Unsupervised quantification of abdominal fat from CT images using Greedy Snakes

Agarwal, Chirag; Dallal, Ahmed; Arbabshirani, Mohammad R.; Patel, Aalpen A.; Moore, Gregory J.

doi:10.1117/12.2254139

Cited by 10 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Older methods utilize classical image processing and binary morphological operations [23][24][25] in order to isolate the SAT and VAT from total adipose tissue (TAT). Other studies use prior knowledge about contours and shapes and actively fit a contour or template to a given CT image [26][27][28][29][30]. Those methods are prone to variations in intensity values and assume certain body structures for algorithmic separation between SAT and VAT.…”

Section: Discussionmentioning

confidence: 99%

Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks

et al. 2020

View full text Add to dashboard Cite

Objectives Body tissue composition is a long-known biomarker with high diagnostic and prognostic value not only in cardiovascular, oncological, and orthopedic diseases but also in rehabilitation medicine or drug dosage. In this study, the aim was to develop a fully automated, reproducible, and quantitative 3D volumetry of body tissue composition from standard CT examinations of the abdomen in order to be able to offer such valuable biomarkers as part of routine clinical imaging. Methods Therefore, an in-house dataset of 40 CTs for training and 10 CTs for testing were fully annotated on every fifth axial slice with five different semantic body regions: abdominal cavity, bones, muscle, subcutaneous tissue, and thoracic cavity. Multi-resolution U-Net 3D neural networks were employed for segmenting these body regions, followed by subclassifying adipose tissue and muscle using known Hounsfield unit limits. Results The Sørensen Dice scores averaged over all semantic regions was 0.9553 and the intra-class correlation coefficients for subclassified tissues were above 0.99. Conclusions Our results show that fully automated body composition analysis on routine CT imaging can provide stable biomarkers across the whole abdomen and not just on L3 slices, which is historically the reference location for analyzing body composition in the clinical routine. Key Points • Our study enables fully automated body composition analysis on routine abdomen CT scans. • The best segmentation models for semantic body region segmentation achieved an averaged Sørensen Dice score of 0.9553. • Subclassified tissue volumes achieved intra-class correlation coefficients over 0.99.

show abstract

Section: Discussionmentioning

confidence: 99%

Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The main barrier for adoption of CT body composition analysis into clinical practice is the lack of accurate fully automated segmentation techniques. Several fully automated techniques have been proposed in the last decade, including threshold-based approaches (10-15) and atlas-based approaches (16)(17)(18)(19); however, the heterogeneous appearance of the abdomen, such as the thin muscle wall, or the similar intensity of gastrointestinal contents to adipose tissue makes this a challenging task.…”

Section: Discussionmentioning

confidence: 99%

“…Several fully automated segmentation methods to assess body composition using CT examinations have been proposed; however, limitations of traditional image-processing techniques and the complexity of abdominal imaging have prevented widespread use. Adipose tissue is primarily identified with threshold-based techniques (10)(11)(12)(13)(14)(15), and atlasbased techniques are used to isolate the abdominal muscles (16)(17)(18)(19). However, anatomic variability in the abdomen poses a substantial challenge to automated segmentation, and manual correction is almost always required.…”

mentioning

confidence: 99%

Automated Abdominal Segmentation of CT Scans for Body Composition Analysis Using Deep Learning

et al. 2019

View full text Add to dashboard Cite

To develop and evaluate a fully automated algorithm for segmenting the abdomen from CT to quantify body composition. Materials and Methods: For this retrospective study, a convolutional neural network based on the U-Net architecture was trained to perform abdominal segmentation on a data set of 2430 two-dimensional CT examinations and was tested on 270 CT examinations. It was further tested on a separate data set of 2369 patients with hepatocellular carcinoma (HCC). CT examinations were performed between 1997 and 2015. The mean age of patients was 67 years; for male patients, it was 67 years (range, 29-94 years), and for female patients, it was 66 years (range, 31-97 years). Differences in segmentation performance were assessed by using twoway analysis of variance with Bonferroni correction. Results: Compared with reference segmentation, the model for this study achieved Dice scores (mean 6 standard deviation) of 0.98 6 0.03, 0.96 6 0.02, and 0.97 6 0.01 in the test set, and 0.94 6 0.05, 0.92 6 0.04, and 0.98 6 0.02 in the HCC data set, for the subcutaneous, muscle, and visceral adipose tissue compartments, respectively. Performance met or exceeded that of expert manual segmentation. Conclusion: Model performance met or exceeded the accuracy of expert manual segmentation of CT examinations for both the test data set and the hepatocellular carcinoma data set. The model generalized well to multiple levels of the abdomen and may be capable of fully automated quantification of body composition metrics in three-dimensional CT examinations.

show abstract

“…Our previous work [ 23 ] describes the algorithm in great detail; here, we just briefly review the main steps. We formulated automatic fat quantification as an unsupervised contour minimization problem.…”

Section: Methodsmentioning

confidence: 99%

“…We also calculated visceral-to-subcutaneous fat ratios (VSRs) and visceral-to-total fat ratios (VTRs) using VAT and SAT. This algorithm identified TAT, VAT, and SAT segmentations with 0.885%, 3.55%, and 3.26% average error, respectively, as compared to a manual segmentation [ 23 ].…”

Section: Methodsmentioning

confidence: 99%

Using Adipose Measures from Health Care Provider-Based Imaging Data for Discovery

et al. 2018

Self Cite

View full text Add to dashboard Cite

The location and type of adipose tissue is an important factor in metabolic syndrome. A database of picture archiving and communication system (PACS) derived abdominal computerized tomography (CT) images from a large health care provider, Geisinger, was used for large-scale research of the relationship of volume of subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT) with obesity-related diseases and clinical laboratory measures. Using a “greedy snake” algorithm and 2,545 CT images from the Geisinger PACS, we measured levels of VAT, SAT, total adipose tissue (TAT), and adipose ratio volumes. Sex-combined and sex-stratified association testing was done between adipose measures and 1,233 disease diagnoses and 37 clinical laboratory measures. A genome-wide association study (GWAS) for adipose measures was also performed. SAT was strongly associated with obesity and morbid obesity. VAT levels were strongly associated with type 2 diabetes-related diagnoses (p = 1.5 × 10−58), obstructive sleep apnea (p = 7.7 × 10−37), high-density lipoprotein (HDL) levels (p = 1.42 × 10−36), triglyceride levels (p = 1.44 × 10−43), and white blood cell (WBC) counts (p = 7.37 × 10−9). Sex-stratified tests revealed stronger associations among women, indicating the increased influence of VAT on obesity-related disease outcomes particularly among women. The GWAS identified some suggestive associations. This study supports the utility of pursuing future clinical and genetic discoveries with existing imaging data-derived adipose tissue measures deployed at a larger scale.

show abstract

Unsupervised quantification of abdominal fat from CT images using Greedy Snakes

Cited by 10 publications

References 9 publications

Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks

Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks

Automated Abdominal Segmentation of CT Scans for Body Composition Analysis Using Deep Learning

Using Adipose Measures from Health Care Provider-Based Imaging Data for Discovery

Contact Info

Product

Resources

About