Share：
Share this content in WeChat
X
[Chinese][PDF]4416
• Clinical Article •
Value of detecting changes in white matter fiber integrity in patinets with amyotrophic lateral sclerosis based on automatic fiber quantification
XU Rui  ZHU Sijia  WANG Ning  KONG Ying  YU Yixing  JIANG Bin  WAN Jiayi  MA Jiali  FANG Qi  ZHU Mo 

XU R, ZHU S J, WANG N, et al. Value of detecting changes in white matter fiber integrity in patinets with amyotrophic lateral sclerosis based on automatic fiber quantification[J]. Chin J Magn Reson Imaging, 2023, 14(9): 44-49. DOI:10.12015/issn.1674-8034.2023.09.008.


[Abstract] Objective To analyze the changes of white matter fiber integrity in patients with amyotrophic lateral sclerosis (ALS) by automatic fiber quantification (AFQ) technology, and explore the feasibility of combining it with support vector machine (SVM) to identify ALS disease.Materials and Methods Clinical and MRI data of 29 patients with ALS (ALS group) and 29 matched healthy controls (HCs group) were prospectively included. Diffusion tensor imaging (DTI) data from all subjects were analyzed using the AFQ software package, and 20 white matter fiber bundles in the whole brain were tracked. Then each fiber bundle was divided into 100 equal parts to acquire quantitative parameter values such as fraction anisotropy (FA), mean diffusion (MD), radial diffusion (RD) and axial diffusion (AD). Partial correlation was further used to explore the relationships between DTI parameters and clinical indicators. Extracting the classification features with white matter fiber difference between two subjects. SVM was used to distinguish them and estimated the accuracy rate.Results The AFQ results showed that, compared with the HCs, the ALS patients had decreased FA values and AD values in the left corticospinal tract, higher AD values in the left inferior fronto-occipital fasciculus and the right superior longitudinal fasciculus, higher MD and RD values of the bilateral corticospinal tract. The average FA value of the left corticospinal tract was positively correlated with Amyotrophic Lateral Sclerosis Functional Rating Scale-Revised (ALSFRS-R) fine functional domain score (r=0.386, P=0.046) and the average AD value of the right superior longitudinal fasciculus was positively correlated with ALSFRS-R bulbar functional domain score (r=0.422, P=0.028). Both the average MD and RD values of the right corticospinal tract were negatively associated with the Edinburgh Cognitive and Behavioural ALS Screen (ECAS) score (r=-0.428, P=0.026; r=-0.416, P=0.031). All the selected nodes with inter-group differences in damaged fiber tracts were used as feature values to achieve a good classification effect. The identification accuracy rate for the ALS and HCs groups was 81.00%, and the maximum area under the curve (AUC) value for the receiver operating characteristic (ROC) was 0.90.Conclusions The white matter microarchitectural damage in ALS is mainly related to the corticospinal tract, and these abnormalities detected by AFQ analysis can be used as a valid biomarker, which can improve the diagnostic evaluation of ALS patients when combined with the SVM method.
[Keywords] amyotrophic lateral sclerosis；diffusion tensor imaging；magnetic resonance imaging；automatic fiber quantification；corticospinal tract；support vector machine

XU Rui1   ZHU Sijia2   WANG Ning1   KONG Ying1   YU Yixing1   JIANG Bin1   WAN Jiayi1   MA Jiali1   FANG Qi2   ZHU Mo1*  

1 Department of Radiology, the First Affiliated Hospital of Soochow University, Suzhou 215006, China

2 Department of Neurology, the First Affiliated Hospital of Soochow University, Suzhou 215006, China

Corresponding author: Zhu M, E-mail: zhumo001@126.com

Conflicts of interest   None.

ACKNOWLEDGMENTS Jiangsu Provincial Health Commission's Elderly Health Project (No. LK2021017).
Received  2023-04-11
Accepted  2023-09-08
DOI: 10.12015/issn.1674-8034.2023.09.008
XU R, ZHU S J, WANG N, et al. Value of detecting changes in white matter fiber integrity in patinets with amyotrophic lateral sclerosis based on automatic fiber quantification[J]. Chin J Magn Reson Imaging, 2023, 14(9): 44-49. DOI:10.12015/issn.1674-8034.2023.09.008.

