Assessment of Kidney Function Using Dynamic Contrast Enhanced MRI Techniques

2010 ◽  
pp. 214-233
Author(s):  
Melih S. Aslan ◽  
Hossam Abd El Munim ◽  
Aly A. Farag ◽  
Mohamed Abou El-Ghar
Keyword(s):  
Kidney Function ◽  
Least Square ◽  
Renal Diseases ◽  
Support Vector ◽  
Data Sets ◽  
Dce Mri ◽  
Dynamic Contrast Enhanced ◽  
Contrast Enhanced ◽  
Vector Machines ◽  
Kidney Rejection

Graft failure of kidneys after transplantation is most often the consequence of the acute rejection. Hence, early detection of the kidney rejection is important for the treatment of renal diseases. In this chapter, authors introduce a new automatic approach to classify normal kidney function from kidney rejection using dynamic contrast enhanced magnetic resonance imaging (DCE-MRI). The kidney has three regions named the cortex, medulla, and pelvis. In their experiment, they use the medulla region because it has specific responses to DCE-MRI that are helpful to identify kidney rejection. In the authors’ process they segment the kidney using the level sets method. They then employ several classification methods such as the Euclidean distance, Mahalanobis distance, and least square support vector machines (LS-SVM). The authors’preliminary results are very encouraging and reproducibility of the results was achieved for 55 clinical data sets. The classification accuracy, diagnostic sensitivity, and diagnostic specificity are 84%, 75%, and 96%, respectively.

scholarly journals Automated Detection and Segmentation of Nonmass-Enhancing Breast Tumors with Dynamic Contrast-Enhanced Magnetic Resonance Imaging

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Ignacio Alvarez Illan ◽  
Javier Ramirez ◽  
J. M. Gorriz ◽  
Maria Adele Marino ◽  
Daly Avendano ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
False Positive Rate ◽  
Lesion Detection ◽  
Support Vector ◽  
Breast Cancer Patients ◽  
Resonance Imaging ◽  
Dce Mri ◽  
Dynamic Contrast Enhanced ◽  
Contrast Enhanced

Nonmass-enhancing (NME) lesions constitute a diagnostic challenge in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast. Computer-aided diagnosis (CAD) systems provide physicians with advanced tools for analysis, assessment, and evaluation that have a significant impact on the diagnostic performance. Here, we propose a new approach to address the challenge of NME lesion detection and segmentation, taking advantage of independent component analysis (ICA) to extract data-driven dynamic lesion characterizations. A set of independent sources was obtained from the DCE-MRI dataset of breast cancer patients, and the dynamic behavior of the different tissues was described by multiple dynamic curves, together with a set of eigenimages describing the scores for each voxel. A new test image is projected onto the independent source space using the unmixing matrix, and each voxel is classified by a support vector machine (SVM) that has already been trained with manually delineated data. A solution to the high false-positive rate problem is proposed by controlling the SVM hyperplane location, outperforming previously published approaches.

scholarly journals Improving Automatic Renal Segmentation in Clinically Normal and Abnormal Paediatric DCE-MRI via Contrast Maximisation and Convolutional Networks for Computing Markers of Kidney Function

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7942
Author(s):  
Hykoush Asaturyan ◽  
Barbara Villarini ◽  
Karen Sarao ◽  
Jeanne S. Chow ◽  
Onur Afacan ◽  
...  
Keyword(s):  
Kidney Function ◽  
Contextual Information ◽  
Support Vector ◽  
Clinical Markers ◽  
Dce Mri ◽  
Convolutional Networks ◽  
Clinically Normal ◽  
Contrast Enhanced ◽  
Dual Stage ◽  
Magnetic Resonance Imaging Mri

There is a growing demand for fast, accurate computation of clinical markers to improve renal function and anatomy assessment with a single study. However, conventional techniques have limitations leading to overestimations of kidney function or failure to provide sufficient spatial resolution to target the disease location. In contrast, the computer-aided analysis of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) could generate significant markers, including the glomerular filtration rate (GFR) and time–intensity curves of the cortex and medulla for determining obstruction in the urinary tract. This paper presents a dual-stage fully modular framework for automatic renal compartment segmentation in 4D DCE-MRI volumes. (1) Memory-efficient 3D deep learning is integrated to localise each kidney by harnessing residual convolutional neural networks for improved convergence; segmentation is performed by efficiently learning spatial–temporal information coupled with boundary-preserving fully convolutional dense nets. (2) Renal contextual information is enhanced via non-linear transformation to segment the cortex and medulla. The proposed framework is evaluated on a paediatric dataset containing 60 4D DCE-MRI volumes exhibiting varying conditions affecting kidney function. Our technique outperforms a state-of-the-art approach based on a GrabCut and support vector machine classifier in mean dice similarity (DSC) by 3.8% and demonstrates higher statistical stability with lower standard deviation by 12.4% and 15.7% for cortex and medulla segmentation, respectively.

