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

Abstract

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.

Radiomic Signatures Associated with CD8+ Tumour-Infiltrating Lymphocytes: A Systematic Review and Quality Assessment Study

“…A series of pancreatic ductal adenocarcinoma (PDAC) studies published by Bian, Y. and colleagues analysed images acquired via contrast-enhanced CT [ 54 ], contrast-enhanced MRI [ 55 ], and non-contrast MRI [ 56 ]. All three studies were aimed at predicting lesion CD8 + TIL levels.…”

“…Even between studies of the same cancer group, the reproducibility of radiomic features was limited. The only exception to this was a higher-order radiomic feature (wavelet-filtered first-order median), which appeared to be reproducible between two PDAC studies using different MRI protocols [ 55 , 56 ]. However, we highlight that both studies originated from the same institution.…”

Radiomics features for assessing tumor-infiltrating lymphocytes correlate with molecular traits of triple-negative breast cancer

“…In addition, the high accuracy (0.71), sensitivity (0.89) and specificity (0.70) also validated our model. Prior to the present study, several studies explored the relationship between radiomics and TILs [ 38 – 46 ]. Consistent with our work, the range of AUC, sensitivity and specificity of these studies were 0.67–0.87, 0.63–0.89 and 0.56–0.91, respectively.…”

Basic pancreatic lesions: Radiologic-pathologic correlation

“…[ 62 , 63 ] The concept behind radiomics is that medical images contain much more information than is visible to the eyes of radiologists, which is called “hidden” information. [ 64 ] Radiomics combined artificial intelligence (AI) algorithms, particularly deep learning, has demonstrated remarkable progress in pancreatic image-recognition tasks including tumor classification, [ 65 , 66 , 67 ] grade, [ 68 , 69 , 70 ] survival, [ 71 , 72 ] treatment respond prediction, [ 73 , 74 , 75 , 76 ] lymphatic metastasis, [ 77 , 78 , 79 ] tumor microenvironment, [ 80 , 81 , 82 ] and so on. In the future, the diagnosis of pancreatic diseases will enter an era of precision and individuation.…”