Association between myosteatosis and impaired glucose metabolism: A deep learning whole-body magnetic resonance imaging population phenotyping approach.

BACKGROUND: There is increasing evidence that myosteatosis, which is currently not assessed in clinical routine, plays an important role in risk estimation in individuals with impaired glucose metabolism, as it is associated with the progression of insulin resistance. With advances in artificial intelligence, automated and accurate algorithms have become feasible to fill this gap. METHODS: In this retrospective study, we developed and tested a fully automated deep learning model using data from two prospective cohort studies (German National Cohort [NAKO] and Cooperative Health Research in the Region of Augsburg [KORA]) to quantify myosteatosis on whole-body T1-weighted Dixon magnetic resonance imaging as (1) intramuscular adipose tissue (IMAT; the current standard) and (2) quantitative skeletal muscle (SM) fat fraction (SMFF). Subsequently, we investigated the two measures for their discrimination of and association with impaired glucose metabolism beyond baseline demographics (age, sex and body mass index [BMI]) and cardiometabolic risk factors (lipid panel, systolic blood pressure, smoking status and alcohol consumption) in asymptomatic individuals from the KORA study. Impaired glucose metabolism was defined as impaired fasting glucose or impaired glucose tolerance (140-200 mg/dL) or prevalent diabetes mellitus. RESULTS: Model performance was high, with Dice coefficients of ≥0.81 for IMAT and ≥0.91 for SM in the internal (NAKO) and external (KORA) testing sets. In the target population (380 KORA participants: mean age of 53.6 ± 9.2 years, BMI of 28.2 ± 4.9 kg/m2, 57.4% male), individuals with impaired glucose metabolism (n = 146; 38.4%) were older and more likely men and showed a higher cardiometabolic risk profile, higher IMAT (4.5 ± 2.2% vs. 3.9 ± 1.7%) and higher SMFF (22.0 ± 4.7% vs. 18.9 ± 3.9%) compared to normoglycaemic controls (all P ≤ 0.005). SMFF showed better discrimination for impaired glucose metabolism than IMAT (area under the receiver operating characteristic curve [AUC] 0.693 vs. 0.582, 95% confidence interval [CI] [0.06-0.16]; P < 0.001) but was not significantly different from BMI (AUC 0.733 vs. 0.693, 95% CI [-0.09 to 0.01]; P = 0.15). In univariable logistic regression, IMAT (odds ratio [OR] = 1.18, 95% CI [1.06-1.32]; P = 0.004) and SMFF (OR = 1.19, 95% CI [1.13-1.26]; P < 0.001) were associated with a higher risk of impaired glucose metabolism. This signal remained robust after multivariable adjustment for baseline demographics and cardiometabolic risk factors for SMFF (OR = 1.10, 95% CI [1.01-1.19]; P = 0.028) but not for IMAT (OR = 1.14, 95% CI [0.97-1.33]; P = 0.11). CONCLUSIONS: Quantitative SMFF, but not IMAT, is an independent predictor of impaired glucose metabolism, and discrimination is not significantly different from BMI, making it a promising alternative for the currently established approach. Automated methods such as the proposed model may provide a feasible option for opportunistic screening of myosteatosis and, thus, a low-cost personalized risk assessment solution.

Deep learning to estimate impaired glucose metabolism from Magnetic Resonance Imaging of the liver: An opportunistic population screening approach.

AIM: Diabetes is a global health challenge, and many individuals are undiagnosed and not aware of their increased risk of morbidity/mortality although dedicated tests are available, which indicates the need for novel population-wide screening approaches. Here, we developed a deep learning pipeline for opportunistic screening of impaired glucose metabolism using routine magnetic resonance imaging (MRI) of the liver and tested its prognostic value in a general population setting. METHODS: In this retrospective study a fully automatic deep learning pipeline was developed to quantify liver shape features on routine MR imaging using data from a prospective population study. Subsequently, the association between liver shape features and impaired glucose metabolism was investigated in individuals with prediabetes, type 2 diabetes and healthy controls without prior cardiovascular diseases. K-medoids clustering (3 clusters) with a dissimilarity matrix based on Euclidean distance and ordinal regression was used to assess the association between liver shape features and glycaemic status. RESULTS: The deep learning pipeline showed a high performance for liver shape analysis with a mean Dice score of 97.0±0.01. Out of 339 included individuals (mean age 56.3±9.1 years; males 58.1%), 79 (23.3%) and 46 (13.6%) were classified as having prediabetes and type 2 diabetes, respectively. Individuals in the high risk cluster using all liver shape features (n = 14) had a 2.4 fold increased risk of impaired glucose metabolism after adjustment for cardiometabolic risk factors (age, sex, BMI, total cholesterol, alcohol consumption, hypertension, smoking and hepatic steatosis; OR 2.44 [95% CI 1.12-5.38]; p = 0.03). Based on individual shape features, the strongest association was found between liver volume and impaired glucose metabolism after adjustment for the same risk factors (OR 1.97 [1.38-2.85]; p<0.001). CONCLUSIONS: Deep learning can estimate impaired glucose metabolism on routine liver MRI independent of cardiometabolic risk factors and hepatic steatosis.

