Statistical iterative reconstruction for streak artefact reduction when using multidetector CT to image the dento-alveolar structures

The use of artificial intelligence in computed tomography image reconstruction - A literature review

BACKGROUND AND PURPOSE

The use of AI in the process of CT image reconstruction may improve image quality of resultant images and therefore facilitate low-dose CT examinations.

METHODS

Articles in this review were gathered from multiple databases (Google Scholar, Ovid and Monash University Library Database). A total of 17 articles regarding AI use in CT image reconstruction was reviewed, including 1 white paper from GE Healthcare.

RESULTS

DLR algorithms performed better in terms of noise reduction abilities, and image quality preservation at low doses when compared to other reconstruction techniques.

CONCLUSION

Further research is required to discuss clinical application and diagnostic accuracy of DLR algorithms, but AI is a promising dose-reduction technique with future computational advances.

Impact of statistical reconstruction and compressed sensing algorithms on projection data elimination during X-ray CT image reconstruction

OBJECTIVES

To examine the effect of incomplete, or total elimination of, projection data on computed tomography (CT) images subjected to statistical reconstruction and/or compressed sensing algorithms.

METHODS

Multidetector row CT images were used. The algebraic reconstruction technique (ART) and the maximum likelihood-expectation maximization (ML-EM) method were compared with filtered back-projection (FBP). Effects on reconstructed images were studied when the projection data of 360° (360 projections) were decreased to 180 or 90 projections by reducing the collection angle or thinning the image data. The total variation (TV) regularization method using compressed sensing was applied to images processed by the ART. Image noise was subjectively evaluated using the root-mean-square error and signal-to-noise ratio.

RESULTS

When projection data were reduced by one-half or three-quarters, ART and ML-EM produced better image quality than FBP. Both ART and ML-EM resulted in high quality at a spread of 90 projections over 180° rotation. Computational loading was high for statistical reconstruction, but not for ML-EM, compared with the ART. TV regularization made it possible to use only 36 projections while still achieving acceptable image quality.

CONCLUSIONS

Incomplete projection data-accomplished by reducing the angle to collect image data or thinning the projection data without reducing the angle of rotation over which it is collected-made it possible to reduce the radiation dose while retaining image quality with statistical reconstruction algorithms and/or compressed sensing. Despite heavier computational calculation loading, these methods should be considered for reducing radiation doses.

Combined use of iterative reconstruction and monochromatic imaging in spinal fusion CT images

BACKGROUND

Spinal fusion surgery is an important procedure for treating spinal diseases and computed tomography (CT) is a critical tool for postoperative evaluation. However, CT image quality is considerably impaired by metal artifacts and image noise.

PURPOSE

To explore whether metal artifacts and image noise can be reduced by combining two technologies, adaptive statistical iterative reconstruction (ASIR) and monochromatic imaging generated by gemstone spectral imaging (GSI) dual-energy CT.

MATERIAL AND METHODS

A total of 51 patients with 318 spinal pedicle screws were prospectively scanned by dual-energy CT using fast kV-switching GSI between 80 and 140 kVp. Monochromatic GSI images at 110 keV were reconstructed either without or with various levels of ASIR (30%, 50%, 70%, and 100%). The quality of five sets of images was objectively and subjectively assessed.

RESULTS

With objective image quality assessment, metal artifacts decreased when increasing levels of ASIR were applied (P < 0.001). Moreover, adding ASIR to GSI also decreased image noise (P < 0.001) and improved the signal-to-noise ratio (P < 0.001). The subjective image quality analysis showed good inter-reader concordance, with intra-class correlation coefficients between 0.89 and 0.99. The visualization of peri-implant soft tissue was improved at higher ASIR levels (P < 0.001).

CONCLUSION

Combined use of ASIR and GSI decreased image noise and improved image quality in post-spinal fusion CT scans. Optimal results were achieved with ASIR levels ≥70%.