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

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

BACKGROUND

Body 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.

METHODS

All 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.

RESULTS

Four 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.

CONCLUSIONS

In 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.

Pancreatic cancer and sarcopenia: a narrative review of the current status

Pancreatic cancer is still a difficult disease to treat, despite recent advances in surgical techniques and chemotherapeutic drugs. Its incidence continues to rise, as does the number of older patients. Sarcopenia is defined as a progressive and generalized loss of skeletal muscle mass and strength. Sarcopenia is present in approximately 40% in patients with pancreatic cancer. Sarcopenia is primarily diagnosed through imaging, and progress is being made in the development of automated methods and artificial intelligence, as well as biomarker research. Sarcopenia has been linked to a poor prognosis in pancreatic cancer patients. However, some studies suggest that sarcopenia is not always associated with a poor prognosis, depending on the resectability of pancreatic cancer and the nature of treatment, such as surgery or chemotherapy. Recent meta-analyses have found that sarcopenia is not linked to postoperative complications. It is still debated whether there is a link between sarcopenia and drug toxicity during chemotherapy. The relationship between sarcopenia and immunity has been investigated, but the mechanism is still unknown.

Diagnosis of Sarcopenia and Myosteatosis by Computed Tomography in Patients with Esophagogastric and Pancreatic Cancer

The increase in the global incidence of cancer highlights the need to continue advancing in the techniques of diagnosis and nutritional assessment of cancer patients, given the prognostic and therapeutic impact of nutritional status. In this study, sarcopenia was evaluated as an independent predictor of morbidity and mortality. Data from 45 patients diagnosed with esophagogastric or pancreatic cancer were analyzed. Body composition was determined using computed tomography images, and functionality tests were performed. Sarcopenia was present in 22.2% of the patients, while only 31.1% had correct musculature. A reduction in muscle mass or function was observed in 46.7% of the patients. Likewise, the prevalence of myosteatosis reached 60% of the patients. No significant differences were found with regard to the presence of sarcopenia according to BMI classifications, so it is necessary to evaluate the patient with body composition techniques that include the evaluation of the different muscle and fat compartments. In conclusion, a comprehensive intervention is necessary to improve the detection of sarcopenia/myosteatosis and, in the future, to be able to carry out an approach that improves the quality of life and survival rates of patients.

Attempt to Establish Prognostic Predictive System for Hepatocellular Carcinoma Using Artificial Intelligence for Assistance with Selection of Treatment Modality

Introduction

Because of recent developments in treatments for hepatocellular carcinoma (HCC), methods for determining suitable therapy for initial or recurrent HCC have become important. This study used artificial intelligence (AI) findings to establish a system for predicting prognosis of HCC patients at time of reoccurrence based on clinical data as a reference for selection of treatment modalities.

Methods

As a training cohort, 5,701 observations obtained at the initial and each subsequent treatment for recurrence from 1,985 HCC patients at a single center from 2000 to 2021 were used. The validation cohort included 5,692 observations from patients at multiple centers obtained at the time of the initial treatment. An AI calculating system (PRAID) was constructed based on 25 clinical factors noted at each treatment from the training cohort, and then predictive prognostic values for 1- and 3-year survival in both cohorts were evaluated.

Results

After exclusion of patients lacking clinical data regarding albumin-bilirubin (ALBI) grade or tumor-node-metastasis stage of the Liver Cancer Study Group of Japan, 6th edition (TNM-LCSGJ 6th), ALBI-TNM-LCSGJ 6th (ALBI-T) and modified ALBI-T scores confirmed that prognosis for patients in both cohorts was similar. The area under the curve for prediction of both 1- and 3-year survival in the validation cohort was 0.841 (sensitivity 0.933 [95% CI: 0.925-0.940], specificity 0.517 [95% CI: 0.484-0.549]) and 0.796 (sensitivity 0.806 [95% CI: 0.790-0.821], specificity 0.646 [95% CI: 0.624-0.668]), respectively.

Conclusion

The present PRAID system might provide useful prognostic information related to short and medium survival for decision-making regarding the best therapeutic modality for both initial and recurrent HCC cases.

