Head CT deep learning model is highly accurate for early infarct estimation.

Non-contrast head CT (NCCT) is extremely insensitive for early (< 3-6 h) acute infarct identification. We developed a deep learning model that detects and delineates suspected early acute infarcts on NCCT, using diffusion MRI as ground truth (3566 NCCT/MRI training patient pairs). The model substantially outperformed 3 expert neuroradiologists on a test set of 150 CT scans of patients who were potential candidates for thrombectomy (60 stroke-negative, 90 stroke-positive middle cerebral artery territory only infarcts), with sensitivity 96% (specificity 72%) for the model versus 61-66% (specificity 90-92%) for the experts; model infarct volume estimates also strongly correlated with those of diffusion MRI (r2 > 0.98). When this 150 CT test set was expanded to include a total of 364 CT scans with a more heterogeneous distribution of infarct locations (94 stroke-negative, 270 stroke-positive mixed territory infarcts), model sensitivity was 97%, specificity 99%, for detection of infarcts larger than the 70 mL volume threshold used for patient selection in several major randomized controlled trials of thrombectomy treatment.

Development and clinical application of a deep learning model to identify acute infarct on magnetic resonance imaging.

Stroke is a leading cause of death and disability. The ability to quickly identify the presence of acute infarct and quantify the volume on magnetic resonance imaging (MRI) has important treatment implications. We developed a machine learning model that used the apparent diffusion coefficient and diffusion weighted imaging series. It was trained on 6,657 MRI studies from Massachusetts General Hospital (MGH; Boston, USA). All studies were labelled positive or negative for infarct (classification annotation) with 377 having the region of interest outlined (segmentation annotation). The different annotation types facilitated training on more studies while not requiring the extensive time to manually segment every study. We initially validated the model on studies sequestered from the training set. We then tested the model on studies from three clinical scenarios: consecutive stroke team activations for 6-months at MGH, consecutive stroke team activations for 6-months at a hospital that did not provide training data (Brigham and Women's Hospital [BWH]; Boston, USA), and an international site (Diagnósticos da América SA [DASA]; Brazil). The model results were compared to radiologist ground truth interpretations. The model performed better when trained on classification and segmentation annotations (area under the receiver operating curve [AUROC] 0.995 [95% CI 0.992-0.998] and median Dice coefficient for segmentation overlap of 0.797 [IQR 0.642-0.861]) compared to segmentation annotations alone (AUROC 0.982 [95% CI 0.972-0.990] and Dice coefficient 0.776 [IQR 0.584-0.857]). The model accurately identified infarcts for MGH stroke team activations (AUROC 0.964 [95% CI 0.943-0.982], 381 studies), BWH stroke team activations (AUROC 0.981 [95% CI 0.966-0.993], 247 studies), and at DASA (AUROC 0.998 [95% CI 0.993-1.000], 171 studies). The model accurately segmented infarcts with Pearson correlation comparing model output and ground truth volumes between 0.968 and 0.986 for the three scenarios. Acute infarct can be accurately detected and segmented on MRI in real-world clinical scenarios using a machine learning model.

Intravascular enhancement with identical iodine delivery rate using different iodine contrast media in a circulation phantom.

PURPOSE: Both iodine delivery rate (IDR) and iodine concentration are decisive factors for vascular enhancement in computed tomographic angiography. It is unclear, however, whether the use of high-iodine concentration contrast media is beneficial to lower iodine concentrations when IDR is kept identical. This study evaluates the effect of using different iodine concentrations on intravascular attenuation in a circulation phantom while maintaining a constant IDR. MATERIALS AND METHODS: A circulation phantom with a low-pressure venous compartment and a high-pressure arterial compartment simulating physiological circulation parameters was used (heart rate, 60 beats per minute; stroke volume, 60 mL; blood pressure, 120/80 mm Hg). Maintaining a constant IDR (2.0 g/s) and a constant total iodine load (20 g), prewarmed (37°C) contrast media with differing iodine concentrations (240-400 mg/mL) were injected into the phantom using a double-headed power injector. Serial computed tomographic scans at the level of the ascending aorta (AA), the descending aorta (DA), and the left main coronary artery (LM) were obtained. Total amount of contrast volume (milliliters), iodine delivery (grams of iodine), peak flow rate (milliliter per second), and intravascular pressure (pounds per square inch) were monitored using a dedicated data acquisition program. Attenuation values in the AA, the DA, and the LM were constantly measured (Hounsfield unit [HU]). In addition, time-enhancement curves, aortic peak enhancement, and time to peak were determined. RESULTS: All contrast injection protocols resulted in similar attenuation values: the AA (516 [11] to 531 [37] HU), the DA (514 [17] to 531 [32] HU), and the LM (490 [10] to 507 [17] HU). No significant differences were found between the AA, the DA, and the LM for either peak enhancement (all P > 0.05) or mean time to peak (AA, 19.4 [0.58] to 20.1 [1.05] seconds; DA, 21.1 [1.0] to 21.4 [1.15] seconds; LM, 19.8 [0.58] to 20.1 [1.05] seconds). CONCLUSIONS: This phantom study demonstrates that constant injection parameters (IDR, overall iodine load) lead to robust enhancement patterns, regardless of the contrast material used. Higher iodine concentration itself does not lead to higher attenuation levels. These results may stimulate a shift in paradigm toward clinical usage of contrast media with lower iodine concentrations (eg, 240 mg iodine/mL) in individual tailored contrast protocols. The use of low-iodine concentration contrast media is desirable because of the lower viscosity and the resulting lower injection pressure.

