Deep Learning–Based Algorithm for Automatic Quantification of Nigrosome-1 and Parkinsonism Classification Using Susceptibility Map–Weighted MRI

References

1. 1.↵
   1. Lang AE,
   2. Lozano AM

   . Parkinson’s disease. First of two parts. N Engl J Med 1998;339:1044–53 doi:10.1056/NEJM199810083391506 pmid:9761807

   CrossRefPubMedWeb of Science
2. 2.↵
   1. Blazejewska AI,
   2. Schwarz ST,
   3. Pitiot A, et al

   . Visualization of nigrosome 1 and its loss in PD: pathoanatomical correlation and in vivo 7 T MRI. Neurology 2013;81:534–40 doi:10.1212/WNL.0b013e31829e6fd2 pmid:23843466

   CrossRefPubMed
3. 3.↵
   1. Damier P,
   2. Hirsch EC,
   3. Agid Y, et al

   . The substantia nigra of the human brain. I. Nigrosomes and the nigral matrix, a compartmental organization based on calbindin D(28K) immunohistochemistry. Brain 1999;122(Pt 8):1421–36 doi:10.1093/brain/122.8.1421 pmid:10430829

   CrossRefPubMedWeb of Science
4. 4.↵
   1. Schwarz ST,
   2. Afzal M,
   3. Morgan PS, et al

   . The ’swallow tail’ appearance of the healthy nigrosome - a new accurate test of Parkinson’s disease: a case-control and retrospective cross-sectional MRI study at 3T. PLoS One 2014;9:e93814 doi:10.1371/journal.pone.0093814 pmid:24710392

   CrossRefPubMed
5. 5.↵
   1. Cosottini M,
   2. Frosini D,
   3. Pesaresi I, et al

   . MR imaging of the substantia nigra at 7 T enables diagnosis of Parkinson disease. Radiology 2014;271:831–38 doi:10.1148/radiol.14131448 pmid:24601752

   CrossRefPubMed
6. 6.↵
   1. Cosottini M,
   2. Frosini D,
   3. Pesaresi I, et al

   . Comparison of 3T and 7T susceptibility-weighted angiography of the substantia nigra in diagnosing Parkinson disease. AJNR Am J Neuroradiol 2015;36:461–66 doi:10.3174/ajnr.A4158 pmid:25376811

   Abstract/FREE Full Text
7. 7.↵
   1. Lee DH,
   2. Heo H,
   3. Suh CH, et al

   . Improved diagnostic performance of susceptibility-weighted imaging with compressed sensing-sensitivity encoding and neuromelanin-sensitive MRI for Parkinson’s disease and atypical Parkinsonism. Clin Radiology 2024;79:e102–11 doi:10.1016/j.crad.2023.09.019 pmid:37863747

   CrossRefPubMed
8. 8.↵
   1. Sung YH,
   2. Noh Y,
   3. Kim EY

   . Early-stage Parkinson’s disease: abnormal nigrosome 1 and 2 revealed by a voxelwise analysis of neuromelanin-sensitive MRI. Hum Brain Mapp 2021;42:2823–32 doi:10.1002/hbm.25406 pmid:33751680

   CrossRefPubMed
9. 9.↵
   1. Kim PH,
   2. Lee DH,
   3. Suh CH, et al

   . Diagnostic performance of loss of nigral hyperintensity on susceptibility-weighted imaging in parkinsonism: an updated meta-analysis. Eur Radiology 2021;31:6342–52 doi:10.1007/s00330-020-07627-6 pmid:33449183

   CrossRefPubMed
10. 10.↵
    1. Cheng Z,
    2. He N,
    3. Huang P, et al

    . Imaging the nigrosome 1 in the substantia nigra using susceptibility weighted imaging and quantitative susceptibility mapping: an application to Parkinson’s disease. Neuroimage Clin 2020;25:102103 doi:10.1016/j.nicl.2019.102103 pmid:31869769

    CrossRefPubMed
11. 11.↵
    1. Kim HK,
    2. Kim T,
    3. Baek MS, et al

    . Nigrosome 1 visibility and its association with nigrostriatal dopaminergic loss in Parkinson’s disease. Eur J Neurol 2023;30:1639–47 doi:10.1111/ene.15781 pmid:36915220

    CrossRefPubMed
12. 12.↵
    1. Sung YH,
    2. Kim JS,
    3. Yoo SW, et al

    . A prospective multi-centre study of susceptibility map-weighted MRI for the diagnosis of neurodegenerative parkinsonism. Eur Radiology 2022;32:3597–608 doi:10.1007/s00330-021-08454-z pmid:35064313

    CrossRefPubMed
13. 13.↵
    1. Bae YJ,
    2. Song YS,
    3. Choi BS, et al

    . Comparison of susceptibility-weighted imaging and susceptibility map-weighted imaging for the diagnosis of Parkinsonism with nigral hyperintensity. Eur J Radiology 2021;134:109398 doi:10.1016/j.ejrad.2020.109398 pmid:33264728

