Radiomics for classification of bone mineral loss: A machine learning study

Rastegar, Sajjad; Vaziri, Maryam Moin; Qasempour, Younes; Akhash, Mohammad Rashid; Abdalvand, Neda; Shiri, Isaac; Abdollahi, Hamid; Zaidi, Habib

doi:10.1016/j.diii.2020.01.008

Cited by 83 publications

(60 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radiomics is an active area of research, aiming to quantify images using different feature categories toward improved clinical tasks. [13][14][15][16][17] In radiomics studies, a wide range of features are extracted from high-quality images for several applications, such as clinical correlations, therapy response prediction, tumor characterization, and survival assessment. [18][19][20][21] Radiomics is a multistep process applied to medical images involving image segmentation, feature extraction, feature selection, and multivariate analysis.…”

Section: Introductionmentioning

confidence: 99%

“…Radiomics is an active area of research, aiming to quantify images using different feature categories toward improved clinical tasks 13–17 . In radiomics studies, a wide range of features are extracted from high‐quality images for several applications, such as clinical correlations, therapy response prediction, tumor characterization, and survival assessment 18–21 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test–retest and image registration analyses

et al. 2020

View full text Add to dashboard Cite

To assess the repeatability of radiomic features in magnetic resonance (MR) imaging of glioblastoma (GBM) tumors with respect to test-retest, different image registration approaches and inhomogeneity bias field correction. Methods: We analyzed MR images of 17 GBM patients including T1-and T2-weighted images (performed within the same imaging unit on two consecutive days). For image segmentation, we used a comprehensive segmentation approach including entire tumor, active area of tumor, necrotic regions in T1-weighted images, and edema regions in T2-weighted images (test studies only; registration to retest studies is discussed next). Analysis included N3, N4 as well as no bias correction performed on raw MR images. We evaluated 20 image registration approaches, generated by cross-combination of four transformation and five cost function methods. In total, 714 images (17 patients × 2 images × ((4 transformations × 5 cost functions) + 1 test image) and 2856 segmentations (714 images × 4 segmentations) were prepared for feature extraction. Various radiomic features were extracted, including the use of preprocessing filters, specifically wavelet (WAV) and Laplacian of Gaussian (LOG), as well as discretization into fixed bin width and fixed bin count (16, 32, 64, 128, and 256), Exponential, Gradient, Logarithm, Square and Square Root scales. Intraclass correlation coefficients (ICC) were calculated to assess the repeatability of MRI radiomic features (high repeatability defined as ICC ≥ 95%). Results: In our ICC results, we observed high repeatability (ICC ≥ 95%) with respect to image preprocessing, different image registration algorithms, and test-retest analysis, for example: RLNU and GLNU from GLRLM, GLNU and DNU from GLDM, Coarseness and Busyness from NGTDM, GLNU and ZP from GLSZM, and Energy and RMS from first order. Highest fraction (percent) of repeatable features was observed, among registration techniques, for the method Full Affine transformation with 12 degrees of freedom using Mutual Information cost function (mean 32.4%), and

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test–retest and image registration analyses

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In a new version of the tool, we will present other feature selection methods such as filter based method, embedded based method and combine methods along with several ML methods. This will allow to systematically evaluate a set of suitable feature selection methods and learning algorithms, which are critical steps to develop clinically relevant models, since there is no “one fits all” approach, but performance of various feature selection methods and learning algorithms have been shown to depend on application and/or type of data 17 – 21 . Therefore, we intend to develop a full-integrated module that executes a complete machine learning analysis inside the application, giving the possibility to split the dataset resulted from the current version of MuSA in test-train sets, to choose from a list of different type of classifier and regressor and to reports graphical summary of results and metrics.…”

Section: Discussionmentioning

confidence: 99%

MuSA: a graphical user interface for multi-OMICs data integration in radiogenomic studies