Pretreatment rectal tumors quantitative dynamic contrast-enhanced MRI characterization and predictability of outcome: Pilot study.

2014 ◽  
Vol 32 (3_suppl) ◽  
pp. 416-416
Author(s):  
Wael Shabana ◽  
Sameh Saif ◽  
Greg Cron ◽  
Rebecca Thornhill ◽  
Natalia Koudrina ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Treatment Outcome ◽  
Support Vector ◽  
Rectal Tumors ◽  
Mapping Procedure ◽  
Dce Mri ◽  
Dynamic Contrast Enhanced ◽  
Contrast Enhanced ◽  
Potential Biomarker ◽  
Pre Treatment

416 Background: Treatment of rectal cancer is currently a one-size-fits-all approach. Unfortunately, some rectal tumors do not respond well to treatment and/or give rise to latent metastases. Therefore, a need exists for biomarkers which can better characterize tumor aggressiveness and help guide treatment decisions. We investigated the feasibility and performance of dynamic contrast-enhanced (DCE) MRI (performed pre-treatment) as a potential biomarker to predict rectal cancer response to treatment. Methods: 47 patients with rectal masses underwent DCE-MRI at 3T pre-treatment. DCE-MRI was performed with 3D FLASH (TR/TE/flip 6ms/1.6 ms/25 deg). Gadolinium concentration-versus-time in tissue was estimated with the aid of a variable-flip-angle T1 mapping procedure performed pre-DCE. The arterial input function was estimated by measuring phase-versus-time in major arteries. Tracer kinetic modeling was used to obtain maps of the quantitative perfusion parameters Ktrans and Kep. Treatment outcome was categorized as successful (regression) or unsuccessful (progression, stable, or recurrence). We also dichotomized latent metastases as absent or present. The pathology outcome of the lesions was categorized as cancerous or non-cancerous. A support vector machine classifier was constructed from the perfusion parameters, and the accuracy of each classifier was determined by 10-fold cross validation. Results: Clinical characteristics were 31 successful outcomes, 8 unsuccessful; 25 with latent metastases absent, 5 with latent metastases present; 40 cancerous, 7 non-cancerous. The accuracies of quantitative DCE-MRI parameters for predicting treatment outcome, latent metastases, and pathology outcome were 78%, 83%, and 84%, respectively. Conclusions: Pre-treatment DCE-MRI appears to be a useful predictor of rectal tumor malignancy, treatment outcome, and latent metastases. Perfusion parameters have very promising potential to predict rectal cancer outcome and may serve as an added tool for rectal cancer treatment planning.

scholarly journals Head and Neck Cancer Tumor Segmentation Using Support Vector Machine in Dynamic Contrast-Enhanced MRI

2017 ◽  
Vol 2017 ◽  
pp. 1-5 ◽  
Author(s):  
Wei Deng ◽  
Liangping Luo ◽  
Xiaoyi Lin ◽  
Tianqi Fang ◽  
Dexiang Liu ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Head And Neck Cancer ◽  
Head And Neck ◽  
Neck Cancer ◽  
Support Vector ◽  
Tumor Segmentation ◽  
Dce Mri ◽  
Dynamic Contrast Enhanced ◽  
Testing Dataset ◽  
Contrast Enhanced

Objective. We aimed to propose an automatic method based on Support Vector Machine (SVM) and Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) to segment the tumor lesions of head and neck cancer (HNC). Materials and Methods. 120 DCE-MRI samples were collected. Five curve features and two principal components of the normalized time-intensity curve (TIC) in 80 samples were calculated as the dataset in training three SVM classifiers. The other 40 samples were used as the testing dataset. The area overlap measure (AOM) and the corresponding ratio (CR) and percent match (PM) were calculated to evaluate the segmentation performance. The training and testing procedure was repeated for 10 times, and the average performance was calculated and compared with similar studies. Results. Our method has achieved higher accuracy compared to the previous results in literature in HNC segmentation. The average AOM with the testing dataset was 0.76 ± 0.08, and the mean CR and PM were 79 ± 9% and 86 ± 8%, respectively. Conclusion. With improved segmentation performance, our proposed method is of potential in clinical practice for HNC.

scholarly journals Perfusion in hand arthritis on dynamic contrast-enhanced computed tomography: a randomized prospective study using MRI as a standard of reference

