Multiparametric analysis of magnetic resonance images for glioma grading and patient survival time prediction

2011 ◽  
Vol 52 (9) ◽  
pp. 1052-1060 ◽  
Author(s):  
Benjamón Garzín ◽  
Kyrre E Emblem ◽  
Kim Mouridsen ◽  
Baard Nedregaard ◽  
Paulina Due-Tønnessen ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Survival Time ◽  
Predictive Value ◽  
Magnetic Resonance Images ◽  
Image Features ◽  
Cox Proportional Hazards ◽  
Survival Prediction ◽  
Dynamic Susceptibility ◽  
Post Contrast ◽  
Time Prediction

Background A systematic comparison of magnetic resonance imaging (MRI) options for glioma diagnosis is lacking. Purpose To investigate multiple MR-derived image features with respect to diagnostic accuracy in tumor grading and survival prediction in glioma patients. Material and Methods T1 pre- and post-contrast, T2 and dynamic susceptibility contrast scans of 74 glioma patients with histologically confirmed grade were acquired. For each patient, a set of statistical features was obtained from the parametric maps derived from the original images, in a region-of-interest encompassing the tumor volume. A forward stepwise selection procedure was used to find the best combinations of features for grade prediction with a cross-validated logistic model and survival time prediction with a cox proportional-hazards regression. Results Presence/absence of enhancement paired with kurtosis of the FM (first moment of the first-pass curve) was the feature combination that best predicted tumor grade (grade II vs. grade III-IV; median AUC = 0.96), with the main contribution being due to the first of the features. A lower predictive value (median AUC = 0.82) was obtained when grade IV tumors were excluded. Presence/absence of enhancement alone was the best predictor for survival time, and the regression was significant ( P < 0.0001). Conclusion Presence/absence of enhancement, reflecting transendothelial leakage, was the feature with highest predictive value for grade and survival time in glioma patients.

scholarly journals Left Atrial Geometry and Phasic Function Determined by Cardiac Magnetic Resonance Are Independent Predictors for Outcome in Non-Ischaemic Dilated Cardiomyopathy

Biomedicines ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 1653
Author(s):  
Bianca Olivia Cojan-Minzat ◽  
Alexandru Zlibut ◽  
Ioana Danuta Muresan ◽  
Rares-Ilie Orzan ◽  
Carmen Cionca ◽  
...  
Keyword(s):  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Dilated Cardiomyopathy ◽  
Predictive Value ◽  
Left Atrial ◽  
Cox Proportional Hazards ◽  
Lv Function ◽  
Composite Outcome ◽  
Chi Square ◽  
Increased Risk

Left atrial (LA) geometry and phasic functions are frequently impaired in non-ischaemic dilated cardiomyopathy (NIDCM). Cardiac magnetic resonance (CMR) can accurately measure LA function and geometry parameters. We sought to investigate their prognostic role in patients with NIDCM. We prospectively examined 212 patients with NIDCM (49 ± 14.2-year-old; 73.5% males) and 106 healthy controls. LA volumes, phasic functions, geometry, and fibrosis were determined using CMR. A composite outcome (cardiac death, ventricular tachyarrhythmias, heart failure hospitalization) was ascertained over a median of 26 months. LA phasic functions, sphericity index (LASI) and late gadolinium enhancement (LA-LGE) were considerably impaired in the diseased group (p < 0.001) and significantly correlated with impaired LV function parameters (p < 0.0001). After multivariate analysis, LA volumes, LASI, LA total strain (LA-εt) and LA-LGE were associated with increased risk of composite outcome (p < 0.001). Kaplan–Meier analysis showed significantly higher risk of composite endpoint for LA volumes (all p < 0.01), LASI > 0.725 (p < 0.003), and LA-εt < 30% (p < 0.0001). Stepwise Cox proportional-hazards models demonstrated a considerable incremental predictive value which resulted by adding LASI to LA-εt (Chi-square = 10.2, p < 0.001), and afterwards LA-LGE (Chi-Square = 15.8; p < 0.0001). NIDCM patients with defective LA volumes, LASI, LA-LGE and LA-εt had a higher risk for an outcome. LA-εt, LASI and LA-LGE provided independent incremental predictive value for outcome.

scholarly journals Assessment of T2-Weighted Coronal Magnetic Resonance Images in the Investigation of Pituitary Lesions

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Ruken Yuksekkaya ◽  
Levent Aggunlu ◽  
Yusuf Oner ◽  
Halil Celik ◽  
Sergin Akpek ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Pituitary Gland ◽  
Predictive Value ◽  
Pituitary Adenomas ◽  
Contrast Material ◽  
Magnetic Resonance Images ◽  
Intravenous Contrast ◽  
Primary Evaluation ◽  
Sensitivity Specificity ◽  
Accuracy Rates

