Advanced models based on computed tomography angiography (CTA) radiomics features in discriminating muscle ischemia from normal condition are lacking.
Purpose
To investigate the feasibility of radiomics of CTA in discriminating ischemic muscle from normal muscle.
Material and Methods
A total of 102 patients (51 ischemia and 51 non-ischemia) were analyzed using a CTA radiomics method. The radiomics features of muscle were compared between ischemic and normal cases. The maximum relevance minimum redundancy (mRMR) algorithm and least absolute shrinkage and selection operator (LASSO) logistic regression model were used. The receiver operating characteristic (ROC) curve was used to determine the performance of radiomics signature.
Results
Thirty-nine CTA radiomics features were significantly different between the two groups (P < 0.05). By LASSO, six features were used to construct a model. The signature area under the curve was 0.92 and 0.91 in the training and validation cohorts, respectively. The sensitivity and specificity of the signature were 92% and 86% for the training cohort, and 80% and 94% for the validation cohort, respectively.
Conclusion
CTA radiomics signature is useful in identifying ischemic muscle in selected patients.
HamburgNMCreagerMA. Pathophysiology of intermittent claudication in peripheral artery disease. Circ J2017;81:281–289.
2.
MorrisDRSkalinaTASinghTP,et al.Association of computed tomographic leg muscle characteristics with lower limb and cardiovascular events in patients with peripheral artery disease. J Am Heart Assoc2018;7:e009943.
3.
BragadeeshTSariIPascottoM,et al.Detection of peripheral vascular stenosis by assessing skeletal muscle flow reserve. J Am Coll Cardiol2005;45:780–785.
4.
NaehleCPSteinbergVASchildH,et al.Assessment of peripheral skeletal muscle microperfusion in a porcine model of peripheral arterial stenosis by steady-state contrast-enhanced ultrasound and Doppler flow measurement. J Vasc Surg2015;61:1312–1320.
5.
HarwoodAEKingSTottyJ,et al.A systematic review of muscle morphology and function in intermittent claudication. J Vasc Surg2017;66:1241–1257.
6.
McClungJMMcCordTJSoutherlandK,et al.Subacute limb ischemia induces skeletal muscle injury in genetically susceptible mice independent of vascular density. J Vasc Surg2016;64:1101–1111.
7.
MutiranguraPRuangsetakitCWongwanitC,et al.Comparative study of the management of diabetic versus nondiabetic patients with atherosclerosis obliterans of the lower extremities. Vascular2008;16:333–339.
8.
WuGYangJZhangT,et al.The diagnostic value of non-contrast enhanced quiescent interval single shot (QISS) magnetic resonance angiography at 3T for lower extremity peripheral arterial disease, in comparison to CT angiography. J Cardiovasc Magn Reson2016;18:71.
9.
SontheimerDL. Peripheral vascular disease: diagnosis and treatment. Am Fam Physician2006;73:1971–1976.
10.
LongCATimminsLHKoutakisP,et al.An endovascular model of ischemic myopathy from peripheral arterial disease. J Vasc Surg2017;66:891–901.
11.
HerbertKJHickeyMJLeporeDA,et al.Effects of the endothelin receptor antagonist bosentan on ischaemia/reperfusion injury in rat skeletal muscle. Eur J Pharmacol2001;424:59–67.
12.
BoutagyNERaveraSPapademetrisX,et al.Noninvasive in vivo quantification of adeno-associated virus serotype 9-mediated expression of the sodium/iodide symporter under hindlimb ischemia and neuraminidase desialylation in skeletal muscle using single-photon emission computed tomography/computed tomography. Circ Cardiovasc Imaging2019;12:e009063.
13.
AlveloJLPapademetrisXMena-HurtadoC,et al.Radiotracer imaging allows for noninvasive detection and quantification of abnormalities in angiosome foot perfusion in diabetic patients with critical limb ischemia and nonhealing wounds. Circ Cardiovasc Imaging2018;11:e006932.
14.
