RESUMO
BACKGROUND & AIMS: Several automated programs have been developed to facilitate body composition analysis of images from abdominal computed tomography (CT) scans. External validation in patients with colorectal cancer is necessary for use in research and clinical practice. Our aim was to validate an automatic method (AutoMATiCA) of segmenting CT images at the third lumbar level (L3) from patients with colorectal cancer, by comparing with manual segmentation. METHODS: Diagnostic abdominal CT scans of consecutive patients with stage I-III colorectal cancer were analysed to measure cross-sectional areas and tissue densities of skeletal muscle and intra-muscular, visceral, and subcutaneous adipose tissue. Trained analysts performed manual segmentation of L3 CT images using SliceOmatic. Automatic segmentation was performed using AutoMATiCA, an open-source software. The Dice similarity coefficient (DSC) was calculated to assess segmentation accuracy. Agreement of automatic with manual segmentation was evaluated using intra-class correlation coefficients (ICCs) and Bland-Altman plots with limits of agreement. RESULTS: A total of 292 scans were included, of which 62% were from male patients. The agreement of AutoMATiCA with the manual segmentation was excellent, with median DSC values ranging from 0.900 to 0.991 and ICCs above 0.95 for all segmented areas. No systematic deviations were observed in Bland-Altman plots for all segmented areas, with overall narrow limits of agreement. CONCLUSIONS: AutoMATiCA provides an accurate segmentation of abdominal CT images from patients with colorectal cancer. Our findings support its use as a highly efficient automated tool for body composition analysis in research and potentially also in clinical practice.
RESUMO
Background: Computerized radiological image analysis (radiomics) enables the investigation of image-derived phenotypes by extracting large numbers of quantitative features. We hypothesized that radiomics features may contain prognostic information that enhances conventional body composition analysis. We aimed to investigate whether body composition-associated radiomics features hold additional value over conventional body composition analysis and clinical patient characteristics used to predict survival of pancreatic ductal adenocarcinoma (PDAC) patients. Methods: Computed tomography images of 304 patients undergoing elective pancreatic cancer resection were analysed. 2D radiomics features were extracted from skeletal muscle and subcutaneous and visceral adipose tissue (SAT and VAT) compartments from a single slice at the third lumbar vertebra. The study population was randomly split (80:20) into training and holdout subsets. Feature ranking with Least Absolute Shrinkage Selection Operator (LASSO) followed by multivariable stepwise Cox regression in 1000 bootstrapped re-samples of the training data was performed and tested on the holdout data. The fitted regression predictors were used as "scores" for a clinical (C-Score), body composition (B-Score), and radiomics (R-Score) model. To stratify patients into the highest 25% and lowest 25% risk of mortality compared to the middle 50%, the Harrell Concordance Index was used. Results: Based on LASSO and stepwise cox regression for overall survival, ASA ≥3 and age were the most important clinical variables and constituted the C-score, and VAT-index (VATI) was the most important body composition variable and constituted the B-score. Three radiomics features (SATI_original_shape2D_Perimeter, VATI_original_glszm_SmallAreaEmphasis, and VATI_original_firstorder_Maximum) emerged as the most frequent set of features and yielded an R-Score. Of the mean concordance indices of C-, B-, and R-scores, R-score performed best (0.61, 95% CI 0.56-0.65, p<0.001), followed by the C-score (0.59, 95% CI 0.55-0.63, p<0.001) and B-score (0.55, 95% CI 0.50-0.60, p=0.03). Kaplan-Meier projection revealed that C-, B, and R-scores showed a clear split in the survival curves in the training set, although none remained significant in the holdout set. Conclusion: It is feasible to implement a data-driven radiomics approach to body composition imaging. Radiomics features provided improved predictive performance compared to conventional body composition variables for the prediction of overall survival of PDAC patients undergoing primary resection.