Magnetic resonance imaging is the most important diagnostic method in the investigation of the pituitary lesions. Our aim is to determine whether T2-weighted coronal images may be helpful in the evaluation of the pituitary gland with suspected pituitary adenomas. One hundred and sixty-seven patients were examined prospectively with T2-weighted coronal and T1-weighted coronal images enhanced with intravenous contrast material. The images were evaluated for the presence, the size, the location, and the ancillary signs including sellar floor erosion or ballooning, infindibulary deviation, convexity of the superior border of the gland, diffuse enlargement of the gland, and the invasion of the cavenous sinuses on both images. In forty-six (28%) patients lesions were revealed on both sequences. In twenty-one (12%) patients the lesions that were revealed on the T1-weighted images were not detected on the T2-weighted images. Positive predictive value, negative predictive value, sensitivity, specificity, and diagnostic accuracy rates of T2-weighted coronal images on the detection of the presence of lesions were 100%, 17.4%, 68.7%, 100%, and 87.4%, respectively. Both T2-weighted coronal and T1-weighted coronal images enhanced with intravenous gadolinium-based contrast material are important in the diagnosis of pituitary adenomas. T2-weighted coronal images could be used as a screening tool for the primary evaluation of the pituitary gland.

scholarly journals Macrovascular Networks on Contrast-Enhanced Magnetic Resonance Imaging Improves Survival Prediction in Newly Diagnosed Glioblastoma

Cancers ◽  
2019 ◽  
Vol 11 (1) ◽  
pp. 84 ◽  
Author(s):  
Josep Puig ◽  
Carles Biarnés ◽  
Pepus Daunis-i-Estadella ◽  
Gerard Blasco ◽  
Alfredo Gimeno ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Prediction Models ◽  
Survival Prediction ◽  
Dynamic Susceptibility ◽  
Imaging Features ◽  
Newly Diagnosed ◽  
Resonance Imaging ◽  
Contrast Enhanced ◽  
Newly Diagnosed Glioblastoma

A higher degree of angiogenesis is associated with shortened survival in glioblastoma. Feasible morphometric parameters for analyzing vascular networks in brain tumors in clinical practice are lacking. We investigated whether the macrovascular network classified by the number of vessel-like structures (nVS) visible on three-dimensional T1-weighted contrast–enhanced (3D-T1CE) magnetic resonance imaging (MRI) could improve survival prediction models for newly diagnosed glioblastoma based on clinical and other imaging features. Ninety-seven consecutive patients (62 men; mean age, 58 ± 15 years) with histologically proven glioblastoma underwent 1.5T-MRI, including anatomical, diffusion-weighted, dynamic susceptibility contrast perfusion, and 3D-T1CE sequences after 0.1 mmol/kg gadobutrol. We assessed nVS related to the tumor on 1-mm isovoxel 3D-T1CE images, and relative cerebral blood volume, relative cerebral flow volume (rCBF), delay mean time, and apparent diffusion coefficient in volumes of interest for contrast-enhancing lesion (CEL), non-CEL, and contralateral normal-appearing white matter. We also assessed Visually Accessible Rembrandt Images scoring system features. We used ROC curves to determine the cutoff for nVS and univariate and multivariate cox proportional hazards regression for overall survival. Prognostic factors were evaluated by Kaplan-Meier survival and ROC analyses. Lesions with nVS > 5 were classified as having highly developed macrovascular network; 58 (60.4%) tumors had highly developed macrovascular network. Patients with highly developed macrovascular network were older, had higher volumeCEL, increased rCBFCEL, and poor survival; nVS correlated negatively with survival (r = −0.286; p = 0.008). On multivariate analysis, standard treatment, age at diagnosis, and macrovascular network best predicted survival at 1 year (AUC 0.901, 83.3% sensitivity, 93.3% specificity, 96.2% PPV, 73.7% NPV). Contrast-enhanced MRI macrovascular network improves survival prediction in newly diagnosed glioblastoma.

scholarly journals A three-dimensional computational analysis of magnetic resonance images characterizes the biological aggressiveness in malignant brain tumours

2018 ◽  
Vol 15 (149) ◽  
pp. 20180503 ◽  
Author(s):  
J. Pérez-Beteta ◽  
A. Martínez-González ◽  
V. M. Pérez-García
Keyword(s):  
Magnetic Resonance ◽  
Prognostic Value ◽  
Three Dimensional ◽  
Magnetic Resonance Images ◽  
Post Contrast ◽  
Primary Brain Tumour ◽  
Malignant Brain Tumours ◽  
Sensitivity Studies ◽  
Pre Treatment ◽  
Shape Complexity

Glioblastoma (GBM) is the most frequent and aggressive type of primary brain tumour. The development of image-based biomarkers from magnetic resonance images (MRIs) has been a topic of recent interest. GBMs on pre-treatment post-contrast T1-weighted (w) MRIs often appear as rim-shaped regions. In this research, we wanted to define rim-shape complexity (RSC) descriptors and study their value as indicators of the tumour’s biological aggressiveness. We constructed a set of widths characterizing the rim-shaped contrast-enhancing areas in T1w MRIs, defined measures of the RSC and computed them for 311 GBM patients. Survival analysis, correlations and sensitivity studies were performed to assess the prognostic value of the measurements. All measures obtained from the histograms were found to depend on the class width to some extent. Several measures (FWHM and β R ) had high prognostic value. Some histogram-independent measures were predictors of survival: maximum rim width, mean rim width and spherically averaged rim width. The later quantity allowed patients to be classified into subgroups with different rates of survival (mean difference 6.28 months, p = 0.006). In conclusion, some of the morphological quantifiers obtained from pre-treatment T1w MRIs provided information on the biological aggressiveness of GBMs. The results can be used to define prognostic measurements of clinical applicability.

