Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types
- 127 Downloads
To investigate the classification ability of quantitative radiomics features extracted on non-contrast-enhanced CT (NECT) image for discrimination of AVM-related hematomas from those caused by other etiologies.
Two hundred sixty-one cases with intraparenchymal hematomas underwent baseline CT scan between 2012 and 2017 in our center. Cases were split into a training dataset (n = 180) and a test dataset (n = 81). Hematoma types were dichotomized into two classes, namely, AVM-related hematomas (AVM-H) and hematomas caused by other etiologies. A total of 576 radiomics features of 6 feature groups were extracted from NECT. We applied 11 feature selection methods to select informative features from each feature group. Selected radiomics features and the clinical feature age were then used to fit machine learning classifiers. In combination of the 11 feature selection methods and 8 classifiers, we constructed 88 predictive models. Predictive models were evaluated and the optimal one was selected and evaluated.
The selected radiomics model was RELF_Ada, which was trained with Adaboost classifier and features selected by Relief method. Cross-validated area under the curve (AUC) on training dataset was 0.988 and the relative standard deviation (RSD%) was 0.062. AUC on the test dataset was 0.957. Accuracy (ACC), sensitivity, specificity, positive prediction value (PPV), and negative predictive value (NPV) were 0.926, 0.889, 0.937, 0.800, and 0.967, respectively.
Machine learning models with radiomics features extracted from NECT scan accurately discriminated AVM-related intraparenchymal hematomas from those caused by other etiologies. This technique provided a fast, non-invasive approach without use of contrast to diagnose this disease.
• Radiomics features from non-contrast-enhanced CT accurately discriminated AVM-related hematomas from those caused by other etiologies.
• AVM-related hematomas tended to be larger in diameter, coarser in texture, and more heterogeneous in composition.
• Adaboost classifier is an efficient approach for analyzing radiomics features.
KeywordsCerebrum Hematoma Radiomics Machine learning Cerebral arteriovenous malformations
Cerebral amyloid angiopathy-related hematomas
Digital subtraction angiography
Magnetic resonance angiography
Rupture of intracranial aneurysms
We thank Erkang Guo, Xin Feng, Wenhua Fan, Luyao Wang, and Fei Peng for data collection. We also thank Dr. Peng Jiang, Yuhua Jiang, and Huijian Ge for the diagnosis of the hematoma types.
This study has received funding by the National Natural Science Foundation of China (Grant No. 81371314) and the High-level Personnel Training Program of Beijing Health system (Grant No. 2013-2-016).
Compliance with ethical standards
The scientific guarantor of this publication is Chuhan Jiang.
Conflict of interest
The authors declare that they have no conflict of interest.
Statistics and biometry
One of the authors has significant statistical expertise.
Written informed consent was obtained from all subjects (patients) in this study.
Institutional Review Board approval was obtained.
• diagnostic or prognostic study
• performed at one institution
- 6.Roh D, Sun CH, Schmidt JM et al (2018) Primary intracerebral hemorrhage: a closer look at hypertension and cerebral amyloid angiopathy. Neurocrit Care. https://doi.org/10.1007/s12028-018-0514-z
- 12.Suh HB, Choi YS, Bae S et al (2018) Primary central nervous system lymphoma and atypical glioblastoma: differentiation using radiomics approach. Eur Radiol https://doi.org/10.1007/s00330-018-5368-4
- 17.Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830Google Scholar
- 21.Hong JF, Song YF, Liu HB, Liu Z, Wang SS (2015) The clinical characteristics and treatment of cerebral microarteriovenous malformation presenting with intracerebral hemorrhage: a series of 13 cases. Biomed Res Int 2015:257153Google Scholar
- 23.Ueyama K, Koyama S (2017) Basal ganglia arteriovenous malformation in an elderly patient presented with putaminal hemorrhage, diagnosed after hematoma evacuation by imaging: a case report. Brain Nerve 69:79–83Google Scholar
- 24.Wagle WA, Smith TW, Weiner M (1984) Intracerebral hemorrhage caused by cerebral amyloid angiopathy: radiographic-pathologic correlation. AJNR Am J Neuroradiol 5:171–176Google Scholar
- 26.Kang D, Park JE, Kim YH et al (2018) Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation. Neuro Oncol https://doi.org/10.1093/neuonc/noy021
- 28.Li Y, Liu X, Qian Z et al (2018) Genotype prediction of ATRX mutation in lower-grade gliomas using an MRI radiomics signature. Eur Radiol https://doi.org/10.1007/s00330-017-5267-0
- 29.Prasanna P, Patel J, Partovi S, Madabhushi A, Tiwari P (2017) Radiomic features from the peritumoral brain parenchyma on treatment-naive multi-parametric MR imaging predict long versus short-term survival in glioblastoma multiforme: preliminary findings. Eur Radiol 27:4188–4197CrossRefGoogle Scholar
- 30.Zhu X, Dong D, Chen Z et al (2018) Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. Eur Radiol https://doi.org/10.1007/s00330-017-5221-1
- 31.Shi Z, Zhu C, Degnan AJ et al (2018) Identification of high-risk plaque features in intracranial atherosclerosis: initial experience using a radiomic approach. Eur Radiol https://doi.org/10.1007/s00330-018-5395-1
- 32.Shen Q, Shan Y, Hu Z et al (2018) Quantitative parameters of CT texture analysis as potential markers for early prediction of spontaneous intracranial hemorrhage enlargement. Eur Radiol https://doi.org/10.1007/s00330-018-5364-8