Deep learning of image-derived measures of body composition in pediatric, adolescent, and young adult lymphoma: association with late treatment effects

OBJECTIVES

The objective of this study was to translate a deep learning (DL) approach for semiautomated analysis of body composition (BC) measures from standard of care CT images to investigate the prognostic value of BC in pediatric, adolescent, and young adult (AYA) patients with lymphoma.

METHODS

This 10-year retrospective, single-site study of 110 pediatric and AYA patients with lymphoma involved manual segmentation of fat and muscle tissue from 260 CT imaging datasets obtained as part of routine imaging at initial staging and first therapeutic follow-up. A DL model was trained to perform semiautomated image segmentation of adipose and muscle tissue. The association between BC measures and the occurrence of 3-year late effects was evaluated using Cox proportional hazards regression analyses.

RESULTS

DL-guided measures of BC were in close agreement with those obtained by a human rater, as demonstrated by high Dice scores (≥ 0.95) and correlations (r > 0.99) for each tissue of interest. Cox proportional hazards regression analyses revealed that patients with elevated subcutaneous adipose tissue at baseline and first follow-up, along with patients who possessed lower volumes of skeletal muscle at first follow-up, have increased risk of late effects compared to their peers.

CONCLUSIONS

DL provides rapid and accurate quantification of image-derived measures of BC that are associated with risk for treatment-related late effects in pediatric and AYA patients with lymphoma. Image-based monitoring of BC measures may enhance future opportunities for personalized medicine for children with lymphoma by identifying patients at the highest risk for late effects of treatment.

KEY POINTS

• Deep learning-guided CT image analysis of body composition measures achieved high agreement level with manual image analysis. • Pediatric patients with more fat and less muscle during the course of cancer treatment were more likely to experience a serious adverse event compared to their clinical counterparts. • Deep learning of body composition may add value to routine CT imaging by offering real-time monitoring of pediatric, adolescent, and young adults at high risk for late effects of cancer treatment.

Abdominal CT Segmentation for Body Composition Assessment Using Network Consistency Learning

Estimating skeletal muscle (SM) and adipose tissues is an invaluable prognostic indicator in cancer treatment, major surgeries, and general health screening. Body composition is usually measured with abdominal computed tomography (CT) scans acquired in clinical settings. The whole-body SM volume is correlated with the estimated SM based on the measurement of a single two-dimensional vertebral slice. It is necessary to label a CT image at the pixel level to estimate SM, known as semantic segmentation. In this work, we trained a segmentation model using the labeled abdominal CT slices and the additional unlabeled slices. In particular, we trained two identical segmentation networks with differently initialized weights. Network Consistency Learning (NCL) allowed learning from unlabeled images by forcing the predictions from both networks to be the same. We segmented abdominal CT images from a newly created in-house dataset. The proposed approach gained 10% better performance in terms of Dice similarity score (DSC) than that obtained by a standard supervised network demonstrating the effectiveness of NCL in exploiting unlabeled images.Clinical relevance- An efficient and cost-effective method is proposed for assessing body composition from limited labeled and abundant unlabeled CT images to facilitate fast diagnosis, prognosis, and interventions.

Prognostic value of pretreatment skeletal muscle index in pancreatic carcinoma patients: A meta-analysis

BACKGROUND

The association between pretreatment skeletal muscle index (SMI) and long-term survival of pancreatic carcinoma patients remains unclear up to now.

METHODS

The PubMed, Web of Science and EMBASE databases were searched up to March 1, 2022 for relevant studies. The primary and secondary outcomes were overall survival and progression-free survival, respectively. The hazard ratios (HRs) and 95% confidence intervals (CIs) were combined to assess the relationship between pretreatment SMI and prognosis of pancreatic carcinoma patients. All statistical analysis was conducted by STATA 15.0 software.

RESULTS

Twenty retrospective studies involving 3765 patients were included. The pooled results demonstrated that lower pretreatment SMI was significantly related to poorer overall survival (HR = 1.42, 95% CI: 1.25-1.62, P < .001) and progression-free survival (HR = 1.41, 95% CI: 1.08-1.84, P = .012). Besides subgroup analysis based on the treatment (non-surgery vs surgery) and tumor stage (advanced vs early stage) showed similar results.

CONCLUSION

Pretreatment SMI could serve as a promising and reliable prognostic factor for pancreatic carcinoma patients and lower pretreatment SMI predicted worse prognosis.

Role of Machine Learning-Based CT Body Composition in Risk Prediction and Prognostication: Current State and Future Directions

CT body composition analysis has been shown to play an important role in predicting health and has the potential to improve patient outcomes if implemented clinically. Recent advances in artificial intelligence and machine learning have led to high speed and accuracy for extracting body composition metrics from CT scans. These may inform preoperative interventions and guide treatment planning. This review aims to discuss the clinical applications of CT body composition in clinical practice, as it moves towards widespread clinical implementation.

Association of sex-specific donor skeletal muscle index with surgical outcomes in living donor liver transplantation recipients

BACKGROUND

A recent study reported a correlation between the muscle mass of male donors and graft failure in living donor liver transplantation (LDLT) recipients. We investigated the association of sex-specific donor skeletal muscle index (SMI) with mortality and graft failure in LDLT recipients.

METHODS

We retrospectively analysed 2750 sets of donors and recipients between January 2008 and January 2018. The recipient outcomes were analysed by dividing the data according to donor sex. Cox regression analyses were performed to evaluate the association between donor SMI by sex and 1-year mortality and graft failure in recipients.

RESULTS

In the male donor group, robust donor (increased SMI) was significantly associated with higher risks for mortality (hazard ratio [HR]: 1.03, 95% confidence interval [CI]: 1.00-1.06, p = .023) and graft failure (HR: 1.04, 95% CI: 1.01-1.06, p = .007) at 1 year. In the female donor group, the robust donor was significantly associated with lower risks for mortality (HR: 0.92, 95% CI: 0.87-0.97, p = .003) and graft failure (HR: 0.95, 95% CI: 0.90-1.00, p = .032) at 1 year.

CONCLUSIONS

Donor SMI was associated with surgical outcomes in recipients. Robust male and female donors were a significant negative and protective factor for grafts respectively.

Pre-Therapeutic Sarcopenia among Cancer Patients: An Up-to-Date Meta-Analysis of Prevalence and Predictive Value during Cancer Treatment

This study will address the prevalence of pre-therapeutic sarcopenia (PS) and its clinical impact during cancer treatment among adult cancer patients ≥ 18 years of age. A meta-analysis (MA) with random-effect models was performed via a MEDLINE systematic review, according to the PRISMA statement, focusing on articles published before February 2022 that reported observational studies and clinical trials on the prevalence of PS and the following outcomes: overall survival (OS), progression-free survival (PFS), post-operative complications (POC), toxicities (TOX), and nosocomial infections (NI). A total of 65,936 patients (mean age: 45.7-85 y) with various cancer sites and extensions and various treatment modes were included. Mainly defined by CT scan-based loss of muscle mass only, the pooled prevalence of PS was 38.0%. The pooled relative risks were 1.97, 1.76, 2.70, 1.47, and 1.76 for OS, PFS, POC, TOX, and NI, respectively (moderate-to-high heterogeneity, I²: 58-85%). Consensus-based algorithm definitions of sarcopenia, integrating low muscle mass and low levels of muscular strength and/or physical performance, lowered the prevalence (22%) and heterogeneity (I² < 50%). They also increased the predictive values with RRs ranging from 2.31 (OS) to 3.52 (POC). PS among cancer patients is prevalent and strongly associated with poor outcomes during cancer treatment, especially when considering a consensus-based algorithm approach.

Sarcopenia in pancreatic cancer: Effect on patient outcomes

Pancreatic cancer is a challenging disease with an increasing incidence and extremely poor prognosis. The clinical outcomes of pancreatic cancer depend on tumor biology, responses to treatments, and malnutrition or cachexia. Sarcopenia represents a severe catabolic condition defined by the age-related loss of muscle mass and strength and affects as much as 70% of malnourished pancreatic cancer patients. The lumbar skeletal muscle index, defined as the total abdominal muscle area at the L3 vertebral level adjusted by the square of the height, is widely used for assessing sarcopenia in patients with pancreatic cancer. Several studies have suggested that sarcopenia may be a risk factor for perioperative complications and decreased recurrence-free or overall survival in patients with pancreatic cancer undergoing surgery. Sarcopenia could also intensify chemotherapy-induced toxicities and worsen the quality of life and survival in the neoadjuvant or palliative chemotherapy setting. Sarcopenia, not only at the time of diagnosis but also during treatment, decreases survival in patients with pancreatic cancer. Theoretically, multimodal interventions may improve sarcopenia and clinical outcomes; however, no study has reported positive results. Further prospective studies are needed to confirm the prognostic role of sarcopenia and the effects of multimodal interventions in patients with pancreatic cancer.

