Deep learning-based age estimation from chest CT scans.

PURPOSE: Medical imaging can be used to estimate a patient's biological age, which may provide complementary information to clinicians compared to chronological age. In this study, we aimed to develop a method to estimate a patient's age based on their chest CT scan. Additionally, we investigated whether chest CT estimated age is a more accurate predictor of lung cancer risk compared to chronological age. METHODS: To develop our age prediction model, we utilized composite CT images and Inception-ResNet-v2. The model was trained, validated, and tested on 13,824 chest CT scans from the National Lung Screening Trial, with 91% for training, 5% for validation, and 4% for testing. Additionally, we independently tested the model on 1849 CT scans collected locally. To assess chest CT estimated age as a risk factor for lung cancer, we computed the relative lung cancer risk between two groups. Group 1 consisted of individuals assigned a CT age older than their chronological age, while Group 2 comprised those assigned a CT age younger than their chronological age. RESULTS: Our analysis revealed a mean absolute error of 1.84 years and a Pearson's correlation coefficient of 0.97 for our local data when comparing chronological age with the estimated CT age. The model showed the most activation in the area associated with the lungs during age estimation. The relative risk for lung cancer was 1.82 (95% confidence interval, 1.65-2.02) for individuals assigned a CT age older than their chronological age compared to those assigned a CT age younger than their chronological age. CONCLUSION: Findings suggest that chest CT age captures some aspects of biological aging and may be a more accurate predictor of lung cancer risk than chronological age. Future studies with larger and more diverse patients are required for the generalization of the interpretations.

Applications of deep learning to reduce the need for iodinated contrast media for CT imaging: a systematic review.

PURPOSE: The usage of iodinated contrast media (ICM) can improve the sensitivity and specificity of computed tomography (CT) for many clinical indications. However, the adverse effects of ICM administration can include renal injury, life-threatening allergic-like reactions, and environmental contamination. Deep learning (DL) models can generate full-dose ICM CT images from non-contrast or low-dose ICM administration or generate non-contrast CT from full-dose ICM CT. Eliminating the need for both contrast-enhanced and non-enhanced imaging or reducing the amount of required contrast while maintaining diagnostic capability may reduce overall patient risk, improve efficiency and minimize costs. We reviewed the current capabilities of DL to reduce the need for contrast administration in CT. METHODS: We conducted a systematic review of articles utilizing DL to reduce the amount of ICM required in CT, searching MEDLINE, Embase, Compendex, Inspec, and Scopus to identify papers published from 2016 to 2022. We classified the articles based on the DL model and ICM reduction. RESULTS: Eighteen papers met the inclusion criteria for analysis. Of these, ten generated synthetic full-dose (100%) ICM from real non-contrast CT, while four augmented low-dose to full-dose ICM CT. Three used DL to create synthetic non-contrast CT from real 100% ICM CT, while one paper used DL to translate the 100% ICM to non-contrast CT and vice versa. DL models commonly used generative adversarial networks trained and tested by paired contrast-enhanced and non-contrast or low ICM CTs. Image quality metrics such as peak signal-to-noise ratio and structural similarity index were frequently used for comparing synthetic versus real CT image quality. CONCLUSION: DL-generated contrast-enhanced or non-contrast CT may assist in diagnosis and radiation therapy planning; however, further work to optimize protocols to reduce or eliminate ICM for specific pathology is still needed along with a dedicated assessment of the clinical utility of these synthetic images.

Comparison of the gamma-Pareto convolution with conventional methods of characterising metformin pharmacokinetics in dogs.