ForghaniRSavadjievPChatterjeeA,et al.Radiomics and artificial intelligence for biomarker and prediction model development in oncology. Comput Struct Biotechnol J2019;17:995–1008.
15.
LaoJChenYLiZC,et al.A deep learning-based radiomics model for prediction of survival in glioblastoma Multiforme. Sci Rep2017;7:10353.
16.
MokraneFZLuLVavasseurA,et al.Radiomics machine-learning signature for diagnosis of hepatocellular carcinoma in cirrhotic patients with indeterminate liver nodules. Eur Radiol2020;30:558–570.
17.
ZhaoSSuYDuanJ,et al.Radiomics signature extracted from diffusion-weighted magnetic resonance imaging predicts outcomes in osteosarcoma. J Bone Oncol2019;19:100263.
18.
MühlbergAMuseykoOLaredoJD,et al.A reproducible semi-automatic method to quantify the muscle-lipid distribution in clinical 3D CT images of the thigh. PLoS One2017;12:e0175174.
19.
WangHNiePWangY,et al.Radiomics nomogram for differentiating between benign and malignant soft-tissue masses of the extremities. J Magn Reson Imaging2020;51:155–163.
20.
MousnierAJean-BaptisteESadaghianlooN,et al.Subintimal recanalization of femoropopliteal occlusive lesions in patients with critical ischemia: 66 cases. Ann Vasc Surg2013;27:467–473.
21.
StabileEMagliuloFZhelevD,et al.Interim analysis at 6months from the LEG-flow drug eluting balloon for the treatment of femoropopliteal occlusions (LEG-DEB) registry. Int J Cardiol2016;223:654–655.
22.
HsuCCKwanGNSinghD,et al.Angioplasty versus stenting for infrapopliteal arterial lesions in chronic limb-threatening ischaemia. Cochrane Database Syst Rev2018;12:CD009195.
23.
BuschmannISchaperW. The pathophysiology of the collateral circulation (arteriogenesis). J Pathol2000;190:338–342.
24.
ParmenterBJRaymondJFiatarone SinghMA. The effect of exercise on haemodynamics in intermittent claudication: a systematic review of randomized controlled trials. Sports Med2010;40:433–447.
25.
LiCLiuXYouH,et al.Perfusion imaging with 320-slice spiral computed tomography and color-coded digital subtraction angiography for assessing acute skeletal muscle ischemia-reperfusion injury in a rabbit model. BMC Med Imaging2019;19:75.
26.
WuGXieRLiY,et al.Histogram analysis with computed tomography angiography for discriminating soft tissue sarcoma from benign soft tissue tumor. Medicine (Baltimore)2020;99:e18742.
27.
MiaoSLYeXNLinTT,et al.The psoas muscle density as a predictor of postoperative complications and 30-day mortality for acute mesenteric ischemia patients. Abdom Radiol2020;47:1644–1653.
28.
StacyMRYuDYMaxfieldMW,et al.Multimodality imaging approach for serial assessment of regional changes in lower extremity arteriogenesis and tissue perfusion in a porcine model of peripheral arterial disease. Circ Cardiovasc Imaging2014;7:92–99.
29.
KrafftSPRaoAStingoF,et al.The utility of quantitative CT radiomics features for improved prediction of radiation pneumonitis. Med Phys2018;45:5317–5324.
30.
QiuWKuangHNairJ,et al.Radiomics-based intracranial thrombus features on CT and CTA predict recanalization with intravenous alteplase in patients with acute ischemic stroke. Am J Neuroradiol2019;40:39–44.
31.
WuGZhouSWangY,et al.A prediction model of outcome of SARS-CoV-2 pneumonia based on laboratory findings. Sci Rep2020;10:14042.
32.
HuangYQLiangCHHeL,et al.Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol2016;34:2157–2164.
33.
ZhangPFengZCaiW,et al.T2-weighted image-based radiomics signature for discriminating between seminomas and nonseminoma. Front Oncol2019;9:1330.
