Probabilistic model for 3D interactive segmentation

•Interactive 3D medical image segmentation based on a Bayesian inference is suggested.•User-machine “dialogue” is allowed by a few mouse clicks in regions of disagreement.•User input is formulated as a probabilistic spatial term in a level-set functional.•A generic method which accommodates differen...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer vision and image understanding Ročník 151; s. 47 - 60
Hlavní autoři: Hershkovich, Tsachi, Shalmon, Tamar, Shitrit, Ohad, Halay, Nir, Menze, Bjoern H., Dolgopyat, Irit, Kahn, Itamar, Shelef, Ilan, Riklin Raviv, Tammy
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Inc 01.10.2016
Témata:
Image segmentation
Modality fusion
MR & CT Brain imaging
Probabilistic model
User interaction
Image segmentation
Probabilistic model
Modality fusion
User interaction
MR & CT Brain imaging
ISSN:1077-3142, 1090-235X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Interactive 3D medical image segmentation based on a Bayesian inference is suggested.•User-machine “dialogue” is allowed by a few mouse clicks in regions of disagreement.•User input is formulated as a probabilistic spatial term in a level-set functional.•A generic method which accommodates different modalities, e.g. CT and multimodal MRI.•GUI for clinical uses allows real-time, high performance with minimal user feedback. [Display omitted] Fully-automated segmentation algorithms offer fast, objective, and reproducible results for large data collections. However, these techniques cannot handle tasks that require contextual knowledge not readily available in the images alone. Thus, the supervision of an expert is necessary. We present a generative model for image segmentation, based on a Bayesian inference. Not only does our approach support an intuitive and convenient user interaction subject to the bottom-up constraints introduced by the image intensities, it also circumvents the main limitations of a human observer—3D visualization and modality fusion. The user “dialogue” with the segmentation algorithm via several mouse clicks in regions of disagreement, is formulated as a continuous probability map, that represents the user’s certainty to whether the current segmentation should be modified. Considering this probability map as the voxel-vise Bernoulli priors on the image labels allows spatial encoding of the user-provided input. The method is exemplified for the segmentation of cerebral hemorrhages (CH) in human brain CT scans; ventricles in degenerative mice brain MRIs, and tumors in multi-modal human brain MRIs and is shown to outperform three interactive, state-of-the-art segmentation methods in terms of accuracy, efficiency and user-workload.
ISSN:1077-3142
1090-235X
DOI:10.1016/j.cviu.2016.03.007