A model was developed for long term metformin tissue retention based upon temporally inclusive models of serum/plasma concentration ([Formula: see text]) having power function tails called the gamma-Pareto type I convolution (GPC) model and was contrasted with biexponential (E2) and noncompartmental (NC) metformin models. GPC models of [Formula: see text] have a peripheral venous first arrival of drug-times parameter, early [Formula: see text] peaks and very slow washouts of [Formula: see text]. The GPC, E2 and NC models were applied to a total of 148 serum samples drawn from 20 min to 72 h following bolus intravenous metformin in seven healthy mongrel dogs. The GPC model was used to calculate area under the curve (AUC), clearance ([Formula: see text]), and functions of time, f(t), for drug mass remaining (M), apparent volume of distribution ([Formula: see text]), as well as [Formula: see text] for [Formula: see text], [Formula: see text] and [Formula: see text]. The GPC models of [Formula: see text] yielded metformin [Formula: see text]-values that were 84.8% of total renal plasma flow (RPF) as estimated from meta-analysis. The GPC [Formula: see text]-values were significantly less than the corresponding NC and E2 [Formula: see text]-values of 104.7% and 123.7% of RPF, respectively. The GPC plasma/serum only model predicted 78.9% drug [Formula: see text] average urinary recovery at 72 h; similar to prior human urine drug [Formula: see text] collection results. The GPC model [Formula: see text] of [Formula: see text], [Formula: see text] and [Formula: see text], were asymptotically proportional to elapsed time, with a constant limiting [Formula: see text] ratio of M/C averaging 7.0 times, a result in keeping with prior simultaneous [Formula: see text] and urine [Formula: see text] collection studies and exhibiting a rate of apparent volume growth of [Formula: see text] that achieved limiting constant values. A simulated constant average drug mass multidosing protocol exhibited increased [Formula: see text] and [Formula: see text] with elapsing time, effects that have been observed experimentally during same-dose multidosing. The GPC heavy-tailed models explained multiple documented phenomena that were unexplained with lighter-tailed models.

Iron quantification in Parkinson's disease using an age-based threshold on susceptibility maps: The advantage of local versus entire structure iron content measurements.

BACKGROUND: Elevated brain iron has been observed in Idiopathic Parkinson's disease (IPD) within the deep gray matter. Using quantitative susceptibility mapping (QSM) and a thresholded high-iron region, we quantified iron content in the midbrain of patients with Parkinson's disease as a function of age. METHODS: We used MRI to scan 24 IPD patients at 3-Tesla. Susceptibility-weighted images were collected with the following parameters, TE: 6 and 20 ms, TR: 30 ms, FA: 15°, and resolution: 0.5 × 0.5 × 2.0 mm3. QSM images were reconstructed from the source phase images. Whole-region and thresholded high-iron (RII) region boundaries for the Substantia Nigra (SN) and Red Nucleus (RN) were traced. Iron content was measured via mean susceptibilities and volumes, which were compared between the groups, as well as between right and left side of the structures within groups. RESULTS: Twenty patients with mild to moderate IPD were used in this study. For the SN, mean RII and whole-region iron and volumes were higher in the IPD group compared to HC, as well as mean RII for the RN, while no differences were seen between the groups when considering whole-region mean susceptibility bilaterally for the RN. CONCLUSION: Using a two-region of interest analysis on QSM, we showed that abnormal iron occurs in IPD patients in the SN and with greater volumes compared to HC. This method may have application as a biomarker for disease diagnosis and early intervention.

Incidence and Economic Impact of Incidental Findings on 18F-FDG PET/CT Imaging.

PURPOSE: The study sought to determine the incidence of incidental findings on whole-body positron emission tomography with computed tomography (PET/CT) imaging and the average costs of investigations to follow-up or further characterize incidental findings. METHODS: Imaging reports of 215 patients who underwent whole-body PET/CT imaging were retrospectively reviewed. Our provincial picture archiving and communication system was queried and patient charts were reviewed to identify all investigations performed to follow-up incidental findings within 1 year of the initial PET/CT study. Costs of follow-up imaging studies (professional and technical components) and other diagnostic tests and procedures were determined in Canadian dollars (CAD) and U.S. dollars (USD) using the 2015 Ontario Health Insurance Plan Schedule of Benefits and Fees and 2016 U.S. Medicare Physician Fee Schedule, respectively. RESULTS: At least 1 incidental finding was reported in 161 reports (74.9%). The mean number of incidental findings ranged from 0.64 in patients <45 years of age to 2.2 in patients 75 years of age and older. Seventy-five recommendations for additional investigations were made for 64 (30%) patients undergoing PET/CT imaging, and 14 of those were carried out specifically to follow-up incidental findings. Averaged across all 215 patients, the total cost of investigations recommended to follow-up incidental findings was CAD$105.51 (USD$127.56) per PET/CT study if all recommendations were acted on, and CAD$22.77 (USD$29.14) based on investigations actually performed. CONCLUSIONS: As the incidence of incidental findings increases with age and a larger proportion of elderly patients is expected as population demographics change, it will be increasingly important to consider incidental findings on PET/CT imaging with standardized approaches to follow-up.

Initial Experience Using a Telerobotic Ultrasound System for Adult Abdominal Sonography.

