Differentiating brain metastases from different pathological types of lung cancers using texture analysis of T1 postcontrast MR

Li, Zhenjiang; Mao, Yu; Li, Hongsheng; Yu, Gang; Wan, Honglin; Li, Baosheng

doi:10.1002/mrm.26029

Cited by 54 publications

(41 citation statements)

References 23 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, the application of texture analysis has gained great attention in the oncology field in recent years. It is widely used in the analysis of various types of medical images to explore the relationship between texture parameters and information about the tumor 57,58 . Such studies have proved the close correlation between texture features and tumor information.…”

Section: Discussionmentioning

confidence: 99%

Performance evaluation of texture analysis based on kinetic parametric maps from breast DCE‐MRI in classifying benign from malignant lesions

Jiang

Yin

2020

Journal of Surgical Oncology

View full text Add to dashboard Cite

Background and Objectives: To investigate the performance of texture analysis based on enhancement kinetic parametric maps derived from breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in discriminating benign from malignant tumors.Methods: A total of 192 cases confirmed by histopathology were retrospectively selected from our Picture Archiving and Communication System, including 93 benign and 99 malignant tumors. Lesion areas were delineated semi-automatically, and six kinetic parametric maps reflecting the perfusion information were generated, namely the maximum slope of increase (MSI), slope of signal intensity (SI slope ), initial percentage of peak enhancement (E initial ), percentage of peak enhancement (E peak ), early signal enhancement ratio (ESER), and second enhancement percentage (SEP) maps. A total of 286 texture features were extracted from those quantitative parametric maps. The Student t test or Mann-Whitney U test was used to select features that were statistically significantly different between the benign and malignant groups. A support vector machine was employed with a leave-one-out crossvalidation method to establish the classification model. Classification performance was evaluated according to the receiver operating characteristic (ROC) theory. Results:The areas under ROC curves (AUCs) indicating the diagnostic performance were 0.925 for MSI, 0.854 for SI slope , 0.756 for E initial , 0.923 for E peak , 0.871 for ESER and 0.881 for SEP. Significant differences in AUCs were found between E initial vs MSI, E initial vs E peak and E initial vs SEP (P < .05). There were no significant differences in other pairwise comparisons.Conclusion: Texture analysis of the kinetic parametric maps derived from breast DCE-MRI can contribute to the discrimination between malignant and benign lesions. It can be considered as a supplementary tool for breast diagnosis. K E Y W O R D S breast cancer, kinetics, machine learning, magnetic resonance imaging, receiver operating characteristic

show abstract

Section: Discussionmentioning

confidence: 99%

Performance evaluation of texture analysis based on kinetic parametric maps from breast DCE‐MRI in classifying benign from malignant lesions

Jiang

Yin

2020

Journal of Surgical Oncology

View full text Add to dashboard Cite

show abstract

“…In recent years, software developments enabled the study of texture parameters of cross-sectional medical images, e.g., MaZda package. 25 Texture analysis has been applied to static structural imaging in many pathologies, outside the brain, e.g., in nasopharyngeal tumors, 26 head and neck cancer, 27 breast cancer, 28 and in the brain, e.g., MS, 29 brain tumors, [30][31][32][33][34] and acute ischemic stroke. 35 Slotboom et al proposed a novel approach called dynamic histogram analysis (DHA) where histogram-based texture parameter analysis is applied to a time series of DSCE-MR images.…”

mentioning

confidence: 99%

Differentiating enhancing multiple sclerosis lesions, glioblastoma, and lymphoma with dynamic texture parameters analysis (DTPA): A feasibility study

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Therefore, it is recommended to check previous works before applying texture analysis in order to select the MRI sequence that better suits each specific task. For example, contrast-enhanced T1-weighted MRI is the most popular MRI protocol for to assessing brain tumor characterization by means of texture analysis as it is employed for initial brain tumor detection and contains abundant diagnostic information [102]- [107]. However, the most desirable approach would be to compare the performance of different modalities, but these imaging data is not always available.…”

Section: Selection Of the Best Mri Sequencementioning

confidence: 99%

“…Brain Primary brain tumors Classification of benign and malign tumors; Grading of gliomas [103], [104], [117], [118] Brain Brain metastases Differentiation from radiation necrosis; Identification of the primary cancer [106], [107] Brain Dementia Identification of Alzheimer's disease [58], [119] Brain Multiple sclerosis Early diagnosis [120], [121] Brain Ischemic Stroke Prediction of hemorrhagic transformation; Evaluation of small vessel disease [122], [123] Brain Mild traumatic brain injury Effect of trauma in cerebral tissue [57] Heart Myocardial infarction Differentiation between acute and chronic [124] Heart Arrhythmias Classification of low and high-risk patients [125] Breast Breast cancer Classification of benign and malign lesions; Classification of cancer molecular subtypes [60], [61], [126] Prostate Prostate cancer Detection of cancerous tissue [127], [128] Kidney Autosomal dominant polycystic disease Prediction of renal function decline [129] Liver Liver fibrosis Assessment of the disease [130] Knee Knee osteoarthritis Quantification of subchondral bone architecture; Identification of bone marrow lesions [131], [132] Data analysis with machine learning…”

