Minimally Interactive MRI Segmentation for Subject-Specific Modelling of the Tongue

Harandi, Negar M.; Abugharbieh, Rafeef; Fels, Sidney

doi:10.1007/978-3-319-03590-1_5

Cited by 3 publications

(3 citation statements)

References 26 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Harandi et al . [51, 52] repeated manual segmentation of the tongue on a high-resolution MRI, and reported that the volume overlap index between different manual segmentations was 91% (equivalently DSC of 0.91). We expect slightly lower volume overlap in our case as we used cine-MRI of which image quality is poorer than high-resolution MRI.…”

Section: Discussionmentioning

confidence: 99%

“…We expect slightly lower volume overlap in our case as we used cine-MRI of which image quality is poorer than high-resolution MRI. Although there exists uncertainty in manual segmentation, the variability of the expert’s manual segmentation of the tongue is not high and is considered as reasonable gold standard [51, 52]. Therefore, DSC of around 0.91 or higher is considered acceptable in our experiments.…”

Section: Discussionmentioning

confidence: 99%

“…Several methods were proposed to segment the tongue [50–52] and the vocal tract [53, 54]. These methods were applied to 2D MR images [50, 53, 54] or a static high-quality 3D MR images [51, 52]. Although these segmentation methods can be applied to the segmentation of time-varying volumes (i.e., motion) by repeatedly segmenting each volume at each time frame, they do not systematically process the entire set of volumes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Semi-automatic segmentation for 3D motion analysis of the tongue with dynamic MRI

Lee

Woo

Xing

et al. 2014

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

Dynamic MRI has been widely used to track the motion of the tongue and measure its internal deformation during speech and swallowing. Accurate segmentation of the tongue is a prerequisite step to define the target boundary and constrain the tracking to tissue points within the tongue. Segmentation of 2D slices or 3D volumes is challenging because of the large number of slices and time frames involved in the segmentation, as well as the incorporation of numerous local deformations that occur throughout the tongue during motion. In this paper, we propose a semi-automatic approach to segment 3D dynamic MRI of the tongue. The algorithm steps include seeding a few slices at one time frame, propagating seeds to the same slices at different time frames using deformable registration, and random walker segmentation based on these seed positions. This method was validated on the tongue of five normal subjects carrying out the same speech task with multi-slice 2D dynamic cine-MR images obtained at three orthogonal orientations and 26 time frames. The resulting semi-automatic segmentations of a total of 130 volumes showed an average dice similarity coefficient (DSC) score of 0.92 with less segmented volume variability between time frames than in manual segmentations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semi-automatic segmentation for 3D motion analysis of the tongue with dynamic MRI

Lee

Woo

Xing

et al. 2014

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

show abstract

Tooth visualization in vowel production MR images for three-dimensional vocal tract modeling

Zhang

Honda

Wei

2018

Speech Communication

View full text Add to dashboard Cite

Computational Modeling of the Female Pelvic Support Structures and Organs to Understand the Mechanism of Pelvic Organ Prolapse: A Review

Chanda

Unnikrishnan

Roy

et al. 2015

Applied Mechanics Reviews

View full text Add to dashboard Cite

Pelvic organ prolapse (POP) is an abnormality of the female pelvic anatomy due to events, such as multiple child births, menopause, and morbid obesity, which may lead to weakening of the pelvic floor striated muscles and smooth musculo-connective tissues. POP leads to dropping of the pelvic organs, namely, the bladder, uterus, and rectum into the vaginal canal and eventual protrusion, causing vaginal pain, pressure, difficulty emptying the bladder and rectum, and sexual dysfunction. Each year, close to 300,000 POP surgeries are performed in the U.S., out of which more than 60% of patients may face relapse conditions. A closer look into the problem reveals that POP surgery failures may be attributed mainly to the lack of understanding among medical practitioners on the mechanics of prolapse. In the literature, there have been attempts in the engineering community to understand prolapse using phenomenological computational modeling. This paper reviews the development and study of these numerical models, aimed at understanding the mechanics of POP. The various computational challenges related to geometry creation, material modeling, finite-element (FE) modeling, and boundary conditions (BCs) will be discussed and significant future research directions will also be highlighted in this review.

show abstract

Minimally Interactive MRI Segmentation for Subject-Specific Modelling of the Tongue

Cited by 3 publications

References 26 publications

Semi-automatic segmentation for 3D motion analysis of the tongue with dynamic MRI

Semi-automatic segmentation for 3D motion analysis of the tongue with dynamic MRI

Tooth visualization in vowel production MR images for three-dimensional vocal tract modeling

Computational Modeling of the Female Pelvic Support Structures and Organs to Understand the Mechanism of Pelvic Organ Prolapse: A Review

Contact Info

Product

Resources

About