Evaluation of the quality and the productivity of neuroradiological reading of multiple sclerosis follow-up MRI scans using an intelligent automation software.
Artificial intelligence
Intelligent automation
Machine learning
Multiple sclerosis
Journal
Neuroradiology
ISSN: 1432-1920
Titre abrégé: Neuroradiology
Pays: Germany
ID NLM: 1302751
Informations de publication
Date de publication:
24 Jan 2024
24 Jan 2024
Historique:
received:
24
09
2023
accepted:
10
01
2024
medline:
24
1
2024
pubmed:
24
1
2024
entrez:
24
1
2024
Statut:
aheadofprint
Résumé
The assessment of multiple sclerosis (MS) lesions on follow-up magnetic resonance imaging (MRI) is tedious, time-consuming, and error-prone. Automation of low-level tasks could enhance the radiologist in this work. We evaluate the intelligent automation software Jazz in a blinded three centers study, for the assessment of new, slowly expanding, and contrast-enhancing MS lesions. In three separate centers, 117 MS follow-up MRIs were blindly analyzed on fluid attenuated inversion recovery (FLAIR), pre- and post-gadolinium T1-weighted images using Jazz by 2 neuroradiologists in each center. The reading time was recorded. The ground truth was defined in a second reading by side-by-side comparison of both reports from Jazz and the standard clinical report. The number of described new, slowly expanding, and contrast-enhancing lesions described with Jazz was compared to the lesions described in the standard clinical report. A total of 96 new lesions from 41 patients and 162 slowly expanding lesions (SELs) from 61 patients were described in the ground truth reading. A significantly larger number of new lesions were described using Jazz compared to the standard clinical report (63 versus 24). No SELs were reported in the standard clinical report, while 95 SELs were reported on average using Jazz. A total of 4 new contrast-enhancing lesions were found in all reports. The reading with Jazz was very time efficient, taking on average 2min33s ± 1min0s per case. Overall inter-reader agreement for new lesions between the readers using Jazz was moderate for new lesions (Cohen kappa = 0.5) and slight for SELs (0.08). The quality and the productivity of neuroradiological reading of MS follow-up MRI scans can be significantly improved using the dedicated software Jazz.
Identifiants
pubmed: 38265684
doi: 10.1007/s00234-024-03293-3
pii: 10.1007/s00234-024-03293-3
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s).
Références
Thompson AJ, Baranzini SE, Geurts J et al (2018) Multiple sclerosis. Lancet 391:1622–1636. https://doi.org/10.1016/S0140-6736(18)30481-1
doi: 10.1016/S0140-6736(18)30481-1
pubmed: 29576504
Kuhlmann T, Moccia M, Coetzee T et al (2023) Multiple sclerosis progression: time for a new mechanism-driven framework. Lancet Neurol 22:78–88. https://doi.org/10.1016/S1474-4422(22)00289-7
doi: 10.1016/S1474-4422(22)00289-7
pubmed: 36410373
Rovaris M, Confavreux C, Furlan R et al (2006) Secondary progressive multiple sclerosis: current knowledge and future challenges. Lancet Neurol 5:343–354. https://doi.org/10.1016/S1474-4422(06)70410-0
doi: 10.1016/S1474-4422(06)70410-0
pubmed: 16545751
Klineova S, Lublin FD (2018) Clinical course of multiple sclerosis. Cold Spring Harb Perspect Med 8:a028928. https://doi.org/10.1101/cshperspect.a028928
doi: 10.1101/cshperspect.a028928
pubmed: 29358317
pmcid: 6120692
