Artificial intelligence to assess body composition on routine abdominal CT scans and predict mortality in pancreatic cancer– A recipe for your local application

Hsu, Tzu-Ming Harry; Schawkat, Khoschy; Berkowitz, Scott A.; Wei, Jesse; Makoyeva, Alina; Legare, Kaila; Decicco, Corinne; Paez, S. Nicolas; Wu, Jim S.; Szolovits, Peter; Kikinis, Ron; Moser, A. James; Goehler, Alexander

doi:10.1016/j.ejrad.2021.109834

Cited by 33 publications

(19 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hsu et al present a general approach for using artificial intelligence-based methods applied to routine abdominal CT scans to assess body composition (17). They used a network pre-trained on the LiTS data challenge (18) and designed a fully automated approach to measure fat and muscle masses.…”

Section: Discussionmentioning

confidence: 99%

Deep-learning-based Segmentation of Skeletal Muscle Mass in Routine Abdominal CT Scans

Kreher

Hinnerichs

Preim

et al. 2022

In Vivo

View full text Add to dashboard Cite

Background: For prediction of many types of clinical outcome, the skeletal muscle mass can be used as an independent biomarker. Manual segmentation of the skeletal muscles is time-consuming, therefore we present a deeplearning-based approach for the identification of muscle mass at the L3 level in clinical routine computed tomographic (CT) data. Patients and Methods: We conducted a retrospective study of 130 patient datasets. Individual CT slice analysis at the L3 level was fed into a U-Net architecture. As a result, we obtained segmentations of the musculus rectus abdominis, abdominal wall muscles, musculus psoas major, musculus quadratus lumborum and musculus erector spinae in the CTslice at the L3 level. Results: The Dice score was 0.95±0.02, 0.86±0.12, 0.93±0.05, 0.92±0.05, 0.86±0.08 for the erector spine, rectus, abdominal wall, psoas and quadratus lumborum muscles, respectively. For the overall skeletal muscle mass, the test data achieved a Dice score of 0.95±0.03. Conclusion: Our network achieved Dice scores larger than 0.86 for each of the five different muscle types and 0.95 for the overall skeletal muscle mass. The subdivision of muscle types can serve as a basis for obtaining future biomarkers. Our network is publicly available so that it might be beneficial for others to improve the clinical workflow within examination of routine CT scans.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep-learning-based Segmentation of Skeletal Muscle Mass in Routine Abdominal CT Scans

Kreher

Hinnerichs

Preim

et al. 2022

In Vivo

View full text Add to dashboard Cite

show abstract

“…12 Several studies have shown promising results using deep learning-based methods for quantification of abdominal SM or adipose tissues. [13][14][15][16][17][18][19][20][21][22][23][24][25][26] As CNNs require large amounts of data, it is common to use multiple available data sets for training purposes. However, no software is trained and tested on CT slices from different anatomical levels acquired from CRC patients.…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies typically rely on single slices at L3. 13,16,17,[19][20][21]26 This may limit the usefulness of these models as clinically acquired CT scans differ according to the protocol used or the region of interest.…”

Section: Introductionmentioning

confidence: 99%

“…In particular, convolutional neural networks (CNNs), directly inspired by brain neurons, are well fitted to process large amounts of imaging data 12 . Several studies have shown promising results using deep learning‐based methods for quantification of abdominal SM or adipose tissues 13–26 . As CNNs require large amounts of data, it is common to use multiple available data sets for training purposes.…”

Section: Introductionmentioning

confidence: 99%

“…However, no software is trained and tested on CT slices from different anatomical levels acquired from CRC patients. Previous studies typically rely on single slices at L3 13,16,17,19–21,26 . This may limit the usefulness of these models as clinically acquired CT scans differ according to the protocol used or the region of interest.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Body composition assessment by artificial intelligence from routine computed tomography scans in colorectal cancer: Introducing BodySegAI