[1]
CALVO A, MOGLIA C, LUNETTA C, et al. Factors predicting survival in ALS: a multicenter Italian study[J]. J Neurol, 2017, 264(1): 54-63. DOI: 10.1007/s00415-016-8313-y.
[2]
GODOY-CORCHUELO J M, FERNÁNDEZ-BELTRÁN L C, ALI Z, et al. Lipid Metabolic Alterations in the ALS-FT Spectrum of Disorders[J]. Biomedicines, 2022, 10(5): 1105. DOI: 10.3390/biomedicines10051105.
[3]
PENDER N, PINTO-GRAU M, HARDIMAN O. Cognitive and behavioural impairment in amyotrophic lateral sclerosis[J]. Curr Opin Neurol, 2020, 33(5): 649-654. DOI: 10.1097/WCO.0000000000000862.
[4]
ARONICA R, ENRICO P, SQUARCINA L, et al. Association between Diffusion Tensor Imaging, inflammation and immunological alterations in unipolar and bipolar depression: A review[J]. Neurosci Biobehav Rev, 2022, 143: 104922. DOI: 10.1016/j.neubiorev.2022.104922.
[5]
MENKE R A L, KÖRNER S, FILIPPINI N, et al. Widespread grey matter pathology dominates the longitudinal cerebral MRI and clinical landscape of amyotrophic lateral sclerosis[J]. Brain, 2014, 137(Pt 9): 2546-2555. DOI: 10.1093/brain/awu162.
[6]
STEINBACH R, GAUR N, ROEDIGER A, et al. Disease aggressiveness signatures of amyotrophic lateral sclerosis in white matter tracts revealed by the D50 disease progression model[J]. Hum Brain Mapp, 2021, 42(3): 737-752. DOI: 10.1002/hbm.25258.
[7]
STEINBACH R, PRELL T, GAUR N, et al. Patterns of grey and white matter changes differ between bulbar and limb onset amyotrophic lateral sclerosis[J]. Neuroimage Clin, 2021, 30: 102674. DOI: 10.1016/j.nicl.2021.102674.
[8]
YEATMAN J D, DOUGHERTY R F, MYALL N J, et al. Tract profiles of white matter properties: automating fiber-tract quantification[J/OL]. PLoS One, 2012, 7(11): e49790 [2023-04-10]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3498174. DOI: 10.1371/journal.pone.0049790.
[9]
WANG J, MA L, LIU G, et al. Tractography in Type 2 Diabetes Mellitus With Subjective Memory Complaints: A Diffusion Tensor Imaging Study[J]. Front Neurosci, 2022, 15: 800420. DOI: 10.3389/fnins.2021.800420.
[10]
GOODRICH-HUNSAKER N J, ABILDSKOV T J, BLACK G, et al. Age- and sex-related effects in children with mild traumatic brain injury on diffusion magnetic resonance imaging properties: A comparison of voxelwise and tractography methods[J]. J Neurosci Res, 2018, 96(4): 626-641. DOI: 10.1002/jnr.24142.
[11]
NOBLE W S. What is a support vector machine?[J]. Nat Biotechnol, 2006, 24(12): 1565-1567. DOI: 10.1038/nbt1206-1565.
[12]
RANE R P, DE MAN E F, KIM J, et al. Structural differences in adolescent brains can predict alcohol misuse[J/OL]. Elife, 2022, 11: e77545 [2023-04-10]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9255959. DOI: 10.7554/eLife.77545.
[13]
MÜNCH M, MÜLLER H P, BEHLER A, et al. Segmental alterations of the corpus callosum in motor neuron disease: A DTI and texture analysis in 575 patients[J]. Neuroimage Clin, 2022, 35: 103061. DOI: 10.1016/j.nicl.2022.103061.
[14]
LUDOLPH A, DRORY V, HARDIMAN O, et al. A revision of the El Escorial criteria-2015[J]. Amyotroph Lateral Scler Frontotemporal Degener, 2015, 16(5-6): 291-292. DOI: 10.3109/21678421.2015.1049183.
[15]
CEDARBAUM J M, STAMBLER N, MALTA E, et al. The ALSFRS-R: a revised ALS functional rating scale that incorporates assessments of respiratory function. BDNF ALS Study Group (Phase Ⅲ)[J]. J Neurol Sci, 1999, 169(1-2): 13-21. DOI: 10.1016/s0022-510x(99)00210-5.
[16]
NIVEN E, NEWTON J, FOLEY J, et al. Validation of the Edinburgh Cognitive and Behavioural Amyotrophic Lateral Sclerosis Screen (ECAS): A cognitive tool for motor disorders[J]. Amyotroph Lateral Scler Frontotemporal Degener, 2015, 16(3-4): 172-179. DOI: 10.3109/21678421.2015.1030430.
[17]
YE S, JI Y, LI C, et al. The Edinburgh Cognitive and Behavioural ALS Screen in a Chinese Amyotrophic Lateral Sclerosis Population[J/OL]. PLoS One, 2016, 11(5): e0155496 [2023-04-10]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4873026. DOI: 10.1371/journal.pone.0155496.
[18]
GORGES M, DEL TREDICI K, DREYHAUPT J, et al. Corticoefferent pathology distribution in amyotrophic lateral sclerosis: in vivo evidence from a meta-analysis of diffusion tensor imaging data[J]. Sci Rep, 2018, 8(1): 15389. DOI: 10.1038/s41598-018-33830-z.
[19]