Katz Sand I, Krieger S, Farrell C, Miller AE (2014) Diagnostic uncertainty during the transition to secondary progressive multiple sclerosis. Mult Scler 20:1654–1657. https://doi.org/10.1177/1352458514521517
doi: 10.1177/1352458514521517
pubmed: 24493475
Brown JWL, Coles A, Horakova D et al (2019) Association of initial disease-modifying therapy with later conversion to secondary progressive multiple sclerosis. JAMA 321:175. https://doi.org/10.1001/jama.2018.20588
doi: 10.1001/jama.2018.20588
pubmed: 30644981
pmcid: 6439772
Lamb YN (2022) Ocrelizumab: a review in multiple sclerosis. Drugs 82:323–334. https://doi.org/10.1007/s40265-022-01672-9
doi: 10.1007/s40265-022-01672-9
pubmed: 35192158
pmcid: 8862399
Kappos L, Bar-Or A, Cree BAC et al (2018) Siponimod versus placebo in secondary progressive multiple sclerosis (EXPAND): a double-blind, randomised, phase 3 study. Lancet 391:1263–1273. https://doi.org/10.1016/S0140-6736(18)30475-6
doi: 10.1016/S0140-6736(18)30475-6
pubmed: 29576505
Moraal B, Wattjes MP, Geurts JJG et al (2010) Improved detection of active multiple sclerosis lesions: 3D subtraction imaging. Radiology 255:154–163. https://doi.org/10.1148/radiol.09090814
doi: 10.1148/radiol.09090814
pubmed: 20308453
Eichinger P, Wiestler H, Zhang H et al (2017) A novel imaging technique for better detecting new lesions in multiple sclerosis. J Neurol 264:1909–1918. https://doi.org/10.1007/s00415-017-8576-y
doi: 10.1007/s00415-017-8576-y
pubmed: 28756606
Eichinger P, Schön S, Pongratz V et al (2019) Accuracy of unenhanced MRI in the detection of new brain lesions in multiple sclerosis. Radiology 291:429–435. https://doi.org/10.1148/radiol.2019181568
doi: 10.1148/radiol.2019181568
pubmed: 30860448
Tan IL, Van Schijndel RA, Pouwels PJW et al (2002) Serial isotropic three-dimensional fast FLAIR imaging: using image registration and subtraction to reveal active multiple sclerosis lesions. Am J Roentgenol 179:777–782. https://doi.org/10.2214/ajr.179.3.1790777
doi: 10.2214/ajr.179.3.1790777
Schmidt MA, Linker RA, Lang S et al (2018) FLAIRfusion processing with contrast inversion: improving detection and reading time of new cerebral MS lesions. Clin Neuroradiol 28:367–376. https://doi.org/10.1007/s00062-017-0567-y
doi: 10.1007/s00062-017-0567-y
pubmed: 28265679
Ganiler O, Oliver A, Diez Y et al (2014) A subtraction pipeline for automatic detection of new appearing multiple sclerosis lesions in longitudinal studies. Neuroradiology 56:363–374. https://doi.org/10.1007/s00234-014-1343-1
doi: 10.1007/s00234-014-1343-1
pubmed: 24590302
Afzal HMR, Luo S, Ramadan S, Lechner-Scott J (2022) The emerging role of artificial intelligence in multiple sclerosis imaging. Mult Scler 28:849–858. https://doi.org/10.1177/1352458520966298
doi: 10.1177/1352458520966298
pubmed: 33112207
Aslani S, Dayan M, Storelli L et al (2019) Multi-branch convolutional neural network for multiple sclerosis lesion segmentation. Neuroimage 196:1–15. https://doi.org/10.1016/j.neuroimage.2019.03.068
doi: 10.1016/j.neuroimage.2019.03.068
pubmed: 30953833
Hashemi SR, Salehi SSM, Erdogmus D et al (2019) Asymmetric loss functions and deep densely connected networks for highly imbalanced medical image segmentation: application to multiple sclerosis lesion detection. IEEE Access 7:1721–1735. https://doi.org/10.1109/ACCESS.2018.2886371
doi: 10.1109/ACCESS.2018.2886371
Andermatt S, Pezold S, Cattin PC (2018) Automated segmentation of multiple sclerosis lesions using multi-dimensional gated recurrent units. In: Crimi A, Bakas S, Kuijf H et al (eds) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. Springer International Publishing, Cham, pp 31–42
