Comprehensive assessment of imaging quality of artificial intelligence-assisted compressed sensing-based MR images in routine clinical settings.


Journal

BMC medical imaging
ISSN: 1471-2342
Titre abrégé: BMC Med Imaging
Pays: England
ID NLM: 100968553

Informations de publication

Date de publication:
21 Oct 2024
Historique:
received: 15 08 2024
accepted: 11 10 2024
medline: 22 10 2024
pubmed: 22 10 2024
entrez: 21 10 2024
Statut: epublish

Résumé

Conventional MR acceleration techniques, such as compressed sensing, parallel imaging, and half Fourier often face limitations, including noise amplification, reduced signal-to-noise ratio (SNR) and increased susceptibility to artifacts, which can compromise image quality, especially in high-speed acquisitions. Artificial intelligence (AI)-assisted compressed sensing (ACS) has emerged as a novel approach that combines the conventional techniques with advanced AI algorithms. The objective of this study was to examine the imaging quality of the ACS approach by qualitative and quantitative analysis for brain, spine, kidney, liver, and knee MR imaging, as well as compare the performance of this method with conventional (non-ACS) MR imaging. This study included 50 subjects. Three radiologists independently assessed the quality of MR images based on artefacts, image sharpness, overall image quality and diagnostic efficacy. SNR, contrast-to-noise ratio (CNR), edge content (EC), enhancement measure (EME), scanning time were used for quantitative evaluation. The Cohen's kappa correlation coefficient (k) was employed to measure radiologists' inter-observer agreement, and the Mann Whitney U-test used for comparison between non-ACS and ACS. The qualitative analysis of three radiologists demonstrated that ACS images showed superior clinical information than non-ACS images with a mean k of ~ 0.70. The images acquired with ACS approach showed statistically higher values (p < 0.05) for SNR, CNR, EC, and EME compared to the non-ACS images. Furthermore, the study's findings indicated that ACS-enabled images reduced scan time by more than 50% while maintaining high imaging quality. Integrating ACS technology into routine clinical settings has the potential to speed up image acquisition, improve image quality, and enhance diagnostic procedures and patient throughput.

Sections du résumé

BACKGROUND BACKGROUND
Conventional MR acceleration techniques, such as compressed sensing, parallel imaging, and half Fourier often face limitations, including noise amplification, reduced signal-to-noise ratio (SNR) and increased susceptibility to artifacts, which can compromise image quality, especially in high-speed acquisitions. Artificial intelligence (AI)-assisted compressed sensing (ACS) has emerged as a novel approach that combines the conventional techniques with advanced AI algorithms. The objective of this study was to examine the imaging quality of the ACS approach by qualitative and quantitative analysis for brain, spine, kidney, liver, and knee MR imaging, as well as compare the performance of this method with conventional (non-ACS) MR imaging.
METHODS METHODS
This study included 50 subjects. Three radiologists independently assessed the quality of MR images based on artefacts, image sharpness, overall image quality and diagnostic efficacy. SNR, contrast-to-noise ratio (CNR), edge content (EC), enhancement measure (EME), scanning time were used for quantitative evaluation. The Cohen's kappa correlation coefficient (k) was employed to measure radiologists' inter-observer agreement, and the Mann Whitney U-test used for comparison between non-ACS and ACS.
RESULTS RESULTS
The qualitative analysis of three radiologists demonstrated that ACS images showed superior clinical information than non-ACS images with a mean k of ~ 0.70. The images acquired with ACS approach showed statistically higher values (p < 0.05) for SNR, CNR, EC, and EME compared to the non-ACS images. Furthermore, the study's findings indicated that ACS-enabled images reduced scan time by more than 50% while maintaining high imaging quality.
CONCLUSION CONCLUSIONS
Integrating ACS technology into routine clinical settings has the potential to speed up image acquisition, improve image quality, and enhance diagnostic procedures and patient throughput.

Identifiants

pubmed: 39434010
doi: 10.1186/s12880-024-01463-6
pii: 10.1186/s12880-024-01463-6
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

284

Informations de copyright

© 2024. The Author(s).

