Deep-Learning Models for Abdominal CT Organ Segmentation in Children: Development and Validation in Internal and Heterogeneous Public Datasets.

Background: Deep-learning abdominal organ segmentation algorithms have shown excellent results in adults; validation in children is sparse. Objective: To develop and validate deep-learning models for liver, spleen, and pancreas segmentation on pediatric CT examinations. Methods: This retrospective study developed and validated deep-learning models for liver, spleen, and pancreas segmentation using 1731 CT examinations (1504 training, 221 testing), derived from three internal institutional pediatric (age ≤18) datasets (n=483) and three public datasets comprising pediatric and adult examinations with various pathologies (n=1248). Three deep-learning model architectures (SegResNet, DynUNet, and SwinUNETR) from the Medical Open Network for AI (MONAI) framework underwent training using native training (NT), relying solely on institutional datasets, and transfer learning (TL), incorporating pre-training on public datasets. For comparison, TotalSegmentator (TS), a publicly available segmentation model, was applied to test data without further training. Segmentation performance was evaluated using mean Dice similarity coefficient (DSC), with manual segmentations as reference. Results: For internal pediatric data, DSC for normal liver was 0.953 (TS), 0.964-0.965 (NT models), and 0.965-0.966 (TL models); normal spleen, 0.914 (TS), 0.942-0.945 (NT models), and 0.937-0.945 (TL models); normal pancreas, 0.733 (TS), 0.774-0.785 (NT models), and 0.775-0.786 (TL models); pancreas with pancreatitis, 0.703 (TS), 0.590-0.640 (NT models), and 0.667-0.711 (TL models). For public pediatric data, DSC for liver was 0.952 (TS), 0.876-0.908 (NT models), and 0.941-0.946 (TL models); spleen, 0.905 (TS), 0.771-0.827 (NT models), and 0.897-0.926 (TL models); pancreas, 0.700 (TS), 0.577-0.648 (NT models), and 0.693-0.736 (TL models). For public primarily adult data, DSC for liver was 0.991 (TS), 0.633-0.750 (NT models), and 0.926-0.952 (TL models); spleen, 0.983 (TS), 0.569-0.604 (NT models), and 0.923-0.947 (TL models); pancreas, 0.909 (TS), 0.148-0.241 (NT models), and 0.699-0.775 (TL models). DynUNet-TL was selected as the best-performing NT or TL model and was made available as an opensource MONAI bundle (https://github.com/cchmc-dll/pediatric_abdominal_segmentation_bundle.git). Conclusion: TL models trained on heterogeneous public datasets and fine-tuned using institutional pediatric data outperformed internal NT models and TotalSegmentator across internal and external pediatric test data. Segmentation performance was better in liver and spleen than in pancreas. Clinical Impact: The selected model may be used for various volumetry applications in pediatric imaging.

Computed tomography-based measurements of normative liver and spleen volumes in children.

BACKGROUND: Quantification of organ size has utility in clinical care and research for diagnostics, prognostics and surgical planning. Volumetry is regarded as the best measure of organ size and change in size over time. Scarce reference values exist for liver and spleen volumes in healthy children. OBJECTIVE: To report liver and spleen volumes for a sample of children defined by manual segmentation of contrast-enhanced CT images with the goal of defining normal values and thresholds that might indicate disease. MATERIALS AND METHODS: This retrospective study included clinically acquired contrast-enhanced CTs of the abdomen/pelvis for children and adolescents imaged between January 2018 and July 2021. Liver and spleen volumes were derived through manual segmentation of CTs reconstructed at 2.5-, 3- or 5-mm slice thickness. A subset of images (5%, n=16) was also segmented using 0.5-mm slice thickness reconstructions to define agreement based on image slice thickness. We used Pearson correlation and multivariable regression to assess associations between organ volumes and patient characteristics. We generated reference intervals for the 5th, 25th, 50th (median), 75th and 95th percentiles for organ volumes as a function of age and weight using quantile regression models. Finally, we calculated Bland-Altman plots and intraclass correlation coefficients (ICC) to quantify agreement. RESULTS: We included a total of 320 children (mean age ± standard deviation [SD] = 9±4.6 years; mean weight 38.1±18.8 kg; 160 female). Liver volume ranged from 340-2,002 mL, and spleen volume ranged from 28-480 mL. Patient weight (kg) (ß=12.5), age (months) (ß=1.7) and sex (female) (ß = -35.3) were independent predictors of liver volume, whereas patient weight (kg) (ß=2.4) and age (months) (ß=0.3) were independent predictors of spleen volume. There was excellent absolute agreement (ICC=0.99) and minimal absolute difference (4 mL) in organ volumes based on reconstructed slice thickness. CONCLUSION: We report reference liver and spleen volumes for children without liver or spleen disease. These results provide reference ranges and potential thresholds to identify liver and spleen size abnormalities that might reflect disease in children.