Alavi

Sakinis

Henriksen

et al. 2022

JCSM Clinical Reports

View full text Add to dashboard Cite

Background Body composition is of clinical importance in colorectal cancer patients, but is rarely assessed because of time-consuming manual segmentation. We developed and tested BodySegAI, a deep learning-based software for automated body composition quantification from routinely acquired computed tomography (CT) scans. Methods A two-dimensional U-Net convolutional network was trained on 2989 abdominal CT slices from L2 to S1 to segment skeletal muscle (SM), visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT), and intermuscular and intramuscular adipose tissue (IMAT). Human ground truth was established by combining segmentations from three human readers. BodySegAI was tested using 154 slices against the human ground truth and compared with a software named AutoMATiCA. Results Median Dice scores for BodySegAI against human ground truth were 0.969, 0.814, 0.986, and 0.990 for SM, IMAT, VAT, and SAT, respectively. The mean differences per slice for SM were À0.09 cm 3 , IMAT: À0.17 cm 3 , VAT: À0.12 cm 3 , and SAT: 0.67 cm 3 . Median absolute errors for SM, IMAT, VAT, and SAT were 1.35, 10.54, 0.91, and 1.07%, respectively. When analysing different anatomical levels separately, L3 and S1 demonstrated the overall highest and lowest Dice scores, respectively. On average, BodySegAI segmented 148 times faster than human readers (4.9 vs. 726.5 seconds, P < 0.001). Also, BodySegAI presented higher Dice scores for SM, IMAT, SAT, and VAT than AutoMATiCA (slices = 154). Conclusions BodySegAI rapidly generates excellent segmentation of SM, VAT, and SAT and good segmentation of IMAT in L2 to S1 among colorectal cancer patients and may replace semi-manual segmentation.

show abstract

Body composition parameters in initial CT imaging of mechanically ventilated trauma patients: Single‐centre observational study

Meyer,

Dermendzhiev,

Hetz

et al. 2024

J cachexia sarcopenia muscle

View full text Add to dashboard Cite

BackgroundBody composition parameters provide relevant prognostic significance in critical care cohorts and cancer populations. Published results regarding polytrauma patients are inconclusive to date. The goal of this study was to analyse the role of body composition parameters in severely injured trauma patients.MethodsAll consecutive patients requiring emergency tracheal intubation and mechanical ventilation before initial computed tomography (CT) at a level‐1 trauma centre over a 12‐year period (2008–2019) were reanalysed. The analysis included CT‐derived body composition parameters based upon whole‐body trauma CT as prognostic variables for 30‐day mortality, intensive care unit length of stay (ICU LOS) and mechanical ventilation duration.ResultsFour hundred seventy‐two patients (75% male) with a median age of 49 years, median injury severity score of 26 and 30‐day mortality rate of 22% (104 patients) met the inclusion criteria and were analysed. Regarding body composition parameters, 231 patients (49%) had visceral obesity, 75 patients had sarcopenia (16%) and 35 patients had sarcopenic obesity (7.4%). After adjustment for statistically significant univariable predictors age, body mass index, sarcopenic obesity, visceral obesity, American Society of Anesthesiologists classification ≥3, injury severity score and Glasgow Coma Scale ≤ 8 points, the Cox proportional hazard model identified sarcopenia as significant prognostic factor of 30‐day mortality (hazard ratio 2.84; 95% confidence interval 1.38–5.85; P = 0.004), which was confirmed in Kaplan–Meier survival analysis (log‐rank P = 0.006). In a subanalysis of 363 survivors, linear multivariable regression analysis revealed no significant associations of body composition parameters with ICU LOS and duration of mechanical ventilation.ConclusionsIn a multivariable analysis of mechanically ventilated trauma patients, CT‐defined sarcopenia was significantly associated with 30‐day mortality whereas no associations of body composition parameters with ICU LOS and duration of mechanical ventilation were observed.

show abstract

Artificial intelligence to assess body composition on routine abdominal CT scans and predict mortality in pancreatic cancer– A recipe for your local application

Cited by 33 publications

References 22 publications

Deep-learning-based Segmentation of Skeletal Muscle Mass in Routine Abdominal CT Scans

Deep-learning-based Segmentation of Skeletal Muscle Mass in Routine Abdominal CT Scans

Body composition assessment by artificial intelligence from routine computed tomography scans in colorectal cancer: Introducing BodySegAI

Body composition parameters in initial CT imaging of mechanically ventilated trauma patients: Single‐centre observational study

Contact Info

Product

Resources

About