A Context-based Chatbot Surpasses Trained Radiologists and Generic ChatGPT in Following the ACR Appropriateness Guidelines.

Background Radiological imaging guidelines are crucial for accurate diagnosis and optimal patient care as they result in standardized decisions and thus reduce inappropriate imaging studies. Purpose In the present study, we investigated the potential to support clinical decision-making using an interactive chatbot designed to provide personalized imaging recommendations from American College of Radiology (ACR) appropriateness criteria documents using semantic similarity processing. Methods We utilized 209 ACR appropriateness criteria documents as specialized knowledge base and employed LlamaIndex, a framework that allows to connect large language models with external data, and the ChatGPT 3.5-Turbo to create an appropriateness criteria contexted chatbot (accGPT). Fifty clinical case files were used to compare the accGPT's performance against general radiologists at varying experience levels and to generic ChatGPT 3.5 and 4.0. Results All chatbots reached at least human performance level. For the 50 case files, the accGPT performed best in providing correct recommendations that were "usually appropriate" according to the ACR criteria and also did provide the highest proportion of consistently correct answers in comparison with generic chatbots and radiologists. Further, the chatbots provided substantial time and cost savings, with an average decision time of 5 minutes and a cost of 0.19 € for all cases, compared to 50 minutes and 29.99 € for radiologists (both p < 0.01). Conclusion ChatGPT-based algorithms have the potential to substantially improve the decision-making for clinical imaging studies in accordance with ACR guidelines. Specifically, a context-based algorithm performed superior to its generic counterpart, demonstrating the value of tailoring AI solutions to specific healthcare applications.

Clinical Characteristics and Outcomes of Colorectal Cancer in the ColoCare Study: Differences by Age of Onset.

Early-onset colorectal cancer has been on the rise in Western populations. Here, we compare patient characteristics between those with early- (<50 years) vs. late-onset (≥50 years) disease in a large multinational cohort of colorectal cancer patients (n = 2193). We calculated descriptive statistics and assessed associations of clinicodemographic factors with age of onset using mutually-adjusted logistic regression models. Patients were on average 60 years old, with BMI of 29 kg/m2, 52% colon cancers, 21% early-onset, and presented with stage II or III (60%) disease. Early-onset patients presented with more advanced disease (stages III-IV: 63% vs. 51%, respectively), and received more neo and adjuvant treatment compared to late-onset patients, after controlling for stage (odds ratio (OR) (95% confidence interval (CI)) = 2.30 (1.82-3.83) and 2.00 (1.43-2.81), respectively). Early-onset rectal cancer patients across all stages more commonly received neoadjuvant treatment, even when not indicated as the standard of care, e.g., during stage I disease. The odds of early-onset disease were higher among never smokers and lower among overweight patients (1.55 (1.21-1.98) and 0.56 (0.41-0.76), respectively). Patients with early-onset colorectal cancer were more likely to be diagnosed with advanced stage disease, to have received systemic treatments regardless of stage at diagnosis, and were less likely to be ever smokers or overweight.

CT-based compartmental quantification of adipose tissue versus body metrics in colorectal cancer patients.

PURPOSE: While obesity is considered a prognostic factor in colorectal cancer (CRC), there is increasing evidence that not simply body mass index (BMI) alone but specifically abdominal fat distribution is what matters. As part of the ColoCare study, this study measured the distribution of adipose tissue compartments in CRC patients and aimed to identify the body metric that best correlates with these measurements as a useful proxy for adipose tissue distribution. MATERIALS AND METHODS: In 120 newly-diagnosed CRC patients who underwent multidetector computed tomography (CT), densitometric quantification of total (TFA), visceral (VFA), intraperitoneal (IFA), retroperitoneal (RFA), and subcutaneous fat area (SFA), as well as the M. erector spinae and psoas was performed to test the association with gender, age, tumor stage, metabolic equivalents, BMI, waist-to-height (WHtR) and waist-to-hip ratio (WHR). RESULTS: VFA was 28.8 % higher in men (pVFA<0.0001) and 30.5 % higher in patients older than 61 years (pVFA<0.0001). WHtR correlated best with all adipose tissue compartments (rVFA=0.69, rTFA=0.84, p<0.0001) and visceral-to-subcutaneous-fat-ratio (VFR, rVFR=0.22, p=<0.05). Patients with tumor stages III/IV showed significantly lower overall adipose tissue than I/II. Increased M. erector spinae mass was inversely correlated with all compartments. CONCLUSION: Densitometric quantification on CT is a highly reproducible and reliable method to show fat distribution across adipose tissue compartments. This distribution might be best reflected by WHtR, rather than by BMI or WHR. KEY POINTS: • Densitometric quantification of adipose tissue on CT is highly reproducible and reliable. • Waist-to-height ratio better correlates with adipose tissue compartments and VFR than BMI or waist-to-hip ratio. • Men have higher a higher visceral fat area than women. • Patients older than 61 years have higher visceral fat area. • Patients with tumor stages III/IV have significantly lower adipose tissue than those in stages I/II.