Defining Normal Ranges of Skeletal Muscle Area and Skeletal Muscle Index in Children on CT Using an Automated Deep Learning Pipeline: Implications for Sarcopenia Diagnosis.

BACKGROUND. Skeletal muscle area (SMA), representing skeletal muscle cross-sectional area at the L3 vertebral level, and skeletal muscle index (SMI), representing height-normalized SMA, can serve as markers of sarcopenia. Normal SMA and SMI values have been reported primarily in adults. OBJECTIVE. The purpose of this study was to use an automated deep learning (DL) pipeline for muscle segmentation on abdominal CT to define normative age- and sex-based values for pediatric muscle cross-sectional area as a guide for diagnosis of sarcopenia in children. METHODS. This retrospective study reviewed records of patients who underwent abdominal CT at Cincinnati Children's Hospital Medical Center from January 1, 2009, to January 3, 2019. Patients were excluded on the basis of age outside of the eligible range (2.00-18.99 years), body mass index (BMI) outside of 5-95% age-based percentiles using CDC and WHO growth charts, known medical condition, medication use, support devices, surgery, or missing axial images at the L3 level. A previously validated automated DL pipeline was used to identify an axial slice at L3 and segment skeletal muscle to generate SMA and SMI. Pearson correlation coefficients were computed. Quantile regression analysis was used to plot SMA and SMI as functions of age and sex and to determine age- and sex-based percentile values. RESULTS. Of 8817 patients who underwent abdominal CT during the study period, 2168 (mean age, 12.3 ± 4.3 [SD] years; 1125 female patients, 1043 male patients) met inclusion criteria. Mean BMI-for-age percentile based on CDC and WHO growth charts was 64.8% ± 25.3% for female patients and 61.4% ± 25.8% for male patients. SMA showed strong correlation with weight, height, age, and BMI for male (0.79-0.94) and female (0.75-0.90) patients; SMI showed weak-to-moderate correlation with weight, height, age, and BMI for male (0.25-0.57) and female (0-0.43) patients. Normal SMA and SMI ranges for age and sex were expressed as curves and as a lookup table, identifying 54 male and 59 female patients with muscle measurements below the 5th percentile regression curve. CONCLUSION. By using an automated DL pipeline in a large sample of carefully selected children, normal ranges for SMA and SMI were calculated as functions of age and sex. CLINICAL IMPACT. The normative values should aid the diagnosis of sarcopenia in children.

Current and emerging artificial intelligence applications for pediatric abdominal imaging.

Artificial intelligence (AI) uses computers to mimic cognitive functions of the human brain, allowing inferences to be made from generally large datasets. Traditional machine learning (e.g., decision tree analysis, support vector machines) and deep learning (e.g., convolutional neural networks) are two commonly employed AI approaches both outside and within the field of medicine. Such techniques can be used to evaluate medical images for the purposes of automated detection and segmentation, classification tasks (including diagnosis, lesion or tissue characterization, and prediction), and image reconstruction. In this review article we highlight recent literature describing current and emerging AI methods applied to abdominal imaging (e.g., CT, MRI and US) and suggest potential future applications of AI in the pediatric population.

Application of reference air kerma alert levels for pediatric fluoroscopic examinations.

The purpose of this study was to provide an empirical model to develop reference air kerma (RAK) alert levels as a function of patient thickness or age for pediatric fluoroscopy for any institution to use in a Quality Assurance program. RAK and patient thickness were collected for 10&663 general fluoroscopic examinations and 1500 fluoroscopically guided interventions (FGIs). RAK and patient age were collected for 6137 fluoroscopic examinations with mobile-C-arms (MC). Coefficients of linear regression fits of logarithmic RAK as a function of patient thickness or age were generated for each fluoroscopy group. Regression fits of RAK for 50%, 90%, and 98% upper prediction levels were used as inputs to derive an empirical formula to estimate alert levels as a function of patient thickness. A methodology is presented to scale results from this study for any patient thickness or age for any institution, for example, the patient thickness dependent RAK alert level at the top 1% of expected RAK can be set using the 98% upper prediction interval boundary given by: RAK 98 % = e m . x avg + s 98 . c ̂ ${\rm{RAK}}_{98\% } = {e}^{m.{x}_{{\rm{avg}}} + {s}_{98}.\hat{c}}\ $ , where xavg is the institute's average patient thickness or age, and c ̂ $\hat{c}$ is the intercept based on the average RAK of the patient population calculated as c ̂ = ln ( RAK avg ) - m . x avg . RA K avg $\hat{c} = \ln ( {{\rm{RAK}}_{{\rm{avg}}}} )\ - m.{x}_{{\rm{avg}}}{\rm{.RA}}{{\rm{K}}}_{{\rm{avg}}}$ is the institution's average RAK (mGy). m and s98 are constants presented for each type of fluoroscope and RAK group and represent slope of the fit and scale factor, respectively. An empirical equation, which estimates alert levels expressed as air Kerma without backscatter at the interventional reference point as a function of patient thickness or age is provided for each fluoroscopic examination type. The empirical equations allow any facility with limited data to scale the results of this study's single facility data to model their practice's unique RAK alert levels and patient population demographics to establish pediatric alert levels for fluoroscopic procedures.

