Preoperative Radiomics Approach to Evaluating Tumor-Infiltrating CD8+ T Cells in Patients With Pancreatic Ductal Adenocarcinoma Using Noncontrast Magnetic Resonance Imaging

BACKGROUND

CD8+ T cell in pancreatic ductal adenocarcinoma (PDAC) is closely related to the prognosis and treatment response of patients. Accurate preoperative CD8+ T-cell expression can better identify the population benefitting from immunotherapy.

PURPOSE

To develop and validate a machine learning classifier based on noncontrast magnetic resonance imaging (MRI) for the preoperative prediction of CD8+ T-cell expression in patients with PDAC.

STUDY TYPE

Retrospective cohort study.

POPULATION

Overall, 114 patients with PDAC undergoing MR scan and surgical resection; 97 and 47 patients in the training and validation cohorts. FIELD STRENGTH/SEQUENCE/3 T: Breath-hold single-shot fast-spin echo T2-weighted sequence and noncontrast T1-weighted fat-suppressed sequences.

ASSESSMENT

CD8+ T-cell expression was quantified using immunohistochemistry. For each patient, 2232 radiomics features were extracted from noncontrast T1- and T2-weighted images and reduced using the Wilcoxon rank-sum test and least absolute shrinkage and selection operator method. Linear discriminative analysis was used to construct radiomics and mixed models. Model performance was determined by its discriminative ability, calibration, and clinical utility.

STATISTICAL TESTS

Kaplan-Meier estimates, Student's t-test, the Kruskal-Wallis H test, and the chi-square test, receiver operating characteristic curve, and decision curve analysis.

RESULTS

A log-rank test showed that the survival duration in the CD8-high group (25.51 months) was significantly longer than that in the CD8-low group (22.92 months). The mixed model included all MRI characteristics and 13 selected radiomics features, and the area under the curve (AUC) was 0.89 (95% confidence interval [CI], 0.77-0.92) and 0.69 (95% CI, 0.53-0.82) in the training and validation cohorts. The radiomics model included 13 radiomics features, which showed good discrimination in the training cohort (AUC, 0.85; 95% CI, 0.77-0.92) and the validation cohort (AUC, 0.76; 95% CI, 0.61-0.87).

DATA CONCLUSIONS

This study developed a noncontrast MRI-based radiomics model that can preoperatively determine CD8+ T-cell expression in patients with PDAC and potentially immunotherapy planning.

EVIDENCE LEVEL

5 TECHNICAL EFFICACY: Stage 2.

Machine learning for MRI radiomics: a study predicting tumor-infiltrating lymphocytes in patients with pancreatic ductal adenocarcinoma

OBJECTIVE

To develop and validate a machine learning classifier based on magnetic resonance imaging (MRI), for the preoperative prediction of tumor-infiltrating lymphocytes (TILs) in patients with pancreatic ductal adenocarcinoma (PDAC).

MATERIALS AND METHODS

In this retrospective study, 156 patients with PDAC underwent MR scan and surgical resection. The expression of CD4, CD8 and CD20 was detected and quantified using immunohistochemistry, and TILs score was achieved by Cox regression model. All patients were divided into TILs score-low and TILs score-high groups. The least absolute shrinkage and selection operator method and the extreme gradient boosting (XGBoost) were used to select the features and to construct a prediction model. The performance of the models was assessed using the training cohort (116 patients) and the validation cohort (40 patients), and decision curve analysis (DCA) was applied for clinical use.

RESULTS

The XGBoost prediction model showed good discrimination in the training (AUC 0.86; 95% CI 0.79-0.93) and validation sets (AUC 0.79; 95% CI 0.64-0.93). The sensitivity, specificity, and accuracy for the training set were 86.67%, 75.00%, and 0.81, respectively, whereas those for the validation set were 84.21%, 66.67%, and 0.75, respectively. Decision curve analysis indicated the clinical usefulness of the XGBoost classifier.

