Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Improving Diagnostic Performance of MRI for Temporal Lobe Epilepsy With Deep Learning-Based Image Reconstruction in Patients With Suspected Focal Epilepsy

  • Pae Sun Suh (Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center) ;
  • Ji Eun Park (Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center) ;
  • Yun Hwa Roh (Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center) ;
  • Seonok Kim (Department of Clinical Epidemiology and Biostatics, University of Ulsan college of Medicine, Asan Medical Center) ;
  • Mina Jung (Department of Neurology, University of Ulsan College of Medicine, Asan Medical Center) ;
  • Yong Seo Koo (Department of Neurology, University of Ulsan College of Medicine, Asan Medical Center) ;
  • Sang-Ahm Lee (Department of Neurology, University of Ulsan College of Medicine, Asan Medical Center) ;
  • Yangsean Choi (Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center) ;
  • Ho Sung Kim (Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center)
  • Received : 2023.08.31
  • Accepted : 2024.01.07
  • Published : 2024.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: To evaluate the diagnostic performance and image quality of 1.5-mm slice thickness MRI with deep learningbased image reconstruction (1.5-mm MRI + DLR) compared to routine 3-mm slice thickness MRI (routine MRI) and 1.5-mm slice thickness MRI without DLR (1.5-mm MRI without DLR) for evaluating temporal lobe epilepsy (TLE). Materials and Methods: This retrospective study included 117 MR image sets comprising 1.5-mm MRI + DLR, 1.5-mm MRI without DLR, and routine MRI from 117 consecutive patients (mean age, 41 years; 61 female; 34 patients with TLE and 83 without TLE). Two neuroradiologists evaluated the presence of hippocampal or temporal lobe lesions, volume loss, signal abnormalities, loss of internal structure of the hippocampus, and lesion conspicuity in the temporal lobe. Reference standards for TLE were independently constructed by neurologists using clinical and radiological findings. Subjective image quality, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were analyzed. Performance in diagnosing TLE, lesion findings, and image quality were compared among the three protocols. Results: The pooled sensitivity of 1.5-mm MRI + DLR (91.2%) for diagnosing TLE was higher than that of routine MRI (72.1%, P < 0.001). In the subgroup analysis, 1.5-mm MRI + DLR showed higher sensitivity for hippocampal lesions than routine MRI (92.7% vs. 75.0%, P = 0.001), with improved depiction of hippocampal T2 high signal intensity change (P = 0.016) and loss of internal structure (P < 0.001). However, the pooled specificity of 1.5-mm MRI + DLR (76.5%) was lower than that of routine MRI (89.2%, P = 0.004). Compared with 1.5-mm MRI without DLR, 1.5-mm MRI + DLR resulted in significantly improved pooled accuracy (91.2% vs. 73.1%, P = 0.010), image quality, SNR, and CNR (all, P < 0.001). Conclusion: The use of 1.5-mm MRI + DLR enhanced the performance of MRI in diagnosing TLE, particularly in hippocampal evaluation, because of improved depiction of hippocampal abnormalities and enhanced image quality.

Keywords

Acknowledgement

This research was supported by National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP) (grant numbers: RS-2023-00208227 and RS-2023-00305153) and by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (grant number: HI22C1723).

