Assessing deep learning reconstruction for faster prostate MRI: visual vs. diagnostic performance metrics
- PMID: 38724765
- DOI: 10.1007/s00330-024-10771-y
Assessing deep learning reconstruction for faster prostate MRI: visual vs. diagnostic performance metrics
Abstract
Objective: Deep learning (DL) MRI reconstruction enables fast scan acquisition with good visual quality, but the diagnostic impact is often not assessed because of large reader study requirements. This study used existing diagnostic DL to assess the diagnostic quality of reconstructed images.
Materials and methods: A retrospective multisite study of 1535 patients assessed biparametric prostate MRI between 2016 and 2020. Likely clinically significant prostate cancer (csPCa) lesions (PI-RADS 4) were delineated by expert radiologists. T2-weighted scans were retrospectively undersampled, simulating accelerated protocols. DL reconstruction (DLRecon) and diagnostic DL detection (DLDetect) were developed. The effect on the partial area under (pAUC), the Free-Response Operating Characteristic (FROC) curve, and the structural similarity (SSIM) were compared as metrics for diagnostic and visual quality, respectively. DLDetect was validated with a reader concordance analysis. Statistical analysis included Wilcoxon, permutation, and Cohen's kappa tests for visual quality, diagnostic performance, and reader concordance.
Results: DLRecon improved visual quality at 4- and 8-fold (R4, R8) subsampling rates, with SSIM (range: -1 to 1) improved to 0.78 ± 0.02 (p < 0.001) and 0.67 ± 0.03 (p < 0.001) from 0.68 ± 0.03 and 0.51 ± 0.03, respectively. However, diagnostic performance at R4 showed a pAUC FROC of 1.33 (CI 1.28-1.39) for DL and 1.29 (CI 1.23-1.35) for naive reconstructions, both significantly lower than fully sampled pAUC of 1.58 (DL: p = 0.024, naïve: p = 0.02). Similar trends were noted for R8.
Conclusion: DL reconstruction produces visually appealing images but may reduce diagnostic accuracy. Incorporating diagnostic AI into the assessment framework offers a clinically relevant metric essential for adopting reconstruction models into clinical practice.
Clinical relevance statement: In clinical settings, caution is warranted when using DL reconstruction for MRI scans. While it recovered visual quality, it failed to match the prostate cancer detection rates observed in scans not subjected to acceleration and DL reconstruction.
Keywords: Cancer of prostate; Deep learning; Diagnosis (computer-assisted); Image analysis (computer-assisted); Magnetic resonance imaging.
© 2024. The Author(s).
Comment in
-
Evaluation of AI-assisted medical image reconstruction: More than meets the eye?Eur Radiol. 2024 May 29. doi: 10.1007/s00330-024-10808-2. Online ahead of print. Eur Radiol. 2024. PMID: 38811390 No abstract available.
Similar articles
-
Deep learning-based reconstruction for acceleration of lumbar spine MRI: a prospective comparison with standard MRI.Eur Radiol. 2023 Dec;33(12):8656-8668. doi: 10.1007/s00330-023-09918-0. Epub 2023 Jul 27. Eur Radiol. 2023. PMID: 37498386
-
Comparison of a Deep Learning-Accelerated vs. Conventional T2-Weighted Sequence in Biparametric MRI of the Prostate.J Magn Reson Imaging. 2023 Oct;58(4):1055-1064. doi: 10.1002/jmri.28602. Epub 2023 Jan 18. J Magn Reson Imaging. 2023. PMID: 36651358 Free PMC article.
-
Comparative Performance of Deep Learning and Radiologists for the Diagnosis and Localization of Clinically Significant Prostate Cancer at MRI: A Systematic Review.Life (Basel). 2022 Sep 26;12(10):1490. doi: 10.3390/life12101490. Life (Basel). 2022. PMID: 36294928 Free PMC article. Review.
-
Deep Learning Reconstruction Enables Highly Accelerated Biparametric MR Imaging of the Prostate.J Magn Reson Imaging. 2022 Jul;56(1):184-195. doi: 10.1002/jmri.28024. Epub 2021 Dec 7. J Magn Reson Imaging. 2022. PMID: 34877735 Free PMC article.
-
Multiparametric MRI in detection and staging of prostate cancer.Dan Med J. 2017 Feb;64(2):B5327. Dan Med J. 2017. PMID: 28157066 Review.
References
Grants and funding
LinkOut - more resources
Full Text Sources
Research Materials
Miscellaneous