Improving Image Quality and Reducing Radiation Dose for Pediatric CT by Using Deep Learning Reconstruction.

Background CT deep learning reconstruction (DLR) algorithms have been developed to remove image noise. How the DLR affects image quality and radiation dose reduction has yet to be fully investigated. Purpose To investigate a DLR algorithm's dose reduction and image quality improvement for pediatric CT. Materials and Methods DLR was compared with filtered back projection (FBP), statistical-based iterative reconstruction (SBIR), and model-based iterative reconstruction (MBIR) in a retrospective study by using data from CT examinations of pediatric patients (February to December 2018). A comparison of object detectability for 15 objects (diameter, 0.5-10 mm) at four contrast difference levels (50, 150, 250, and 350 HU) was performed by using a non-prewhitening-matched mathematical observer model with eye filter (d'NPWE), task transfer function, and noise power spectrum analysis. Object detectability was assessed by using area under the curve analysis. Three pediatric radiologists performed an observer study to assess anatomic structures with low object-to-background signal and contrast to noise in the azygos vein, right hepatic vein, common bile duct, and superior mesenteric artery. Observers rated from 1 to 10 (worst to best) for edge definition, quantum noise level, and object conspicuity. Analysis of variance and Tukey honest significant difference post hoc tests were used to analyze differences between reconstruction algorithms. Results Images from 19 patients (mean age, 11 years ± 5 [standard deviation]; 10 female patients) were evaluated. Compared with FBP, SBIR, and MBIR, DLR demonstrated improved object detectability by 51% (16.5 of 10.9), 18% (16.5 of 13.9), and 11% (16.5 of 14.8), respectively. DLR reduced image noise without noise texture effects seen with MBIR. Radiologist ratings were 7 ± 1 (DLR), 6.2 ± 1 (MBIR), 6.2 ± 1 (SBIR), and 4.6 ± 1 (FBP); two-way analysis of variance showed a difference on the basis of reconstruction type (P < .001). Radiologists consistently preferred DLR images (intraclass correlation coefficient, 0.89; 95% CI: 0.83, 0.93). DLR demonstrated 52% (1 of 2.1) greater dose reduction than SBIR. Conclusion The DLR algorithm improved image quality and dose reduction without sacrificing noise texture and spatial resolution. © RSNA, 2020 Online supplemental material is available for this article.

Comparison of 0.3-mSv CT to Standard-Dose CT for Detection of Lung Nodules in Children and Young Adults With Cancer.

BACKGROUND. CT is the imaging modality of choice to identify lung metastasis. OBJECTIVE. The purpose of this study was to evaluate the performance of reduced-dose CT for the detection of lung nodules in children and young adults with cancer. METHODS. This prospective study enrolled patients 4-21 years old with known or suspected malignancy who were undergoing clinically indicated chest CT. Study participants underwent an additional investigational reduced-dose chest CT examination in the same imaging encounter. Separated deidentified CT examinations were reviewed in blinded fashion by three independent radiologists. One reviewer performed a subsequent secondary review to match nodules between the standard- and reduced-dose examinations. Diagnostic performance was computed for the reduced-dose examinations using the clinical examinations as the reference standard. Intraobserver agreement and interobserver agreement were calculated using Cohen kappa. RESULTS. A total of 78 patients (44 male patients and 34 female patients; mean age, 15.2 ± 3.8 [SD] years) were enrolled. The mean estimated effective dose was 1.8 ± 1.1 mSv for clinical CT and 0.3 ± 0.1 mSv for reduced-dose CT, which is an 83% dose reduction. Forty-five of the 78 (58%) patients had 162 total lung nodules (mean size, 3.4 ± 3.3 mm) detected on the clinical CT examinations. A total of 92% of nodules were visible on reduced-dose CT. The sensitivity and specificity of reduced-dose CT for nodules ranged from 63% to 77% and from 80% to 90%, respectively, across the three reviewers. Intraob-server agreement between clinical CT and reduced-dose CT was moderate to substantial for the presence of nodules (κ = 0.45-0.67) and was good to excellent for the number of nodules (κ = 0.68-0.84) and nodule size (κ = 0.69-0.86). Interobserver agreement for the presence of nodules was moderate for both reduced-dose (κ = 0.53) and clinical (κ = 0.54) CT. A median of one nodule was present on clinical CT in patients with a falsely negative reduced-dose CT examination. CONCLUSION. Reduced-dose CT depicts more than 90% of lung nodules in children and young adults with cancer. Reviewers identified the presence of nodules with moderate sensitivity and high specificity. CLINICAL IMPACT. CT performed at a 0.3-mSv mean effective dose has acceptable diagnostic performance for lung nodule detection in children and young adults and has the potential to reduce patient dose or expand CT utilization (e.g., to replace radiography in screening or monitoring protocols). TRIAL REGISTRATION. ClinicalTrials.gov NCT03681873.

