for the CT model, resulting in an AUC of 0.72. However, volume alone produced a higher AUC, whereas adding radiomics features reduced the AUC. HPV status and one radiomics feature were selected as covariates for the PET model, resulting in an AUC of 0.59, but neither covariate was significantly associated with survival. Limiting the training and independent testing to patients with the same imaging protocol reduced the AUC for CT patients to 0.55, and no covariates were selected for PET patients. Radiomics features were not consistently associated with survival in CT or PET images of head and neck patients, even within patients with the same imaging protocol.

Radiomics involves high-throughput extraction of large numbers of quantitative features from medical images and analysis of these features to predict patients’ outcome and support clinical decision-making. However, radiomics features are sensitive to several factors, including scanning protocols. The purpose of this study was to investigate the robustness of magnetic resonance imaging (MRI) radiomics features with various MRI scanning protocol parameters and scanners using an MRI radiomics phantom. The variability of the radiomics features with different scanning parameters and repeatability measured using a test–retest scheme were evaluated using the coefficient of variation and intraclass correlation coefficient (ICC) for both T1- and T2-weighted images. For variability measures, the features were categorized into three groups: large, intermediate, and small variation. For repeatability measures, the average T1- and T2-weighted image ICCs for the phantom (0.963 and 0.959, respectively) were higher than those for a healthy volunteer (0.856 and 0.849, respectively). Our results demonstrated that various radiomics features are dependent on different scanning parameters and scanners. The radiomics features with a low coefficient of variation and high ICC for both the phantom and volunteer can be considered good candidates for MRI radiomics studies. The results of this study will assist current and future MRI radiomics studies.

Radiomics is the use of quantitative imaging features extracted from medical images to characterize tumor pathology or heterogeneity. Features measured at pretreatment have successfully predicted patient outcomes in numerous cancer sites. This project was designed to determine whether radiomics features measured from non–small cell lung cancer (NSCLC) change during therapy and whether those features (delta-radiomics features) can improve prognostic models. Features were calculated from pretreatment and weekly intra-treatment computed tomography images for 107 patients with stage III NSCLC. Pretreatment images were used to determine feature-specific image preprocessing. Linear mixed-effects models were used to identify features that changed significantly with dose-fraction. Multivariate models were built for overall survival, distant metastases, and local recurrence using only clinical factors, clinical factors and pretreatment radiomics features, and clinical factors, pretreatment radiomics features, and delta-radiomics features. All of the radiomics features changed significantly during radiation therapy. For overall survival and distant metastases, pretreatment compactness improved the c-index. For local recurrence, pretreatment imaging features were not prognostic, while texture-strength measured at the end of treatment significantly stratified high- and low-risk patients. These results suggest radiomics features change due to radiation therapy and their values at the end of treatment may be indicators of tumor response.

Background Variation in imaging protocol, patient positioning, and the presence of artifacts can vary image quality in CT images used for radiotherapy planning. Automated methods for spatial resolution (SR) estimation exist but require further investigation and validation for wider adoption. Purpose To validated previously existing algorithm for SR estimation and introduce improvements that make it robust to patient positioning, CT protocol, site, and artifacts. Method A reference algorithm based on the previous gold standard was recreated and modified to improve robustness. The algorithms were tested on three different datasets: (1) a cylindrical ACR CT QC phantom scanned using a Siemens SOMATOM Definition Edge scanner and reconstructed using 61 different kernels, (2) a set of anthropomorphic phantoms scanned with the presence of artifacts common to clinical acquisitions such as blankets and immobilization devices, and (3) a clinical patient dataset of head and neck (HN) CT scans (nine patients) and spine/pelvis (10 patients). The robustness of both algorithms was tested on the clinical patient data. Results Over the range of tested kernels, both algorithms were accurate when the ground truth MTF f50 was within the range 0.2–0.7 mm−1 in the cylindrical phantom datasets with an RMS error of 10.3% and 3.8% for the reference and modified versions of the algorithm, respectively, as compared to the ground truth. In the anthropomorphic phantom datasets the reference algorithm showed an 8.4% and 30.0% difference from ground truth for the Pelvic and HN phantoms, respectively, while the modified algorithm showed 4.9% and 3.9% percent difference from ground truth. In the clinical dataset the reference algorithm estimated a mean f50 value of 0.21 ± 0.03 mm−1 and 0.25 ± 0.03 mm−1 for pelvis/spine while the reference algorithm estimated mean of 0.28 ± 0.02 and 0.29 ± 0.01 mm−1 for HN and pelvis/spine, respectively, as compared to the ground truth found to be 0.28 mm−1 on the cylindrical phantom. Conclusion The SR algorithm was validated cylindrical/anthropomorphic phantoms and clinical CT scans. Further modifications were tested and showed improved accuracy in more challenging CT acquisitions.