Références

Rao R, Venkatesan R, Geethanath S. Role of MRI in medical diagnostics. Resonance. 2015;20:1003–11. https://doi.org/10.1007/s12045-015-0268-2 .
doi: 10.1007/s12045-015-0268-2
Bitar R, Leung G, Perng R, et al. MR pulse sequences: what every radiologist wants to know but is afraid to ask. Radiographics. 2006;26(2):513–37. https://doi.org/10.1148/rg.262055063 .
doi: 10.1148/rg.262055063 pubmed: 16549614
Kozak BM, Jaimes C, Kirsch J, Gee MS. MRI techniques to decrease imaging times in children. Radiographics. 2020;40(2):485–502. https://doi.org/10.1148/rg.2020190112 .
doi: 10.1148/rg.2020190112 pubmed: 32031912
Xiang L, Chen Y, Chang W, et al. Ultra-fast T2-weighted MR reconstruction using complementary T1-weighted information. Med Image Comput Comput Assist Interv. 2018;11070:215–23. https://doi.org/10.1007%2F978-3-030-00928-1_25 .
pubmed: 30906934 pmcid: 6430217
van Sambeek JR, Joustra PE, Das SF, et al. Reducing MRI access times by tackling the appointment-scheduling strategy. BMJ Qual Saf. 2011;20(12):1075–80. https://doi.org/10.1136/bmjqs.2010.049643 .
doi: 10.1136/bmjqs.2010.049643 pubmed: 21984746
Garwood ER, Recht MP, White LM. Advanced imaging techniques in the knee: benefits and limitations of new rapid acquisition strategies for routine knee MRI. AJR Am J Roentgenol. 2017;209:552–60. https://doi.org/10.2214/ajr.17.18228 .
doi: 10.2214/ajr.17.18228 pubmed: 28639870
Magnotta VA, Friedman L, FIRST BIRN. Measurement of signal-to-noise and contrast-to-noise in the fBIRN multicenter imaging study. J Digit Imaging. 2006;19(2):140–7. https://doi.org/10.1007%2Fs10278-006-0264-x .
doi: 10.1007/s10278-006-0264-x pubmed: 16598643 pmcid: 3045184
Akila K, Jayashree L, Vasuki A. Mammographic image enhancement using indirect contrast enhancement techniques–a comparative study. Procedia Comput Sci. 2015;47:255–61. https://doi.org/10.1016/j.procs.2015.03.205 .
doi: 10.1016/j.procs.2015.03.205
Gandhamal A, Talbar S, Gajre S, Hani AF, Kumar D. Local gray level S-curve transformation - a generalized contrast enhancement technique for medical images. Comput Biol Med. 2017;83:120–33. https://doi.org/10.1016/j.compbiomed.2017.03.001 .
doi: 10.1016/j.compbiomed.2017.03.001 pubmed: 28279861
Wang S, Su Z, Ying L, et al. Accelerating magnetic resonance imaging via deep learning. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). Prague: IEEE. 2016;514–7. https://doi.org/10.1109/ISBI.2016.7493320 .
Shrividya G, Bharathi SH. Application of compressed sensing on magnetic resonance imaging: a brief survey. In: 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT). Bangalore: IEEE. 2016;2037–41. https://doi.org/10.1109/RTEICT.2016.7808197 .
Huang F, Lin W, Li Y. Partial fourier reconstruction through data fitting and convolution in k-space. Magn Reson Med. 2009;62(5):1261–9. https://doi.org/10.1002/mrm.22128 .
doi: 10.1002/mrm.22128 pubmed: 19780148
Sheng RF, Zheng LY, Jin KP, et al. Single-breath-hold T2WI liver MRI with deep learning-based reconstruction: a clinical feasibility study in comparison to conventional multi-breath-hold T2WI liver MRI. Magn Reson Imaging. 2021;81:75–81. https://doi.org/10.1016/j.mri.2021.06.014 .
doi: 10.1016/j.mri.2021.06.014 pubmed: 34147594
Chandrasekar V, Ansari MY, Singh AV, et al. Investigating the use of machine learning models to understand the drugs permeability across placenta. IEEE Access. 2023;11:52726–39. https://doi.org/10.1109/ACCESS.2023.3272987 .
doi: 10.1109/ACCESS.2023.3272987
Ansari MY, Chandrasekar V, Singh AV, et al. Re-routing drugs to blood brain barrier: a comprehensive analysis of machine learning approaches with fingerprint amalgamation and data balancing. IEEE Access. 2023;11:9890–906. https://doi.org/10.1109/ACCESS.2022.3233110 .
doi: 10.1109/ACCESS.2022.3233110
Ansari MY, Qaraqe M, Righetti R, et al. Unveiling the future of breast cancer assessment: a critical review on generative adversarial networks in elastography ultrasound. Front Oncol. 2023;6(13):1282536. https://doi.org/10.3389/fonc.2023.1282536 .