DeepLiverNet: a deep transfer learning model for classifying liver stiffness using clinical and T2-weighted magnetic resonance imaging data in children and young adults.

BACKGROUND: Although MR elastography allows for quantitative evaluation of liver stiffness to assess chronic liver diseases, it has associated drawbacks related to additional scanning time, patient discomfort, and added costs. OBJECTIVE: To develop a machine learning model that can categorically classify the severity of liver stiffness using both anatomical T2-weighted MRI and clinical data for children and young adults with known or suspected pediatric chronic liver diseases. MATERIALS AND METHODS: We included 273 subjects with known or suspected chronic liver disease. We extracted data including axial T2-weighted fast spin-echo fat-suppressed images, clinical data (e.g., demographic/anthropomorphic data, particular medical diagnoses, laboratory values) and MR elastography liver stiffness measurements. We propose DeepLiverNet (a deep transfer learning model) to classify patients into one of two groups: no/mild liver stiffening (<3 kPa) or moderate/severe liver stiffening (≥3 kPa). We conducted internal cross-validation using 178 subjects, and external validation using an independent cohort of 95 subjects. We assessed diagnostic performance using accuracy, sensitivity, specificity and area under the receiver operating characteristic curve (AuROC). RESULTS: In the internal cross-validation experiment, the combination of clinical and imaging data produced the best performance (AuROC=0.86) compared to clinical (AuROC=0.83) or imaging (AuROC=0.80) data alone. Using both clinical and imaging data, the DeepLiverNet correctly classified patients with accuracy of 88.0%, sensitivity of 74.3% and specificity of 94.6%. In our external validation experiment, this same deep learning model achieved an accuracy of 80.0%, sensitivity of 61.1%, specificity of 91.5% and AuROC of 0.79. CONCLUSION: A deep learning model that incorporates clinical data and anatomical T2-weighted MR images might provide a means of risk-stratifying liver stiffness and directing the use of MR elastography.

Radiation Dose for Pediatric CT: Comparison of Pediatric versus Adult Imaging Facilities.

Background The American College of Radiology Dose Index Registry for CT enables evaluation of radiation dose as a function of patient characteristics and examination type. The hypothesis of this study was that academic pediatric CT facilities have optimized CT protocols that may result in a lower and less variable radiation dose in children. Materials and Methods A retrospective study of doses (mean patient age, 12 years; age range, 0-21 years) was performed by using data from the National Radiology Data Registry (year range, 2016-2017) (n = 239 622). Three examination types were evaluated: brain without contrast enhancement, chest without contrast enhancement, and abdomen-pelvis with intravenous contrast enhancement. Three dose indexes-volume CT dose index (CTDIvol), size-specific dose estimate (SSDE), and dose-length product (DLP)-were analyzed by using six different size groups. The unequal variance t test and the F test were used to compare mean dose and variances, respectively, at academic pediatric facilities with those at other facility types for each size category. The Bonferroni-Holm correction factor was applied to account for the multiple comparisons. Results Pediatric radiation dose in academic pediatric facilities was significantly lower, with smaller variance for all brain, 42 of 54 (78%) chest, and 48 of 54 (89%) abdomen-pelvis examinations across all six size groups, three dose descriptors, and when compared with that at the other three facilities. For example, abdomen-pelvis SSDE for the 14.5-18-cm size group was 3.6, 5.4, 5.5, and 8.3 mGy, respectively, for academic pediatric, nonacademic pediatric, academic adult, and nonacademic adult facilities (SSDE mean and variance P < .001). Mean SSDE for the smallest patients in nonacademic adult facilities was 51% (6.1 vs 11.9 mGy) of the facility's adult dose. Conclusion Academic pediatric facilities use lower CT radiation dose with less variation than do nonacademic pediatric or adult facilities for all brain examinations and for the majority of chest and abdomen-pelvis examinations. © RSNA, 2019 See also the editorial by Strouse in this issue.

Machine Learning Prediction of Liver Stiffness Using Clinical and T2-Weighted MRI Radiomic Data.

