Segmentation of the temporalis muscle from MR data

Ng, Howard P.; Hu, Qingmao; Ong, Sim‐Heng; Foong, Kelvin Weng Chiong; Goh, Poh Sun; Liu, J.; Nowinski, Wiesław L.

doi:10.1007/s11548-007-0073-9

Cited by 4 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our technique produced generally better segmentation than previous approaches for the same muscle: previous models achieved DSC of 0.86 for masticatory muscles [44], 0.826 and 0.788 for masseter and temporalis [17] and 0.902 for temporalis [16], compared to DSC of 0.893 in this study. Our DSC is also comparable to previous models for segmentation of other muscles, for example, abdominal (DSC 0.90-0.97) [20][21][22][23][24], thigh (DSC 0.90-0.97) [18,19] and shoulder (DSC 0.71-0.88) [26,27]; our precision and recall of 0.867 and 0.926 is comparable to 0.93 and 0.91 for abdominal muscle [20]; and our HD of 1.889 mm is better than an existing model for masticatory muscles (8.2 mm) [44] as well as those for thigh (2.3-8.2 mm) [18] and lumbar abdominal (4.6-7.9 mm) muscles [22].…”

Section: Discussioncontrasting

confidence: 48%

“…Automated methods have been developed for muscle segmentation, including thresholding, fuzzy c-means clustering, atlas/ registration-based methods and shape prior modelling. One study applied range-constrained thresholding and adaptive morphological operations to segment temporalis [16], while another used Markov random field approach and region growing [17]. However, these have shortcomings: thresholding may fail when neighbouring tissues have similar intensity (as with facial muscles), atlas/ registration-based methods require high computational resources and substantial time to segment each case and can fail to locate complex facial muscle structures with sufficient precision.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning-based quantification of temporalis muscle has prognostic value in patients with glioblastoma

Mauricaite

Pakzad-Shahabi

et al. 2021

Br J Cancer

View full text Add to dashboard Cite

Background Glioblastoma is the commonest malignant brain tumour. Sarcopenia is associated with worse cancer survival, but manually quantifying muscle on imaging is time-consuming. We present a deep learning-based system for quantification of temporalis muscle, a surrogate for skeletal muscle mass, and assess its prognostic value in glioblastoma. Methods A neural network for temporalis segmentation was trained with 366 MRI head images from 132 patients from 4 different glioblastoma data sets and used to quantify muscle cross-sectional area (CSA). Association between temporalis CSA and survival was determined in 96 glioblastoma patients from internal and external data sets. Results The model achieved high segmentation accuracy (Dice coefficient 0.893). Median age was 55 and 58 years and 75.6 and 64.7% were males in the in-house and TCGA-GBM data sets, respectively. CSA was an independently significant predictor for survival in both the in-house and TCGA-GBM data sets (HR 0.464, 95% CI 0.218–0.988, p = 0.046; HR 0.466, 95% CI 0.235–0.925, p = 0.029, respectively). Conclusions Temporalis CSA is a prognostic marker in patients with glioblastoma, rapidly and accurately assessable with deep learning. We are the first to show that a head/neck muscle-derived sarcopenia metric generated using deep learning is associated with oncological outcomes and one of the first to show deep learning-based muscle quantification has prognostic value in cancer.

show abstract

Section: Discussioncontrasting

confidence: 48%

Section: Introductionmentioning

confidence: 99%

Deep learning-based quantification of temporalis muscle has prognostic value in patients with glioblastoma

Mauricaite

Pakzad-Shahabi

et al. 2021

Br J Cancer

View full text Add to dashboard Cite

show abstract

“…Ng et al [27][28][29] have tested several methods for FST segmentation using prior knowledge. The process starts with manual segmentation of the training sets.…”

Section: Facial Soft Tissue Segmentationmentioning

confidence: 99%

The Effect of Labeled/Unlabeled Prior Information for Masseter Segmentation

Tabar

Ulusoy

2013

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Several segmentation methods are implemented and applied to segment the facial masseter tissue from magnetic resonance images. The common idea for all methods is to take advantage of prior information from different MR images belonging to different individuals in segmentation of a test MR image. Standard atlas-based segmentation methods and probabilistic segmentation methods based on Markov random field use labeled prior information. In this study, a new approach is also proposed where unlabeled prior information from a set of MR images is used to segment masseter tissue in a probabilistic framework. The proposed method uses only a seed point that indicates the target tissue and performs automatic segmentation for the selected tissue without using labeled training set. The segmentation results of all methods are validated and compared where the influences of labeled or unlabeled prior information and initialization are discussed particularly. It is shown that if appropriate modeling is done, there is no need for labeled prior information. The best accuracy is obtained by the proposed approach where unlabeled prior information is used.

show abstract

“…A modeling method for muscles in the crural area was then proposed for analysis of their motor function in MR images [6]. A recognition method for the temporal muscle was proposed for surgical planning and analysis of loss of the mastication function [7]. These two methods, however, were used for MR images.…”

Section: Introductionmentioning

confidence: 99%

Automated segmentation of psoas major muscle in X-ray CT images by use of a shape model: preliminary study

Kamiya

Zhou

Chen

et al. 2011

Radiol Phys Technol

View full text Add to dashboard Cite

Our motivation was to provide an automatic tool for radiologists and orthopedic surgeons for improving the quality of life of an aging population. We propose a method for generating a shape model and a fully automated segmenting scheme for the psoas major muscle in X-ray CT images by using the shape model. Our approach consists of two steps: (1) The generation of a shape model and its application to muscle segmentation. The shape model describes the muscle's outer shape and has two parameters, an outer shape parameter and a fitting parameter. The former was determined by approximating of the outer shape of the muscle region in training cases. The latter was determined for each test case in the recognition process. (2) Finally, the psoas major muscle was segmented by use of the shape model. To evaluate the performance of the method, we applied it to CT images for constructing the shape models by using 20 cases as training samples; 80 cases were used for testing. The accuracy of this method was measured by comparison of the extracted muscle regions with regions that were identified manually by an expert radiologist. The experimental results of the segmentation of the psoas major muscle gave a mean Jaccard similarity coefficient of 72.3%. The mean true segmentation coefficient was 76.2%. The proposed method can be used for the analysis of cross-sectional area and muscular thickness in a transverse section, offering radiologists an alternative to manual measurement for saving their time and improving the reproducibility of segmentation.

show abstract

Segmentation of the temporalis muscle from MR data

Cited by 4 publications

References 21 publications

Deep learning-based quantification of temporalis muscle has prognostic value in patients with glioblastoma

Deep learning-based quantification of temporalis muscle has prognostic value in patients with glioblastoma

The Effect of Labeled/Unlabeled Prior Information for Masseter Segmentation

Automated segmentation of psoas major muscle in X-ray CT images by use of a shape model: preliminary study

Contact Info

Product

Resources

About