Zanfardino

Castaldo

Pane

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Analysis of large-scale omics data along with biomedical images has gaining a huge interest in predicting phenotypic conditions towards personalized medicine. Multiple layers of investigations such as genomics, transcriptomics and proteomics, have led to high dimensionality and heterogeneity of data. Multi-omics data integration can provide meaningful contribution to early diagnosis and an accurate estimate of prognosis and treatment in cancer. Some multi-layer data structures have been developed to integrate multi-omics biological information, but none of these has been developed and evaluated to include radiomic data. We proposed to use MultiAssayExperiment (MAE) as an integrated data structure to combine multi-omics data facilitating the exploration of heterogeneous data. We improved the usability of the MAE, developing a Multi-omics Statistical Approaches (MuSA) tool that uses a Shiny graphical user interface, able to simplify the management and the analysis of radiogenomic datasets. The capabilities of MuSA were shown using public breast cancer datasets from TCGA-TCIA databases. MuSA architecture is modular and can be divided in Pre-processing and Downstream analysis. The pre-processing section allows data filtering and normalization. The downstream analysis section contains modules for data science such as correlation, clustering (i.e., heatmap) and feature selection methods. The results are dynamically shown in MuSA. MuSA tool provides an easy-to-use way to create, manage and analyze radiogenomic data. The application is specifically designed to guide no-programmer researchers through different computational steps. Integration analysis is implemented in a modular structure, making MuSA an easily expansible open-source software.

show abstract

“…41,42 Therefore, we assessed bone microarchitecture in complement to BMD using radiomics-based feature extraction after collecting baseline CT images and follow-up CT images at 6 months and 12 months. 41,43,44 Figure 6).…”

Section: Discussionmentioning

confidence: 99%

Safety and efficacy of Wharton's jelly-derived mesenchymal stem cells with teriparatide for osteoporotic vertebral fractures: A phase I/IIa study

Shim¹,

Kim

et al. 2020

Stem Cells Translational Medicine

View full text Add to dashboard Cite

Osteoporotic vertebral compression fractures (OVCFs) are serious health problems. We conducted a randomized, open-label, phase I/IIa study to determine the feasibility, safety, and effectiveness of Wharton's jelly-derived mesenchymal stem cells (WJ-MSCs) and teriparatide (parathyroid hormone 1-34) in OVCFs. Twenty subjects with recent OVCFs were randomized to teriparatide (20 μg/day, daily subcutaneous injection for 6 months) treatment alone or combined treatment of WJ-MSCs (intramedullary [4 × 10 7 cells] injection and intravenous [2 × 10 8 cells] injection after 1 week) and teriparatide (20 μg/day, daily subcutaneous injection for 6 months). Fourteen subjects (teriparatide alone, n = 7; combined treatment, n = 7) completed follow-up assessment (visual analog scale [VAS], Oswestry Disability Index [ODI], Short Form-36 [SF-36], bone mineral density [BMD], bone turnover measured by osteocalcin and C-terminal telopeptide of type 1 collagen, dual-energy x-ray absorptiometry [DXA], computed tomography [CT]). Our results show that (a) combined treatment with WJ-MSCs and teriparatide is feasible and tolerable for the patients with OVCFs; (b) the mean VAS, ODI, and SF-36 scores significantly improved in the combined treatment group; (c) the level of bone turnover markers were not significantly different between the two groups; (d) BMD T-scores of spine and hip by DXA increased in both control and experimental groups without a statistical difference; and (e) baseline spine CT images and follow-up CT images at 6 and 12 months showed better microarchitecture in the combined treatment group. Our results indicate that combined treatment of WJ-MSCs and teriparatide is feasible and tolerable and has a clinical benefit for fracture healing by promoting bone architecture. Clinical trial registration: https://nedrug.mfds.go.kr/, MFDS: 201600282-30937.

show abstract

Radiomics for classification of bone mineral loss: A machine learning study

Abstract: Please cite this article in press as: Rastegar S, et al. Radiomics for classification of bone mineral loss: A machine learning study. Diagnostic and Interventional Imaging (2020),

Cited by 83 publications

References 37 publications

Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test–retest and image registration analyses

Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test–retest and image registration analyses

MuSA: a graphical user interface for multi-OMICs data integration in radiogenomic studies

Safety and efficacy of Wharton's jelly-derived mesenchymal stem cells with teriparatide for osteoporotic vertebral fractures: A phase I/IIa study

Contact Info

Product

Resources

About