Automated body composition analysis of clinically acquired computed tomography scans using neural networks

Paris, Michael T.; Tandon, Puneeta; Heyland, Daren K.; Furberg, Helena; Premji, Tahira; Low, Gavin; Mourtzakis, Marina

doi:10.1016/j.clnu.2020.01.008

Cited by 79 publications

(79 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AI-based method for automated segmentation of SAT and muscle showed a high accuracy when compared to manual segmentations on a CT slice at the L3 level, with a Sørensen-Dice index of 0.96 and 0.94, respectively. These results are comparable to previous published data [12][13][14][15][16]. The reproducibility was, as expected, significantly better for 3D volumes compared to 2D area measurements.…”

Section: Discussionsupporting

confidence: 91%

“…In the field of artificial intelligence (AI), deep learning methods offer new possibilities for automated analysis of medical images. Recently AI-based methods for automated analysis of body composition on CT images have been presented [12][13][14][15][16]. These methods are, however, trained to segment muscle and fat on single CT slices and not using the whole 3D volume.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence-aided CT segmentation for body composition analysis: a validation study

et al. 2021

View full text Add to dashboard Cite

Background Body composition is associated with survival outcome in oncological patients, but it is not routinely calculated. Manual segmentation of subcutaneous adipose tissue (SAT) and muscle is time-consuming and therefore limited to a single CT slice. Our goal was to develop an artificial-intelligence (AI)-based method for automated quantification of three-dimensional SAT and muscle volumes from CT images. Methods Ethical approvals from Gothenburg and Lund Universities were obtained. Convolutional neural networks were trained to segment SAT and muscle using manual segmentations on CT images from a training group of 50 patients. The method was applied to a separate test group of 74 cancer patients, who had two CT studies each with a median interval between the studies of 3 days. Manual segmentations in a single CT slice were used for comparison. The accuracy was measured as overlap between the automated and manual segmentations. Results The accuracy of the AI method was 0.96 for SAT and 0.94 for muscle. The average differences in volumes were significantly lower than the corresponding differences in areas in a single CT slice: 1.8% versus 5.0% (p < 0.001) for SAT and 1.9% versus 3.9% (p < 0.001) for muscle. The 95% confidence intervals for predicted volumes in an individual subject from the corresponding single CT slice areas were in the order of ± 20%. Conclusions The AI-based tool for quantification of SAT and muscle volumes showed high accuracy and reproducibility and provided a body composition analysis that is more relevant than manual analysis of a single CT slice.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-aided CT segmentation for body composition analysis: a validation study

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Other studies approached the automated segmentation of muscle, VAT and SAT within the L3 vertebra region in a variety of ways, also including deep learning. These reported DSC ranged from 0.85–0.99 [ 16 , 17 , 18 , 19 , 37 ]; however, good comparisons between those studies cannot be made due to the use of similar patient cohorts in development and accuracy testing and restrictive sample sizes. These models were able to extract semantic information, overall muscle shape and adipose tissue; nevertheless, these studies analyzed computed tomography scans, which were made in a controlled (non-trauma) setting [ 16 , 17 , 38 ].…”

Section: Discussionmentioning

confidence: 99%

“…For example, recent studies showed improved and accurate body composition on CT [ 14 , 15 ]. For muscle mass measurement, recent studies created and validated automated segmentation of the abdominal muscle on manually extracted CT-image at the L3 level [ 16 , 17 , 18 , 19 ]. These studies, including patients with varying medical conditions, showed detailed information regarding severity of sarcopenia.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Automated Segmentation for Muscle and Adipose Tissue from Abdominal Computed Tomography in Polytrauma Patients