OBJECTIVE. The purpose of this study is to develop a machine learning model to categorically classify MR elastography (MRE)-derived liver stiffness using clinical and nonelastographic MRI radiomic features in pediatric and young adult patients with known or suspected liver disease. MATERIALS AND METHODS. Clinical data (27 demographic, anthropomorphic, medical history, and laboratory features), MRI presence of liver fat and chemical shift-encoded fat fraction, and MRE mean liver stiffness measurements were retrieved from electronic medical records. MRI radiomic data (105 features) were extracted from T2-weighted fast spin-echo images. Patients were categorized by mean liver stiffness (< 3 vs ≥ 3 kPa). Support vector machine (SVM) models were used to perform two-class classification using clinical features, radiomic features, and both clinical and radiomic features. Our proposed model was internally evaluated in 225 patients (mean age, 14.1 years) and externally evaluated in an independent cohort of 84 patients (mean age, 13.7 years). Diagnostic performance was assessed using ROC AUC values. RESULTS. In our internal cross-validation model, the combination of clinical and radiomic features produced the best performance (AUC = 0.84), compared with clinical (AUC = 0.77) or radiomic (AUC = 0.70) features alone. Using both clinical and radiomic features, the SVM model was able to correctly classify patients with accuracy of 81.8%, sensitivity of 72.2%, and specificity of 87.0%. In our external validation experiment, this SVM model achieved an accuracy of 75.0%, sensitivity of 63.6%, specificity of 82.4%, and AUC of 0.80. CONCLUSION. An SVM learning model incorporating clinical and T2-weighted radiomic features has fair-to-good diagnostic performance for categorically classifying liver stiffness.

Development and validation of an open source Monte Carlo dosimetry model for wide-beam CT scanners using Fluka.

PURPOSE: Development and validation of an open source Fluka-based Monte Carlo source model for diagnostic patient dose calculations. METHODS: A framework to simulate a computed tomography (CT) scanner using Fluka Monte Carlo particle transport code was developed. The General Electric (GE) Revolution scanner with the large body filter and 120 kV tube potential was characterized using measurements. The model was validated on benchmark CT test problems and on dose measurements in computed tomography dose index (CTDI) and anthropomorphic phantoms. Axial and helical operation modes with provision for tube current modulation (TCM) were implemented. The particle simulations in Fluka were accelerated by executing them on a high-performance computing cluster. RESULTS: The simulation results agreed to better than an average of 4% of the reference simulation results from the AAPM Report 195 test scenarios, namely: better than 2% for both test problems in case 4 using the PMMA phantom, and better than 5% of the reference result for 14 of 17 organs in case 5, and within 10% for the three remaining organs. The Fluka simulation results agreed to better than 2% of the air kerma measured in-air at isocenter of the GE Revolution scanner. The simulated air kerma in the center of the CTDI phantom overestimated the measurement by 7.5% and a correction factor was introduced to account for this. The simulated mean absorbed doses for a chest scan of the pediatric anthropomorphic phantom was completed in ~9 min and agreed to within the 95% CI for bone, soft tissue, and lung measurements made using MOSFET detectors for fixed current axial and helical scans as well as helical scan with TCM. CONCLUSION: A Fluka-based Monte Carlo simulation model of axial and helical acquisition techniques using a wide-beam collimation CT scanner demonstrated good agreement between measured and simulated results for both fixed current and TCM in complex and simple geometries. Code and dataset will be made available at https://github.com/chezhia/FLUKA_CT.

The role of chest computed tomography (CT) as a surveillance tool in children with high-risk neuroblastoma.

BACKGROUND: Standardization of imaging obtained in children with neuroblastoma is not well established. This study examines chest CT in pediatric patients with high-risk neuroblastoma. PROCEDURE: Medical records and imaging from 88 patients with high-risk neuroblastoma, diagnosed at St. Jude Children's Research Hospital between January, 2002 and December, 2009, were reviewed. Surveillance imaging was conducted through 2013. Ten patients with thoracic disease at diagnosis were excluded. Event free survival (EFS) and overall survival (OS) were estimated. Size specific dose estimates for CT scans of the chest, abdomen, and pelvis were used to estimate absolute organ doses to 23 organs. Organ dosimetry was used to calculate cohort effective dose. RESULTS: The 5 year OS and EFS were 51.9% ± 6.5% and 42.6% ± 6.5%, respectively. Forty-six (58.9%) patients progressed/recurred and 41 (52.6%) died of disease. Eleven patients (14%) developed thoracic disease progression/recurrence identified by chest CT (1 paraspinal mass, 1 pulmonary nodules, and 9 nodal). MIBG (metaiodobenzylguanidine) scans identified thoracic disease in six patients. Five of the 11 had normal chest MIBG scans; three were symptomatic and two were asymptomatic with normal chest MIBG scans but avid bone disease. The estimated radiation dose savings from surveillance without CT chest imaging was 42%, 34% when accounting for modern CT acquisition (2011-2013). CONCLUSIONS: Neuroblastoma progression/recurrence in the chest is rare and often presents with symptoms or is identified using standard non-CT imaging modalities. For patients with non-thoracic high-risk neuroblastoma at diagnosis, omission of surveillance chest CT imaging can save 35-42% of the radiation burden without compromising disease detection.

A Comprehensive Risk Assessment Method for Pediatric Patients Undergoing Research Examinations Using Ionizing Radiation: How We Answered the Institutional Review Board.

