Share：
Share this content in WeChat
X
[Chinese][PDF]81
• Technical Article •
Research on radiomics reconstruction from cerebral cortex surface based on anatomical magnetic resonance imaging
ZHANG Zhifan  WANG Xunheng  LI Lihua 

Cite this article as: ZHANG Z F, WANG X H, LI L H. Research on radiomics reconstruction from cerebral cortex surface based on anatomical magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2024, 15(7): 143-150. DOI:10.12015/issn.1674-8034.2024.07.024.


[Abstract] Objective To design a computational method of cortical surface radiomics, to provide rich and reliable local features of brain regions for brain imaging research.Materials and Methods Based on the T1WI magnetic resonance data sets of 21 groups of repeated measurements of healthy subjects and 222 attention deficit hyperactivity disorder (ADHD)-related subjects, four surface morphological indices including cortical thickness, gray matter volume, mean curvature and cortical surface area were extracted. Using the Desikan-Killiany (DK) brain atlas and spherical local projection, the brain area is flattened from the three-dimensional cortical surface to two-dimensional. Pyradiomics was used to extract 968 two-dimensional radiomics features for each of the four morphological indices. Combining repeated measurement data set and intra-class correlation coefficients (ICC), the ICC value was used as the standard for evaluating radiomics features to comprehensively evaluate the differences in test-retest reliability among different morphological indices, different radiomics feature types and different brain regions. And based on the ADHD dataset, we predict the patient's attention deficit index and hyperactivity index.Results For different morphological indicators, the radiomics features of gray matter volume and cortical surface area have better reproducibility, and are significantly different from the cortical thickness and average curvature groups (P<0.05). For different types of radiomics features, the first-order features and gray-level co-occurrence matrix features based on cortical thickness showed significant differences from other types of features (P<0.05). For different brain regions, the features extracted from the left and right entorhinal cortex, the left and right temporal poles, and the right frontal pole have lower retest retestability than other regions (P<0.05). However, in general, the brain radiomics features extracted by the surface reconstruction method proposed in this study have high reproducibility (mean ICC>0.76). In the prediction tasks of the two symptom indicators of attention deficit hyperactivity disorder (ADHD), it was found that the left hippocampal gyrus, superior frontal gyrus and superior temporal gyrus were significantly correlated with ADHD symptoms (|r|=0.33-0.52, P<0.05).Conclusions It is feasible to construct brain radiomics features based on DK brain atlas and surface morphology index. The extracted new features have good repeatability and have certain clinical value in attention prediction and other studies.
[Keywords] attention deficit hyperactivity disorder (ADHD)；attention prediction；surface morphological index；spherical local projection；radiomics features；magnetic resonance imaging

ZHANG Zhifan   WANG Xunheng*   LI Lihua  

School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China

Corresponding author: WANG X H, E-mail: xhwang@hdu.edu.cn

Conflicts of interest   None.

Received  2024-04-01
Accepted  2024-07-05
DOI: 10.12015/issn.1674-8034.2024.07.024
Cite this article as: ZHANG Z F, WANG X H, LI L H. Research on radiomics reconstruction from cerebral cortex surface based on anatomical magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2024, 15(7): 143-150. DOI:10.12015/issn.1674-8034.2024.07.024.

