Impact of different peak tube voltage settings on adrenal adenomas attenuation at unenhanced CT.

OBJECTIVES: To assess the influence of peak tube voltage peak setting on adrenal adenomas (AA) attenuation on unenhanced abdominal CT. MATERIALS AND METHODS: IRB-approved retrospective observational cohort study. We included 89 patients with imaging-defined AAs with shortest diameter > 6 mm who underwent two or more unenhanced abdominal CTs using at least two different peak tube voltage settings. Two readers independently measured adenoma attenuation on different CT acquisitions by drawing a round ROI on 3 mm thick axial MPR reconstructions encompassing at least 2/3 of the lesion's surface. The mean of the values measured by the two readers was used for further analysis. Interobserver variability was assessed (Intraclass Correlation Coefficient). Attenuation values measured on 100, 110 and 140 kVp acquisitions were compared with standard 120 kVp ones (Bland-Altman analysis). RESULTS: We included 275 unenhanced abdominal CTs (3.1 ± 0.9/patient) in image analysis; 131 acquired at 120 kVp, 65 at 100 kVp, 59 at 110 kVp, and 20 at 140 kVp. 107 lesions were detected in 89 patients (1-4/patient), with a mean maximum diameter of 17 ± 6 mm. Interobserver agreement in attenuation measurement was excellent (ICC: 0.95, CI (92-97)). Median adenoma attenuation was significantly lower on 100 kVp images than on 120 kVp ones (-1 HU, IQR (-5 to 3.6), vs, 2.5 HU, IQR (-1.5 to 8.5); p < 0.001) whereas we didn't find statistically significant differences in adenoma attenuation between 110 kVp or 140 kVp and 120 kVp ones. CONCLUSION: AA attenuation is significantly lower on unenhanced CT scans acquired at 100 kVp than on those acquired at "standard" 120 kVp. CLINICAL RELEVANCE STATEMENT: AA attenuation is significantly lower at 100 kVp in comparison to 120 kVp. This might be exploited to increase unenhanced CT sensitivity in adenoma characterisation, but further studies including non-adenoma lesions are mandatory to confirm this hypothesis. KEY POINTS: CT scans are often acquired using peak tube voltage settings different from the "standard" 120 kVp. AA attenuation varies if CT scans are acquired using different tube peak voltage settings. At 100 kVp AAs show a significantly lower attenuation than at 120 kVp.

Radiomic- and dosiomic-based clustering development for radio-induced neurotoxicity in pediatric medulloblastoma.

BACKGROUND: Texture analysis extracts many quantitative image features, offering a valuable, cost-effective, and non-invasive approach for individual medicine. Furthermore, multimodal machine learning could have a large impact for precision medicine, as texture biomarkers can underlie tissue microstructure. This study aims to investigate imaging-based biomarkers of radio-induced neurotoxicity in pediatric patients with metastatic medulloblastoma, using radiomic and dosiomic analysis. METHODS: This single-center study retrospectively enrolled children diagnosed with metastatic medulloblastoma (MB) and treated with hyperfractionated craniospinal irradiation (CSI). Histological confirmation of medulloblastoma and baseline follow-up magnetic resonance imaging (MRI) were mandatory. Treatment involved helical tomotherapy (HT) delivering a dose of 39 Gray (Gy) to brain and spinal axis and a posterior fossa boost up to 60 Gy. Clinical outcomes, such as local and distant brain control and neurotoxicity, were recorded. Radiomic and dosiomic features were extracted from tumor regions on T1, T2, FLAIR (fluid-attenuated inversion recovery) MRI-maps, and radiotherapy dose distribution. Different machine learning feature selection and reduction approaches were performed for supervised and unsupervised clustering. RESULTS: Forty-eight metastatic medulloblastoma patients (29 males and 19 females) with a mean age of 12 ± 6 years were enrolled. For each patient, 332 features were extracted. Greater level of abstraction of input data by combining selection of most performing features and dimensionality reduction returns the best performance. The resulting one-component radiomic signature yielded an accuracy of 0.73 with sensitivity, specificity, and precision of 0.83, 0.64, and 0.68, respectively. CONCLUSIONS: Machine learning radiomic-dosiomic approach effectively stratified pediatric medulloblastoma patients who experienced radio-induced neurotoxicity. Strategy needs further validation in external dataset for its potential clinical use in ab initio management paradigms of medulloblastoma.

Clinical validation of an automatic atlas-based segmentation tool for male pelvis CT images.