References

  1. Engel J Jr, McDermott MP, Wiebe S, Langfitt JT, Stern JM, Dewar S, et al. Early surgical therapy for drug-resistant temporal lobe epilepsy: a randomized trial. JAMA 2012;307:922-930 
  2. Jones AL, Cascino GD. Evidence on use of neuroimaging for surgical treatment of temporal lobe epilepsy: a systematic review. JAMA Neurol 2016;73:464-470 
  3. Cascino GD, Jack CR Jr, Parisi JE, Sharbrough FW, Hirschorn KA, Meyer FB, et al. Magnetic resonance imaging-based volume studies in temporal lobe epilepsy: pathological correlations. Ann Neurol 1991;30:31-36 
  4. Bien CG, Szinay M, Wagner J, Clusmann H, Becker AJ, Urbach H. Characteristics and surgical outcomes of patients with refractory magnetic resonance imaging-negative epilepsies. Arch Neurol 2009;66:1491-1499 
  5. Winston GP, Micallef C, Kendell BE, Bartlett PA, Williams EJ, Burdett JL, et al. The value of repeat neuroimaging for epilepsy at a tertiary referral centre: 16 years of experience. Epilepsy Res 2013;105:349-355 
  6. Muhlhofer W, Tan YL, Mueller SG, Knowlton R. MRI-negative temporal lobe epilepsy-what do we know? Epilepsia 2017;58:727-742 
  7. Vargas MI, Martelli P, Xin L, Ipek O, Grouiller F, Pittau F, et al. Clinical neuroimaging using 7 T MRI: challenges and prospects. J Neuroimaging 2018;28:5-13 
  8. Barisano G, Sepehrband F, Ma S, Jann K, Cabeen R, Wang DJ, et al. Clinical 7 T MRI: are we there yet? A review about magnetic resonance imaging at ultra-high field. Br J Radiol 2019;92:20180492 
  9. Santyr BG, Goubran M, Lau JC, Kwan BYM, Salehi F, Lee DH, et al. Investigation of hippocampal substructures in focal temporal lobe epilepsy with and without hippocampal sclerosis at 7T. J Magn Reson Imaging 2017;45:1359-1370 
  10. Stefanits H, Springer E, Pataraia E, Baumgartner C, Hainfellner JA, Prayer D, et al. Seven-tesla MRI of hippocampal sclerosis: an in vivo feasibility study with histological correlations. Invest Radiol 2017;52:666-671 
  11. Henry TR, Chupin M, Lehericy S, Strupp JP, Sikora MA, Sha ZY, et al. Hippocampal sclerosis in temporal lobe epilepsy: findings at 7 T. Radiology 2011;261:199-209 
  12. Zhang Y, Lv Y, You H, Dou W, Hou B, Shi L, et al. Study of the hippocampal internal architecture in temporal lobe epilepsy using 7 T and 3 T MRI. Seizure 2019;71:116-123 
  13. Bernasconi A, Cendes F, Theodore WH, Gill RS, Koepp MJ, Hogan RE, et al. Recommendations for the use of structural magnetic resonance imaging in the care of patients with epilepsy: a consensus report from the international league against epilepsy neuroimaging task force. Epilepsia 2019;60:1054-1068 
  14. Sijbers J, Scheunders P, Bonnet N, Van Dyck D, Raman E. Quantification and improvement of the signal-to-noise ratio in a magnetic resonance image acquisition procedure. Magn Reson Imaging 1996;14:1157-1163 
  15. Lebel RM. Performance characterization of a novel deep learning-based MR image reconstruction pipeline. arXiv [Preprint]. 2020 [accessed on March 21, 2023]. Available at: https://doi.org/10.48550/arXiv.2008.06559 
  16. Park JC, Park KJ, Park MY, Kim MH, Kim JK. Fast T2-weighted imaging with deep learning-based reconstruction: evaluation of image quality and diagnostic performance in patients undergoing radical prostatectomy. J Magn Reson Imaging 2022;55:1735-1744 
  17. Kim M, Kim HS, Kim HJ, Park JE, Park SY, Kim YH, et al. Thinslice pituitary MRI with deep learning-based reconstruction: diagnostic performance in a postoperative setting. Radiology 2021;298:114-122 
  18. Lee DH, Park JE, Nam YK, Lee J, Kim S, Kim YH, et al. Deep learning-based thin-section MRI reconstruction improves tumour detection and delineation in pre- and post-treatment pituitary adenoma. Sci Rep 2021;11:21302 
  19. Ueda T, Ohno Y, Yamamoto K, Murayama K, Ikedo M, Yui M, et al. Deep learning reconstruction of diffusion-weighted MRI improves image quality for prostatic imaging. Radiology 2022;303:373-381 
  20. Yasaka K, Akai H, Sugawara H, Tajima T, Akahane M, Yoshioka N, et al. Impact of deep learning reconstruction on intracranial 1.5 T magnetic resonance angiography. Jpn J Radiol 2022;40:476-483 
  21. Iwamura M, Ide S, Sato K, Kakuta A, Tatsuo S, Nozaki A, et al. Thin-slice two-dimensional T2-weighted imaging with deep learning-based reconstruction: improved lesion detection in the brain of patients with multiple sclerosis. Magn Reson Med Sci 2023 Mar 16. [Epub]. https://doi.org/10.2463/mrms.mp.2022-0112 
  22. Jung W, Lee HS, Seo M, Nam Y, Choi Y, Shin NY, et al. MR-self Noise2Noise: self-supervised deep learning-based image quality improvement of submillimeter resolution 3D MR images. Eur Radiol 2023;33:2686-2698 
  23. Abud LG, Thivard L, Abud TG, Nakiri GS, Santos AC, Dormont D. Partial epilepsy: a pictorial review of 3 TESLA magnetic resonance imaging features. Clinics (Sao Paulo) 2015;70:654-661 
  24. Kim M, Kim HS, Park JE, Park SY, Kim YH, Kim SJ, et al. Thinslice pituitary MRI with deep learning-based reconstruction for preoperative prediction of cavernous sinus invasion by pituitary adenoma: a prospective study. AJNR Am J Neuroradiol 2022;43:280-285 
  25. Wang X, Ma J, Bhosale P, Ibarra Rovira JJ, Qayyum A, Sun J, et al. Novel deep learning-based noise reduction technique for prostate magnetic resonance imaging. Abdom Radiol (NY) 2021;46:3378-3386 
  26. Zochowski KC, Tan ET, Argentieri EC, Lin B, Burge AJ, Queler SC, et al. Improvement of peripheral nerve visualization using a deep learning-based MR reconstruction algorithm. Magn Reson Imaging 2022;85:186-192 
  27. Kim SE, Andermann F, Olivier A. The clinical and electrophysiological characteristics of temporal lobe epilepsy with normal MRI. J Clin Neurol 2006;2:42-50 
  28. Andermann F. Pseudotemporal vs neocortical temporal epilepsy: things aren't always where they seem to be. Neurology 2003;61:732-733 
  29. Bronen RA, Fulbright RK, Kim JH, Spencer SS, Spencer DD, al-Rodhan NR. Regional distribution of MR findings in hippocampal sclerosis. AJNR Am J Neuroradiol 1995;16:1193-1200 
  30. Oppenheim C, Dormont D, Biondi A, Lehericy S, Hasboun D, Clemenceau S, et al. Loss of digitations of the hippocampal head on high-resolution fast spin-echo MR: a sign of mesial temporal sclerosis. AJNR Am J Neuroradiol 1998;19:457-463 
  31. Erasmus L, Hurter D, Naude M, Kritzinger H, Acho S. A short overview of MRI artefacts. SA J Radiol 2004;8:13-17