[1]
FREEMAN M. The World Mental Health Report: transforming mental health for all[J]. World Psychiatry, 2022, 21(3): 391-392. DOI: 10.1002/wps.21018.
[2]
BRAMMER M. The role of neuroimaging in diagnosis and personalized medicine: current position and likely future directions[J]. Dialogues Clin Neurosci, 2009, 11(4): 389-396. DOI: 10.31887/DCNS.2009.11.4/mbrammer.
[3]
ASKEN B M, TANNER J A, GAYNOR L S, et al. Alzheimer's pathology is associated with altered cognition, brain volume, and plasma biomarker patterns in traumatic encephalopathy syndrome[J/OL]. Alzheimers Res Ther, 2023, 15(1): 126 [2023-12-24]. https://pubmed.ncbi.nlm.nih.gov/37480088/. DOI: 10.1186/s13195-023-01275-w.
[4]
MEI T, LLERA A, FORDE N J, et al. Gray matter covariations in autism: out-of-sample replication using the ENIGMA autism cohort[J/OL]. Mol Autism, 2024, 15(1): 3 [2024-03-05]. https://pubmed.ncbi.nlm.nih.gov/38229192/. DOI: 10.1186/s13229-024-00583-8.
[5]
BARON-COHEN S, WHEELWRIGHT S, SKINNER R, et al. The autism-spectrum quotient (AQ): evidence from Asperger syndrome/high-functioning autism, males and females, scientists and mathematicians[J]. J Autism Dev Disord, 2001, 31(1): 5-17. DOI: 10.1023/a:1005653411471.
[6]
JIAO Y, CHEN R, KE X Y, et al. Predictive models of autism spectrum disorder based on brain regional cortical thickness[J]. NeuroImage, 2010, 50(2): 589-599. DOI: 10.1016/j.neuroimage.2009.12.047.
[7]
DESAI R, LIEBENTHAL E, POSSING E T, et al. Volumetric vs. surface-based alignment for localization of auditory cortex activation[J]. Neuroimage, 2005, 26(4): 1019-1029. DOI: 10.1016/j.neuroimage.2005.03.024.
[8]
VAN ESSEN D C. Surface-based approaches to spatial localization and registration in primate cerebral cortex[J/OL]. Neuroimage, 2004, 23(Suppl 1): S97-S107 [2024-03-05]. https://pubmed.ncbi.nlm.nih.gov/15501104/. DOI: 10.1016/j.neuroimage.2004.07.024.
[9]
SUK H I, LEE S W, SHEN D G, et al. Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis[J/OL]. NeuroImage, 2014, 101: 569-582 [2024-03-05]. https://pubmed.ncbi.nlm.nih.gov/25042445/. DOI: 10.1016/j.neuroimage.2014.06.077.
[10]
SCHAER M, KOCHALKA J, PADMANABHAN A, et al. Sex differences in cortical volume and gyrification in autism[J/OL]. Mol Autism, 2015, 6: 42 [2024-03-05]. https://pubmed.ncbi.nlm.nih.gov/26146534/. DOI: 10.1186/s13229-015-0035-y.
[11]
XU H, XU C, GU P P, et al. Neuroanatomical restoration of salience network links reduced headache impact to cognitive function improvement in mild traumatic brain injury with posttraumatic headache[J/OL]. J Headache Pain, 2023, 24(1): 43 [2024-03-05]. https://pubmed.ncbi.nlm.nih.gov/37081382/. DOI: 10.1186/s10194-023-01579-0.
[12]
YOU W F, LI Q, CHEN L Z, et al. Common and distinct cortical thickness alterations in youth with autism spectrum disorder and attention-deficit/hyperactivity disorder[J/OL]. BMC Med, 2024, 22(1): 92 [2024-04-02]. https://pubmed.ncbi.nlm.nih.gov/38433204/. DOI: 10.1186/s12916-024-03313-2.
[13]
MAYERHOEFER M E, MATERKA A, LANGS G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-495. DOI: 10.2967/jnumed.118.222893.
[14]
RIZZO S, BOTTA F, RAIMONDI S, et al. Radiomics: the facts and the challenges of image analysis[J/OL]. Eur Radiol Exp, 2018, 2(1): 36 [2023-12-24]. https://eurradiolexp.springeropen.com/articles/10.1186/s41747-018-0068-z. DOI: 10.1186/s41747-018-0068-z.
[15]
LAMBIN P, LEIJENAAR R T H, DEIST T M, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12): 749-762. DOI: 10.1038/nrclinonc.2017.141.
[16]
ABDEL RAZEK A A K, ALKSAS A, SHEHATA M, et al. Clinical applications of artificial intelligence and radiomics in neuro-oncology imaging[J/OL]. Insights Imaging, 2021, 12(1): 152 [2023-12-24]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10047107/. DOI: 10.1186/s13244-021-01102-6.
[17]
CHADDAD A, PENG J H, XU J, et al. Survey of explainable AI techniques in healthcare[J/OL]. Sensors, 2023, 23(2): 634 [2024-04-02]. https://pubmed.ncbi.nlm.nih.gov/36679430/. DOI: 10.3390/s23020634.
[18]