AN INTERACTIVE CBIR SYSTEM BASED ON ANFIS LEARNING SCHEME FOR HUMAN BRAIN MAGNETIC RESONANCE IMAGES RETRIEVAL

2012 ◽  
Vol 24 (01) ◽  
pp. 27-36 ◽  
Author(s):  
Mana Tarjoman ◽  
Emad Fatemizadeh ◽  
Kambiz Badie
Keyword(s):  
Magnetic Resonance ◽  
Human Brain ◽  
Image Retrieval ◽  
Medical Images ◽  
Magnetic Resonance Images ◽  
Image Features ◽  
Medical Decision ◽  
Query Image ◽  
Fuzzy Classifier ◽  
Inference System

Content-based image retrieval (CBIR) has turned into an important and active potential research field with the advance of multimedia and imaging technology. It makes use of image features, such as color, texture and shape, to index images with minimal human intervention. A CBIR system can be used to locate medical images in large databases. In this paper we propose a CBIR system which describes the methodology for retrieving digital human brain magnetic resonance images (MRI) based on textural features and the Adaptive neuro-fuzzy inference system (ANFIS) learning to retrieve similar images from database in two categories: normal and tumoral. A fuzzy classifier has been used, because of the uncertainty in the results of classifier and capacity of learning. ANFIS is a good candidate for our categorization problem. Our proposed CBIR system can locate a query image in the category of normal or tumoral images in the online retrieval part. Finally, using a relevance feedback, we improve the effectiveness of our retrieval system. This research uses the knowledge of the CBIR approach to the application of medical decision support and discrimination between the normal and abnormal medical images based on features. We present and compare the results of the proposed method with the CBIR systems used in recent works. The experimental results indicate that the proposed method is reliable and has high image retrieval efficiency compared with the previous works.

Multifocal Haemangioblastoma: Usefulness of MR Examination with a High Dose of Contrast-Medium and Late Acquisition

1997 ◽  
Vol 10 (5) ◽  
pp. 609-612
Author(s):  
I. Aprile ◽  
E. Biasizzo ◽  
M.C. De Colle ◽  
P. Dolso ◽  
G. Fabris
Keyword(s):  
Magnetic Resonance ◽  
Contrast Medium ◽  
Pulse Sequences ◽  
Magnetic Resonance Images ◽  
High Dose ◽  
Double Dose ◽  
Enhancement Pattern ◽  
Post Contrast ◽  
Contrast Medium Administration ◽  
High Doses

A rare cerebral tumour is described with a particular enhancement pattern in post-contrast medium administration magnetic resonance images. The tumour was a supratentorial, multifocal haemangioblastoma, whose solid components did not enhance in pulse sequences acquired after contrast medium administration (double dose), but only in later acquisitions (after about 1 hour). This particular behaviour suggests using contrast medium at high doses with late acquisitions when a cerebral haemangioblastoma is suspected.

A FUZZY FRAMEWORK FOR CONTENT BASED MAGNETIC RESONANCE IMAGES RETRIEVAL USING SALIENCY MAP

2017 ◽  
Vol 29 (05) ◽  
pp. 1750033
Author(s):  
Mana Tarjoman
Keyword(s):  
Magnetic Resonance ◽  
Image Retrieval ◽  
Fuzzy Inference ◽  
Saliency Map ◽  
Magnetic Resonance Images ◽  
Image Features ◽  
Research Field ◽  
Textural Features ◽  
Query Image ◽  
Inference System

Content-based image retrieval (CBIR) has turned into an important research field with the advancement in multimedia and imaging technology. The term CBIR has been widely used to describe the process of retrieving desired images from a large collection on the basis of features such as color, texture and shape that can be automatically extracted from the images themselves. Considering the gap between low-level image features and the high-level semantic concepts in the CBIR, we proposed an image retrieval system for brain magnetic resonance images based on saliency map. First, the proposed approach exploits the ant colony optimization (ACO) technique to measure the image’s saliency through ants’ movements on the image. The textural features are then calculated from the saliency map of the images. The image retrieval of the proposed CBIR system is based on textural features and the fuzzy approach using Adaptive neuro-fuzzy inference system (ANFIS). Regarding the various categories of images in a database, we define some membership functions in the ANFIS output in order to determine the membership values of the images related to the existing categories. In online image retrieval, a query image is introduced to the system and the relevant images can be retrieved based on query membership values into different classes including normal or tumoral. The experimental results indicate that the proposed method is reliable and has high image retrieval efficiency compared with the previous works.

Sign in / Sign up

Export Citation Format

Share Document