PURPOSE: The study sought to assess the feasibility of performing adult abdominal examinations using a telerobotic ultrasound system in which radiologists or sonographers can control fine movements of a transducer and all ultrasound settings from a remote location. METHODS: Eighteen patients prospectively underwent a conventional sonography examination (using EPIQ 5 [Philips] or LOGIQ E9 [GE Healthcare]) followed by a telerobotic sonography examination (using the MELODY System [AdEchoTech] and SonixTablet [BK Ultrasound]) according to a standardized abdominal imaging protocol. For telerobotic examinations, patients were scanned remotely by a sonographer 2.75 km away. Conventional examinations were read independently from telerobotic examinations. Image quality and acceptability to patients and sonographers was assessed. RESULTS: Ninety-two percent of organs visualized on conventional examinations were sufficiently visualized on telerobotic examinations. Five pathological findings were identified on both telerobotic and conventional examinations, 3 findings were identified using only conventional sonography, and 2 findings were identified using only telerobotic sonography. A paired sample t test showed no significant difference between the 2 modalities in measurements of the liver, spleen, and diameter of the proximal aorta; however, telerobotic assessments overestimated distal aorta and common bile duct diameters and underestimated kidney lengths (P values < .05). All patients responded that they would be willing to have another telerobotic examination. CONCLUSIONS: A telerobotic ultrasound system is feasible for performing abdominal ultrasound examinations at a distant location with minimal training and setup requirements and a moderate learning curve. Telerobotic sonography (robotic telesonography) may open up the possibility of remote ultrasound clinics for communities that lack skilled sonographers and radiologists, thereby improving access to care.

Imaging of late complications of cancer therapy in children.

Long-term survival after childhood cancer has improved dramatically over recent decades but survivors face lifelong risks of adverse health effects. Many of these chronic conditions are a direct result of previous therapeutic exposures. Compared to their siblings, survivors face a greater than 8-fold increase in relative risk of severe or life-threatening medical conditions; the most significant of these include second malignancies and cardiovascular and pulmonary diseases. Imaging can play a key role in identifying and characterizing such complications, which can be reasonably predicted with knowledge of the child's treatment. This article highlights the varied radiologic presentations and features seen in late cancer-therapy-related conditions.

A gamma-distribution convolution model of 99mTc-MIBI thyroid time-activity curves.

BACKGROUND: The convolution approach to thyroid time-activity curve (TAC) data fitting with a gamma distribution convolution (GDC) TAC model following bolus intravenous injection is presented and applied to 99mTc-MIBI data. The GDC model is a convolution of two gamma distribution functions that simultaneously models the distribution and washout kinetics of the radiotracer. The GDC model was fitted to thyroid region of interest (ROI) TAC data from 1 min per frame 99mTc-MIBI image series for 90 min; GDC models were generated for three patients having left and right thyroid lobe and total thyroid ROIs, and were contrasted with washout-only models, i.e., less complete models. GDC model accuracy was tested using 10 Monte Carlo simulations for each clinical ROI. RESULTS: The nine clinical GDC models, obtained from least counting error of counting, exhibited corrected (for 6 parameters) fit errors ranging from 0.998% to 1.82%. The range of all thyroid mean residence times (MRTs) was 212 to 699 min, which from noise injected simulations of each case had an average coefficient of variation of 0.7% and a not statistically significant accuracy error of 0.5% (p = 0.5, 2-sample paired t test). The slowest MRT value (699 min) was from a single thyroid lobe with a tissue diagnosed parathyroid adenoma also seen on scanning as retained marker. The two total thyroid ROIs without substantial pathology had MRT values of 278 and 350 min overlapping a published 99mTc-MIBI thyroid MRT value. One combined value and four unrelated washout-only models were tested and exhibited R-squared values for MRT with the GDC, i.e., a more complete concentration model, ranging from 0.0183 to 0.9395. CONCLUSIONS: The GDC models had a small enough TAC noise-image misregistration (0.8%) that they have a plausible use as simulations of thyroid activity for querying performance of other models such as washout models, for altered ROI size, noise, administered dose, and image framing rates. Indeed, of the four washout-only models tested, no single model approached the apparent accuracy of the GDC model using only 90 min of data. Ninety minutes is a long gamma-camera acquisition time for a patient, but a short a time for most kinetic models. Consequently, the results should be regarded as preliminary.

Liver MR Imaging in Children: Current Concepts and Technique.

