Statistical Validation of Automated Probabilistic Segmentation against Composite Latent Expert Ground Truth in MR Imaging of Brain Tumors

Abstract

Abstract. The validity of segmentation is an important issue in image processing because it has a direct impact on surgical planning. Binary manual segmentation is not only time-consuming but also lacks the ability of differentiating subtle intensity variations among voxels, particularly for those on the border of a tumor and for different tumor types. Previously we have developed an automated segmentation method that yields voxel-wise continuous probabilistic measures, indicating a level of tumor presence. The goal of this work is to examine three accuracy metrics based on two-sample statistical methods, against the estimated composite latent ground truth derived from several experts' manual segmentation by a maximum likelihood algorithm. We estimated the distribution functions of the tumor and control voxel data parametrically by assuming a mixture of two beta distributions with different shape parameters. We derived the resulting receiver operating characteristic curves, Dice similarity coefficients, and mutual information, over all possible decision thresholds. Based on each validation metric, an optimal threshold was then computed via maximization. We illustrated these methods on MR imaging data from nine brain tumor cases, three with meningiomas, three astrocytomas, and three other low-grade gliomas. The automated segmentation yielded satisfactory accuracy, with varied optimal thresholds.

Statistical validation based on parametric receiver operating characteristic analysis of continuous classification data1

“…For comparing two sets of segmentation results, existing validation metrics other than area under the ROC curve, for example, entropy-based mutual information (26), Jaccard (27) and Dice (28) similarity coefficient, and Hausdorff distance measure (29,30). We have already investigated such metrics in separate articles (19,31).…”

“…For comparing two sets of segmentation results, existing validation metrics other than area under the ROC curve, for example, entropy-based mutual information (26), Jaccard (27) and Dice (28) similarity coefficient, and Hausdorff distance measure (29,30). We have already investigated such metrics in separate articles (19,31).In summary, we have conducted parametric evaluations of two types of continuous classification data using ROC analysis, with application to three clinical examples. The proposed method may be adapted to several validation tasks in radiologic research, as illustrated in our clinical examples.…”

Three validation metrics for automated probabilistic image segmentation of brain tumours

“…The cases: A total of nine patients were randomly selected from a neuro-surgical database of 260 brain tumour patients, of which three had meningiomas (M), three astrocytomas (A), and three other low-grade gliomas (G) [7,55]. Visually the meningiomas enhanced better on greyscale images than the remaining two tumour types.…”

Automated Brain Tumor Detection and Segmentation from MRI Images using Adaptive Connected Component Pixel Segmentation

“…Segments provide categorical classification results like volume size, distance between region surface and so on [6].…”

“…region [1] region [2] region [3] region [4] region [5] region [6] region [7] region [8] region [9] With an I3 processor 4 GB RAM PC, it is not plausible to figure the associated segment progressively when N=1, 2 or 3. Our new calculation figures associated segment inside of 2 seconds for a picture size of 2008K with N=25.…”