CONCLUSION

The model constructed by XGBoost could predict PDAC TILs and may aid clinical decision making for immune therapy.

[Correlation of qAnti-HBc with antiviral efficacy in children with chronic hepatitis B and exploration of its possible immune mechanism]

Objective: To compare the baseline difference in the quantitative hepatitis B core antibody levels (qAnti-HBc) between non-response and response group in children with HBeAg-positive chronic hepatitis B (CHB) who received antiviral therapy, and further explore the proportion and functional activity of CD8 + memory T lymphocyte subsets with different qAnti-HBC levels in peripheral blood of children. Methods: The baseline anti-HBc quantification (qAnti-HBc) levels of 85 children with HBeAg-positive CHB who visited the Department of Infectious Diseases, Children's Hospital of Chongqing Medical University from June 2018 to December 2020 were detected retrospectively. The relationship between the baseline qAnti-HBc level and HBeAg serological response in 37 children who received antiviral therapy was analyzed. The proportion of CD8(+) memory T lymphocyte subsets and the secretion levels of interferon (IFN) γ, and tumor necrosis factor (TNF) α in peripheral blood of 59 children at baseline were detected by flow cytometry. The relationship between qAnti-HBc level and the proportion and functional activity of CD8(+) memory T lymphocyte subsets was analyzed. Pearson's Chi-square test was used to compare the count data. Mann-Whitney U test or Kruskal-Wallis test was used to compare measurement data between two or more groups, and Spearman's rank correlation analysis was used for the correlation between continuous variables. Results: Among 37 children who received entecavir (ETV, 21/37 cases) or pegylated interferon (Peg-IFN, 16/37 cases), 18 cases had developed HBeAg seroconversion (10/ 21 cases in the ETV group, 8/16 cases in the Peg-IFN group). The baseline qAnti-HBc level was significantly higher in the response group [4.71 (4.64~4.81) log(10)IU/ml] than the non-response group children [4.54 (4.45~4.64) log(10)IU/ml, Z = -3.316, P = 0.001]. The proportion of CD8(+) Tem, CD38(+)CD8(+) Tem, CD38(+)CD8(+) Temra cells and the levels of IFNγ and TNFα secreted by CD8(+) T lymphocytes were significantly higher in the high-qAnti-HBc group than the low-qAnti-HBc group (P < 0.05). The proportion of CD8(+) Tem, CD38(+)CD8(+) Tem and CD38(+)CD8(+) Temra cells was significantly higher in ALT > 1× upper limit of normal value (ULN) group than ALT≤1×ULN group (P < 0.05). However, there were no significant differences in the levels of IFNγ and TNFα secreted by CD8(+) T lymphocytes between the two groups (P > 0.05). Spearman's correlation analysis showed that qAnti-HBc was positively correlated with the proportion of CD8(+) Tem, CD38(+)CD8(+) Tem, CD38(+)CD8(+) Temra cells and the level of IFNγ secreted by CD8(+)T lymphocytes (P < 0.05). Additionally, ALT was only positively correlated with the proportion of CD38(+)CD8(+) TEM and CD38(+) CD8(+) Temra cells (P < 0.05). Conclusion: Raised baseline qAnti-HBc level is related to the HBeAg serological response to antiviral therapy in children with CHB. Peripheral blood effector CD8+ T lymphocytes of CHB children with higher qAnti-HBc show stronger phenotype and functional activation characteristics, which may shed some light on the underlying immune mechanism related to antiviral therapy efficacy in children with CHB.

XGBoost Classifier Based on Computed Tomography Radiomics for Prediction of Tumor-Infiltrating CD8+ T-Cells in Patients With Pancreatic Ductal Adenocarcinoma

Objectives

This study constructed and validated a machine learning model to predict CD8⁺ tumor-infiltrating lymphocyte expression levels in patients with pancreatic ductal adenocarcinoma (PDAC) using computed tomography (CT) radiomic features.