PURPOSE: This retrospective work aims to evaluate the possible impact on intra- and inter-observer variability, contouring time, and contour accuracy of introducing a pelvis computed tomography (CT) auto-segmentation tool in radiotherapy planning workflow. METHODS: Tests were carried out on five structures (bladder, rectum, pelvic lymph-nodes, and femoral heads) of six previously treated subjects, enrolling five radiation oncologists (ROs) to manually re-contour and edit auto-contours generated with a male pelvis CT atlas created with the commercial software MIM MAESTRO. The ROs first delineated manual contours (M). Then they modified the auto-contours, producing automatic-modified (AM) contours. The procedure was repeated to evaluate intra-observer variability, producing M1, M2, AM1, and AM2 contour sets (each comprising 5 structures × 6 test patients × 5 ROs = 150 contours), for a total of 600 contours. Potential time savings was evaluated by comparing contouring and editing times. Structure contours were compared to a reference standard by means of Dice similarity coefficient (DSC) and mean distance to agreement (MDA), to assess intra- and inter-observer variability. To exclude any automation bias, ROs evaluated both M and AM sets as "clinically acceptable" or "to be corrected" in a blind test. RESULTS: Comparing AM to M sets, a significant reduction of both inter-observer variability (p < 0.001) and contouring time (-45% whole pelvis, p < 0.001) was obtained. Intra-observer variability reduction was significant only for bladder and femoral heads (p < 0.001). The statistical test showed no significant bias. CONCLUSION: Our atlas-based workflow proved to be effective for clinical practice as it can improve contour reproducibility and generate time savings. Based on these findings, institutions are encouraged to implement their auto-segmentation method.

Validation of a secondary dose check tool against Monte Carlo and analytical clinical dose calculation algorithms in VMAT.

PURPOSE: Patient-specific quality assurance (QA) is very important in radiotherapy, especially for patients with highly conformed treatment plans like VMAT plans. Traditional QA protocols for these plans are time-consuming reducing considerably the time available for patient treatments. In this work, a new MC-based secondary dose check software (SciMoCa) is evaluated and benchmarked against well-established TPS (Monaco and Pinnacle3 ) by means of treatment plans and dose measurements. METHODS: Fifty VMAT plans have been computed using same calculation parameters with SciMoCa and the two primary TPSs. Plans were validated with measurements performed with a 3D diode detector (ArcCHECK) by translating patient plans to phantom geometry. Calculation accuracy was assessed by measuring point dose differences and gamma passing rates (GPR) from a 3D gamma analysis with 3%-2 mm criteria. Comparison between SciMoCa and primary TPS calculations was made using the same estimators and using both patient and phantom geometry plans. RESULTS: TPS and SciMoCa calculations were found to be in very good agreement with validation measurements with average point dose differences of 0.7 ± 1.7% and -0.2 ± 1.6% for SciMoCa and two TPSs, respectively. Comparison between SciMoCa calculations and the two primary TPS plans did not show any statistically significant difference with average point dose differences compatible with zero within error for both patient and phantom geometry plans and GPR (98.0 ± 3.0% and 99.0 ± 3.0% respectively) well in excess of the typical 95 % clinical tolerance threshold. CONCLUSION: This work presents results obtained with a significantly larger sample than other similar analyses and, to the authors' knowledge, compares SciMoCa with a MC-based TPS for the first time. Results show that a MC-based secondary patient-specific QA is a clinically viable, reliable, and promising technique, that potentially allows significant time saving that can be used for patient treatment and a per-plan basis QA that effectively complements traditional commissioning and calibration protocols.

Methodological approach to create an atlas using a commercial auto-contouring software.

PURPOSE: The aim of this work was to establish a methodological approach for creation and optimization of an atlas for auto-contouring, using the commercial software MIM MAESTRO (MIM Software Inc. Cleveland OH). METHODS: A computed tomography (CT) male pelvis atlas was created and optimized to evaluate how different tools and options impact on the accuracy of automatic segmentation. Pelvic lymph nodes (PLN), rectum, bladder, and femurs of 55 subjects were reviewed for consistency by a senior consultant radiation oncologist with 15 yr of experience. Several atlas and workflow options were tuned to optimize the accuracy of auto-contours. The deformable image registration (DIR), the finalization method, the k number of atlas best matching subjects, and several post-processing options were studied. To test our atlas performances, automatic and reference manual contours of 20 test subjects were statistically compared based on dice similarity coefficient (DSC) and mean distance to agreement (MDA) indices. The effect of field of view (FOV) reduction on auto-contouring time was also investigated. RESULTS: With the optimized atlas and workflow, DSC and MDA median values of bladder, rectum, PLN, and femurs were 0.91 and 1.6 mm, 0.85 and 1.6 mm, 0.85 and 1.8 mm, and 0.96 and 0.5 mm, respectively. Auto-contouring time was more than halved by strictly cropping the FOV of the subject to be contoured to the pelvic region. CONCLUSION: A statistically significant improvement of auto-contours accuracy was obtained using our atlas and optimized workflow instead of the MIM Software pelvic atlas.