Magnetic resonance (MR) imaging is increasingly being used for comprehensive evaluation of liver diseases in children because of the lack of radiation and better lesion detection and characterization. Liver examination involves routine sequences such as T2-weighted, balanced steady-state free precession, and in-phase and out-of-phase sequences. Dynamic imaging is an essential component of liver examination to characterize focal lesions and involves capturing snapshots of the passage of contrast material in the arterial, portal venous, equilibrium, and sometimes hepatobiliary phases, generally by using T1-weighted three-dimensional gradient-echo sequences. Optimal arterial phase imaging is important for detection and characterization of hypervascular lesions. In the equilibrium phase, the concentration of contrast material is similar in the microvasculature and the extracellular interstitial space. Some superficial, spreading, inflammatory lesions are better seen on equilibrium phase images. Meticulous attention to intravenous access and use of an appropriate timing method are critical for successful dynamic imaging. Commonly used contrast media for liver imaging include gadolinium-based extracellular contrast agents and hepatobiliary contrast agents. A portion of hepatobiliary contrast agents such as gadoxetate and gadobenate is taken up by hepatocytes and excreted through bile. Hepatobiliary phase images acquired after hepatobiliary contrast agent administration are increasingly used to characterize liver lesions in children, such as focal nodular hyperplasia. Interpretation of liver MR images involves synthesis of information acquired from evaluation of background hepatic parenchyma, detection of lesions, and evaluation of signal intensity characteristics on images obtained with various sequences to arrive at a diagnosis or reasonable differential diagnoses. Understanding the appropriate technique, sequences, and contrast media when performing pediatric liver MR imaging is important for high diagnostic yield. (©)RSNA, 2016.

Time Varying Apparent Volume of Distribution and Drug Half-Lives Following Intravenous Bolus Injections.

We present a model that generalizes the apparent volume of distribution and half-life as functions of time following intravenous bolus injection. This generalized model defines a time varying apparent volume of drug distribution. The half-lives of drug remaining in the body vary in time and become longer as time elapses, eventually converging to the terminal half-life. Two example fit models were substituted into the general model: biexponential models from the least relative concentration error, and gamma variate models using adaptive regularization for least relative error of clearance. Using adult population parameters from 41 studies of the renal glomerular filtration marker 169Yb-DTPA, simulations of extracellular fluid volumes of 5, 10, 15 and 20 litres and plasma clearances of 40 and 100 ml/min were obtained. Of these models, the adaptively obtained gamma variate models had longer times to 95% of terminal volume and longer half-lives.

Imaging of acute and subacute toxicities of cancer therapy in children.

Effective cancer therapies have resulted in significant improvement in survival. However, treatment-related acute and subacute complications are a cause of significant morbidity and mortality. Effects of cancer therapy in children can be seen early in the survival period or later in life in almost all organ systems of the body. Many of these conditions are evaluated by imaging and some are diagnosed based on characteristic imaging features. This article aims to discuss acute and subacute toxicities of cancer therapy in children involving multiple organ systems, pulmonary, gastrointestinal, hepatobiliary, genitourinary and musculoskeletal systems with emphasis on those in which imaging plays a role in diagnosis or management. We also discuss the role of imaging and choice of imaging modalities in these conditions.

Accurate and precise plasma clearance measurement using four 99mTc-DTPA plasma samples over 4 h.

OBJECTIVES: Glomerular filtration rate can be measured as the plasma clearance (CL) of a glomerular filtration rate marker despite body fluid disturbances using numerous, prolonged time samples. We desire a simplified technique without compromised accuracy and precision. MATERIALS AND METHODS: We compared CL values derived from two plasma concentration curve area methods - (a) biexponential fitting [CL (E2)] and (b) Tikhonov adaptively regularized gamma variate fitting [CL (Tk-GV)] - for 4 versus 8 h time samplings from 412 Tc-DTPA studies in 142 patients, mostly paediatric patients, with suspected fluid disturbances. RESULTS: CL (Tk-GV) from four samples/4 h and from nine samples/8 h, both accurately and precisely agreed with the standard, which was taken to be nine samples/8 h CL from (noncompartmental) numerical integration [CL (NI)]. The E2 method, four samples/4 h, and nine samples/8 h median CL values significantly overestimated the CL (NI) values by 4.9 and 3.8%, respectively. CONCLUSION: Compared with the standard, CL (E2) from four samples/4 h and from nine samples/8 h proved to be the most inaccurate and imprecise method examined, and can be replaced by better methods for calculating CL. The CL (Tk-GV) can be used to reduce sampling time in half from 8 to 4 h and from nine to four samples for a precise and accurate, yet more easily tolerated and simplified test.

Metal Artifact Reduction: Added Value of Rapid-Kilovoltage-Switching Dual-Energy CT in Relation to Single-Energy CT in a Piglet Animal Model.