RESUMO
INTRODUCTION: Sarcopenia is a muscle disease that involves loss of muscle strength and physical function and is associated with adverse health effects. Even though sarcopenia has attracted increasing attention in the literature, many research findings have not yet been translated into clinical practice. In this article, we aim to validate a deep learning neural network for automated segmentation of L3 CT slices and aim to explore the potential for clinical utilization of such a tool for clinical practice. MATERIALS AND METHODS: A deep learning neural network was trained on a multi-centre collection of 3413 abdominal cancer surgery subjects to automatically segment muscle, subcutaneous and visceral adipose tissue at the L3 lumbar vertebral level. 536 Polytrauma subjects were used as an independent test set to show generalizability. The Dice Similarity Coefficient was calculated to validate the geometric similarity. Quantitative agreement was quantified using Bland-Altman's Limits of Agreement interval and Lin's Concordance Correlation Coefficient. To determine the potential clinical usability, randomly selected segmentation images were presented to a panel of experienced clinicians to rate on a Likert scale. RESULTS: Deep learning results gave excellent agreement versus a human expert operator for all of the body composition indices, with Concordance Correlation Coefficient for skeletal muscle index of 0.92, Skeletal muscle radiation attenuation 0.94, Visceral Adipose Tissue index 0.99 and Subcutaneous Adipose Tissue Index 0.99. Triple-blinded visual assessment of segmentation by clinicians correlated only to the Dice coefficient, but had no association to quantitative body composition metrics which were accurate irrespective of clinicians' visual rating. CONCLUSION: A deep learning method for automatic segmentation of truncal muscle, visceral and subcutaneous adipose tissue on individual L3 CT slices has been independently validated against expert human-generated results for an enlarged polytrauma registry dataset. Time efficiency, consistency and high accuracy relative to human experts suggest that quantitative body composition analysis with deep learning should is a promising tool for clinical application in a hospital setting.
Assuntos
Traumatismo Múltiplo , Sarcopenia , Composição Corporal , Humanos , Traumatismo Múltiplo/diagnóstico por imagem , Gordura Subcutânea , Tomografia Computadorizada por Raios XRESUMO
BACKGROUND: This study aimed to evaluate whether hypertrophy after portal vein embolization (PVE) and maximum liver function capacity (LiMAx) are predictable by an artificial neural network (ANN) model based on computed tomography (CT) texture features. METHODS: We report a retrospective analysis on 118 patients undergoing preoperative assessment by CT before and after PVE for subsequent extended liver resection due to a malignant tumor at RWTH Aachen University Hospital. The LiMAx test was carried out in a subgroup of 55 patients prior to PVE. Associations between CT texture features and hypertrophy as well as liver function were assessed by a multilayer perceptron ANN model. RESULTS: Liver volumetry showed a median hypertrophy degree of 33.9% (16.5-60.4%) after PVE. Non-response, defined as a hypertrophy grade lower than 25%, was found in 36.5% (43/118) of the cases. The ANN prediction of the hypertrophy response showed a sensitivity of 95.8%, specificity of 44.4% and overall prediction accuracy of 74.6% (p < 0.001). The observed median LiMAx was 327 (248-433) µg/kg/h and was strongly correlated with the predicted LiMAx (R2 = 0.89). CONCLUSION: Our study shows that an ANN model based on CT texture features is able to predict the maximum liver function capacity and may be useful to assess potential hypertrophy after performing PVE.
RESUMO
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.
Assuntos
Aprendizado Profundo , Traumatismo Múltiplo , Tecido Adiposo/diagnóstico por imagem , Estudos Transversais , Humanos , Traumatismo Múltiplo/diagnóstico por imagem , Músculo Esquelético/diagnóstico por imagem , Tomografia Computadorizada por Raios XRESUMO
Schizophrenia is a severe mental disorder characterized by numerous subtle changes in brain structure and function. Machine learning allows exploring the utility of combining structural and functional brain magnetic resonance imaging (MRI) measures for diagnostic application, but this approach has been hampered by sample size limitations and lack of differential diagnostic data. Here, we performed a multi-site machine learning analysis to explore brain structural patterns of T1 MRI data in 2668 individuals with schizophrenia, bipolar disorder or attention-deficit/ hyperactivity disorder, and healthy controls. We found reproducible changes of structural parameters in schizophrenia that yielded a classification accuracy of up to 76% and provided discrimination from ADHD, through it lacked specificity against bipolar disorder. The observed changes largely indexed distributed grey matter alterations that could be represented through a combination of several global brain-structural parameters. This multi-site machine learning study identified a brain-structural signature that could reproducibly differentiate schizophrenia patients from controls, but lacked specificity against bipolar disorder. While this currently limits the clinical utility of the identified signature, the present study highlights that the underlying alterations index substantial global grey matter changes in psychotic disorders, reflecting the biological similarity of these conditions, and provide a roadmap for future exploration of brain structural alterations in psychiatric patients.