ObjectivesTo develop a model using radiomic features extracted from MR images to distinguish radiation necrosis from tumour progression in brain metastases after Gamma Knife radiosurgery.MethodsWe retrospectively identified 87 patients with pathologically confirmed necrosis (24 lesions) or progression (73 lesions) and calculated 285 radiomic features from four MR sequences (T1, T1 post-contrast, T2, and fluid-attenuated inversion recovery) obtained at two follow-up time points per lesion per patient. Reproducibility of each feature between the two time points was calculated within each group to identify a subset of features with distinct reproducible values between two groups. Changes in radiomic features from one time point to the next (delta radiomics) were used to build a model to classify necrosis and progression lesions.ResultsA combination of five radiomic features from both T1 post-contrast and T2 MR images were found to be useful in distinguishing necrosis from progression lesions. Delta radiomic features with a RUSBoost ensemble classifier had an overall predictive accuracy of 73.2% and an area under the curve value of 0.73 in leave-one-out cross-validation.ConclusionsDelta radiomic features extracted from MR images have potential for distinguishing radiation necrosis from tumour progression after radiosurgery for brain metastases.Key points• Some radiomic features showed better reproducibility for progressive lesions than necrotic ones• Delta radiomic features can help to distinguish radiation necrosis from tumour progression• Delta radiomic features had better predictive value than did traditional radiomic features

When imaging studies (e.g. CT) are used to quantify morphological changes in an anatomical structure, it is necessary to understand the extent and source of motion which can give imaging artifacts (e.g. blurring or local distortion). The objective of this study was to assess the magnitude of esophageal motion due to cardiac motion. We used retrospective electrocardiogram-gated contrast-enhanced computed tomography angiography images for this study. The anatomic region from the carina to the bottom of the heart was taken at deep-inspiration breath hold with the patients' arms raised above their shoulders, in a position similar to that used for radiation therapy. The esophagus was delineated on the diastolic phase of cardiac motion, and deformable registration was used to sequentially deform the images in nearest-neighbor phases among the 10 cardiac phases, starting from the diastolic phase. Using the 10 deformation fields generated from the deformable registration, the magnitude of the extreme displacements was then calculated for each voxel, and the mean and maximum displacement was calculated for each computed tomography slice for each patient. The average maximum esophageal displacement due to cardiac motion for all patients was 5.8 mm (standard deviation: 1.6 mm, maximum: 10.0 mm) in the transverse direction. For 21 of 26 patients, the largest esophageal motion was found in the inferior region of the heart; for the other patients, esophageal motion was approximately independent of superior-inferior position. The esophagus motion was larger at cardiac phases where the electrocardiogram R-wave occurs. In conclusion, the magnitude of esophageal motion near the heart due to cardiac motion is similar to that due to other sources of motion, including respiratory motion and intra-fraction motion. A larger cardiac motion will result into larger esophagus motion in a cardiac cycle.

Consistent pixel sizes are of fundamental importance for assessing texture features that relate intensity and spatial information in radiomics studies. To correct for the effects of variable pixel sizes, we combined image resampling with Butterworth filtering in the frequency domain and tested the correction on computed tomography (CT) scans of lung cancer patients reconstructed 5 times with pixel sizes varying from 0.59 to 0.98 mm. One hundred fifty radiomics features were calculated for each preprocessing and field-of-view combination. Intra-patient agreement and inter-patient agreement were compared using the overall concordance correlation coefficient (OCCC). To further evaluate the corrections, hierarchical clustering was used to identify patient scans before and after correction. To assess the general applicability of the corrections, they were applied to 17 CT scans of a radiomics phantom. The reduction in the inter-scanner variability relative to non-small cell lung cancer patient scans was quantified. The variation in pixel sizes caused the intra-patient variability to be large (OCCC <95%) relative to the inter-patient variability in 79% of the features. However, with the resampling and filtering corrections, the intra-patient variability was relatively large in only 10% of the features. With the filtering correction, 8 of 8 patients were correctly clustered, in contrast to only 2 of 8 without the correction. In the phantom study, resampling and filtering the images of a rubber particle cartridge substantially reduced variability in 61% of the radiomics features and substantially increased variability in only 6% of the features. Surprisingly, resampling without filtering tended to increase the variability. In conclusion, applying a correction based on resampling and Butterworth low-pass filtering in the frequency domain effectively reduced variability in CT radiomics features caused by variations in pixel size. This correction may also reduce the variability introduced by other CT scan acquisition parameters.

Purpose To investigate the impact of computed tomography (CT) image acquisition and reconstruction parameters, including slice thickness, pixel size, and dose, on automatic contouring algorithms. Methods Eleven scans from patients with head‐and‐neck cancer were reconstructed with varying slice thicknesses and pixel sizes. CT dose was varied by adding noise using low‐dose simulation software. The impact of these imaging parameters on two in‐house auto‐contouring algorithms, one convolutional neural network (CNN)‐based and one multiatlas‐based system (MACS) was investigated for 183 reconstructed scans. For each algorithm, auto‐contours for organs‐at‐risk were compared with auto‐contours from scans with 3 mm slice thickness, 0.977 mm pixel size, and 100% CT dose using Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD). Results Increasing the slice thickness from baseline value of 3 mm gave a progressive reduction in DSC and an increase in HD and MSD on average for all structures. Reducing the CT dose only had a relatively minimal effect on DSC and HD. The rate of change with respect to dose for both auto‐contouring methods is approximately 0. Changes in pixel size had a small effect on DSC and HD for CNN‐based auto‐contouring with differences in DSC being within 0.07. Small structures had larger deviations from the baseline values than large structures for DSC. The relative differences in HD and MSD between the large and small structures were small. Conclusions Auto‐contours can deviate substantially with changes in CT acquisition and reconstruction parameters, especially slice thickness and pixel size. The CNN was less sensitive to changes in pixel size, and dose levels than the MACS. The results contraindicated more restrictive values for the parameters should be used than a typical imaging protocol for head‐and‐neck.