Deep Learning-based Quantification of Abdominal Subcutaneous and Visceral Fat Volume on CT Images

Grainger, Andrew T.; Krishnaraj, Arun; Quinones, Michael H.; Tustison, Nicholas J.; Epstein, Susan L.; Fuller, Daniela; Jha, Aakash; Allman, Kevin L.; Shi, Weibin

doi:10.1016/j.acra.2020.07.010

Cited by 26 publications

(24 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pickhardt et al ( Kalinkovich and Livshits, 2017 ) developed an automated CT-based algorithm with pre-defined metrics for quantifying aortic calcification, muscle density, and visceral/subcutaneous fat for cancer screening. ( Grainger et al (2021) developed a deep learning-based algorithm using the U-NET architecture to measure abdominal fat on CT images.…”

Section: Introductionmentioning

confidence: 99%

Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

Wang

Han

et al. 2023

Front. Physiol.

View full text Add to dashboard Cite

Background: Sarcopenia is an aging syndrome that increases the risks of various adverse outcomes, including falls, fractures, physical disability, and death. Sarcopenia can be diagnosed through medical images-based body part analysis, which requires laborious and time-consuming outlining of irregular contours of abdominal body parts. Therefore, it is critical to develop an efficient computational method for automatically segmenting body parts and predicting diseases.Methods: In this study, we designed an Artificial Intelligence Body Part Measure System (AIBMS) based on deep learning to automate body parts segmentation from abdominal CT scans and quantification of body part areas and volumes. The system was developed using three network models, including SEG-NET, U-NET, and Attention U-NET, and trained on abdominal CT plain scan data.Results: This segmentation model was evaluated using multi-device developmental and independent test datasets and demonstrated a high level of accuracy with over 0.9 DSC score in segment body parts. Based on the characteristics of the three network models, we gave recommendations for the appropriate model selection in various clinical scenarios. We constructed a sarcopenia classification model based on cutoff values (Auto SMI model), which demonstrated high accuracy in predicting sarcopenia with an AUC of 0.874. We used Youden index to optimize the Auto SMI model and found a better threshold of 40.69.Conclusion: We developed an AI system to segment body parts in abdominal CT images and constructed a model based on cutoff value to achieve the prediction of sarcopenia with high accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

Wang

Han

et al. 2023

Front. Physiol.

View full text Add to dashboard Cite

show abstract

“…However, in clinical practice, these factors are unavoidable, so we need to develop a more comprehensive clinical prediction model. Fourth, the development of imaging technologies, such as CT, three-dimensional (3D) imaging volumetric analyses and MRI, will be more accurate for the calculation of abdominal subcutaneous fat, and the application of big data, arti cial intelligence and deep machine learning will be bene cial to lipid absorption prediction (41)(42)(43)(44).…”

Section: Discussionmentioning

confidence: 99%

Association Between Anthropometric Measurements and the Amount of Fat Aspirated in Waist and Abdominal Liposuction: A 20-year Retrospective Study

Yang

Dou

Peng

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Previous studies revealed that larger liposuction volumes were related to an increased risk of complications. However, no concrete data exist to support the most critical factor which affects the liposuction volume in the waist and abdominal area. This study was undertaken to investigate the relationship between the anthropometric measurements and lipoaspirate volume.Methods: The present study was a single-center retrospective study. 742 patients who met the inclusion and exclusion criteria in our hospital, from January 2001 to August 2020, were reviewed. Spearman correlation analyses and multivariable regressions were used to assess the relationship between the anthropometric measurements and lipoaspirate volume. Linear-by-linear association chi-square statistic and Goodman-Kruskal gamma method were used to test the consistency and to develop a rank prediction formula.Results: A total of 742 patients aged 18-59 years old met the inclusion criteria. Among all the anthropometric measurements, the highest correlation coefficient was observed in waist circumference. Subgroup analyses indicated that there was an interaction between the BMI and waist circumference on liposuction volume. Formula was generated to estimate the range of liposuction volume based on the nine grouped waist circumferences [liposuction volume (mean) = 106.3 waist circumference (mean) - 7497, P < 0.001, adjusted R2 = 0.9638].Conclusions: Waist circumference was the most influential factor for lipoaspirate volume. Roughly predicting the lipoaspirate volume allows surgeons to estimate their operating volume even if no iconography machine is available during suction-assisted lipectomy. This can increase safety, potentially decreasing the number of adverse events.

show abstract

“…Lemak ini dapat menyebabkan resistensi insulin, walau pasien tersebut sebelumnya belum pernah menderita diabetes atau prediabetes. Lemak visceral (PPN) didefinisikan sebagai lemak di dalam rongga perut (Grainger et al, 2021). Studi memperkirakan, resistensi insulin tersebut disebabkan oleh protein pengikat retinol yang dilepaskan lemak viseral.…”

Section: Pendahuluanunclassified

Segmentasi Lemak Visceral dan Kanker Paru-paru Menggunakan Deep Learning

et al. 2022

View full text Add to dashboard Cite

Lemak Visceral memberikan dampak yang sangat besar terhadap beberapa penyakit dan salah satunya Kanker paru-paru penyebab utama kematian, Kondisi ini memberikan pengaruh besar dalam dunia kesehatan terhadap permasalahan Lemak visceral dan kanker paru-paru Computer vision menghembalangkan penelitian dari permasalahan yang besar ini computer vision ingin melihat keakuratan penelitian, dengan dataset yang telah di tentukan dengan ini peneliti menggunakan metode deep learning dan di dukung dengan metode Segmentasi-CNN, Segmentation & VFI Calculation. Metode tersebut mampu menampilkan gambar yang tersegmentasi dengan detail dari mengubah warna satu dimensi dan dua dimensi sehingga akan memberikan keakuratan segmentasi, lemak yang telah tersegmentasi daerah gambar lemak dan garis tepinya pada Lemak visceral dan kanker paru-paru memisahkan lemak dan kanker dengan jumlah pixel putih lemak lemah dengan ration area akurat dan Memiliki pixel yang tinggi dan tepat dalam pemrosesan pixel.

show abstract

Deep Learning-based Quantification of Abdominal Subcutaneous and Visceral Fat Volume on CT Images

Cited by 26 publications

References 23 publications

Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

Association Between Anthropometric Measurements and the Amount of Fat Aspirated in Waist and Abdominal Liposuction: A 20-year Retrospective Study

Segmentasi Lemak Visceral dan Kanker Paru-paru Menggunakan Deep Learning

Contact Info

Product

Resources

About