Synthetic Ground Truth for Validation of Brain Tumor MRI Segmentation

Prastawa, Marcel; Bullitt, Elizabeth; Gerig, Guido

doi:10.1007/11566465_4

Cited by 40 publications

(20 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dice overlap ± std deviations over 5 different initial seed lines for each tumor for synthetic tumor data set from [12] Graph cut Grow cut tCA tCA-Level Set Synthetic Tumor 1 6.6 ± 2. 7 patients obtained from Anadolu Medical Center.…”

Section: Validations On Tumors That Undergo Radiation Therapy Planningmentioning

confidence: 99%

Cellular Automata Segmentation of Brain Tumors on Post Contrast MR Images

Hamamcı

Ünal

Kucuk

et al. 2010

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2010

View full text Add to dashboard Cite

Abstract. In this paper, we re-examine the cellular automata(CA) algorithm to show that the result of its state evolution converges to that of the shortest path algorithm. We proposed a complete tumor segmentation method on post contrast T1 MR images, which standardizes the VOI and seed selection, uses CA transition rules adapted to the problem and evolves a level set surface on CA states to impose spatial smoothness. Validation studies on 13 clinical and 5 synthetic brain tumors demonstrated the proposed algorithm outperforms graph cut and grow cut algorithms in all cases with a lower sensitivity to initialization and tumor type.

show abstract

Section: Validations On Tumors That Undergo Radiation Therapy Planningmentioning

confidence: 99%

Cellular Automata Segmentation of Brain Tumors on Post Contrast MR Images

Hamamcı

Ünal

Kucuk

et al. 2010

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2010

View full text Add to dashboard Cite

show abstract

“…However, these statistical methods need a large number of patient images and the corresponding true displacements. To overcome this problem, it was proposed to train the statistical model on tumor growth simulations [46,47]. Numerical simulation could then be used to train the model for any tumor and at any location in the brain.…”

Section: Registration Algorithm In the Presence Of Tumormentioning

confidence: 99%

Glioma Dynamics and Computational Models: A Review of Segmentation, Registration, and In Silico Growth Algorithms and their Clinical Applications

Angelini¹,

Clatz²,

Mandonnet³

et al. 2007

CMIR

103

View full text Add to dashboard Cite

Tracking gliomas dynamics on MRI has became more and more important for therapeutic management. Powerful computational tools have been recently developed in this context enabling in silico growth on a virtual brain that can be matched with real 3D segmented evolution through registration between atlases and patient brain MRI data. In this paper, we provide an extensive review of existing algorithms for the three computational tasks involved in patient-specific tumor modeling: image segmentation, image registration, and in silico growth modelling (with special emphasis on the proliferation-diffusion model). Accuracy and limits of the reviewed algorithms are systematically discussed. Finally applications of these methods for both clinical practice and fundamental research are also discussed.

show abstract

“…We used simulated brain tumor growth images to assess error estimation performance for more realistic deformation modes, and for the images of different contrast. The images were created from the BrainWeb anatomical data as described in [18]. We used two versions of the simulated data: (1) with the intensity distribution close to that of the healthy subject image, and (2) with the intensity distribution derived from the real tumor data.…”

Section: Resultsmentioning

confidence: 99%

Evaluation of Brain MRI Alignment with the Robust Hausdorff Distance Measures

Fedorov

Billet

Prastawa

et al. 2008

Advances in Visual Computing

Self Cite

View full text Add to dashboard Cite

Abstract. We present a novel automated method for assessment of image alignment, applied to non-rigid registration of brain Magnetic Resonance Imaging data (MRI) for image-guided neurosurgery. We propose a number of robust modifications to the Hausdorff distance (HD) metric, and apply it to the edges recovered from the brain MRI to evaluate the accuracy of image alignment. The evaluation results on synthetic images, simulated tumor growth MRI and real neurosurgery data with expertidentified anatomical landmarks, confirm that the accuracy of alignment error estimation is improved compared to the conventional HD. The proposed approach can be used to increase confidence in the registration results, assist in registration parameter selection, and provide local estimates and visual assessment of the registration error.

show abstract

Synthetic Ground Truth for Validation of Brain Tumor MRI Segmentation

Cited by 40 publications

References 11 publications

Cellular Automata Segmentation of Brain Tumors on Post Contrast MR Images

Cellular Automata Segmentation of Brain Tumors on Post Contrast MR Images

Glioma Dynamics and Computational Models: A Review of Segmentation, Registration, and In Silico Growth Algorithms and their Clinical Applications

Evaluation of Brain MRI Alignment with the Robust Hausdorff Distance Measures

Contact Info

Product

Resources

About