doi: 10.3389/fonc.2023.1282536
Ansari MY, Mangalote IAC, Meher PK. Advancements in deep learning for B-mode ultrasound segmentation: a comprehensive review. IEEE Trans Emerg Top Comput Intell. 2024;8(3):2126–49. https://doi.org/10.1109/TETCI.2024.3377676 .
doi: 10.1109/TETCI.2024.3377676
Ansari MY, Mangalote IAC, Masri D, et al. Neural network-based fast liver ultrasound image segmentation. In: 2023 IEEE International Joint Conference on Neural Networks (IJCNN). Gold Coast: IEEE. 2023;1–8. https://doi.org/10.1109/IJCNN54540.2023.10191085 .
Ansari MY, Mohanty S, Mathew SJ, et al. Towards developing a lightweight neural network for liver CT segmentation. In: Su R, Zhang Y, Liu H, F Frangi A. (eds) Medical imaging and computer-aided diagnosis. MICAD 2022. Lecture Notes in Electrical Engineering. Singapore: Springer. 2023;810:27–35. https://doi.org/10.1007/978-981-16-6775-6_3 .
Ansari MY, Qaraqe M, Charafeddine F, et al. Estimating age and gender from electrocardiogram signals: a comprehensive review of the past decade. Artif Intell Med. 2023;146:102690. https://doi.org/10.1016/j.artmed.2023.102690 .
doi: 10.1016/j.artmed.2023.102690 pubmed: 38042607
Ansari MY, Qaraqe M, Righetti R, et al. Enhancing ECG-based heart age: impact of acquisition parameters and generalization strategies for varying signal morphologies and corruptions. Front Cardiovasc Med. 2024;11:1424585. https://doi.org/10.3389/fcvm.2024.1424585 .
doi: 10.3389/fcvm.2024.1424585 pubmed: 39027006 pmcid: 11254851
Ghodrati V, Shao J, Bydder M, et al. MR image reconstruction using deep learning: evaluation of network structure and loss functions. Quant Imaging Med Surg. 2019;9(9):1516–27. https://doi.org/10.21037%2Fqims.2019.08.10 .
doi: 10.21037/qims.2019.08.10 pubmed: 31667138 pmcid: 6785508
Li H, Hu C, Yang Y, et al. Single-breath-hold T2WI MRI with artificial intelligence-assisted technique in liver imaging: as compared with conventional respiratory-triggered T2WI. Magn Reson Imaging. 2022;93:175–218. https://doi.org/10.1016/j.mri.2022.08.012 .
doi: 10.1016/j.mri.2022.08.012 pubmed: 35987419
Wang Q, Zhao W, Xing X, et al. Feasibility of AI-assisted compressed sensing protocols in knee MR imaging: a prospective multi-reader study. Eur Radiol. 2023;33(12):8585–96. https://doi.org/10.1007/s00330-023-09823-6 .
doi: 10.1007/s00330-023-09823-6 pubmed: 37382615 pmcid: 10667384
Zhao Y, Peng C, Wang S, Liang X, Meng X. The feasibility investigation of AI -assisted compressed sensing in kidney MR imaging: an ultra-fast T2WI imaging technology. BMC Med Imaging. 2022;22(1):119–27. https://doi.org/10.1186/s12880-022-00842-1 .
doi: 10.1186/s12880-022-00842-1 pubmed: 35787673 pmcid: 9254529
Priyanka KR, Nayak SS, Chandran M, et al. Impact of artificial intelligence assisted compressed sensing technique on scan time and image quality in musculoskeletal MRI - a systematic review. Radiography (Lond). 2024;S1078–8174(24):00212–8. https://doi.org/10.1016/j.radi.2024.08.012 .
doi: 10.1016/j.radi.2024.08.012
Zhai R, Huang X, Zhao Y, et al. Intelligent incorporation of AI with model constraints for MRI acceleration. In: Proceedings of the 29th Annual Meeting of ISMRM [Virtual]. 2021. https://archive.ismrm.org/2021/1760.html .
Quan TM, Nguyen-Duc T, Jeong WK. Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss. IEEE Trans Med Imaging. 2018;37:1488–97. https://doi.org/10.1109/TMI.2018.2820120 .
doi: 10.1109/TMI.2018.2820120 pubmed: 29870376
Yang G, Yu S, Dong H, et al. DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Trans Med Imaging. 2018;37:1310–21. https://doi.org/10.1109/TMI.2017.2785879 .
doi: 10.1109/TMI.2017.2785879 pubmed: 29870361
Gupta S, Porwal R. Appropriate contrast enhancement measures for brain and breast cancer images. Int J Biomed Imaging. 2016;4710842. https://doi.org/10.1155/2016/4710842 .
Again SS, Panetta, Grigoryan AM. Transform-based image enhancement algorithms with performance measure. IEEE Trans Image Process. 2001;10(3):367–382. https://doi.org/10.1109/83.908502 .
