DCE-MRI Data Analysis for Cancer Area Classification

Castellani, Umberto; Cristiani, Marco; Daducci, Alessandro; Farace, Paolo; Marzola, Pasquina; Murino, Vittorio; Sbarbati, Andrea

doi:10.3414/me9224

Cited by 11 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This agent, usually gadolinium based, is a paramagnetic substance which generates its own magnetic field. This magnetic field decreases relaxation times (T 1 , T 2 ) and so enables differences between tissues according to the volume of contrast agent (9,10,11,14,16). Gadolinium -diethylenetriamine pentaacetic acid (Gd -DTPA) contrast agent is commonly used in breast DCE MRI (10,11).…”

Section: Dynamic Contrast Enhanced Mri (Dce Mri)mentioning

confidence: 99%

Nuclear Magnetic Resonance as a Diagnostic Tool in Breast Cancer

Hnilicová¹,

Dobrota²

2012

Acta Medica Martiniana

View full text Add to dashboard Cite

A b s t r a c tThe early detection and treatment of breast cancer is of direct benefit to patients. Magnetic resonance imaging (MRI) is a promising modality for detection, diagnosis, and staging of breast cancer. MRI enables two methods: the diffusion-weighted MRI (DW MRI) and the dynamic contrast enhanced MRI (DCE MRI). DW MRI reflects the diffusion of water molecules in the extracellular fluid space and allows the estimation of cellularity and tissue structure. The value of the diffusion of water in tissue is called the apparent diffusion coefficient (ADC). ADC values in malignant lesions are smaller than in benign tissue. DCE MRI yields appropriate pharmacokinetic data of physiological parameters that relate to tissue perfusion, microvascular vessel wall permeability and extracellular volume fraction. Gadolinium based contrast agent is usually used in breast DCE MRI diagnostics. Changes in the post-contrast signal intensity help to distinguish lesions according to characteristically enhanced accumulation of contrast agent. Malignant lesions are characterized by a faster and stronger signal enhancement than benign lesions which relate to their neoangiogenesis. Over the last few years, there has been appreciable interest in the use of magnetic resonance spectroscopy (MRS) for the non-invasive analysis of breast tisue metabolites. One of the spectroscopic hallmarks of the neoplastic process appears to be the presence of total choline signal in the in vivo spectrum. Despite the fact that MRI and MRS achieve excellent results, they are still not so frequently used in comparison to mammography and breast ultrasound.

show abstract

Section: Dynamic Contrast Enhanced Mri (Dce Mri)mentioning

confidence: 99%

Nuclear Magnetic Resonance as a Diagnostic Tool in Breast Cancer

Hnilicová¹,

Dobrota²

2012

Acta Medica Martiniana

View full text Add to dashboard Cite

show abstract

“…The gadolinium-based contrast agent is a paramagnetic substance that causes shortening of the T1 relaxation time [9], [40], and [45]. Therefore, the DCE MRI can differentiate tissues due to accumulation of contrast medium, reflecting the increased tissue vascularity [5], [46], [47]. The measured dynamic data could be evaluated in the form of kinetic curves (Fig.3) and in appropriate software (e.g., JIM-Xinapse Systems Ltd., Northants.…”

Section: Introductionmentioning

confidence: 99%

Non-Invasive Multi-Parametric in vivo Mapping of the Brain Tumors and Brain Metastases

2015

4th International Conference on Advances in Engineering Sciences and Applied Mathematics (ICAESAM-2015) Dec. 8-9, 2015 Kuala Lu

View full text Add to dashboard Cite

However, magnetic resonance (MR) is a well-known non-invasive medical tool, its modalities are not routinely used in the clinical oncologic practice. The multi-modal comprehensive set of computer-evaluated quantitative MR parameters of the brain tissue in patients with suspected intracranial tumors could provide more recent, more accurate and wealthier information about the tumor tissue. Most helpful are in this regard, proton and phosphorus magnetic resonance spectroscopy (1H and 31P MRS), relaxometry of T2 values, dynamic-contrast enhancement MRI (DCE MRI), and diffusion-weighted MRI (DWI). Their measurement techniques, evaluating methods as well as clustering multi-parametric analysis could be key instruments in diagnostic of intracranial tumors.

show abstract

“…Classification techniques have been applied widely in medical imaging, process monitoring and computer science, for example to face recognition [10] and classification of tumours [1]. In [4] the cancer area classification problem is investigated with voxels produced by (DCE-)MRI data as inputs. The author uses unsupervised clustering techniques first and then goes on to classify the voxels in the tumoral regions where 'voxels of the same cluster are fed with the same label into the classifier'.…”

Section: Introductionmentioning

confidence: 99%

On discrimination algorithms for ill-posed problems with an application to magnetic tomography

et al. 2012

View full text Add to dashboard Cite

In this paper we explore classification techniques for ill-posed problems. Two classes are linearly separable in some Hilbert space X if they can be separated by a hyperplane. We investigate stable separability, i.e. the case where we have a positive distance between two separating hyperplanes. When the data in the space Y is generated by a compact operator A applied to the system states ϕ ∈ X, we will show that in general we do not obtain stable separability in Y even if the problem in X is stably separable. In particular, we show this for the case where a nonlinear classification is generated from a non-convergent family of linear classes in X. We apply our results to the problem of quality control of fuel cells where we classify fuel cells according to their efficiency. We can potentially classify a fuel cell using either some external measured magnetic field or some internal current. However we cannot measure the current directly since we cannot access the fuel cell in operation. The first possibility is to apply discrimination techniques directly to the measured magnetic fields. The second approach first reconstructs currents and then carries out the classification on the current distributions. We show that both approaches need regularization and that the regularized classifications are not equivalent in general. Finally, we investigate a widely used linear classification algorithm Fisher's linear discriminant with respect to it's ill-posedness when applied to data generated via a compact integral operator. We show that the method cannot stay stable when the number of measurement points becomes large.

show abstract

DCE-MRI Data Analysis for Cancer Area Classification

Abstract: The proposed method allows to analyze the DCE-MRI data more precisely and faster than previous automated or manual approaches.

Cited by 11 publications

References 16 publications

Nuclear Magnetic Resonance as a Diagnostic Tool in Breast Cancer

Nuclear Magnetic Resonance as a Diagnostic Tool in Breast Cancer

Non-Invasive Multi-Parametric in vivo Mapping of the Brain Tumors and Brain Metastases

On discrimination algorithms for ill-posed problems with an application to magnetic tomography

Contact Info

Product

Resources

About