Classifiers for Ischemic Stroke Lesion Segmentation: A Comparison Study - PubMed (original) (raw)

Comparative Study

Classifiers for Ischemic Stroke Lesion Segmentation: A Comparison Study

Oskar Maier et al. PLoS One. 2015.

Erratum in

Abstract

Motivation: Ischemic stroke, triggered by an obstruction in the cerebral blood supply, leads to infarction of the affected brain tissue. An accurate and reproducible automatic segmentation is of high interest, since the lesion volume is an important end-point for clinical trials. However, various factors, such as the high variance in lesion shape, location and appearance, render it a difficult task.

Methods: In this article, nine classification methods (e.g. Generalized Linear Models, Random Decision Forests and Convolutional Neural Networks) are evaluated and compared with each other using 37 multiparametric MRI datasets of ischemic stroke patients in the sub-acute phase in terms of their accuracy and reliability for ischemic stroke lesion segmentation. Within this context, a multi-spectral classification approach is compared against mono-spectral classification performance using only FLAIR MRI datasets and two sets of expert segmentations are used for inter-observer agreement evaluation.

Results and conclusion: The results of this study reveal that high-level machine learning methods lead to significantly better segmentation results compared to the rather simple classification methods, pointing towards a difficult non-linear problem. The overall best segmentation results were achieved by a Random Decision Forest and a Convolutional Neural Networks classification approach, even outperforming all previously published results. However, none of the methods tested in this work are capable of achieving results in the range of the human observer agreement and the automatic ischemic stroke lesion segmentation remains a complicated problem that needs to be explored in more detail to improve the segmentation results.

PubMed Disclaimer

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.

Figures

Fig 1

Fig 1. Processing pipeline.

Fig 2

Fig 2. Results for case 21.

Slice 21 with besteffort scenario trained on GTG. (a) ground-truth (GTG). (b) 100NN. (c) 10NN. (d) 5NN. (e) AdaBoost. (f) ET. (g) GNB. (h) GLM. (i) GB. (j) RDF.

Fig 3

Fig 3. Results for case 04.

Slice 30 with besteffort scenario trained on GTG. Note the presence of other white matter hyperintensities. (a) ground-truth (GTG). (b) 100NN. (c) 5NN. (d) AdaBoost. (e) ET. (f) GNB. (g) GLM. (h) GB. (i) RDF. (j) tunedET.

Fig 4

Fig 4. ROC curves for both evaluation scenarios computed over the GTG ground truth.

(a) besteffort scenario. (b) flair scenario.

Fig 5

Fig 5. Cases failed by at least one classifier.

(a) 09/24 ground-truth (GTG). (b) 11/29 ground-truth (GTG). (c) 39/36 ground-truth (GTG). (d) 41/24 ground-truth (GTG).

Fig 6

Fig 6. Worst two cases.

See text for description. (a) 37/44 ground-truth (GTG). (b) 37/32 tunedET. (c) 44/24 ground-truth (GTG). (d) 44/24 CNN.

Fig 7

Fig 7. Best overall case 36 and the worst (GNB, DM = 0.61) as well as best (ET, DM = 0.86) result obtained over all methods.

(a) 36/27 ground-truth (GTG). (b) 36/27 GNB. (c) 36/27 ET.

Fig 8

Fig 8. Case with low agreement between methods in flair scenario.

(a) 18/28 ground-truth (GTG). (b) 18/28 AdaBoost. (c) 18/28 CNN. (d) 18/28 ET.

Similar articles

Cited by

References

    1. Kaesemann P, Thomalla G, Cheng B, Treszl A, Fiehler J, Forkert ND. Impact of severe extracranial ICA stenosis on MRI perfusion and diffusion parameters in acute ischemic stroke. Frontiers in Neurology. 2014;5(254). 10.3389/fneur.2014.00254 - DOI - PMC - PubMed
    1. Rekik I, Allassonniere S, Carpenter TK, Wardlaw JM. Medical image analysis methods in MR/CT-imaged acute-subacute ischemic stroke lesion: Segmentation, prediction and insights into dynamic evolution simulation models. A critical appraisal. NeuroImage: Clinical. 2012;1(1):164–178. 10.1016/j.nicl.2012.10.003 - DOI - PMC - PubMed
    1. Seghier ML, Ramlackhansingh A, Crinion J, Leff AP, Price CJ. Lesion identification using unified segmentation-normalisation models and fuzzy clustering. NeuroImage. 2008. July;41(4):1253–1266. 10.1016/j.neuroimage.2008.03.028 - DOI - PMC - PubMed
    1. Forbes F, Doyle S, Garcia-Lorenzo D, Barillot C, Dojat M. Adaptive weighted fusion of multiple MR sequences for brain lesion segmentation In: Biomedical Imaging: From Nano to Macro, 2010 IEEE International Symposium on; 2010. p. 69–72.
    1. Wilke M, de Haan B, Juenger H, Karnath HO. Manual, semi-automated, and automated delineation of chronic brain lesions: a comparison of methods. NeuroImage. 2011. June;56(4):2038–2046. 10.1016/j.neuroimage.2011.04.014 - DOI - PubMed

Publication types

MeSH terms

Grants and funding

OM holds a scholarship of the Graduate School for Computing in Medicine and Life Sciences, Universität zu Lübeck, Lübeck, Germany. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

LinkOut - more resources