Cardiothoracic CT angiography: current contrast medium delivery strategies.

OBJECTIVE: Over the last decade, rapid technologic evolution in CT has resulted in improved spatial and temporal resolution and acquisition speed, enabling cardiothoracic CT angiography to become a viable and effective noninvasive alternative in the diagnostic algorithm. These new technologic advances have imposed new challenges for the optimization of contrast medium delivery and image acquisition strategies. CONCLUSION: Thorough understanding of contrast medium dynamics is essential for the design of effective acquisition and injection protocols. This article provides an overview of the fundamentals affecting contrast enhancement, emphasizing the modifications to contrast material delivery protocols required to optimize cardiothoracic CT angiography.

Current contrast media delivery strategies for cardiac and pulmonary multidetector-row computed tomography angiography.

Recent advances in multidetector-row computed tomography (MDCT) have led to substantial improvements in coverage area, acquisition speed, and temporal/spatial resolution, which have strengthened the performance of thoracic and cardiac MDCT angiography but have also imposed new challenges for optimization of contrast medium enhancement and scan acquisition strategies. Understanding contrast media dynamics is fundamental for the design of scan acquisition and injection protocols. This article examines the fundamentals of the physiological and contrast delivery factors that determine the quality of contrast enhancement, emphasizing the modifications required in contrast delivery protocols for optimizing cardiothoracic MDCT angiography with modern-era MDCT scanners.

A personalized and optimal approach for dosing contrast material at coronary computed tomography angiography.

A method for constructing a personalized contrast medium protocol at contrast enhanced, Coronary CT Angiography (CCTA) is presented. A one compartment pharmacokinetic model is parameterized and identified with a minimal data set from a test-bolus injection. A direct-search optimization is performed to construct a protocol that achieves target enhancement in the cardiac structures. Clinical results demonstrating the method's ability to achieve prospectively chosen image enhancement levels while reducing contrast medium dose are presented.

Introduction of an individually optimized protocol for the injection of contrast medium for coronary CT angiography.

The aim of this study was to determine whether individually tailored protocols for the injection of contrast medium (CM) result in higher and more homogeneous vascular attenuation throughout the coronary arteries at coronary CT angiography compared with conventional injection protocols using fixed injection parameters. Of 120 patients included in the study, 80 patients were randomized into two groups. Group 1 received 80 mL of CM at 6 mL/s. For group 2 injection parameters were individually adjusted to patient weight, the duration of CT data acquisition, and attenuation parameters following a test bolus. In the control group (group 3) the volume of CM was adjusted to the duration of CT data acquisition and injected at 5 mL/s. Attenuation was measured in the proximal, middle, and distal right coronary artery (RCA), in the proximal and middle left anterior descending artery (LAD), and in cranial and caudal sections of both ventricles. Patient parameters, scan delay, and scan duration did not differ significantly between the groups. Mean CM volume was 82.5 mL (flow rate 5.1 mL/s) in group 2 and 73.5 mL in group 3. Attenuation in both RCA and LAD was significantly higher for group 2 vs. group 3 (RCA: 414.9 + or - 49.9)-396.1(+ or - 52.1) HU vs. 366.0(+ or - 64.3)-341.6(+ or - 72.5) HU; LAD: 398.9(+ or - 48.6)-364.6(+ or - 44.6) HU vs. 356.3(+ or - 69.5)-323.0(+ or - 67.2) HU). For group 1 vs. group 2 only attenuation in the distal RCA differed significantly: 396.1(+ or - 52.1) vs. 370.7(+ or - 70.5) HU. Individually tailored CM injection protocols yield higher attenuation, especially in the distal segments of the coronary vessels, compared with injection protocols using fixed injection parameters.

Patient-specific contrast injection protocols for cardiovascular multidetector row computed tomography.

OBJECTIVE: To develop patient-specific contrast injections for uniform enhancement of cardiovascular multidetector row computed tomography (MDCT) images. METHODS: Sixty-two patients were imaged using electrocardiogram (ECG)-gated spiral MDCT. Thirty patients (group 1) received a uniphasic injection; the remaining 32 patients (group 2) received patient-specific multiphasic injections. For group 2 patients, the vasculature between injection and imaging sites was considered a "gray box" whose transfer function was determined from a test bolus injection and the resulting enhancement in the left side of the heart. This transfer function was used to determine the injection necessary to achieve 250 Hounsfield units in the left side of the heart. Intraindividual and interindividual variation of enhancement were determined for both groups. Superior vena cava (SVC) artifacts were graded on a 4-point scale. RESULTS: The measured indices of intraindividual variation were significantly smaller in group 2 than in group 1 (P < 0.05), indicating improved uniformity with patient-specific injections. The interindividual variation of mean enhancement in group 2 was smaller than in group 1, but the difference was not significant. The severity of SVC artifacts was significantly reduced (P < 0.05) for thinner patients (<83 kg) in group 2 compared with similar patients in group 1. CONCLUSIONS: Patient-specific multiphasic contrast injections yielded more uniform enhancement in the left side of the heart on MDCT images with reduced intraindividual variation of enhancement compared with standard uniphasic injections. Patient-specific injections also reduced SVC artifacts in patients <83 kg.