Assuntos
Transtorno do Deficit de Atenção com Hiperatividade/fisiopatologia , Transtorno Bipolar/fisiopatologia , Substância Cinzenta/fisiopatologia , Esquizofrenia/fisiopatologia , Adolescente , Adulto , Transtorno do Deficit de Atenção com Hiperatividade/diagnóstico por imagem , Transtorno Bipolar/diagnóstico por imagem , Estudos de Casos e Controles , Feminino , Substância Cinzenta/diagnóstico por imagem , Humanos , Aprendizado de Máquina , Imageamento por Ressonância Magnética , Masculino , Pessoa de Meia-Idade , Esquizofrenia/diagnóstico por imagem , Adulto JovemRESUMO
Given the fact that clinical bedside examinations can have a high rate of misdiagnosis, machine learning techniques based on neuroimaging and electrophysiological measurements are increasingly being considered for comatose patients and patients with unresponsive wakefulness syndrome, a minimally conscious state or locked-in syndrome. Machine learning techniques have the potential to move from group-level statistical results to personalized predictions in a clinical setting. They have been applied for the purpose of (1) detecting changes in brain activation during functional tasks, equivalent to a behavioral command-following test and (2) estimating signs of consciousness by analyzing measurement data obtained from multiple subjects in resting state. In this review, we provide a comprehensive overview of the literature on both approaches and discuss the translation of present findings to clinical practice. We found that most studies struggle with the difficulty of establishing a reliable behavioral assessment and fluctuations in the patient's levels of arousal. Both these factors affect the training and validation of machine learning methods to a considerable degree. In studies involving more than 50 patients, small to moderate evidence was found for the presence of signs of consciousness or good outcome, where one study even showed strong evidence for good outcome.
Assuntos
Transtornos da Consciência/diagnóstico , Aprendizado de Máquina , Transtornos da Consciência/classificação , Transtornos da Consciência/diagnóstico por imagem , Transtornos da Consciência/fisiopatologia , HumanosRESUMO
BACKGROUND: Taking multiple anthropometric measurements for the description of body proportions in an accurate way is a time-consuming procedure that requires specific tools and skills. This is why we developed an alternative method based on digital photography for taking these measurements which is faster and easier to use, to make anthropometry more user-friendly and approachable to paediatricians. METHODS: We conducted a cross-sectional study in 54 children between 2 and 18 years of age. We compared manual measurements with photogrammetric measurements to validate our method. RESULTS: Inter-observer correlations of all measurements are ≥0.96 and mean differences are 0.3-0.9 cm, except for arm span. Comparison of manual to photogrammetric measurements shows mean differences of 0.6-1.3 cm, with correlations ≥0.92, except for sitting height and arm span. Correlations of ratios between methods are height/sitting height (r=0.77), biacromium/biiliacum (r=0.74) and subischial leg length/sitting height (r=0.75). CONCLUSION: Photogrammetric anthropometry is faster, easier to use and provides the paediatrician with more flexibility as taking the digital photographs and performing the analysis are separated.
Assuntos
Antropometria/métodos , Estatura/fisiologia , Adolescente , Criança , Pré-Escolar , Estudos Transversais , Feminino , Humanos , Masculino , SoftwareRESUMO
Fiber tracking of Diffusion Tensor Imaging (DTI) data offers a unique insight into the three-dimensional organisation of white matter structures in the living brain. However, fiber tracking algorithms require a number of user-defined input parameters that strongly affect the output results. Usually the fiber tracking parameters are set once and are then re-used for several patient datasets. However, the stability of the chosen parameters is not evaluated and a small change in the parameter values can give very different results. The user remains completely unaware of such effects. Furthermore, it is difficult to reproduce output results between different users. We propose a visualization tool that allows the user to visually explore how small variations in parameter values affect the output of fiber tracking. With this knowledge the user cannot only assess the stability of commonly used parameter values but also evaluate in a more reliable way the output results between different patients. Existing tools do not provide such information. A small user evaluation of our tool has been done to show the potential of the technique.