OBJECTIVE: The objectives of this study are to establish a comprehensive method for radiation dose estimates for the most common imaging examinations performed for research, for internal use of institutional review board (IRB) and radiation safety committees; to provide investigators with relative examination doses so that they may better assess the potential radiation effects and risks for research subjects; and to provide simplified language that investigators can use in consent documents. MATERIALS AND METHODS: Nineteen common radiation-based examinations used in clinical research at our institution were identified. For each modality (CT, digital radiography, dual-energy x-ray absorptiometry, PET/CT, and nuclear medicine), a comprehensive patient-specific dosimetry method was established. Effective dose was calculated according to average population calculated doses for the following age groups: 0-1, 2-8, 9-13, 14-15, and older than 15 years. RESULTS: Estimated effective dose values were tabulated and posted on our institutional IRB intranet site for use by IRB and radiation safety committee members and institutional investigators. Relative examination dose levels were compared for all ages and for all examinations. A three-tiered approach to establish consent language for radiation exposure was established for research subjects receiving an effective dose less than 3 mSv, a dose between 3 and 50 mSv, and a dose greater than 50 mSv. CONCLUSION: The method to estimate effective dose was tabulated for 19 of the most common ionizing radiation examinations at our institute. These results will act as a resource to help investigators better understand the implications of radiation exposure in research and can assist investigators in protocol development and correct categorization of radiation exposure risk.

How to Appropriately Calculate Effective Dose for CT Using Either Size-Specific Dose Estimates or Dose-Length Product.

OBJECTIVE: The purpose of this study is to show how to calculate effective dose in CT using size-specific dose estimates and to correct the current method using dose-length product (DLP). MATERIALS AND METHODS: Data were analyzed from 352 chest and 241 abdominopelvic CT images. Size-specific dose estimate was used as a surrogate for organ dose in the chest and abdominopelvic regions. Organ doses were averaged by patient weight-based populations and were used to calculate effective dose by the International Commission on Radiological Protection (ICRP) report 103 method using tissue-weighting factors (EICRP). In addition, effective dose was calculated using population-averaged CT examination DLP for the chest and abdominopelvic region using published k-coefficients (EDLP = k × DLP). RESULTS: EDLP differed from EICRP by an average of 21% (1.4 vs 1.1) in the chest and 42% (2.4 vs 3.4) in the abdominopelvic region. The differences occurred because the published kcoefficients did not account for pitch factor other than unity, were derived using a 32-cm diameter CT dose index (CTDI) phantom for CT examinations of the pediatric body, and used ICRP 60 tissue-weighting factors. Once it was corrected for pitch factor, the appropriate size of CTDI phantom, and ICRP 103 tissue-weighting factors, EDLP improved in agreement with EICRP to better than 7% (1.4 vs 1.3) and 4% (2.4 vs 2.5) for chest and abdominopelvic regions, respectively. CONCLUSION: Current use of DLP to calculate effective dose was shown to be deficient because of the outdated means by which the k-coefficients were derived. This study shows a means to calculate EICRP using patient size-specific dose estimate and how to appropriately correct EDLP.

Pediatric CT: implementation of ASIR for substantial radiation dose reduction while maintaining pre-ASIR image noise.

PURPOSE: To determine a comprehensive method for the implementation of adaptive statistical iterative reconstruction (ASIR) for maximal radiation dose reduction in pediatric computed tomography (CT) without changing the magnitude of noise in the reconstructed image or the contrast-to-noise ratio (CNR) in the patient. MATERIALS AND METHODS: The institutional review board waived the need to obtain informed consent for this HIPAA-compliant quality analysis. Chest and abdominopelvic CT images obtained before ASIR implementation (183 patient examinations; mean patient age, 8.8 years ± 6.2 [standard deviation]; range, 1 month to 27 years) were analyzed for image noise and CNR. These measurements were used in conjunction with noise models derived from anthropomorphic phantoms to establish new beam current-modulated CT parameters to implement 40% ASIR at 120 and 100 kVp without changing noise texture or magnitude. Image noise was assessed in images obtained after ASIR implementation (492 patient examinations; mean patient age, 7.6 years ± 5.4; range, 2 months to 28 years) the same way it was assessed in the pre-ASIR analysis. Dose reduction was determined by comparing size-specific dose estimates in the pre- and post-ASIR patient cohorts. Data were analyzed with paired t tests. RESULTS: With 40% ASIR implementation, the average relative dose reduction for chest CT was 39% (2.7/4.4 mGy), with a maximum reduction of 72% (5.3/18.8 mGy). The average relative dose reduction for abdominopelvic CT was 29% (4.8/6.8 mGy), with a maximum reduction of 64% (7.6/20.9 mGy). Beam current modulation was unnecessary for patients weighing 40 kg or less. The difference between 0% and 40% ASIR noise magnitude was less than 1 HU, with statistically nonsignificant increases in patient CNR at 100 kVp of 8% (15.3/14.2; P = .41) for chest CT and 13% (7.8/6.8; P = .40) for abdominopelvic CT. CONCLUSION: Radiation dose reduction at pediatric CT was achieved when 40% ASIR was implemented as a dose reduction tool only; no net change to the magnitude of noise in the reconstructed image or the patient CNR occurred.