doi: 10.1007/978-3-319-75238-9_3
Valverde S, Cabezas M, Roura E et al (2017) Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach. Neuroimage 155:159–168. https://doi.org/10.1016/j.neuroimage.2017.04.034
doi: 10.1016/j.neuroimage.2017.04.034
pubmed: 28435096
Maier O (2015) Handels H MS lesion segmentation in MRI with random forests. Proc Longitudinal Multiple Sclerosis Lesion Segmentation Challenge 1–2. https://iacl.ece.jhu.edu/images/d/d7/Oskar_Maier.pdf
Birenbaum A, Greenspan H (2016) Longitudinal multiple sclerosis lesion segmentation using multi-view convolutional neural networks. In: Carneiro G, Mateus D, Peter L et al (eds) Deep Learning and Data Labeling for Medical Applications. Springer International Publishing, Cham, pp 58–67
doi: 10.1007/978-3-319-46976-8_7
Deshpande H, Maurel P, Barillot C (2015) Adaptive dictionary learning for competitive classification of multiple sclerosis lesions. 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI). IEEE, Brooklyn, NY, USA, pp 136–139
doi: 10.1109/ISBI.2015.7163834
Jain S, Sima DM, Ribbens A et al (2015) Automatic segmentation and volumetry of multiple sclerosis brain lesions from MR images. NeuroImage: Clin 8:367–375
doi: 10.1016/j.nicl.2015.05.003
pubmed: 26106562
Sudre CH, Cardoso MJ, Bouvy WH et al (2015) Bayesian model selection for pathological neuroimaging data applied to white matter lesion segmentation. IEEE Trans Med Imaging 34:2079–2102. https://doi.org/10.1109/TMI.2015.2419072
doi: 10.1109/TMI.2015.2419072
pubmed: 25850086
Tomas-Fernandez X, Warfield SK (2015) A model of population and subject (MOPS) intensities with application to multiple sclerosis lesion segmentation. IEEE Trans Med Imaging 34:1349–1361. https://doi.org/10.1109/TMI.2015.2393853
doi: 10.1109/TMI.2015.2393853
pubmed: 25616008
pmcid: 4506921
Hindsholm AM, Andersen FL, Cramer SP et al (2023) Scanner agnostic large-scale evaluation of MS lesion delineation tool for clinical MRI. Front Neurosci 17:1177540. https://doi.org/10.3389/fnins.2023.1177540
doi: 10.3389/fnins.2023.1177540
pubmed: 37274207
pmcid: 10235534
Krishnan AP, Song Z, Clayton D et al (2023) Multi-arm U-Net with dense input and skip connectivity for T2 lesion segmentation in clinical trials of multiple sclerosis. Sci Rep 13:4102. https://doi.org/10.1038/s41598-023-31207-5
doi: 10.1038/s41598-023-31207-5
pubmed: 36914715
pmcid: 10011580
Hainc N, Federau C, Stieltjes B et al (2017) The bright, artificial intelligence-augmented future of neuroimaging reading. Front Neurol 8:489. https://doi.org/10.3389/fneur.2017.00489
doi: 10.3389/fneur.2017.00489
pubmed: 28983278
pmcid: 5613097
Wikipedia - Intelligent automation. https://en.wikipedia.org/wiki/Intelligent_automation . Accessed 1 Jan 2023
Jazz, www.ai-medical.ch
Carrasco M (2011) Visual attention: the past 25 years. Vision Res 51:1484–1525. https://doi.org/10.1016/j.visres.2011.04.012
doi: 10.1016/j.visres.2011.04.012
pubmed: 21549742
pmcid: 3390154
Kinchla RA (1992) Attention. Annu Rev Psychol 43:711–742. https://doi.org/10.1146/annurev.ps.43.020192.003431
doi: 10.1146/annurev.ps.43.020192.003431
pubmed: 1539951
Beck DM, Kastner S (2009) Top-down and bottom-up mechanisms in biasing competition in the human brain. Vision Res 49:1154–1165. https://doi.org/10.1016/j.visres.2008.07.012
doi: 10.1016/j.visres.2008.07.012
pubmed: 18694779
Reynolds JH, Chelazzi L (2004) Attentional modulation of visual processing. Annu Rev Neurosci 27:611–647. https://doi.org/10.1146/annurev.neuro.26.041002.131039