Section: Organ Lesion / Disease Objectives Referencesmentioning

confidence: 99%

“…Another approach could be based on texture analysis applied to conventional MRI. Texture analysis has been proved to be an promising source of imaging biomarkers for identifying and classifying brain tumor lesions, including BMs [102]- [107]. Particularly, contrast-enhanced T1-weigted MRI was the main sequence evaluated in these studies as it is employed for initial brain tumor detection and contains abundant diagnostic information [107], [226].…”

Section: Classification Of Brain Metastases By Their Primary Site Of mentioning

confidence: 99%

See 1 more Smart Citation

Radiomics for diagnosis and assessing brain diseases: an approach based on texture analysis on magnetic resonance imaging

Ortiz-Ramón¹

View full text Add to dashboard Cite

IIIn the third project, we evaluated the hippocampus MRI profile of Alzheimer's disease (AD) patients to identify the different stages of the disease. The current criteria for diagnosing AD require the presence of relevant cognitive deficits, so the underlying neuropathological damage is important by the time the diagnosis is made. With the purpose of establishing new biomarkers to detect AD in its early stages, we evaluated a set of 2D and 3D texture features extracted from MRI scans of the hippocampus of patients with advanced AD, early mild cognitive impairment and cognitive normality. Many 3D texture parameters resulted to be statistically significant to differentiate between AD patients and subjects from the other two populations. When combining these 3D parameters with machine learning techniques, high accuracy was obtained, thus suggesting that texture analysis could at least help identify the presence of AD.In the fourth project, we attempted to characterize the heterogeneity patterns of ischemic stroke in structural MRI. In brain MRI of older individuals, some pathological processes present similar imaging characteristics, like in the case of stroke lesions and white matter hyperintensities (WMH) of diverse natures, thus hindering the study of cerebrovascular diseases by means of imaging. Given that stroke effects are present not only in the affected region, but also in unaffected tissue, we investigated the feasibility of 3D texture features from WMH, normal-appearing white matter and subcortical structures to differentiate individuals who had a lacunar or cortical stroke visible on conventional brain MRI (T1-weighted, T2-weighted and FLAIR images) from subjects who did not. Texture features were not useful to differentiate between post-acute cortical and lacunar strokes, but promising results were achieved for discerning between patients presenting an old stroke and normal-ageing patients who never had a stroke. These results suggest that texture features may help in the detection of stroke lesions.This thesis presents four novel feasibility studies to help clinicians in the evaluation of different brain disorders by means of a radiomics approach based on texture analysis in conventional MRI. The results achieved highlight the potential of this practice for defining and characterizing brain lesions in a fast, reliable and non-invasive way. Abbreviations and Acronyms Brain and DiseasesAD Alzheimer's disease ADNI Alzheimer's Disease Neuroimaging Initiative BM brain metastasis CN cognitively normal, cognitive normality CNS central nervous system CSF cerebrospinal fluid EMCI early mild cognitive impairment GBM glioblastoma multiforme MCI mild cognitive impairment NAWM normal appearing white matter PNS peripheral nervous system SRS stereotactic radiosurgery SS subcortical structures SVD small vessel disease WBRT whole-brain radiotherapy WHO World Health Organization WMH white matter hyperintensities VIII Medical Imaging CAD computer-aided detection and diagnosis CT computed tomography FID free induction dec...

show abstract

Differentiating brain metastases from different pathological types of lung cancers using texture analysis of T1 postcontrast MR

Cited by 54 publications

References 23 publications

Performance evaluation of texture analysis based on kinetic parametric maps from breast DCE‐MRI in classifying benign from malignant lesions

Performance evaluation of texture analysis based on kinetic parametric maps from breast DCE‐MRI in classifying benign from malignant lesions

Differentiating enhancing multiple sclerosis lesions, glioblastoma, and lymphoma with dynamic texture parameters analysis (DTPA): A feasibility study

Radiomics for diagnosis and assessing brain diseases: an approach based on texture analysis on magnetic resonance imaging

Contact Info

Product

Resources

About