New Method to Reduce Artifacts in Cardiac Imaging
Author Information
Author(s): Chen Zhuo, Gong Yiwen, Chen Haiyang, Emu Yixin, Gao Juan, Zhou Zhongjie, Shen Yiwen, Tang Xin, Hua Sha, Jin Wei, Hu Chenxi
Primary Institution: Shanghai Jiao Tong University
Hypothesis
Can a twofold phase cycling sequence with a neural network improve artifact suppression in cardiac cine imaging?
Conclusion
The 2P-SSFP+Network method effectively suppresses banding and flow artifacts in cardiac imaging, providing reliable results across various conditions.
Supporting Evidence
- 2P-SSFP+Network showed improved artifact suppression compared to 1P-SSFP and 2P-SSFP+Average.
- Overall image quality scores were significantly higher for 2P-SSFP+Network.
- 2P-SSFP+Network achieved better results in the left atrium compared to other methods.
Takeaway
This study found a new way to make heart images clearer by using a special technique that reduces unwanted lines and blurriness.
Methodology
The study used a dual-encoder neural network trained on cine images from healthy subjects to compare different imaging methods for artifact suppression.
Potential Biases
Potential bias due to the limited diversity of the sample population and the use of a single vendor's equipment.
Limitations
The study had a relatively small sample size and was conducted at only two centers, which may limit the generalizability of the findings.
Participant Demographics
38 healthy subjects (mean age 23.8 years, 18 females) and 25 patients (mean age 58.6 years, 9 females).
Statistical Information
P-Value
p<0.01
Confidence Interval
[0.54, 0.87]
Statistical Significance
p<0.01
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website