Andre JB, Bresnahan BW, Mossa-Basha M, et al. Toward quantifying the prevalence, severity, and cost associated with patient motion during clinical MR examinations. J Am College Radiol. 2015;12(7):689–95. https://doi.org/10.1016/j.jacr.2015.03.007 .
doi: 10.1016/j.jacr.2015.03.007
Johnson PM, Recht MP, Knoll F. Improving the speed of MRI with artificial intelligence. Semin Musculoskelet Radiol. 2020;24:12–20. https://doi.org/10.1055/s-0039-3400265 .
doi: 10.1055/s-0039-3400265 pubmed: 31991448 pmcid: 7416509
Hammernik K, Klatzer T, Kobler E, et al. Learning a variational network for reconstruction of accelerated MRI data. Magn Reson Med. 2018;79:3055–71. https://doi.org/10.1002/mrm.26977 .
doi: 10.1002/mrm.26977 pubmed: 29115689
Knoll F, Hammernik K, Kobler E, et al. Assessment of the generalization of learned image reconstruction and the potential for transfer learning. Magn Reson Med. 2019;81:116–212. https://doi.org/10.1002/mrm.27355 .
doi: 10.1002/mrm.27355 pubmed: 29774597
Wu HH, Nishimura DG. 3D magnetization-prepared imaging using a stack-of-rings trajectory. Magn Reson Med. 2010;63(5):1210–8 https://doi.org/10.1002%2Fmrm.22288 .
doi: 10.1002/mrm.22288 pubmed: 20432292 pmcid: 2905147
Sui H, Gong Y, Liu L, et al. Comparison of artificial intelligence-assisted compressed sensing (ACS) and routine two-dimensional sequences on lumbar spine imaging. J Pain Res. 2023;16:257–67. https://doi.org/10.2147/jpr.s388219 .
doi: 10.2147/jpr.s388219 pubmed: 36744117 pmcid: 9891076
Zhai X, Eslami M, Hussein ES, et al. Real-time automated image segmentation technique for cerebral aneurysm on reconfigurable system-on-chip. J Comput Sci. 2018;27:35–45. https://doi.org/10.1016/j.jocs.2018.05.002 .
doi: 10.1016/j.jocs.2018.05.002
Zhai X, Amira A, Bensaali F, et al. Zynq SoC based acceleration of the lattice boltzmann method. Concurrency Computation: Pract Experience. 2019;31(17):e5184. https://doi.org/10.1002/cpe.5184 .
doi: 10.1002/cpe.5184
Esfahani SS, Zhai X, Chen M, et al. Lattice-Boltzmann interactive blood flow simulation pipeline. Int J Comput Assist Radiol Surg. 2020;15(4):629–39. https://doi.org/10.1007/s11548-020-02120-3 .
doi: 10.1007/s11548-020-02120-3 pubmed: 32130645
Zhai X, Chen M, Esfahani SS, et al. Heterogeneous system-on-chip-based Lattice-Boltzmann visual simulation system. IEEE Syst J. 2019;14(2):1592–601. https://doi.org/10.1109/JSYST.2019.2952459 .
doi: 10.1109/JSYST.2019.2952459
Ansari MY, Yang Y, Balakrishnan S, et al. A lightweight neural network with multiscale feature enhancement for liver CT segmentation. Sci Rep. 2022;12:14153. https://doi.org/10.1038/s41598-022-16828-6 .
doi: 10.1038/s41598-022-16828-6 pubmed: 35986015 pmcid: 9391485
Ansari MY, Yang Y, Meher PK, et al. Dense-PSP-UNet: a neural network for fast inference liver ultrasound segmentation. Comput Biol Med. 2023;153:106478. https://doi.org/10.1016/j.compbiomed.2022.106478 .
doi: 10.1016/j.compbiomed.2022.106478 pubmed: 36603437
Mohanty S, Dakua SP. Toward computing cross-modality symmetric non-rigid medical image registration. IEEE Access. 2022;10:24528–39. https://doi.org/10.1109/ACCESS.2022.3154771 .
doi: 10.1109/ACCESS.2022.3154771

Auteurs

Adiraju Karthik (A)

Department of Radiology, Sprint Diagnostics, Jubilee Hills, Hyderabad, India.

Kamal Aggarwal (K)

Department of Radiology, SSB Hospital, Faridabad, India.

Aakaar Kapoor (A)

Department of Radiology, City Imaging & Clinical Labs, Delhi, India.

Dharmesh Singh (D)

Central Research Institute, United Imaging Healthcare, Shanghai, China. dharmeshsingh03@gmail.com.

Lingzhi Hu (L)

Central Research Institute, United Imaging Healthcare, Houston, USA.

Akash Gandhamal (A)

Central Research Institute, United Imaging Healthcare, Shanghai, China.

Dileep Kumar (D)

Central Research Institute, United Imaging Healthcare, Shanghai, China.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH