Clinically essential requirement for brain CT with iterative reconstruction

Deep learning-based image reconstruction for brain CT: improved image quality compared with adaptive statistical iterative reconstruction-Veo (ASIR-V)

PURPOSE

To compare the image quality of brain computed tomography (CT) images reconstructed with deep learning-based image reconstruction (DLIR) and adaptive statistical iterative reconstruction-Veo (ASIR-V).

METHODS

Sixty-two patients underwent routine noncontrast brain CT scans and datasets were reconstructed with 30% ASIR-V and DLIR with three selectable reconstruction strength levels (low, medium, high). Objective parameters including CT attenuation, noise, noise reduction rate, artifact index of the posterior cranial fossa, and contrast-to-noise ratio (CNR) were measured at the levels of the centrum semiovale and basal ganglia. Subjective parameters including gray matter-white matter differentiation, sharpness, and overall diagnostic quality were also assessed and compared with the interobserver agreement.

RESULTS

There was a gradual reduction in the image noise and artifact index of the posterior cranial fossa as the strength levels of DLIR increased (all P < 0.001) compared with that of ASIR-V. CNR in both the centrum semiovale and basal ganglia levels also improved from the low to high strength levels of DLIR compared with that of ASIR-V (all P < 0.001). DLIR images with medium and high strength levels demonstrated the best subjective image quality scores among the reconstruction datasets. There was moderate to good interobserver agreement for the subjective image quality assessments with ASIR-V and DLIR.

CONCLUSION

On routine brain CT scans, optimized protocols with DLIR allowed significant reduction of noise and artifacts with improved subjective image quality compared with ASIR-V.

Thin-slice brain CT with iterative model reconstruction algorithm for small lacunar lesions detection: Image quality and diagnostic accuracy evaluation

This study was aimed to evaluate the image quality and lacunar lesion detection of thin-slice brain computed tomography (CT) images with different reconstruction algorithms, including filtered back projection (FBP), hybrid iterative reconstruction (HIR), and iterative model reconstruction (IMR) by comparison of routine slice images with FBP reconstruction. Sixty-one patients underwent noncontrast brain CT and images were reconstructed with a routine slice of 5.0 mm by FBP and thin slice of 1.0 mm by IMR, HIR, and FBP algorithms, respectively. Objective analyses included CT attenuation, noise, artifacts index of posterior cranial fossa, and contrast-to-noise ratio (CNR). Subjective analyses were performed according to overall image quality using a 5-point scale [1 (unacceptable) to 5 (excellent)]. In addition, lacunar lesion detection was compared in images with different reconstruction settings among 26 patients with lacunar lesions, with magnetic resonance imaging (MRI) as reference.Thin-slice IMR images enabled the lowest noise, artifacts index, and the best CNR. Both IMR and HIR thin-slice images enabled better scores in subjective image quality than routine slice FBP images. Moreover, both thin-slice IMR and HIR images enabled higher sensitivity and positive predictive value (PPV) in lesion detection of 35-mm lacunar lesions compared with routine slice FBP images.Thin-slice IMR images improve image quality, meanwhile yield better detection of small lacunar lesions in brain CT compared with routine slice FBP images.