doi: 10.1146/annurev.neuro.26.041002.131039
pubmed: 15217345
Enns JT, Austen EL, Lollo VD et al (2001) New objects dominate luminance transients in setting attentional priority. J Exp Psychol Hum Percept Perform 27(6):1287–1302
doi: 10.1037/0096-1523.27.6.1287
pubmed: 11766925
Yantis S, Hillstrom AP (1994) Stimulus-driven attentional capture: Evidence from equiluminant visual objects. J Exp Psychol Hum Percept Perform 20:95–107. https://doi.org/10.1037/0096-1523.20.1.95
doi: 10.1037/0096-1523.20.1.95
pubmed: 8133227
Yantis S, Jonides J (1984) Abrupt visual onsets and selective attention: evidence from visual search. J Exp Psychol Hum Percept Perform 10:601–621. https://doi.org/10.1037/0096-1523.10.5.601
doi: 10.1037/0096-1523.10.5.601
pubmed: 6238122
Filippi M, Preziosa P, Langdon D et al (2020) Identifying progression in multiple sclerosis: new perspectives. Ann Neurol 88:438–452. https://doi.org/10.1002/ana.25808
doi: 10.1002/ana.25808
pubmed: 32506714
Kalincik T, Cutter G, Spelman T et al (2015) Defining reliable disability outcomes in multiple sclerosis. Brain 138:3287–3298. https://doi.org/10.1093/brain/awv258
doi: 10.1093/brain/awv258
pubmed: 26359291
D’Souza M, Papadopoulou A, Girardey C, Kappos L (2021) Standardization and digitization of clinical data in multiple sclerosis. Nat Rev Neurol 17:119–125. https://doi.org/10.1038/s41582-020-00448-7
doi: 10.1038/s41582-020-00448-7
pubmed: 33452493
Alessandrino F, Pichiecchio A, Mallucci G et al (2018) Do MRI structured reports for multiple sclerosis contain adequate information for clinical decision making? Am J Roentgenol 210:24–29. https://doi.org/10.2214/AJR.17.18451
doi: 10.2214/AJR.17.18451
Voigt I, Inojosa H, Dillenseger A et al (2021) Digital twins for multiple sclerosis. Front Immunol 12:669811. https://doi.org/10.3389/fimmu.2021.669811
doi: 10.3389/fimmu.2021.669811
pubmed: 34012452
pmcid: 8128142
Calvi A, Haider L, Prados F, et al (2020) In vivo imaging of chronic active lesions in multiple sclerosis. Mult Scler 135245852095858. https://doi.org/10.1177/1352458520958589
Elliott C, Wolinsky JS, Hauser SL et al (2019) Slowly expanding/evolving lesions as a magnetic resonance imaging marker of chronic active multiple sclerosis lesions. Mult Scler 25:1915–1925. https://doi.org/10.1177/1352458518814117
doi: 10.1177/1352458518814117
pubmed: 30566027
Elliott C, Belachew S, Wolinsky JS et al (2019) Chronic white matter lesion activity predicts clinical progression in primary progressive multiple sclerosis. Brain 142:2787–2799. https://doi.org/10.1093/brain/awz212
doi: 10.1093/brain/awz212
pubmed: 31497864
pmcid: 6736181
Preziosa P, Pagani E, Meani A et al (2022) Slowly expanding lesions predict 9-year multiple sclerosis disease progression. Neurol Neuroimmunol Neuroinflamm 9:e1139. https://doi.org/10.1212/NXI.0000000000001139
doi: 10.1212/NXI.0000000000001139
pubmed: 35105685
pmcid: 8808355
Calvi A, Carrasco FP, Tur C et al (2022) Association of slowly expanding lesions on MRI with disability in people with secondary progressive multiple sclerosis. Neurology 98:e1783–e1793. https://doi.org/10.1212/WNL.0000000000200144
doi: 10.1212/WNL.0000000000200144
pubmed: 35277438
Yong HYF, Yong VW (2022) Mechanism-based criteria to improve therapeutic outcomes in progressive multiple sclerosis. Nat Rev Neurol 18:40–55. https://doi.org/10.1038/s41582-021-00581-x
doi: 10.1038/s41582-021-00581-x
pubmed: 34732831