AGOSTA F, ROCCA M A, VALSASINA P, et al. A longitudinal diffusion tensor MRI study of the cervical cord and brain in amyotrophic lateral sclerosis patients[J]. J Neurol Neurosurg Psychiatry, 2009, 80(1): 53-55. DOI: 10.1136/jnnp.2008.154252.
[20]
EGLE M, HILAL S, TULADHAR A M, et al. Determining the OPTIMAL DTI analysis method for application in cerebral small vessel disease[J]. Neuroimage Clin, 2022, 35: 103114. DOI: 10.1016/j.nicl.2022.103114.
[21]
XU C, NEUROTH T, FUJIWARA T, et al. A Predictive Visual Analytics System for Studying Neurodegenerative Disease Based on DTI Fiber Tracts[J]. IEEE Trans Vis Comput Graph, 2023, 29(4): 2020-2035. DOI: 10.1109/TVCG.2021.3137174.
[22]
ALRUWAILI A R, PANNEK K, COULTHARD A, et al. A combined tract-based spatial statistics and voxel-based morphometry study of the first MRI scan after diagnosis of amyotrophic lateral sclerosis with subgroup analysis[J]. J Neuroradiol, 2018, 45(1): 41-48. DOI: 10.1016/j.neurad.2017.03.007.
[23]
BEHLER A, LULÉ D, LUDOLPH A C, et al. Longitudinal monitoring of amyotrophic lateral sclerosis by diffusion tensor imaging: Power calculations for group studies[J]. Front Neurosci, 2022, 16: 929151. DOI: 10.3389/fnins.2022.929151.
[24]
SARICA A, CERASA A, VALENTINO P, et al. The corticospinal tract profile in amyotrophic lateral sclerosis[J]. Hum Brain Mapp, 2017, 38(2): 727-739. DOI: 10.1002/hbm.23412.
[25]
BAJADA C J, LAMBON RALPH M A, CLOUTMAN L L. Transport for language south of the Sylvian fissure: The routes and history of the main tracts and stations in the ventral language network[J]. Cortex, 2015, 69: 141-151. DOI: 10.1016/j.cortex.2015.05.011.
[26]
CHANG E F, RAYGOR K P, BERGER M S. Contemporary model of language organization: an overview for neurosurgeons[J]. J Neurosurg, 2015, 122(2): 250-261. DOI: 10.3171/2014.10.JNS132647.
[27]
EGOROVA-BRUMLEY N, LIANG C, KHLIF M S, et al. White matter microstructure and verbal fluency[J]. Brain Struct Funct, 2022, 227(9): 3017-3025. DOI: 10.1007/s00429-022-02579-7.
[28]
MANERA U, D'OVIDIO F, CABRAS S, et al. Amyotrophic lateral sclerosis regional progression intervals change according to time of involvement of different body regions[J]. Eur J Neurol, 2023, 30(4): 872-880. DOI: 10.1111/ene.15674.
[29]
MÜLLER H P, TURNER M R, GROSSKREUTZ J, et al. A large-scale multicentre cerebral diffusion tensor imaging study in amyotrophic lateral sclerosis[J]. J Neurol Neurosurg Psychiatry, 2016, 87(6): 570-579. DOI: 10.1136/jnnp-2015-311952.
[30]
TA D, ISHAQUE A H, ELAMY A, et al. Severity of in vivo corticospinal tract degeneration is associated with survival in amyotrophic lateral sclerosis: a longitudinal, multicohort study[J]. Eur J Neurol, 2023, 30(5): 1220-1231. DOI: 10.1111/ene.15686.
[31]
BAO Y, YANG L, CHEN Y, et al. Radial diffusivity as an imaging biomarker for early diagnosis of non-demented amyotrophic lateral sclerosis[J]. Eur Radiol, 2018, 28(12): 4940-4948. DOI: 10.1007/s00330-018-5506-z.
[32]
BAEK S H, PARK J, KIM Y H, et al. Usefulness of diffusion tensor imaging findings as biomarkers for amyotrophic lateral sclerosis[J]. Sci Rep, 2020, 10(1): 5199. DOI: 10.1038/s41598-020-62049-0.
[33]
CRESPI C, DODICH A, IANNACCONE S, et al. Diffusion tensor imaging evidence of corticospinal pathway involvement in frontotemporal lobar degeneration[J]. Cortex, 2020, 125: 1-11. DOI: 10.1016/j.cortex.2019.11.022.
[34]
WELSH R C, JELSONE-SWAIN L M, FOERSTER B R. The utility of independent component analysis and machine learning in the identification of the amyotrophic lateral sclerosis diseased brain[J]. Front Hum Neurosci, 2013, 7: 251. DOI: 10.3389/fnhum.2013.00251.
[35]
AGOSTA F, SPINELLI E G, FILIPPI M. Neuroimaging in amyotrophic lateral sclerosis: current and emerging uses[J]. Expert Rev Neurother, 2018, 18(5): 395-406. DOI: 10.1080/14737175.2018.1463160.
[36]
BEHLER A, MÜLLER H P, LUDOLPH A C, et al. Diffusion Tensor Imaging in Amyotrophic Lateral Sclerosis: Machine Learning for Biomarker Development[J]. Int J Mol Sci, 2023, 24(3): 1911. DOI: 10.3390/ijms24031911.

PREV White matter microstructural changes shortly after acute stress: A DTI study
NEXT Machine learning models based on radiomics in differentiating solitary fibrous tumor from angiomatous meningioma
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn