Automated and accurate quantification of subcutaneous and visceral adipose tissue from magnetic resonance imaging based on machine learning

AATCT-IDS: A benchmark Abdominal Adipose Tissue CT Image Dataset for image denoising, semantic segmentation, and radiomics evaluation

BACKGROUND AND OBJECTIVE

The metabolic syndrome induced by obesity is closely associated with cardiovascular disease, and the prevalence is increasing globally, year by year. Obesity is a risk marker for detecting this disease. However, current research on computer-aided detection of adipose distribution is hampered by the lack of open-source large abdominal adipose datasets.

METHODS

In this study, a benchmark Abdominal Adipose Tissue CT Image Dataset (AATCT-IDS) containing 300 subjects is prepared and published. AATCT-IDS publics 13,732 raw CT slices, and the researchers individually annotate the subcutaneous and visceral adipose tissue regions of 3213 of those slices that have the same slice distance to validate denoising methods, train semantic segmentation models, and study radiomics. For different tasks, this paper compares and analyzes the performance of various methods on AATCT-IDS by combining the visualization results and evaluation data. Thus, verify the research potential of this data set in the above three types of tasks.

RESULTS

In the comparative study of image denoising, algorithms using a smoothing strategy suppress mixed noise at the expense of image details and obtain better evaluation data. Methods such as BM3D preserve the original image structure better, although the evaluation data are slightly lower. The results show significant differences among them. In the comparative study of semantic segmentation of abdominal adipose tissue, the segmentation results of adipose tissue by each model show different structural characteristics. Among them, BiSeNet obtains segmentation results only slightly inferior to U-Net with the shortest training time and effectively separates small and isolated adipose tissue. In addition, the radiomics study based on AATCT-IDS reveals three adipose distributions in the subject population.

CONCLUSION

AATCT-IDS contains the ground truth of adipose tissue regions in abdominal CT slices. This open-source dataset can attract researchers to explore the multi-dimensional characteristics of abdominal adipose tissue and thus help physicians and patients in clinical practice. AATCT-IDS is freely published for non-commercial purpose at: https://figshare.com/articles/dataset/AATTCT-IDS/23807256.

Automated abdominal adipose tissue segmentation and volume quantification on longitudinal MRI using 3D convolutional neural networks with multi-contrast inputs

OBJECTIVE

Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs.

MATERIALS AND METHODS

920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC).

RESULTS

ACD 3D U-Net achieved rapid (< 4.8 s/subject) segmentation with high DICE-SAT (median ≥ 0.994) and DICE-VAT (median ≥ 0.976), small FN (median ≤ 0.7%), and FP (median ≤ 1.1%). 3D nnU-Net yielded rapid (< 2.5 s/subject) segmentation with similar DICE-SAT (median ≥ 0.992), DICE-VAT (median ≥ 0.979), FN (median ≤ 1.1%) and FP (median ≤ 1.2%). Both models yielded excellent agreement in SAT/VAT volume versus reference measurements (ICC > 0.997) in longitudinal analysis.

DISCUSSION

ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.

Emergence of imaging technology beyond the clinical setting: Utilization of mobile health tools for at-home testing

Body composition assessment plays a pivotal role in understanding health, disease risk, and treatment efficacy. This narrative review explores two primary aspects: imaging techniques, namely ultrasound (US) and dual-energy x-ray absorptiometry (DXA), and the emergence of artificial intelligence (AI) and mobile health apps in telehealth for body composition. Although US is valuable for assessing subcutaneous fat and muscle thickness, DXA accurately quantifies bone mineral content, fat mass, and lean mass. Despite their effectiveness, accessibility and cost remain barriers to widespread adoption. The integration of AI-powered image analysis may help explain tissue differentiation, whereas mobile health apps offer real-time metabolic monitoring and personalized feedback. New apps such as MeThreeSixty and Made Health and Fitness offer the advantages of clinic-based imaging techniques from the comfort of home. These innovations hold the potential for individualizing strategies and interventions, optimizing clinical outcomes, and empowering informed decision-making for both healthcare professionals and patients/clients. Navigating the intricacies of these emerging tools, critically assessing their validity and reliability, and ensuring inclusivity across diverse populations and conditions will be crucial in harnessing their full potential. By integrating advancements in body composition assessment, healthcare can move beyond the limitations of traditional methods and deliver truly personalized, data-driven care to optimize well-being.

Lightweight convolutional neural network (CNN) model for obesity early detection using thermal images

Objective

The presence of a lightweight convolutional neural network (CNN) model with a high-accuracy rate and low complexity can be useful in building an early obesity detection system, especially on mobile-based applications. The previous works of the CNN model for obesity detection were focused on the accuracy performances without considering the complexity size. In this study, we aim to build a new lightweight CNN model that can accurately classify normal and obese thermograms with low complexity sizes.

Methods

The DenseNet201 CNN architectures were modified by replacing the standard convolution layers with multiple depthwise and pointwise convolution layers from the MobileNet architectures. Then, the depth network of the dense block was reduced to determine which depths were the most comparable to obtain minimum validation losses. The proposed model then was compared with state-of-the-art DenseNet and MobileNet CNN models in terms of classification performances, and complexity size, which is measured in model size and computation cost.

Results

The results of the testing experiment show that the proposed model has achieved an accuracy of 81.54% with a model size of 1.44 megabyte (MB). This accuracy was comparable to that of DenseNet, which was 83.08%. However, DenseNet's model size was 71.77 MB. On the other hand, the proposed model's accuracy was higher than that of MobileNetV2, which was 79.23%, with a computation cost of 0.69 billion floating-point operations per second (GFLOPS), which approximated that of MobileNetV2, which was 0.59 GFLOPS.

Conclusions

The proposed model inherited the feature-extracting ability from the DenseNet201 architecture while keeping the lightweight complexity characteristic of the MobileNet architecture.

Abdominal fat quantification using convolutional networks

OBJECTIVES

To present software for automated adipose tissue quantification of abdominal magnetic resonance imaging (MRI) data using fully convolutional networks (FCN) and to evaluate its overall performance-accuracy, reliability, processing effort, and time-in comparison with an interactive reference method.

MATERIALS AND METHODS

Single-center data of patients with obesity were analyzed retrospectively with institutional review board approval. Ground truth for subcutaneous (SAT) and visceral adipose tissue (VAT) segmentation was provided by semiautomated region-of-interest (ROI) histogram thresholding of 331 full abdominal image series. Automated analyses were implemented using UNet-based FCN architectures and data augmentation techniques. Cross-validation was performed on hold-out data using standard similarity and error measures.

RESULTS

The FCN models reached Dice coefficients of up to 0.954 for SAT and 0.889 for VAT segmentation during cross-validation. Volumetric SAT (VAT) assessment resulted in a Pearson correlation coefficient of 0.999 (0.997), relative bias of 0.7% (0.8%), and standard deviation of 1.2% (3.1%). Intraclass correlation (coefficient of variation) within the same cohort was 0.999 (1.4%) for SAT and 0.996 (3.1%) for VAT.

CONCLUSION

The presented methods for automated adipose-tissue quantification showed substantial improvements over common semiautomated approaches (no reader dependence, less effort) and thus provide a promising option for adipose tissue quantification.

CLINICAL RELEVANCE STATEMENT

Deep learning techniques will likely enable image-based body composition analyses on a routine basis. The presented fully convolutional network models are well suited for full abdominopelvic adipose tissue quantification in patients with obesity.

KEY POINTS

• This work compared the performance of different deep-learning approaches for adipose tissue quantification in patients with obesity. • Supervised deep learning-based methods using fully convolutional networks  were suited best. • Measures of accuracy were equal to or better than the operator-driven approach.

Automatic segmentation of large-scale CT image datasets for detailed body composition analysis

BACKGROUND

Body composition (BC) is an important factor in determining the risk of type 2-diabetes and cardiovascular disease. Computed tomography (CT) is a useful imaging technique for studying BC, however manual segmentation of CT images is time-consuming and subjective. The purpose of this study is to develop and evaluate fully automated segmentation techniques applicable to a 3-slice CT imaging protocol, consisting of single slices at the level of the liver, abdomen, and thigh, allowing detailed analysis of numerous tissues and organs.

METHODS

The study used more than 4000 CT subjects acquired from the large-scale SCAPIS and IGT cohort to train and evaluate four convolutional neural network based architectures: ResUNET, UNET++, Ghost-UNET, and the proposed Ghost-UNET++. The segmentation techniques were developed and evaluated for automated segmentation of the liver, spleen, skeletal muscle, bone marrow, cortical bone, and various adipose tissue depots, including visceral (VAT), intraperitoneal (IPAT), retroperitoneal (RPAT), subcutaneous (SAT), deep (DSAT), and superficial SAT (SSAT), as well as intermuscular adipose tissue (IMAT). The models were trained and validated for each target using tenfold cross-validation and test sets.

RESULTS

The Dice scores on cross validation in SCAPIS were: ResUNET 0.964 (0.909-0.996), UNET++ 0.981 (0.927-0.996), Ghost-UNET 0.961 (0.904-0.991), and Ghost-UNET++ 0.968 (0.910-0.994). All four models showed relatively strong results, however UNET++ had the best performance overall. Ghost-UNET++ performed competitively compared to UNET++ and showed a more computationally efficient approach.

CONCLUSION

Fully automated segmentation techniques can be successfully applied to a 3-slice CT imaging protocol to analyze multiple tissues and organs related to BC. The overall best performance was achieved by UNET++, against which Ghost-UNET++ showed competitive results based on a more computationally efficient approach. The use of fully automated segmentation methods can reduce analysis time and provide objective results in large-scale studies of BC.

Effect of orlistat during individualized comprehensive life-style intervention on visceral fat in overweight or obese PCOS patients

ObjectiveTo investigate the effect of orlistat combined with drospirenone/ethinylestradiol tablets (DRSP/EE) on the visceral fat area (VFA) compared to DRSP/EE-alone in overweight or obese patients with polycystic ovary syndrome (PCOS).Methods90 PCOS patients [body mass index (BMI) ≥24kg/m²] were recruited for a prospective, open-label, 1:2 paired 3-monthly study. All were included during the per-protocol defined recruitment time and numbered according to the entry-order: group-1: No.1-60, orlistat plus DRSP/EE; group-2: No.61-90, DRSP/EE-alone. Both groups received the same comprehensive intervention in terms of individualized, standardized management and lifestyle monitoring such as diet and exercise. Primary study-endpoint was VFA, secondary endpoints were anthropometric indices, sex hormones and glucolipid metabolism. Within- and between-group analyses were performed.ResultsVFA [cm²] in group-1 after treatment decreased significantly (p = 0.001), and the between-group comparison was highly significant (p = 0.001). Body weight, hip circumference (HC), BMI, body fat (BF), free testosterone (FT) and low-density lipoprotein-cholesterol (LDL-C) significantly decreased in both groups (within-group analysis); the decrease in group-1 was significantly greater than in group-2 (p < 0.05). Systolic and diastolic blood pressure (SBP/DBP) and fasting plasma glucose (FPG) in group-1 were significantly decreased, significantly more in group-1 than in group-2 (p < 0.05).ConclusionThis study is the first to investigate the effect of orlistat combined with DRSP/EE in overweight or obese PCOS patients compared with using DRSP/EE-alone. Orlistat combined with DRSP/EE was better than using DRSP/EE-alone in reducing VFA, body weight, FT, BP and FPG, which provides evidence for the choice of rational drug use in clinical practice.

A Novel Computational Framework for Precision Diagnosis and Subtype Discovery of Plant With Lesion

Plants are often attacked by various pathogens during their growth, which may cause environmental pollution, food shortages, or economic losses in a certain area. Integration of high throughput phenomics data and computer vision (CV) provides a great opportunity to realize plant disease diagnosis in the early stage and uncover the subtype or stage patterns in the disease progression. In this study, we proposed a novel computational framework for plant disease identification and subtype discovery through a deep-embedding image-clustering strategy, Weighted Distance Metric and the t-stochastic neighbor embedding algorithm (WDM-tSNE). To verify the effectiveness, we applied our method on four public datasets of images. The results demonstrated that the newly developed tool is capable of identifying the plant disease and further uncover the underlying subtypes associated with pathogenic resistance. In summary, the current framework provides great clustering performance for the root or leave images of diseased plants with pronounced disease spots or symptoms.

Quantification of lumbar vertebral fat deposition: Correlation with menopausal status, non-alcoholic fatty liver disease and subcutaneous adipose tissue

PURPOSE

To assess abdominal fat deposition and lumbar vertebra with iterative decomposition of water and fat with echo asymmetry and least-squares estimation (IDEAL-IQ) and investigate their correlation with menopausal status.

MATERIALS AND METHODS

Two hundred forty women who underwent routine abdominal MRI and IDEAL-IQ between January 2016 and April 2021 were divided into two cohorts (first cohort: 120 pre- or postmenopausal women with severe fatty livers or without fatty livers; second cohort: 120 pre- or postmenopausal women who were obese or normal weight). The fat fraction (FF) values of the liver (FF_liver) and lumbar vertebra (FF_lumbar) in the first group and the FF values of subcutaneous adipose tissue (SAT) (FF_SAT) and FF_lumbar in the second group were measured and compared using IDEAL-IQ.

RESULTS

Two hundred forty women were evaluated. FF_lumbar was significantly higher in both pre- and postmenopausal women with severe fatty liver than in patients without fatty livers (premenopausal women: p < 0.001, postmenopausal women: p < 0.001). No significant difference in the FF_lumbar was observed between obese patients and normal-weight patients among pre- and postmenopausal women (premenopausal women: p = 0.113, postmenopausal women: p = 0.092). Significantly greater lumbar fat deposition was observed in postmenopausal women than in premenopausal women with or without fatty liver and obesity (p < 0.001 for each group). A high correlation was detected between FF_liver and FF_lumbar in women with severe fatty liver (premenopausal women: r=0.76, p<0.01; postmenopausal women: r=0.82, p<0.01).

CONCLUSION

Fat deposition in the vertebral marrow was significantly associated with liver fat deposition in postmenopausal women.

3D Neural Networks for Visceral and Subcutaneous Adipose Tissue Segmentation using Volumetric Multi-Contrast MRI

Individuals with obesity have larger amounts of visceral (VAT) and subcutaneous adipose tissue (SAT) in their body, increasing the risk for cardiometabolic diseases. The reference standard to quantify SAT and VAT uses manual annotations of magnetic resonance images (MRI), which requires expert knowledge and is time-consuming. Although there have been studies investigating deep learning-based methods for automated SAT and VAT segmentation, the performance for VAT remains suboptimal (Dice scores of 0.43 to 0.89). Previous work had key limitations of not fully considering the multi-contrast information from MRI and the 3D anatomical context, which are critical for addressing the complex spatially varying structure of VAT. An additional challenge is the imbalance between the number and distribution of pixels representing SAT/VAT. This work proposes a network based on 3D U-Net that utilizes the full field-of-view volumetric T₁-weighted, water, and fat images from dual-echo Dixon MRI as the multi-channel input to automatically segment SAT and VAT in adults with overweight/obesity. In addition, this work extends the 3D U-Net to a new Attention-based Competitive Dense 3D U-Net (ACD 3D U-Net) trained with a class frequency-balancing Dice loss (FBDL). In an initial testing dataset, the proposed 3D U-Net and ACD 3D U-Net with FBDL achieved 3D Dice scores of (mean ± standard deviation) 0.99 ±0.01 and 0.99±0.01 for SAT, and 0.95±0.04 and 0.96 ±0.04 for VAT, respectively, compared to manual annotations. The proposed 3D networks had rapid inference time (<60 ms/slice) and can enable automated segmentation of SAT and VAT.Clinical relevance- This work developed 3D neural networks to automatically, accurately, and rapidly segment visceral and subcutaneous adipose tissue on MRI, which can help to characterize the risk for cardiometabolic diseases such as diabetes, elevated glucose levels, and hypertension.

Artificial intelligence and abdominal adipose tissue analysis: a literature review

Body composition imaging relies on assessment of tissues composition and distribution. Quantitative data provided by body composition imaging analysis have been linked to pathogenesis, risk, and clinical outcomes of a wide spectrum of diseases, including cardiovascular and oncologic. Manual segmentation of imaging data allows to obtain information on abdominal adipose tissue; however, this procedure can be cumbersome and time-consuming. On the other hand, quantitative imaging analysis based on artificial intelligence (AI) has been proposed as a fast and reliable automatic technique for segmentation of abdominal adipose tissue compartments, possibly improving the current standard of care. AI holds the potential to extract quantitative data from computed tomography (CT) and magnetic resonance (MR) images, which in most of the cases are acquired for other purposes. This information is of great importance for physicians dealing with a wide spectrum of diseases, including cardiovascular and oncologic, for the assessment of risk, pathogenesis, clinical outcomes, response to treatments, and complications. In this review we summarize the available evidence on AI algorithms aimed to the segmentation of visceral and subcutaneous adipose tissue compartments on CT and MR images.

Automatic segmentation of whole-body adipose tissue from magnetic resonance fat fraction images based on machine learning

OBJECTIVE

To propose a fully automated algorithm, which is implemented to segment subcutaneous adipose tissue (SAT) and internal adipose tissue (IAT) from the total adipose tissue for whole-body fat distribution analysis using proton density fat fraction (PDFF) magnetic resonance images.

