Abdominal muscle segmentation from CT using a convolutional neural network

Edwards, Ka'toria; Chhabra, Avneesh; Dormer, James D.; Jones, Phillip H.; Boutin, Robert D.; Lenchik, Leon; Fei, Baowei

doi:10.1117/12.2549406

Cited by 12 publications

(19 citation statements)

References 13 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, deep learning-based body composition segmentation at CT images was validated 29 – 31 and this technique could provide robust segmentation from noise 32 . In addition, deep learning also enables researchers to perform time-consuming process more easily 33 . We believe that utilization of deep learning-based technique can bring another breakthrough to body composition measurements.…”

Section: Discussionmentioning

confidence: 99%

Validation for measurements of skeletal muscle areas using low-dose chest computed tomography

Lim

Park

2022

Sci Rep

View full text Add to dashboard Cite

Various methods were suggested to measure skeletal muscle areas (SMAs) using chest low-dose computed tomography (chest LDCT) as a substitute for SMA at 3rd lumbar vertebra level (L3-SMA). In this study, four SMAs (L1-SMA, T12-erector spinae muscle areas, chest wall muscle area at carina level, pectoralis muscle area at aortic arch level) were segmented semi-automatically in 780 individuals taking concurrent chest and abdomen LDCT for healthcare screening. Four SMAs were compared to L3-SMA and annual changes were calculated from individuals with multiple examinations (n = 101). Skeletal muscle index (SMI; SMA/height2) cut-off for sarcopenia was determined by lower 5th percentile of young individuals (age ≤ 40 years). L1-SMA showed the greatest correlation to L3-SMA (men, R2 = 0.7920; women, R2 = 0.7396), and the smallest annual changes (0.3300 ± 4.7365%) among four SMAs. L1-SMI cut-offs for determining sarcopenia were 39.2cm2/m2 in men, and 27.5cm2/m2 in women. Forty-six men (9.5%) and ten women (3.4%) were found to have sarcopenia using L1-SMI cut-offs. In conclusion, L1-SMA could be a reasonable substitute for L3-SMA in chest LDCT. Suggested L1-SMI cut-offs for sarcopenia were 39.2cm2/m2 for men and 27.5cm2/m2 for women in Asian.

show abstract

Section: Discussionmentioning

confidence: 99%

Validation for measurements of skeletal muscle areas using low-dose chest computed tomography

Lim

Park

2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…both used a VGG‐16 27 pre‐trained on ImageNet, a large‐scale natural image data set comprising over 14 million images belonging to 1000 categories, 28 to initialize the encoder in an FCN or U‐Net architecture, respectively. Although the authors train their models on much smaller data sets (250 and 160 axial CT slices, respectively) compared to those discussed previously, 18,20,21 we believe that further research surrounding optimization of the transfer learning procedure will allow much smaller training set sizes and in consequence, more adaptable models.…”

Section: Introductionmentioning

confidence: 97%

Transfer learning for data‐efficient abdominal muscle segmentation with convolutional neural networks

et al. 2022

View full text Add to dashboard Cite

Background: Skeletal muscle segmentation is an important procedure for assessing sarcopenia, an emerging imaging biomarker of patient frailty. Data annotation remains the bottleneck for training deep learning auto-segmentation models. Purpose: There is a need to define methodologies for applying models to different domains (e.g., anatomical regions or imaging modalities) without dramatically increasing data annotation. Methods: To address this problem, we empirically evaluate the generalizability of various source tasks for transfer learning: natural image classification, natural image segmentation, unsupervised image reconstruction, and self -supervised jigsaw solving. Axial CT slices at L3 were extracted from PET-CT scans for 204 oesophago-gastric cancer patients and the skeletal muscle manually delineated by an expert. Features were transferred and segmentation models trained on subsets (n = 5, 10, 25, 50, 75, 100, 125) of the manually annotated training set. Four-fold cross-validation was performed to evaluate model generalizability. Human-level performance was established by performing an inter-observer study consisting of ten trained radiographers. Results: We find that accurate segmentation models can be trained on a fraction of the data required by current approaches. The Dice similarity coefficient and root mean square distance-to-agreement were calculated for each prediction and used to assess model performance. Models pre-trained on a segmentation task and fine-tuned on 10 images produce delineations that are comparable to those from trained observers and extract reliable measures of muscle health. Conclusions: Appropriate transfer learning can generate convolutional neural networks for abdominal muscle segmentation that achieve human-level performance while decreasing the required data by an order of magnitude, compared to previous methods (n = 160 → 10). This work enables the development of future models for assessing skeletal muscle at other anatomical sites where large annotated data sets are scarce and clinical needs are yet to be addressed.

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%

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

Abdominal muscle segmentation from CT using a convolutional neural network

Cited by 12 publications

References 13 publications

Validation for measurements of skeletal muscle areas using low-dose chest computed tomography

Validation for measurements of skeletal muscle areas using low-dose chest computed tomography

Transfer learning for data‐efficient abdominal muscle segmentation with convolutional neural networks

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

Contact Info

Product

Resources

About