SUN L, ZHANG S T, CHEN H, et al. Brain tumor segmentation and survival prediction using multimodal MRI scans with deep learning[J/OL]. Front Neurosci, 2019, 13: 810 [2023-12-24]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6707136/. DOI: 10.3389/fnins.2019.00810.
[19]
LI G Z, LI L, LI Y M, et al. An MRI radiomics approach to predict survival and tumour-infiltrating macrophages in gliomas[J]. Brain, 2022, 145(3): 1151-1161. DOI: 10.1093/brain/awab340.
[20]
ZHAO K, ZHENG Q, CHE T T, et al. Regional radiomics similarity networks (R2SNs) in the human brain: Reproducibility, small-world properties and a biological basis[J]. Netw Neurosci, 2021, 5(3): 783-797. DOI: 10.1162/netn_a_00200.
[21]
PINA V, CAMPELLO V M, LEKADIR K, et al. Mathematical abilities in school-aged children: a structural magnetic resonance imaging analysis with radiomics[J/OL]. Front Neurosci, 2022, 16: 819069 [2024-04-02]. https://pubmed.ncbi.nlm.nih.gov/35495063/. DOI: 10.3389/fnins.2022.819069.
[22]
LANDMAN B A, HUANG A J, GIFFORD A, et al. Multi-parametric neuroimaging reproducibility: a 3-T resource study[J]. Neuroimage, 2011, 54(4): 2854-2866. DOI: 10.1016/j.neuroimage.2010.11.047.
[23]
VIESEL-NORDMEYER N, PRADO J. Arithmetic skills are associated with left fronto-temporal gray matter volume in 536 children and adolescents[J/OL]. NPJ Sci Learn, 2023, 8(1): 56 [2023-12-24]. https://www.nature.com/articles/s41539-023-00201-x. DOI: 10.1038/s41539-023-00201-x.
[24]
TAVARES V, PRATA D, FERREIRA H A. Comparing SPM12 and CAT12 segmentation pipelines: a brain tissue volume-based age and Alzheimer's disease study[J/OL]. J Neurosci Methods, 2019, 334: 108565 [2023-12-24]. https://pubmed.ncbi.nlm.nih.gov/31887318/. DOI: 10.1016/j.jneumeth.2019.108565.
[25]
GHIRELLI A, TAFURI B, URSO D, et al. Cortical signature of depressive symptoms in frontotemporal dementia: a surface-based analysis[J]. Ann Clin Transl Neurol, 2023, 10(10): 1704-1713. DOI: 10.1002/acn3.51860.
[26]
RUIZ MIRAS J. Fractal analysis in MATLAB: a tutorial for neuroscientists[J/OL]. Adv Neurobiol, 2024, 36: 815-825 [2024-04-02]. https://pubmed.ncbi.nlm.nih.gov/38468065/. DOI: 10.1007/978-3-031-47606-8_41.
[27]
AY U, KIZILATES-EVIN G, BAYRAM A, et al. Comparison of FreeSurfer and CAT12 software in parcel-based cortical thickness calculations[J]. Brain Topogr, 2022, 35(5/6): 572-582. DOI: 10.1007/s10548-022-00919-8.
[28]
HOVE D TEN, JORGENSEN T D, VAN DER ARK L A. Updated guidelines on selecting an intraclass correlation coefficient for interrater reliability, with applications to incomplete observational designs[J/OL]. Psychol Methods, 2022 [2023-12-24]. https://pubmed.ncbi.nlm.nih.gov/36048052/. DOI: 10.1037/met0000516.
[29]
NIU H J, LI Z, LIAO X H, et al. Test-retest reliability of graph metrics in functional brain networks: a resting-state fNIRS study[J/OL]. PLoS One, 2013, 8(9): e72425 [2023-12-24]. https://pubmed.ncbi.nlm.nih.gov/24039763/. DOI: 10.1371/journal.pone.0072425.
[30]
MARUKATAT S. Tutorial on PCA and approximate PCA and approximate kernel PCA[J/OL]. Artif Intell Rev, 2023, 56(6): 5445-5477 [2024-04-02]. https://link.springer.com/article/10.1007/s10462-022-10297-z#citeas. DOI: 10.1007/s10462-022-10297-z.
[31]
OKUBO G, OKADA T, YAMAMOTO A, et al. MP2RAGE for deep gray matter measurement of the brain: a comparative study with MPRAGE[J]. J Magn Reson Imaging, 2016, 43(1): 55-62. DOI: 10.1002/jmri.24960.
[32]
KNUSSMANN G N, ANDERSON J S, PRIGGE M B D, et al. Test-retest reliability of FreeSurfer-derived volume, area and cortical thickness from MPRAGE and MP2RAGE brain MRI images[J/OL]. Neuroimage Rep, 2022, 2(2): 100086 [2024-04-02]. https://pubmed.ncbi.nlm.nih.gov/36032692/. DOI: 10.1016/j.ynirp.2022.100086.
[33]
PAN T S, YIN Y. An application of theril indexes for the interrater reliability: a comparison with intraclass correlations[J/OL]. Engl J Educ Meas Eval, 2023, 4(2) [2024-04-02]. https://www.ce-jeme.org/journal/vol4/iss2/1/. DOI: 10.59863/wddk7257.
[34]