2020 ◽  
Vol 50 (1) ◽  
pp. 59-68
Author(s):  
Sevtap Tugce Ulas ◽  
Kay Geert Hermann ◽  
Marcus R. Makowski ◽  
Robert Biesen ◽  
Fabian Proft ◽  
...  
Keyword(s):  
Rheumatoid Arthritis ◽  
Mean Transit Time ◽  
Region Of Interest ◽  
T Test ◽  
Dose Length Product ◽  
Suitable Alternative ◽  
Dce Mri ◽  
Dynamic Contrast Enhanced ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced

Abstract Objective To evaluate the performance of dynamic contrast-enhanced CT (DCE-CT) in detecting and quantitatively assessing perfusion parameters in patients with arthritis of the hand compared with dynamic contrast-enhanced MRI (DCE-MRI) as a standard of reference. Materials and methods In this IRB-approved randomized prospective single-centre study, 36 consecutive patients with suspected rheumatoid arthritis underwent DCE-CT (320-row, tube voltage 80 kVp, tube current 8.25 mAs) and DCE-MRI (1.5 T) of the hand. Perfusion maps were calculated separately for mean transit time (MTT), time to peak (TTP), relative blood volume (rBV), and relative blood flow (rBF) using four different decomposition techniques. Region of interest (ROI) analysis was performed in metacarpophalangeal joints II–V and in the wrist. Pairs of perfusion parameters in DCE-CT and DCE-MRI were compared using a two-tailed t test for paired samples and interpreted for effect size (Cohen’s d). According to the Rheumatoid Arthritis Magnetic Resonance Imaging Score (RAMRIS) scoring results, differentiation of synovitis-positive and synovitis-negative joints with both modalities was assessed with the independent t test. Results The two modalities yielded similar perfusion parameters. Identified differences had small effects (d 0.01–0.4). DCE-CT additionally differentiates inflamed and noninflamed joints based on rBF and rBV but tends to underestimate these parameters in severe inflammation. The total dose-length product (DLP) was 48 mGy*cm with an estimated effective dose of 0.038 mSv. Conclusion DCE-CT is a promising imaging technique in arthritis. In patients with a contraindication to MRI or when MRI is not available, DCE-CT is a suitable alternative to detect and assess arthritis.

scholarly journals Radiomic and Artificial Intelligence Analysis with Textural Metrics, Morphological and Dynamic Perfusion Features Extracted by Dynamic Contrast-Enhanced Magnetic Resonance Imaging in the Classification of Breast Lesions

2021 ◽  
Vol 11 (4) ◽  
pp. 1880
Author(s):  
Roberta Fusco ◽  
Adele Piccirillo ◽  
Mario Sansone ◽  
Vincenza Granata ◽  
Paolo Vallone ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Artificial Intelligence ◽  
Feature Selection ◽  
Resonance Imaging ◽  
Dynamic Features ◽  
Surgical Specimen ◽  
Dce Mri ◽  
Dynamic Contrast Enhanced ◽  
Contrast Enhanced ◽  
Malignant Lesions

Purpose: The aim of the study was to estimate the diagnostic accuracy of textural, morphological and dynamic features, extracted by dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) images, by carrying out univariate and multivariate statistical analyses including artificial intelligence approaches. Methods: In total, 85 patients with known breast lesion were enrolled in this retrospective study according to regulations issued by the local Institutional Review Board. All patients underwent DCE-MRI examination. The reference standard was pathology from a surgical specimen for malignant lesions and pathology from a surgical specimen or fine needle aspiration cytology, core or Tru-Cut needle biopsy for benign lesions. In total, 91 samples of 85 patients were analyzed. Furthermore, 48 textural metrics, 15 morphological and 81 dynamic parameters were extracted by manually segmenting regions of interest. Statistical analyses including univariate and multivariate approaches were performed: non-parametric Wilcoxon–Mann–Whitney test; receiver operating characteristic (ROC), linear classifier (LDA), decision tree (DT), k-nearest neighbors (KNN), and support vector machine (SVM) were utilized. A balancing approach and feature selection methods were used. Results: The univariate analysis showed low accuracy and area under the curve (AUC) for all considered features. Instead, in the multivariate textural analysis, the best performance (accuracy (ACC) = 0.78; AUC = 0.78) was reached with all 48 metrics and an LDA trained with balanced data. The best performance (ACC = 0.75; AUC = 0.80) using morphological features was reached with an SVM trained with 10-fold cross-variation (CV) and balanced data (with adaptive synthetic (ADASYN) function) and a subset of five robust morphological features (circularity, rectangularity, sphericity, gleaning and surface). The best performance (ACC = 0.82; AUC = 0.83) using dynamic features was reached with a trained SVM and balanced data (with ADASYN function). Conclusion: Multivariate analyses using pattern recognition approaches, including all morphological, textural and dynamic features, optimized by adaptive synthetic sampling and feature selection operations obtained the best results and showed the best performance in the discrimination of benign and malignant lesions.

Sign in / Sign up

Export Citation Format

Share Document