Is routine pelvic surveillance imaging necessary in patients with Wilms tumor?

BACKGROUND: It is unclear whether routine pelvic imaging is needed in patients with Wilms tumor. Thus, the primary objective of the current study was to examine the role of routine pelvic computed tomography (CT) in a cohort of pediatric patients with Wilms tumor. METHODS: With institutional review board approval, the authors retrospectively identified 110 patients who had Wilms tumor diagnosed between January 1999 and December 2009 with surveillance imaging that continued through March 2011. The authors estimated overall survival (OS), event-free survival (EFS), and dosimetry from dose length product (DLP) conversion to the effective dose (ED) for every CT in a subgroup of 80 patients who had CT studies obtained using contemporary scanners (2002-2011). Metal-oxide-semiconductor field-effect transistor (MOSFET) dosimeters were placed within organs of anthropomorphic phantoms to directly calculate the truncal ED. ED(DLP) was correlated with ED(MOSFET) to calculate potential pelvic dose savings. RESULTS: Eighty patients underwent 605 CT examinations that contained DLP information, including 352 CT scans of the chest, abdomen, and pelvis; 123 CT scans of the chest and abdomen; 102 CT scans of the chest only; 18 CT scans of the abdomen and pelvis; 9 CT scans of the abdomen only; and 1 CT that was limited to the pelvis. The respective 5-year OS and EFS estimates were 92.8% ± 3% and 2.6% ± 4.3%. Sixteen of 110 patients (15%) developed a relapse a median of 11.3 months (range, 5.0 months to 7.3 years) after diagnosis, and 4 patients died of disease recurrence. Three patients developed pelvic relapses, all 3 of which were symptomatic. The estimated ED savings from sex-neutral CT surveillance performed at a 120-kilovolt peak without pelvic imaging was calculated as 30.5% for the average patient aged 1 year, 30.4% for the average patient aged 5 years, 39.4% for the average patient aged 10 years, and 44.9% for the average patient aged 15 years. CONCLUSIONS: Omitting pelvic CT from the routine, off-therapy follow-up of patients with Wilms tumor saved an average 30% to 45% of the ED without compromising disease detection.

Implementation of AI image reconstruction in CT-how is it validated and what dose reductions can be achieved.

CT reconstruction has undergone a substantial change over the last decade with the introduction of iterative reconstruction (IR) and now with deep learning reconstruction (DLR). In this review, DLR will be compared to IR and filtered back-projection (FBP) reconstructions. Comparisons will be made using image quality metrics such as noise power spectrum, contrast-dependent task-based transfer function, and non-prewhitening filter detectability index (dNPW'). Discussion on how DLR has impacted CT image quality, low-contrast detectability, and diagnostic confidence will be provided. DLR has shown the ability to improve in areas that IR is lacking, namely: noise magnitude reduction does not alter noise texture to the degree that IR did, and the noise texture found in DLR is more aligned with noise texture of an FBP reconstruction. Additionally, the dose reduction potential for DLR is shown to be greater than IR. For IR, the consensus was dose reduction should be limited to no more than 15-30% to preserve low-contrast detectability. For DLR, initial phantom and patient observer studies have shown acceptable dose reduction between 44 and 83% for both low- and high-contrast object detectability tasks. Ultimately, DLR is able to be used for CT reconstruction in place of IR, making it an easy "turnkey" upgrade for CT reconstruction. DLR for CT is actively being improved as more vendor options are being developed and current DLR options are being enhanced with second generation algorithms being released. DLR is still in its developmental early stages, but is shown to be a promising future for CT reconstruction.

Investigation of American Association of Physicists in Medicine Report 204 size-specific dose estimates for pediatric CT implementation.