CT angiography prior to endovascular procedures: can artificial intelligence improve reporting?

CT angiography prior to endovascular aortic surgery is the standard non-invasive imaging method for evaluation of aortic dimensions and access sites. A detailed report is crucial to a proper planning. We assessed Artificial Intelligence (AI)-algorithm accuracy to measure vessels diameters at CT prior to transcatheter aortic valve implantation (TAVI). CT scans of 50 patients were included. Two Radiologists with experience in vascular imaging together manually assessed diameters at nine landmark positions according to the American Heart Association guidelines: 450 values were obtained. We implemented TOST (Two One-Sided Test) to determine whether the measurements were equivalent to the values obtained from the AI algorithm. When the equivalence bound was a range of ± 2 mm the test showed equivalence for every point; if the range was equal to ± 1 mm the two measurements were not equivalent in 6 points out of 9 (p-value > 0.05), close to the aortic valve. The time for automatic evaluation (average 1 min 47 s) was significantly lower compared with manual measurements (5 min 41 s) (p < 0.01). In conclusion, our results indicate that AI-algorithms can measure aortic diameters at CT prior to endovascular surgery with high accuracy. AI-assisted reporting promises high efficiency, reduced inter-reader variabilities and time saving. In order to perform optimal TAVI procedure planning aortic root analysis could be improved, including annulus dimensions.

Quantification of pulmonary involvement in COVID-19 pneumonia by means of a cascade of two U-nets: training and assessment on multiple datasets using different annotation criteria.

PURPOSE: This study aims at exploiting artificial intelligence (AI) for the identification, segmentation and quantification of COVID-19 pulmonary lesions. The limited data availability and the annotation quality are relevant factors in training AI-methods. We investigated the effects of using multiple datasets, heterogeneously populated and annotated according to different criteria. METHODS: We developed an automated analysis pipeline, the LungQuant system, based on a cascade of two U-nets. The first one (U-net[Formula: see text]) is devoted to the identification of the lung parenchyma; the second one (U-net[Formula: see text]) acts on a bounding box enclosing the segmented lungs to identify the areas affected by COVID-19 lesions. Different public datasets were used to train the U-nets and to evaluate their segmentation performances, which have been quantified in terms of the Dice Similarity Coefficients. The accuracy in predicting the CT-Severity Score (CT-SS) of the LungQuant system has been also evaluated. RESULTS: Both the volumetric DSC (vDSC) and the accuracy showed a dependency on the annotation quality of the released data samples. On an independent dataset (COVID-19-CT-Seg), both the vDSC and the surface DSC (sDSC) were measured between the masks predicted by LungQuant system and the reference ones. The vDSC (sDSC) values of 0.95±0.01 and 0.66±0.13 (0.95±0.02 and 0.76±0.18, with 5 mm tolerance) were obtained for the segmentation of lungs and COVID-19 lesions, respectively. The system achieved an accuracy of 90% in CT-SS identification on this benchmark dataset. CONCLUSION: We analysed the impact of using data samples with different annotation criteria in training an AI-based quantification system for pulmonary involvement in COVID-19 pneumonia. In terms of vDSC measures, the U-net segmentation strongly depends on the quality of the lesion annotations. Nevertheless, the CT-SS can be accurately predicted on independent test sets, demonstrating the satisfactory generalization ability of the LungQuant.

Comprehensive Analysis of Radiomic Datasets by RadAR.

Quantitative analysis of biomedical images, referred to as radiomics, is emerging as a promising approach to facilitate clinical decisions and improve patient stratification. The typical radiomic workflow includes image acquisition, segmentation, feature extraction, and analysis of high-dimensional datasets. While procedures for primary radiomic analyses have been established in recent years, processing the resulting radiomic datasets remains a challenge due to the lack of specific tools for doing so. Here we present RadAR (Radiomics Analysis with R), a new software to perform comprehensive analysis of radiomic features. RadAR allows users to process radiomic datasets in their entirety, from data import to feature processing and visualization, and implements multiple statistical methods for analysis of these data. We used RadAR to analyze the radiomic profiles of more than 850 patients with cancer from publicly available datasets and showed that it was able to recapitulate expected results. These results demonstrate RadAR as a reliable and valuable tool for the radiomics community. SIGNIFICANCE: A new computational tool performs comprehensive analysis of high-dimensional radiomic datasets, recapitulating expected results in the analysis of radiomic profiles of >850 patients with cancer from independent datasets.