Ackermans

Volmer

Wee

et al. 2021

Sensors

View full text Add to dashboard Cite

Manual segmentation of muscle and adipose compartments from computed tomography (CT) axial images is a potential bottleneck in early rapid detection and quantification of sarcopenia. A prototype deep learning neural network was trained on a multi-center collection of 3413 abdominal cancer surgery subjects to automatically segment truncal muscle, subcutaneous adipose tissue and visceral adipose tissue at the L3 lumbar vertebral level. Segmentations were externally tested on 233 polytrauma subjects. Although after severe trauma abdominal CT scans are quickly and robustly delivered, with often motion or scatter artefacts, incomplete vertebral bodies or arms that influence image quality, the concordance was generally very good for the body composition indices of Skeletal Muscle Radiation Attenuation (SMRA) (Concordance Correlation Coefficient (CCC) = 0.92), Visceral Adipose Tissue index (VATI) (CCC = 0.99) and Subcutaneous Adipose Tissue Index (SATI) (CCC = 0.99). In conclusion, this article showed an automated and accurate segmentation system to segment the cross-sectional muscle and adipose area L3 lumbar spine level on abdominal CT. Future perspectives will include fine-tuning the algorithm and minimizing the outliers.

show abstract

“…In particular, deep learning has been shown to be particularly well suited to segmentation tasks (14,15). Previous work has demonstrated high accuracy deep learning segmentation in skeletal muscle of diagnostic quality CT scans acquired for a range of cancer and non-cancer indications (16)(17)(18). Positron Emission Tomography PET/CT studies are standard of care in staging and surveillance for a range of cancers (19)(20)(21), and are typically whole body acquisitions therefore are well suited for measurement of L3 skeletal muscle area.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Model to Automate Skeletal Muscle Area Measurement on Computed Tomography Images

et al. 2021

View full text Add to dashboard Cite

BackgroundMuscle wasting (Sarcopenia) is associated with poor outcomes in cancer patients. Early identification of sarcopenia can facilitate nutritional and exercise intervention. Cross-sectional skeletal muscle (SM) area at the third lumbar vertebra (L3) slice of a computed tomography (CT) image is increasingly used to assess body composition and calculate SM index (SMI), a validated surrogate marker for sarcopenia in cancer. Manual segmentation of SM requires multiple steps, which limits use in routine clinical practice. This project aims to develop an automatic method to segment L3 muscle in CT scans.MethodsAttenuation correction CTs from full body PET-CT scans from patients enrolled in two prospective trials were used. The training set consisted of 66 non-small cell lung cancer (NSCLC) patients who underwent curative intent radiotherapy. An additional 42 NSCLC patients prescribed curative intent chemo-radiotherapy from a second trial were used for testing. Each patient had multiple CT scans taken at different time points prior to and post- treatment (147 CTs in the training and validation set and 116 CTs in the independent testing set). Skeletal muscle at L3 vertebra was manually segmented by two observers, according to the Alberta protocol to serve as ground truth labels. This included 40 images segmented by both observers to measure inter-observer variation. An ensemble of 2.5D fully convolutional neural networks (U-Nets) was used to perform the segmentation. The final layer of U-Net produced the binary classification of the pixels into muscle and non-muscle area. The model performance was calculated using Dice score and absolute percentage error (APE) in skeletal muscle area between manual and automated contours.ResultsWe trained five 2.5D U-Nets using 5-fold cross validation and used them to predict the contours in the testing set. The model achieved a mean Dice score of 0.92 and an APE of 3.1% on the independent testing set. This was similar to inter-observer variation of 0.96 and 2.9% for mean Dice and APE respectively. We further quantified the performance of sarcopenia classification using computer generated skeletal muscle area. To meet a clinical diagnosis of sarcopenia based on Alberta protocol the model achieved a sensitivity of 84% and a specificity of 95%.ConclusionsThis work demonstrates an automated method for accurate and reproducible segmentation of skeletal muscle area at L3. This is an efficient tool for large scale or routine computation of skeletal muscle area in cancer patients which may have applications on low quality CTs acquired as part of PET/CT studies for staging and surveillance of patients with cancer.

show abstract

Automated body composition analysis of clinically acquired computed tomography scans using neural networks

Cited by 79 publications

References 47 publications

Artificial intelligence-aided CT segmentation for body composition analysis: a validation study

Artificial intelligence-aided CT segmentation for body composition analysis: a validation study

Deep Learning Automated Segmentation for Muscle and Adipose Tissue from Abdominal Computed Tomography in Polytrauma Patients

A Deep Learning Model to Automate Skeletal Muscle Area Measurement on Computed Tomography Images

Contact Info

Product

Resources

About