Materials and Methods

In this retrospective study, 184 PDAC patients were randomly assigned to a training dataset (n =137) and validation dataset (n =47). All patients were divided into CD8⁺ T-high and -low groups using X-tile plots. A total of 1409 radiomics features were extracted from the segmentation of regions of interest, based on preoperative CT images of each patient. The LASSO algorithm was applied to reduce the dimensionality of the data and select features. The extreme gradient boosting classifier (XGBoost) was developed using a training set consisting of 137 consecutive patients admitted between January 2017 and December 2017. The model was validated in 47 consecutive patients admitted between January 2018 and April 2018. The performance of the XGBoost classifier was determined by its discriminative ability, calibration, and clinical usefulness.

Results

The cut-off value of the CD8⁺ T-cell level was 18.69%, as determined by the X-tile program. A Kaplan−Meier analysis indicated a correlation between higher CD8⁺ T-cell levels and better overall survival (p = 0.001). The XGBoost classifier showed good discrimination in the training set (area under curve [AUC], 0.75; 95% confidence interval [CI]: 0.67–0.83) and validation set (AUC, 0.67; 95% CI: 0.51–0.83). Moreover, it showed a good calibration. The sensitivity, specificity, accuracy, positive and negative predictive values were 80.65%, 60.00%, 0.69, 0.63, and 0.79, respectively, for the training set, and 80.95%, 57.69%, 0.68, 0.61, and 0.79, respectively, for the validation set.

Conclusions

We developed a CT-based XGBoost classifier to extrapolate the infiltration levels of CD8⁺ T-cells in patients with PDAC. This method could be useful in identifying potential patients who can benefit from immunotherapies.

[Correlation between CTL and Th1 cell proportion in peripheral blood of liver transplantation recipients and the success of hepatitis B vaccination]

Objective: To investigate the correlation between the proportion of CTL and Th1 cells in peripheral blood of liver transplant recipients and the success of hepatitis B vaccination. Methods: The subjects of this study were liver transplantation recipients with chronic HBV-related liver diseases in Organ transplantation institute of the third medical center of PLA general hospital. Subjects were randomly divided into two groups for prospective study. In the rapid group, one dose of 40 μg hepatitis B vaccine was administered at 0, 1, 2and 3 months, and one dose of 20 μg hepatitis B vaccine was administered at 4, 5 and 6 months. In the rapid-enhanced group, one dose of 40 μg hepatitis B vaccine was administered at 0, 1, 2 and 3 months, and one dose of 60 μg hepatitis B vaccine was administered at 4, 5 and 6months. Compare and analyze the success rate of inoculation, the titer of hepatitis B surface antibody (anti-HBs), the proportion of CTL cells in CD8(+)T cells and Th1 cells in CD4(+)T cells. Correlation analysis was performed for CTL and Th1 cells and anti-HBs, Observe the safety of vaccination. Results: The inoculation success rate, anti-HBs growth rate, CTL cell percentage increase and Th1 cell percentage increase in the rapid enhancement group were all higher than those in the rapid enhancement group, and the differences were statistically significant, they were 38.3% (23/60) vs 21.7% (13/60) (P=0.046), 91.3(72.5,124.2) vs 22.1(12.4, 31.6) (P=0.001), 1.4(0.8,1.9) vs 0.4(0.2,1.4) (P=0.001) and 7.4±2.6 vs 5.6±3.7 (P=0.001) respectively. The percentage increase of CTL cells and Th1 cells in the successful group was greater than that in the non-successful group, and the difference was statistically significant. They were 1.9(1.4,2.5) vs 0.1(0.0,1.1) (P=0.024) and 9.6±3.1 vs 2.4±2.0 (P<0.001). There was no significant correlation between anti-HBs increase (105.5±37.1) and CTL increase 1(0,3) (P=0.099), while there was significant positive correlation with Th1 increase 7(2,11) (P<0.001). No rejection reaction occurred during the study period, and there was no special abnormal change in the safety index. Conclusion: Reasonable increase of vaccine dose can up-regulate Th1 cell expression and promote the generation of anti-HBs.