MATERIALS AND METHODS

Adipose tissue segmentation was implemented using the U-Net deep neural network model. All datasets were collected using a 3.0 T magnetic resonance imaging (MRI) scanner for whole-body scan of 20 volunteers covering from neck to knee with about 160 images for each volunteer. PDFF images were reconstructed based on chemical-shift-encoded fat-water imaging. After selecting the representative PDFF images (total 906 images), the manual labeling of the SAT area was used for model training (504 images), validation (168 images), and testing (234 images).

RESULTS

The automatic segmentation model was validated through three indices using the validation and test sets. The dice similarity coefficient, precision rate, and recall rate were 0.976 ± 0.048, 0.978 ± 0.048, and 0.978 ± 0.050, respectively, in both validation and test sets.

CONCLUSION

The proposed algorithm can reliably and automatically segment SAT and IAT from whole-body MRI PDFF images. The proposed method provides a simple and automatic tool for whole-body fat distribution analysis to explore the relationship between fat deposition and metabolic-related chronic diseases.

Assessing visceral and subcutaneous adiposity using segmented T2-MRI and multi-frequency segmental bioelectrical impedance: A sex-based comparative study

BACKGROUND AND AIM

This study aims to quantify abdominal visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) using T2-weighted magnetic resonance imaging (MRI), and assess the extent of its concordance with VAT surface-area measured by a state-of-the-art segmental multi-frequency bioelectrical impedance analysis (BIA) device. A comparison between manual and semi-automated segmentation was conducted. Further, abdominal VAT and SAT sex-based comparison in healthy Arab adults was piloted.

METHODS

A cross-sectional design was followed to recruit subjects. Abdominal VAT and SAT were determined on T2-weighted MRI manually and semi-automatically. Body composition was assessed using a BIA machine. Statistical differences between the abdominal VAT areas defined by BIA, manual, and semi-automated MRI were compared. Correlation between all methods was assessed, and statistical differences between sex abdominal VAT/SAT defined areas were compared.

RESULTS

A total of 165 abdominal T2-weighted MR images taken for 55 overweight/obese adult subjects were analyzed Differences between manual and semi-automated MRI-obtained abdominal VAT and SAT were found statistically significant (P<0.001) for all subjects. Mean abdominal VAT using the BIA technique was found to correlate significantly with manually and semi-automated T2-weighted MRI defined VAT (r=0.7436; P<0.001 and r=0.8275; P<0.001, respectively). Abdominal VAT was significantly (P<0.001) different between male and female subjects accumulating at different abdominal levels.

CONCLUSION

Semi-automatic segmentation showed a stronger significant correlation with BIA compared to manual segmentation, implying a more reliable quantification of abdominal VAT/SAT. Segmental BIA technique may serve as a feasible and convenient assessment tool for the visceral adiposity in obese subjects.

Pancreatic Fat is not significantly correlated with β-cell Dysfunction in Patients with new-onset Type 2 Diabetes Mellitus using quantitative Computed Tomography

Objective: Type 2 diabetes mellitus (T2DM) is a chronic condition resulting from insulin resistance and insufficient β-cell secretion, leading to improper glycaemic regulation. Previous studies have found that excessive fat deposits in organs such as the liver and muscle can cause insulin resistance through lipotoxicity that affects β-cell function. The relationships between fat deposits in pancreatic tissue, the function of β-cells, the method of visceral fat evaluation and T2DM have been sought by researchers. This study aims to elucidate the role of pancreatic fat deposits in the development of T2DM using quantitative computed tomography (QCT), especially their effects on islet β-cell function. Methods: We examined 106 subjects at the onset of T2DM who had undergone abdominal QCT. Estimated pancreatic fat and liver fat were quantified using QCT and calculated. We analysed the correlations with Homeostatic Model Assessment of Insulin Resistance (HOMA-IR) scores and other oral glucose tolerance test-derived parameters that reflect islet function. Furthermore, correlations of estimated pancreatic fat and liver fat with the area under the curve for insulin (AUC_INS) and HOMA-IR were assessed with partial correlation analysis and demonstrated by scatter plots. Results: Associations were found between estimated liver fat and HOMA-IR, AUC_INS, the modified β-cell function index (MBCI) and Homeostatic Model Assessment β (HOMA-β). However, no significant differences existed between estimated pancreas fat and those parameters. Similarly, after adjustment for sex, age and body mass index, only estimated liver fat was correlated with HOMA-IR and AUC_INS. Conclusions: This study suggests no significant correlation between pancreatic fat deposition and β-cell dysfunction in the early stages of T2DM using QCT as a screening tool. The deposits of fat in the pancreas and the resulting lipotoxicity may play an important role in the late stage of islet cell function dysfunction as the course of T2DM progresses.