    CrossRefPubMed
14. 14.↵
    1. Lee S,
    2. Suh CH,
    3. Jo S, et al

    . Comparative performance of susceptibility map-weighted MRI according to the acquisition planes in the diagnosis of neurodegenerative parkinsonism. Korean J Radiology 2024;25:267–76 doi:10.3348/kjr.2023.0920 pmid:38413111

    CrossRefPubMed
15. 15.↵
    1. Suh CH,
    2. Shim WH,
    3. Kim SJ, et al

    ; Alzheimer’s Disease Neuroimaging Initiative. Development and validation of a deep learning-based automatic brain segmentation and classification algorithm for Alzheimer disease using 3D T1-weighted volumetric images. AJNR Am J Neuroradiol 2020;41:2227–34 doi:10.3174/ajnr.A6848 pmid:33154073

    Abstract/FREE Full Text
16. 16.↵
    1. Doss DJ,
    2. Johnson GW,
    3. Narasimhan S, et al

    . Deep learning segmentation of the nucleus basalis of Meynert on 3T MRI. AJNR Am J Neuroradiol 2023;44:1020–25 doi:10.3174/ajnr.A7950 pmid:37562826

    Abstract/FREE Full Text
17. 17.↵
    1. Fan S,
    2. Ponisio MR,
    3. Xiao P, et al

    ; Alzheimer’s Disease Neuroimaging Initiative. AmyloidPETNet: classification of amyloid positivity in brain PET imaging using end-to-end deep learning. Radiology 2024;311:e231442 doi:10.1148/radiol.231442 pmid:38860897

    CrossRefPubMed
18. 18.↵
    1. Chen H,
    2. Liu X,
    3. Luo X, et al

    . An automated hybrid approach via deep learning and radiomics focused on the midbrain and substantia nigra to detect early-stage Parkinson’s disease. Front Aging Neurosci 2024;16:1397896 doi:10.3389/fnagi.2024.1397896

    CrossRefPubMed
19. 19.↵
    1. Shin DH,
    2. Heo H,
    3. Song S, et al

    . Automated assessment of the substantia nigra on susceptibility map-weighted imaging using deep convolutional neural networks for diagnosis of idiopathic Parkinson’s disease. Parkinsonism Relat Disord 2021;85:84–90 doi:10.1016/j.parkreldis.2021.03.004 pmid:33761389

    CrossRefPubMed
20. 20.↵
    1. Ariz M,
    2. Martinez M,
    3. Alvarez I, et al

    ; Catalonian Neuroimaging Parkinson’s Disease Consortium. Automatic segmentation and quantification of nigrosome-1 neuromelanin and iron in MRI: a candidate biomarker for Parkinson’s disease. J Magn Reson Imaging 2024;60:534–47 doi:10.1002/jmri.29073 pmid:37915245

    CrossRefPubMed
21. 21.↵
    1. Wang C,
    2. He N,
    3. Zhang Y, et al

    . Enhancing nigrosome-1 sign identification via interpretable AI using true susceptibility weighted imaging. J Magn Reson Imaging 2024;60:1904–15 doi:10.1002/jmri.29245 pmid:38236577

    CrossRefPubMed
22. 22.↵
    1. Tejani AS,
    2. Klontzas ME,
    3. Gatti AA, et al

    ; CLAIM 2024 Update Panel. Checklist for Artificial Intelligence in Medical Imaging (CLAIM): 2024 Update. Radiology Artif Intell 2024;6:e240300 doi:10.1148/ryai.240300 pmid:38809149

    CrossRefPubMed
23. 23.↵
    1. Sung YH,
    2. Noh Y,
    3. Lee J, et al

    . Drug-induced parkinsonism versus idiopathic Parkinson disease: utility of nigrosome 1 with 3-T imaging. Radiology 2016;279:849–58 doi:10.1148/radiol.2015151466 pmid:26690908

    CrossRefPubMed
24. 24.↵
    1. Nam Y,
    2. Gho SM,
    3. Kim DH, et al

    . Imaging of nigrosome 1 in substantia nigra at 3T using multiecho susceptibility map-weighted imaging (SMWI). J Magn Reson Imaging 2017;46:528–36 doi:10.1002/jmri.25553 pmid:27859983

    CrossRefPubMed
25. 25.↵
    1. Sung YH,
    2. Lee J,
    3. Nam Y, et al

    . Differential involvement of nigral subregions in idiopathic Parkinson’s disease. Hum Brain Mapp 2018;39:542–53 doi:10.1002/hbm.23863 pmid:29064601

    CrossRefPubMed
26. 26.↵
    1. Gho SM,
    2. Liu C,
    3. Li W, et al

    . Susceptibility map-weighted imaging (SMWI) for neuroimaging. Magn Reson Med 2014;72:337–46 doi:10.1002/mrm.24920 pmid:24006248