Artificial Intellgence in the Era of Precision Oncological Imaging

Rapid-paced development and adaptability of artificial intelligence algorithms have secured their almost ubiquitous presence in the field of oncological imaging. Artificial intelligence models have been created for a variety of tasks, including risk stratification, automated detection, and segmentation of lesions, characterization, grading and staging, prediction of prognosis, and treatment response. Soon, artificial intelligence could become an essential part of every step of oncological workup and patient management. Integration of neural networks and deep learning into radiological artificial intelligence algorithms allow for extrapolating imaging features otherwise inaccessible to human operators and pave the way to truly personalized management of oncological patients.Although a significant proportion of currently available artificial intelligence solutions belong to basic and translational cancer imaging research, their progressive transfer to clinical routine is imminent, contributing to the development of a personalized approach in oncology. We thereby review the main applications of artificial intelligence in oncological imaging, describe the example of their successful integration into research and clinical practice, and highlight the challenges and future perspectives that will shape the field of oncological radiology.

Pancreatic cancer, radiomics and artificial intelligence

Patients with pancreatic ductal adenocarcinoma (PDAC) are generally classified into four categories based on contrast-enhanced CT at diagnosis: resectable, borderline resectable, unresectable, and metastatic disease. In the initial grading and staging of PDAC, structured radiological templates are useful but limited, as there is a need to define the aggressiveness and microscopic disease stage of these tumours to ensure adequate treatment allocation. Quantitative imaging analysis allows radiomics and dynamic imaging features to provide information of clinical outcomes, and to construct clinical models based on radiomics signatures or imaging phenotypes. These quantitative features may be used as prognostic and predictive biomarkers in clinical decision-making, enabling personalised management of advanced PDAC. Deep learning and convolutional neural networks also provide high level bioinformatics tools that can help define features associated with a given aspect of PDAC biology and aggressiveness, paving the way to define outcomes based on these features. Thus, the prediction of tumour phenotype, treatment response and patient prognosis may be feasible by using such comprehensive and integrated radiomics models. Despite these promising results, quantitative imaging is not ready for clinical implementation in PDAC. Limitations include the instability of metrics and lack of external validation. Large properly annotated datasets, including relevant semantic features (demographics, blood markers, genomics), image harmonisation, robust radiomics analysis, clinically significant tasks as outputs, comparisons with gold-standards (such as TNM or pretreatment classifications) and fully independent validation cohorts, will be required for the development of trustworthy radiomics and artificial intelligence solutions to predict PDAC aggressiveness in a clinical setting.

Influence of Baseline CT Body Composition Parameters on Survival in Patients with Pancreatic Adenocarcinoma

Pancreatic cancer is the seventh leading cause of cancer death in both sexes. The aim of this study is to analyze baseline CT body composition using artificial intelligence to identify possible imaging predictors of survival. We retrospectively included 103 patients. First, the presence of surgical treatment and cut-off values for sarcopenia and obesity served as independent variates. Second, the presence of surgery, subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and skeletal muscle index (SMI) served as independent variates. Cox regression analysis was performed for 1-year, 2-year, and 3-year survival. Possible differences between patients undergoing surgical versus nonsurgical treatment were analyzed. Presence of surgery significantly predicted 1-year, 2-year, and 3-year survival (p = 0.01, <0.001, and <0.001, respectively). Across the follow-up periods of 1-year, 2-year, and 3-year survival, the presence of sarcopenia became an equally important predictor of survival (p = 0.25, 0.07, and <0.001, respectively). Additionally, increased VAT predicted 2-year and 3-year survival (p = 0.02 and 0.04, respectively). The impact of sarcopenia on 3-year survival was higher in the surgical treatment group (p = 0.02 and odds ratio = 2.57) compared with the nonsurgical treatment group (p = 0.04 and odds ratio = 1.92). Fittingly, a lower SMI significantly affected 3-year survival only in patients who underwent surgery (p = 0.02). Especially if surgery is performed, AI-derived sarcopenia and reduced muscle mass are unfavorable imaging predictors.

