Lin, Lu

ABSTRACT Background and Purpose Radiomics extracts imaging features that may not be detectable through conventional volumetric analyses. Given their role in multiple sclerosis (MS), we applied radiomics to thalamic nuclei and examined their associations with cognitive performance. Methods A total of 601 individuals were included (342 people with MS [PwMS] from two cohorts and 259 healthy controls [HC]). Radiomic features (RF) and volumes were extracted from the whole thalamus, five thalamic nuclei, and the putamen segmented on three‐dimensional T1‐weighted images. Cognitive performance was assessed using the Symbol Digit Modalities Test (SDMT) and Paced Auditory Serial Addition Test (PASAT) in PwMS and the Digit Symbol Substitution Test (DSST) in HC. In the first MS cohort, multivariate linear regression in a discovery set ( N = 103) identified thalamus‐derived RF associated with SDMT, which were retested in a replication set ( N = 63). Their associations with PASAT in a second MS cohort ( N = 176) and DSST in HC were also evaluated. We then tested whether the same RFs, when extracted from the putamen, was associated with SDMT. Least Absolute Shrinkage and Selection Operator (LASSO) models assessed the combined predictive value of RF and volumes. Results Twenty‐eight RF–region of interest (ROI) pairs were associated with SDMT in the replication set (false discovery rate [FDR] < 0.05). Of these, 24 were also associated with PASAT (FDR ≤ 0.03), and 2 with DSST. Only ventral nuclei volume showed replicated associations among volumetrics. Only four putamen‐derived pairs were associated with SDMT (FDR = 0.04). LASSO results confirmed RF outperformed volumes. Conclusion RF extracted from the thalamus is strongly associated with cognitive performance in PwMS, outperforming volumetric measures and supporting their potential as sensitive imaging biomarkers.

Abstract Background and Objectives Radiomics extracts imaging features that may not be detectable through conventional volumetric analyses. Given their role in multiple sclerosis (MS), we applied radiomics to thalamic nuclei and examined their associations with cognitive performance. Methods A total of 601 individuals were included (342 people with MS-PwMS from two cohorts, and 259 healthy controls-HC). Radiomic features (RF) and volumes were extracted from the whole thalamus, five thalamic nuclei, and the putamen segmented on 3D T1-weighted images. Cognitive performance was assessed using the Symbol Digit Modalities Test (SDMT) and Paced Auditory Serial Addition Test (PASAT) in PwMS, and the Digit Symbol Substitution Test (DSST) in HC. In the first MS cohort, multivariate linear regression in a discovery set (N=103) identified thalamus-derived RF associated with SDMT, which were retested in a replication set (N=63). Their associations with PASAT in a second MS cohort (N=176) and DSST in HC were also evaluated. We then tested whether the same RF, when extracted from the putamen, were associated with SDMT. LASSO models assessed the combined predictive value of RF and volumes. Figure 2 presents an overview of the involvement of different cohorts in the study, outlining the specific study objectives and the statistical analysis approaches employed. Results Twenty-eight RF–ROI pairs were associated with SDMT in the replication set (FDR<0.05). Of these, 24 were also associated with PASAT (FDR≤0.03), and 2 with DSST. Only ventral nuclei volume showed replicated associations among volumetrics. Only 4 putamen-derived pairs were associated with SDMT (FDR=0.04). LASSO results confirmed RF outperformed volumes. Discussion RF extracted from the thalamus are strongly associated with cognitive performance in PwMS, outperforming volumetric measures and supporting their potential as sensitive imaging biomarkers.

1562 Background: In Caucasian-predominant populations, overweight or obese NSCLC pts (BMI≥25-kg/m2) have better prognosis while underweight (BMI≤18.5-kg/m2) pts have a worse prognosis. A large pooled sample allowed us to evaluate the role of ethnicity in this BMI-NSCLC OS relationship. Methods: Using individual data, survival analysis was performed on 15 ILCCO studies, assessing the interactions between ethnicity and BMI on overall survival (OS). Adjusted Hazard Ratios (aHR) from Cox models and adjusted penalized smoothing spline plots were generated. Results: Among 13416 (77%) Caucasian, 2975 (17%) Asian, and 935 (5%) Black NSCLC pts analyzed, we confirmed that for all pts, being underweight at NSCLC diagnosis was associated with worse OS (aHR=1.68, CI 1.5-1.8, p<0.001), while overweight/obese pts had improved survival (aHR 0.89, CI 0.8-0.9, p<0.001), when compared to pts with normal BMI. In general, Black pts had poorer OS than Caucasian pts (aHR 1.26 CI 1.1-1.4, p<0.001). However, the BMI-OS relationship differed according to ethnicity (BMI-ethnicity interaction, p=0.009): Caucasian underweight pts had poorer OS (aHR 1.67, CI 1.5-1.8, P<0.001) while overweight/obese pts had improved OS (aHR 0.89, CI 0.8-0.9, P<0.001). In Asian pts, these two associations were aHR 1.15, CI 0.8-1.5, P=0.33, and aHR 0.91, CI 0.7-1.1, P=0.32, respectively. In Black pts, these two associations were aHR 1.06, CI 0.7-1.5, p=0.73 and 0.75, CI 0.6-0.8 p<0.001, respectively. For overweight/obese patients, as BMI rises from 25-kg/m2 through 45-kg/m2, the prognosis worsens for Caucasian pts, remains stable for Asian pts, but improves for Black pts. Conclusions: InCaucasian pts, being underweight had a greater negative impact on OS than for Asian or Black pts, while being obese had a greater beneficial impact in Blacks than in other ethnic groups. These ethnic differences likely reflect genetically-informed muscle/adipose tissue distributions, where Black pts may have less sarcopenic obesity than other ethnicities. In future prognostic studies, BMI relationships must account for ethnic differences.