    CrossRefPubMed
27. 27.↵
    1. Cheng T,
    2. Wang X,
    3. Chen S, et al

    . Sparse instance activation for real-time instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022;4433–42.
28. 28.↵
    1. Billot B,
    2. Greve DN,
    3. Puonti O

    ; ADNI, et al. SynthSeg: segmentation of brain MRI scans of any contrast and resolution without retraining. Med Image Anal 2023;86:102789 doi:10.1016/j.media.2023.102789 pmid:36857946

    CrossRefPubMed
29. 29.↵
    1. Ge Z,
    2. Liu S,
    3. Wang F, et al

    . Yolox: exceeding yolo series in 2021. arXiv.org 2021. https://doi.org/10.48550/arXiv.2107.08430 Accessed December 26, 2023
30. 30.↵
    1. Kim EY,
    2. Sung YH,
    3. Shin HG, et al

    . Diagnosis of early-stage idiopathic Parkinson’s disease using high-resolution quantitative susceptibility mapping combined with histogram analysis in the substantia nigra at 3 T. J Clin Neurol 2018;14:90–97 doi:10.3988/jcn.2018.14.1.90 pmid:29629545

    CrossRefPubMed
31. 31.↵
    1. He N,
    2. Ghassaban K,
    3. Huang P, et al

    . Imaging iron and neuromelanin simultaneously using a single 3D gradient echo magnetization transfer sequence: combining neuromelanin, iron and the nigrosome-1 sign as complementary imaging biomarkers in early stage Parkinson’s disease. Neuroimage 2021;230:117810 doi:10.1016/j.neuroimage.2021.117810 pmid:33524572

    CrossRefPubMed
32. 32.↵
    1. Chau MT,
    2. Agzarian M,
    3. Wilcox RA, et al

    . Simple quantitative planimetric measurement of nigrosome-1 for clinical settings. J Neurol Sci 2023;454:120857 doi:10.1016/j.jns.2023.120857 pmid:37939625

    CrossRefPubMed
33. 33.↵
    1. Ariz M,
    2. Abad RC,
    3. Castellanos G, et al

    . Dynamic atlas-based segmentation and quantification of neuromelanin-rich brainstem structures in Parkinson disease. IEEE Trans Med Imaging 2019;38:813–23 doi:10.1109/TMI.2018.2872852 pmid:30281440

    CrossRefPubMed
34. 34.↵
    1. Bae YJ,
    2. Kim JM,
    3. Kim E, et al

    . Loss of nigral hyperintensity on 3 Tesla MRI of parkinsonism: comparison with (123) I-FP-CIT SPECT. Mov Disord 2016;31:684–92 doi:10.1002/mds.26584 pmid:26990970

    CrossRefPubMed
35. 35.↵
    1. Bae YJ,
    2. Kim JM,
    3. Sohn CH, et al

    . Imaging the substantia nigra in Parkinson disease and other parkinsonian syndromes. Radiology 2021;300:260–78 doi:10.1148/radiol.2021203341 pmid:34100679

    CrossRefPubMed
36. 36.↵
    1. Biondetti E,
    2. Gaurav R,
    3. Yahia-Cherif L, et al

    . Spatiotemporal changes in substantia nigra neuromelanin content in Parkinson’s disease. Brain 2020;143:2757–70 doi:10.1093/brain/awaa216 pmid:32856056

    CrossRefPubMed
37. 37.↵
    1. Chu YT,
    2. Yu CF,
    3. Fan SP, et al

    . Substantia nigra nigrosome-1 imaging correlates with the severity of motor symptoms in Parkinson’s disease. J Neurol Sci 2023;451:120731 doi:10.1016/j.jns.2023.120731 pmid:37454574

    CrossRefPubMed
38. 38.↵
    1. Evans JR,
    2. Mason SL,
    3. Williams-Gray CH, et al

    . The natural history of treated Parkinson’s disease in an incident, community based cohort. J Neurol Neurosurg Psychiatry 2011;82:1112–18 doi:10.1136/jnnp.2011.240366 pmid:21593513

    Abstract/FREE Full Text
39. 39.↵
    1. Goetz CG,
    2. Stebbins GT,
    3. Blasucci LM

    . Differential progression of motor impairment in levodopa-treated Parkinson’s disease. Mov Disord 2000;15:479–84 doi:10.1002/1531-8257(200005)15:3<479::AID-MDS1009>3.0.CO;2-P

    CrossRefPubMedWeb of Science
40. 40.↵
    1. Roos RA,
    2. Jongen JC,
    3. van der Velde EA

    . Clinical course of patients with idiopathic Parkinson’s disease. Mov Disord 1996;11:236–42 doi:10.1002/mds.870110304 pmid:8723138

    CrossRefPubMedWeb of Science
41. 41.↵
    1. Wang W,
    2. Xie E,
    3. Li X, et al

    . Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021;568–578.
42. 42.↵
    1. Qiao S,
    2. Chen L-C,
    3. Yuille A

    . Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. In: Proceedings of the IEEE/CVF Conference On Computer Vision and Pattern Recognition. 2021;10213–24.