Diffusion-weighted imaging and texture analysis: current role for diffuse liver disease

Gourtsoyianni, Sofia; Santinha, João; Matos, Celso; Papanikolaou, Nikolaos

doi:10.1007/s00261-020-02772-4

Cited by 9 publications

(10 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, TA has become a promising technique for quantitative imaging analysis, providing biomarkers for pathological changes or the response to treatment 12 – 17 . In our analysis, TA of kidney MRI was not a good discriminator of eGFR groups, especially in the clinical setting.…”

Section: Discussionmentioning

confidence: 99%

“…Texture analysis (TA) is an emerging technique that permits the quantification of image characteristics based on the distribution of pixels and their surface intensity or patterns 12 , 13 . TA has been applied to several medical image analyses, including oncologic imaging 14 , neuroimaging 15 , and abdominal imaging 16 , 17 . Recent reports have demonstrated the utility of TA based on DWI, BOLD, Susceptibility-weighted imaging (SWI), and T1 and T2 mapping 18 , 19 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The utility of texture analysis of kidney MRI for evaluating renal dysfunction with multiclass classification model

Hara

Nagawa

Yamamoto

et al. 2022

Sci Rep

View full text Add to dashboard Cite

We evaluated a multiclass classification model to predict estimated glomerular filtration rate (eGFR) groups in chronic kidney disease (CKD) patients using magnetic resonance imaging (MRI) texture analysis (TA). We identified 166 CKD patients who underwent MRI comprising Dixon-based T1-weighted in-phase (IP)/opposed-phase (OP)/water-only (WO) images, apparent diffusion coefficient (ADC) maps, and T2* maps. The patients were divided into severe, moderate, and control groups based on eGFR borderlines of 30 and 60 mL/min/1.73 m2. After extracting 93 texture features (TFs), dimension reduction was performed using inter-observer reproducibility analysis and sequential feature selection (SFS) algorithm. Models were created using linear discriminant analysis (LDA); support vector machine (SVM) with linear, rbf, and sigmoid kernels; decision tree (DT); and random forest (RF) classifiers, with synthetic minority oversampling technique (SMOTE). Models underwent 100-time repeat nested cross-validation. Overall performances of our classification models were modest, and TA based on T1-weighted IP/OP/WO images provided better performance than those based on ADC and T2* maps. The most favorable result was observed in the T1-weighted WO image using RF classifier and the combination model was derived from all T1-weighted images using SVM classifier with rbf kernel. Among the selected TFs, total energy and energy had weak correlations with eGFR.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The utility of texture analysis of kidney MRI for evaluating renal dysfunction with multiclass classification model

Hara

Nagawa

Yamamoto

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The examples include the utilization of fractal computations to describe self-similarity nature of nuclear chromatin, as well as the use of textural features to detect changes of tissue structural entropy during the process of physiological aging. These methods also have a potentially significant diagnostic value in medicine since they may be used to enhance objectivity and the level of automation of various protocols and techniques during pathohistological analysis of tissues and cells (1)(2)(3)(4)(5).…”

Section: Introductionmentioning

confidence: 99%

“…Both fractal and textural methods can be used for analyzing various signals in medicine (3)(4)(5). These mostly include two-dimensional data such as the ones associated with digital micrographs.…”

Section: Introductionmentioning

confidence: 99%

Application of fractal and textural analysis in medical physiology, pathophysiology and pathology

Pantić¹,

Paunovic²,

Radojević-Škodrić³

2022

Medicinska istraživanja

View full text Add to dashboard Cite

Fractal and textural analyses represent a rapidly developing class of computational and mathematical methods with potential wide applications in medicine and biology. In recent years, they have been successfully used for the evaluation of subtle alterations in cell and tissue morphology associated with various physiological and pathological processes. It has been shown that cells in early stages of apoptosis exhibit changes in chromatin fractal and textural features. Cellular senescence is also sometimes associated with changes in textural patterns in some cell populations. So far, artificial intelligence approaches based on co-occurrence matrix textural data were successfully implemented in predicting cell damage in in vitro conditions, with artificial neural networks achieving the best performance. In the future, several methodological issues and challenges related to the use of fractal and textural methods will have to be resolved before their introduction into contemporary clinical practice. This concise review focuses on the recent research on the application of fractal and textural methods in experimental physiology and related fields.

show abstract

“…DWI and DTI have also seen a wide spectrum of non-oncological applications throughout the body, including but not limited to the kidney [ 32 ], liver [ 33 , 34 ], and breast [ 35 ]. DWI has proven promising to detect and stage fibrosis [ 36 , 37 ] as well as to characterize inflammation [ 38 , 39 ].…”

mentioning

confidence: 99%

Diffusion-Weighted Magnetic Resonance Imaging: Clinical Potential and Applications

Caroli

2022

JCM

View full text Add to dashboard Cite

show abstract

Diffusion-weighted imaging and texture analysis: current role for diffuse liver disease

Cited by 9 publications

References 48 publications

The utility of texture analysis of kidney MRI for evaluating renal dysfunction with multiclass classification model

The utility of texture analysis of kidney MRI for evaluating renal dysfunction with multiclass classification model

Application of fractal and textural analysis in medical physiology, pathophysiology and pathology

Diffusion-Weighted Magnetic Resonance Imaging: Clinical Potential and Applications

Contact Info

Product

Resources

About