JO S W, KIM E S, YOON D Y, et al. Changes in radiomic and radiologic features in meningiomas after radiation therapy[J/OL]. BMC Med Imaging, 2023, 23(1): 164 [2024-04-02]. https://pubmed.ncbi.nlm.nih.gov/37858048/. DOI: 10.1186/s12880-023-01116-0.
[35]
FUJITA S, BUONINCONTRI G, CENCINI M, et al. Repeatability and reproducibility of human brain morphometry using three-dimensional magnetic resonance fingerprinting[J]. Hum Brain Mapp, 2021, 42(2): 275-285. DOI: 10.1002/hbm.25232.
[36]
CRAIG F, MARGARI F, LEGROTTAGLIE A R, et al. A review of executive function deficits in autism spectrum disorder and attention-deficit/hyperactivity disorder[J/OL]. Neuropsychiatr Dis Treat, 2016, 12: 1191-1202 [2024-04-02]. https://pubmed.ncbi.nlm.nih.gov/27274255/. DOI: 10.2147/NDT.S104620.
[37]
NORMAN L J, CARLISI C, LUKITO S, et al. Structural and functional brain abnormalities in attention-deficit/hyperactivity disorder and obsessive-compulsive disorder: a comparative meta-analysis[J]. JAMA Psychiatry, 2016, 73(8): 815-825. DOI: 10.1001/jamapsychiatry.2016.0700.
[38]
HOOGMAN M, MUETZEL R, GUIMARAES J P, et al. Brain imaging of the cortex in ADHD: a coordinated analysis of large-scale clinical and population-based samples[J]. Am J Psychiatry, 2019, 176(7): 531-542. DOI: 10.1176/appi.ajp.2019.18091033.
[39]
MOUS S E, MUETZEL R L, MARROUN H E, et al. Cortical thickness and inattention/hyperactivity symptoms in young children: a population-based study[J]. Psychol Med, 2014, 44(15): 3203-3213. DOI: 10.1017/S0033291714000877.
[40]
MCCARTHY H, SKOKAUSKAS N, FRODL T. Identifying a consistent pattern of neural function in attention deficit hyperactivity disorder: a meta-analysis[J]. Psychol Med, 2014, 44(4): 869-880. DOI: 10.1017/S0033291713001037.
[41]
HART H, RADUA J, NAKAO T, et al. Meta-analysis of functional magnetic resonance imaging studies of inhibition and attention in attention-deficit/hyperactivity disorder: exploring task-specific, stimulant medication, and age effects[J]. JAMA Psychiatry, 2013, 70(2): 185-198. DOI: 10.1001/jamapsychiatry.2013.277.
[42]
LUKITO S, NORMAN L, CARLISI C, et al. Comparative meta-analyses of brain structural and functional abnormalities during cognitive control in attention-deficit/hyperactivity disorder and autism spectrum disorder[J]. Psychol Med, 2020, 50(6): 894-919. DOI: 10.1017/S0033291720000574.
[43]
CORTESE S, KELLY C, CHABERNAUD C, et al. Toward systems neuroscience of ADHD: a meta-analysis of 55 fMRI studies[J]. Am J Psychiatry, 2012, 169(10): 1038-1055. DOI: 10.1176/appi.ajp.2012.11101521.
[44]
WANG H, JIN X Q, ZHANG Y, et al. Single-subject morphological brain networks: connectivity mapping, topological characterization and test-retest reliability[J/OL]. Brain Behav, 2016, 6(4): e00448 [2023-12-24]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4782249/. DOI: 10.1002/brb3.448.
[45]
MA L Y, XU X P, CUI C C, et al. Automated screening of COVID-19 using two-dimensional variational mode decomposition and locally linear embedding[J/OL]. Biomed Signal Process Control, 2022, 78: 103889 [2023-12-24]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4782249/. DOI: 10.1016/j.bspc.2022.103889.
[46]
LIU Z, LIN Y, SUN M. Network Representation. In: Representation Learning for Natural Language Processing[J/OL]. Springer Singapore, 2020: 217-284 [2023-12-23]. https://link.springer.com/chapter/10.1007/978-981-15-5573-2_8#citeas. DOI: 10.1007/978-981-15-5573-2_8.
[47]
ANOWAR F, SADAOUI S, SELIM B. Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE)[J/OL]. Comput Sci Rev, 2021, 40: 100378 [2023-12-23]. https://www.sciencedirect.com/science/article/abs/pii/S1574013721000186?via%3Dihub. DOI: 10.1016/j.cosrev.2021.100378.
[48]
DONOHO D L, GRIMES C. Hessian eigenmaps: locally linear embedding techniques for high-dimensional data[J]. Proc Natl Acad Sci USA, 2003, 100(10): 5591-5596. DOI: 10.1073/pnas.1031596100.

PREV Study on the correlation between infrapatellar fat pad IDEAL-IQ and T2 mapping sequences and the severity of knee osteoarthritis
NEXT One case of cerebrotendinous xanthomatosis
  


LINK


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