Ground Truth in MS Lesion Volumetry – A Phantom Study

Rexilius, Jan; Hahn, Horst K.; Bourquain, Holger; Peitgen, Heinz‐Otto

doi:10.1007/978-3-540-39903-2_67

Cited by 9 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The common values for the diameter are between 3.5 mm and 13.5 mm [24]. For any input MRI studies, the square w × w blocks are selected automatically to tightly cover the smallest possible diameter as a function of the given pixel sizes calculated from the input resolution and field of view.…”

Section: Textural Based Detection Of Initial Ms Lesions Regionsmentioning

confidence: 99%

Textural Based SVM for MS Lesion Segmentation in FLAIR MRIs

Abdullah¹,

Younis²,

Pattany³

et al. 2011

OJMI

View full text Add to dashboard Cite

In this paper, a new technique is proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI). The technique uses textural features to describe the blocks of each MRI slice along with position and neighborhood features. A trained support vector machine (SVM) is used to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions based on mainly the textural features with aid of the other features. The MRI slice blocks' classification is used to provide an initial segmentation. A comprehensive post processing module is then utilized to refine and improve the quality of the initial segmentation. The main contribution of the proposed technique described in this paper is the use of textural features to detect MS lesions in a fully automated process without the need to manually define regions of interest (ROIs). In addition, the post processing module is generic enough to be applied to the results of any other MS segmentation technique to improve the segmentation quality. This technique is evaluated using ten real MRI data-sets with 10% used in the training of the textural-based SVM. The average results for the performance evaluation of the presented technique were 0.79 for dice similarity, 0.68 for sensitivity and 0.9 for the percentage of the detected lesion load. These results indicate that the proposed method would be useful in clinical practice for the detection of MS lesions from MRI.

show abstract

Section: Textural Based Detection Of Initial Ms Lesions Regionsmentioning

confidence: 99%

Textural Based SVM for MS Lesion Segmentation in FLAIR MRIs

Abdullah¹,

Younis²,

Pattany³

et al. 2011

OJMI

View full text Add to dashboard Cite

show abstract

“…In our group we employ the convolution in the process of simulation of fluorescence microscopy images [12]. The simulation process usually consists of three consecutive stages: generation of digital phantoms [13], simulation of optical system, and simulation of acquisition device. We use the convolution in the first two stages:…”

Section: Applicationmentioning

confidence: 99%

Efficient Computation of Convolution of Huge Images

Svoboda

2011

Image Analysis and Processing – ICIAP 2011

View full text Add to dashboard Cite

Abstract. In image processing, convolution is a frequently used operation. It is an important tool for performing basic image enhancement as well as sophisticated analysis. Naturally, due to its necessity and still continually increasing size of processed image data there is a great demand for its efficient implementation. The fact is that the slowest algorithms (that cannot be practically used) implementing the convolution are capable of handling the data of arbitrary dimension and size. On the other hand, the fastest algorithms have huge memory requirements and hence impose image size limits. Regarding the convolution of huge images, which might be the subtask of some more sophisticated algorithm, fast and correct solution is essential. In this paper, we propose a fast algorithm implementing exact computation of the shift invariant convolution over huge multi-dimensional image data.

show abstract

“…Then, it is incorporated into an MR scan of the brain of a normal volunteer. A similar concept was used in [8] to generate realistic phantoms of small white matter lesions that occur in patients with Multiple Sclerosis.…”

Section: Modeling Active Tumor Tissue and Necrosismentioning

confidence: 99%

“…A ditigal phantom for the brain is available from the BrainWeb project [7]. A phantom for Multiple Sclerosis lesions was proposed in [8]. However, there are no suitable phantoms available for brain tumors.…”

Section: Introductionmentioning

confidence: 99%

A Framework for the Generation of Realistic Brain Tumor Phantoms and Applications

Rexilius

Hahn

Schlüter

et al. 2004

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2004

Self Cite

View full text Add to dashboard Cite

Abstract.A quantitative analysis of brain tumors is an important factor that can have direct impact on a patient's prognosis and treatment. In order to achieve clinical relevance, reproducibility and especially accuracy of a proposed method have to be tested. We propose a framework for the generation of realistic digital phantoms of brain tumors of known volumes and their incorporation into an MR dataset of a healthy volunteer. Deformations that occur due to tumor growth inside the brain are simulated by means of a biomechanical model. Furthermore, a model for the amount of edema at each voxel is included as well as a simulation of contrast enhancement, which provides us with an additional characterization of the tumor. A "ground truth" is generally not available for brain tumors. Our proposed framework provides a flexible tool to generate representative datasets with known ground truth, which is essential for the validation and comparison of current and new quantitative approaches. Experiments are carried out using a semi-automated volumetry approach for a set of generated tumor datasets.

show abstract

Ground Truth in MS Lesion Volumetry – A Phantom Study

Cited by 9 publications

References 11 publications

Textural Based SVM for MS Lesion Segmentation in FLAIR MRIs

Textural Based SVM for MS Lesion Segmentation in FLAIR MRIs

Efficient Computation of Convolution of Huge Images

A Framework for the Generation of Realistic Brain Tumor Phantoms and Applications

Contact Info

Product

Resources

About