PURPOSE: To compare five methodologies the American Association of Physicists in Medicine Report 204 used to calculate size-specific dose estimates (SSDEs) for pediatric computed tomography (CT). MATERIALS AND METHODS: The institutional review board waived consent for this HIPAA-compliant retrospective study. The five SSDE methodologies were investigated for calculation variation based on volumetric CT dose index (CTDI), or CTDI(vol), of chest, abdominal, and pelvic CT. SSDE calculations were derived from a predominantly pediatric population of 186 patients retrospectively and consecutively analyzed from June through November 2011. Eighty (43%) of the 186 patients were female, and 106 (57%) were male. Mean patient age was 8.6 years ± 6.3 (standard deviation), the age range was 1 month to 28 years, and mean weight was 37.7 kg ± 33.1, with a range of 3.4-146.6 kg. SSDE conversion factors were derived from anteroposterior (AP) and lateral dimensions measured on the patient's CT radiograph. The measurements were either used independently, or as a summation, or to calculate the patient's effective diameter; additionally, SSDE was derived on the basis of the patient's age (International Commission on Radiation Units Report 74 data). SSDE conversion factors were applied to CTDI(vol) data that corrected for both 16- and 32-cm-diameter CTDI phantom measurements. SSDE data were summarized by using the patient's originally prescribed weight-based CT scanning protocols. Data were summarized by using descriptive statistics. RESULTS: SSDEs derived from individual measurements varied 2%-12%. The combination of measurements (sum or effective diameter) varied 0.9%-2%. The age approach varied by an average of 2% (in the younger population [0-13 years]), but up to 44%, with an average of 18% (in the older population [14-18 years]). No SSDE correction was required for patients of varying size who weighed 36 kg or less when CTDI(vol) was measured by using a 16-cm CTDI phantom or for patients weighing 100-140 kg when CTDI(vol) was measured by using a 32-cm phantom. CTDI(vol) measured by using a 32-cm phantom in patients weighing between 36 and 100 kg and patients weighing more than 140 kg differed from SSDE by an average of 35%. An average difference of 1% was found between male and female SSDE-corrected values when the two sexes were compared within the same CT weight scanning categories. CONCLUSION: The combination of AP and lateral measurements should be used to determine SSDE correction factors when possible. For pediatric patients, CTDI(vol) calculated with a 32-cm phantom requires SSDE conversion to more accurately estimate patient dose; CTDI(vol) calculated with a 16-cm phantom for pediatric patients weighing 36 kg or less does not require SSDE conversion.

Reducing Pediatric Intraoral Radiography Radiation Dose Using Reduced-Power Dental X-Ray Units: A Randomized Trial.

Purpose: To assess the diagnostic confidence of intraoral radiographic image quality while reducing the pediatric patient's radiation exposure using a longer position indicating device (PID), additional X-ray beam filtration and rectangular collimation while using modern, lower-power intraoral dental X-ray units.
Methods: A randomized prospective study scored bitewing intraoral dental images based on relevant clinical features. Observer studies with pediatric dentists and dental residents were conducted to verify whether diagnostic confidence remained unchanged after dose reduction modifications. The study involved a two-phase investigation to determine: (1) the best thickness of aluminum (Al) 2024-T3 alloy filter and (2) required increased exposure time to maintain intraoral radiographic image quality. A 30 cm PID with a rectangular collimator was used to further manage patient dose. For each phase, images from 125 patients were collected from February 2017 to September 2018 and analyzed.
Results: The results from the observer study using a 30 cm PID, 1.02 mm thick Al alloy filter, and a rectangular collimator resulted in a patient dose reduction between 64 percent (exposure time of 400 msec) to 77 percent (250 msec), without any statis- tically significant effect to the diagnostic confidence of the observers in evaluating the reduced radiation images.
Conclusion: Long recognized dose reduction methods, when implemented on a modern, low-power intraoral dental X-ray unit, do not impact confidence in bite- wing diagnostic images, but substantially reduce patient dose and should be adopted to increase patient safety, especially for children.

Detection of urinary tract calculi on CT images reconstructed with deep learning algorithms.

BACKGROUND: Deep learning Computed Tomography (CT) reconstruction (DLR) algorithms promise to improve image quality but the impact on clinical diagnostic performance remains to be demonstrated. We aimed to compare DLR to standard iterative reconstruction for detection of urolithiasis by unenhanced CT in children and young adults. METHODS: This was an IRB approved retrospective study involving post-hoc reconstruction of clinically acquired unenhanced abdomen/pelvis CT scans. Images were reconstructed with six different manufacturer-standard DLR algorithms and reformatted in 3 planes (axial, sagittal, and coronal) at 3 mm intervals. De-identified reconstructions were loaded as independent examinations for review by 3 blinded radiologists (R1, R2, R3) tasked with identifying and measuring all stones. Results were compared to the clinical iterative reconstruction images as a reference standard. IntraClass correlation coefficients and kappa (k) statistics were used to quantify agreement. RESULTS: CT data for 14 patients (mean age: 17.3 ± 3.4 years, 5 males and 9 females, weight class: 31-70 kg (n = 6), 71-100 kg (n = 7), > 100 kg (n = 1)) were reconstructed into 84 total exams. 7 patients had urinary tract calculi. Interobserver agreement on the presence of any urinary tract calculus was substantial to almost perfect (k = 0.71-1) for all DLR algorithms. Agreement with the reference standard on number of calculi was excellent (ICC = 0.78-0.96) and agreement on the size of the largest calculus was fair to excellent (ICC = 0.51-0.97) depending on reviewer and DLR algorithm. CONCLUSION: Deep learning reconstruction of unenhanced CT images allows similar renal stone detectability compared to iterative reconstruction.