OBJECTIVE: The purpose of this article is to evaluate virtual monochromatic spectral imaging and metal artifact reduction software for reducing metal artifact and to compare it with conventional single-energy CT (SECT) in an animal model. MATERIALS AND METHODS: Postmortem juvenile (n = 5) and adult (n = 1) swine specimens were scanned with SECT followed by a dual-energy CT (DECT) pediatric protocol after the insertion of two rods into their paraspinal thoracolumbar regions. Virtual monochromatic spectral images were extrapolated from DECT images at five monoenergetic levels (64, 69, 75, 88, and 105 keV) with and without the use of metal artifact reduction software. Images were evaluated by a 5-point scoring system for the extent of metallic artifacts and image interpretability in soft-tissue and bone windows. The density in the most pronounced artifact was measured. CT dose index was recorded. RESULTS: In studies without metal artifact reduction software, higher energy reconstructions resulted in fewer artifacts and better image interpretability in both soft-tissue and bone windows (p < 0.0001). Artifact density decreased from -792 HU at 64 keV to -128 HU at 105 keV without the use of metal artifact reduction software. No difference was noted in attributes' scores or in artifact density in studies using metal artifact reduction software (p > 0.05). DECT studies showed lower scores compared with SECT with regard to all attributes. A new faint perimetallic hypodense halo was seen in all studies with metal artifact reduction software. The CT dose index of DECT was 1.18-3.56 times higher than that of SECT techniques. CONCLUSION: DECT at all energy levels with metal artifact reduction software and higher energy extrapolations without metal artifact reduction software reduced metallic artifact and enhanced image interpretability compared with SECT. Radiation dose with DECT could be significantly higher than SECT.

Pediatric Body MR Angiography: Principles, Techniques, and Current Status in Body Imaging.

OBJECTIVE: The purpose of this article is to describe the principles and various techniques of MR angiography (MRA) that can be applied to pediatric body imaging and the current noncardiac, nonneurologic applications of MRA of children. CONCLUSION: The choice between CT angiography and MRA for body imaging should depend on the clinical query, ROI, and vessel size. MRA is useful for assessment of stenosis of the main renal artery, portal hypertension, tumor vascularity, vascular malformations, generalized vasculopathy in vasculitis and syndromes, and thoracic outlet syndrome.

The early plasma concentration of 51Cr-EDTA in patients with cirrhosis and ascites: a comparison of three models.

OBJECTIVES: The aim of the study was to determine which of three two-parameter fitting functions (exponential, linear-log, and negative-power function of time) most accurately models early chromium-51-EDTA (51Cr-EDTA) plasma concentration data prior to 120 min in patients with cirrhosis and ascites and understand how these fitting functions affect the calculation of the area under the plasma concentration curve (AUC). METHODS: A bolus, antecubital intravenous injection of 2.6 MBq of 51Cr-EDTA was given to 13 patients with cirrhosis and ascites. Up to 16 blood samples were drawn at time points ranging from 5 to 1440 min following injection. The concentration data prior to 120 min were used as reference data. Early time concentration values, estimated by fitting exponential, linear-log, and negative-power functions of time to the time samples at 120, 180, and 240 min, were then compared with reference data. The AUC was calculated for each patient using the exponential, Bröchner-Mortensen-corrected exponential, and linear-log functions, and these values were compared. RESULTS: The withheld, observed plasma concentrations were (a) most accurately estimated by linear-log functions (Wilcoxon P=0.4548), (b) significantly underestimated by exponential functions (Wilcoxon P=0.0002), and (c) significantly overestimated by negative-power functions (Wilcoxon P=0.0034). The relative errors when ranked from best to worst were those for the linear-log (12.0%, 9.0%), exponential (22.9%, 14.2%), and negative-power (31.9%, 48.4%) functions of time, respectively (median, interquartile range). For each patient, the values for AUC calculated by the exponential function differed significantly (range=3.4-15.3%, median=8.3%) from those calculated by the corrected Bröchner-Mortensen exponential, as to a lesser extent did those values calculated using linear-log functions (range=0.4-8.0%, median=3.0%). CONCLUSION: In patients with cirrhosis, linear-log functions were significantly more accurate than exponential or power functions in estimating early time plasma concentrations (<120 min). However, the improved linear-log early time plasma concentration model does not provide as much correction to the total AUC as does the corrected Bröchner-Mortensen exponential method. This is likely because of the large contribution of late time data to the AUC, and future work is suggested to explore the late time fit problem.