The Value of Artificial Intelligence-Assisted Imaging in Identifying Diagnostic Markers of Sarcopenia in Patients with Cancer

Sarcopenia is defined as the loss of skeletal muscle mass and muscle function. It is common in patients with malignancies and often associated with adverse clinical outcomes. The presence of sarcopenia in patients with cancer is determined by body composition, and recently, radiologic technology for the accurate estimation of body composition is under development. Artificial intelligence- (AI-) assisted image measurement facilitates the detection of sarcopenia in clinical practice. Sarcopenia is a prognostic factor for patients with cancer, and confirming its presence helps to recognize those patients at the greatest risk, which provides a guide for designing individualized cancer treatments. In this review, we examine the recent literature (2017-2021) on AI-assisted image assessment of body composition and sarcopenia, seeking to synthesize current information on the mechanism and the importance of sarcopenia, its diagnostic image markers, and the interventions for sarcopenia in the medical care of patients with cancer. We concluded that AI-assisted image analysis is a reliable automatic technique for segmentation of abdominal adipose tissue. It has the potential to improve diagnosis of sarcopenia and facilitates identification of oncology patients at the greatest risk, supporting individualized prevention planning and treatment evaluation. The capability of AI approaches in analyzing series of big data and extracting features beyond manual skills would no doubt progressively provide impactful information and greatly refine the standard for assessing sarcopenia risk in patients with cancer.

The impact of nutritional status on pancreatic cancer therapy

INTRODUCTION

Pancreatic Ductal Adenocarcinoma (PDAC) is an aggressive disease with poor outcomes. One of the reasons for the dismal prognosis resides in its impressive ability to alter the nutritional status of patients who develop malnutrition, cachexia, anorexia, and sarcopenia in most cases. The ideal way to measure such changes in PDAC patients, in order to readily identify them and avoid complications or discontinuations of treatment is a relatively unexplored area. In addition, most PDAC patients experience pancreatic exocrine insufficiency (PEI) that contributes to the complex puzzle of malnutrition and that can be treated with Pancreatic Enzyme Replacement Therapy (PERT).

AREAS COVERED

We review current knowledge on the impact of nutritional status on both surgical and medical treatments for PDAC, reporting available data on the causes of malnutrition, characteristics, and advantages of different tools to investigate nutritional status and possible strategies to improve patient outcomes.

EXPERT OPINION

All PDAC patients should receive a careful nutritional assessment at diagnosis, and this should be repeated alongside their treatment path. Screening tools and biochemical variables or scores are associated with prognosis, but bioimpedance vector analysis (BIVA) and radiological assessment of body composition seem more accurate in predicting clinical outcomes and postoperative complications.

Application of artificial intelligence to pancreatic adenocarcinoma

BACKGROUND AND OBJECTIVES

Pancreatic cancer (PC) is one of the deadliest cancers worldwide although substantial advancement has been made in its comprehensive treatment. The development of artificial intelligence (AI) technology has allowed its clinical applications to expand remarkably in recent years. Diverse methods and algorithms are employed by AI to extrapolate new data from clinical records to aid in the treatment of PC. In this review, we will summarize AI's use in several aspects of PC diagnosis and therapy, as well as its limits and potential future research avenues.

METHODS

We examine the most recent research on the use of AI in PC. The articles are categorized and examined according to the medical task of their algorithm. Two search engines, PubMed and Google Scholar, were used to screen the articles.

RESULTS

Overall, 66 papers published in 2001 and after were selected. Of the four medical tasks (risk assessment, diagnosis, treatment, and prognosis prediction), diagnosis was the most frequently researched, and retrospective single-center studies were the most prevalent. We found that the different medical tasks and algorithms included in the reviewed studies caused the performance of their models to vary greatly. Deep learning algorithms, on the other hand, produced excellent results in all of the subdivisions studied.

CONCLUSIONS

AI is a promising tool for helping PC patients and may contribute to improved patient outcomes. The integration of humans and AI in clinical medicine is still in its infancy and requires the in-depth cooperation of multidisciplinary personnel.