Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics

Jiang, Yuming; Zhou, Kangneng; Sun, Zhiwei; Wang, Hongyu; Xie, Jingjing; Zhang, Taojun; Sang, Shengtian; Islam, Md Tauhidul; Wang, Jen-Yeu; Chen, Chuanli; Yuan, Qingyu; Shi, Xi; Li, Tuanjie; Xu, Yikai; Xiong, Wenjun; Wang, Wei; Li, Guoxin; Li, Ruijiang

doi:10.1016/j.xcrm.2023.101146

Cited by 6 publications

(4 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By integrating radiomics and deep learning analysis, a noninvasive method for predicting the TME status from radiological images was created. The approach predicts the clinical response in patients receiving checkpoint blockade immunotherapy, and, when paired with current biomarkers, it further increases prediction accuracy [ 56 ].…”

Section: Other Factorsmentioning

confidence: 99%

Predictive Factors of Immunotherapy in Gastric Cancer: A 2024 Update

Bintintan,

Burz,

Pintea

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Many studies on gastric cancer treatment have identified predictors of immunotherapy benefits. This article provides an update on the major developments in research related to predictive factors of immunotherapy for gastric cancer. We used the search term “predictive factors, immunotherapy, gastric cancer” to find the most current publications in the PubMed database related to predictive factors of immunotherapy in gastric cancer. Programmed cell death, genetic, and immunological factors are the main study topics of immunotherapy’s predictive factors in gastric cancer. Other preventive factors for immunotherapy in gastric cancer were also found, including clinical factors, tumor microenvironment factors, imaging factors, and extracellular factors. Since there is currently no effective treatment for gastric cancer, we strongly propose that these studies be prioritized.

show abstract

Section: Other Factorsmentioning

confidence: 99%

Predictive Factors of Immunotherapy in Gastric Cancer: A 2024 Update

Bintintan,

Burz,

Pintea

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…11 12 The effectiveness of immune checkpoint inhibition is intricately influenced by the intricate interplay between tumor, microenvironment, and host factors, resulting in the overall treatment outcome. [13][14][15][16] H&E-stained whole slide images (WSI) contain valuable information about the tumor microenvironment. Pathomics analyses hold potential in a range of tasks.…”

Section: Introductionmentioning

confidence: 99%

Development and interpretation of a pathomics-driven ensemble model for predicting the response to immunotherapy in gastric cancer

Han,

Zhang,

Yang

et al. 2024

J Immunother Cancer

Self Cite

View full text Add to dashboard Cite

BackgroundOnly a subset of patients with gastric cancer experience long-term benefits from immune checkpoint inhibitors (ICIs). Currently, there is a deficiency in precise predictive biomarkers for ICI efficacy. The aim of this study was to develop and validate a pathomics-driven ensemble model for predicting the response to ICIs in gastric cancer, using H&E-stained whole slide images (WSI).MethodsThis multicenter study retrospectively collected and analyzed H&E-stained WSIs and clinical data from 584 patients with gastric cancer. An ensemble model, integrating four classifiers: least absolute shrinkage and selection operator, k-nearest neighbors, decision trees, and random forests, was developed and validated using pathomics features, with the objective of predicting the therapeutic efficacy of immune checkpoint inhibition. Model performance was evaluated using metrics including the area under the curve (AUC), sensitivity, and specificity. Additionally, SHAP (SHapley Additive exPlanations) analysis was used to explain the model’s predicted values as the sum of the attribution values for each input feature. Pathogenomics analysis was employed to explain the molecular mechanisms underlying the model’s predictions.ResultsOur pathomics-driven ensemble model effectively stratified the response to ICIs in training cohort (AUC 0.985 (95% CI 0.971 to 0.999)), which was further validated in internal validation cohort (AUC 0.921 (95% CI 0.839 to 0.999)), as well as in external validation cohort 1 (AUC 0.914 (95% CI 0.837 to 0.990)), and external validation cohort 2 (0.927 (95% CI 0.802 to 0.999)). The univariate Cox regression analysis revealed that the prediction signature of pathomics-driven ensemble model was a prognostic factor for progression-free survival in patients with gastric cancer who underwent immunotherapy (p<0.001, HR 0.35 (95% CI 0.24 to 0.50)), and remained an independent predictor after multivariable Cox regression adjusted for clinicopathological variables, (including sex, age, carcinoembryonic antigen, carbohydrate antigen 19-9, therapy regime, line of therapy, differentiation, location and programmed death ligand 1 (PD-L1) expression in all patients (p<0.001, HR 0.34 (95% CI 0.24 to 0.50)). Pathogenomics analysis suggested that the ensemble model is driven by molecular-level immune, cancer, metabolism-related pathways, and was correlated with the immune-related characteristics, including immune score, Estimation of STromal and Immune cells in MAlignant Tumor tissues using Expression data score, and tumor purity.ConclusionsOur pathomics-driven ensemble model exhibited high accuracy and robustness in predicting the response to ICIs using WSIs. Therefore, it could serve as a novel and valuable tool to facilitate precision immunotherapy.

show abstract

“…The pre-treatment TIME is a major determinant of response to immunotherapy across various cancers [11,16,17]. Recent studies have established that the pre-treatment TIME plays an important role in determining BCG therapy response in patients with NMIBC [18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Increased stromal densities of B cells, CD103+ cells, and CD163+ M2-like macrophages associate with poor clinical outcomes in BCG treated non-muscle invasive bladder cancer

Ravenscroft,

Yolmo,

Chenard

et al. 2023

Preprint

View full text Add to dashboard Cite

Non-muscle invasive bladder cancer (NMIBC) constitutes a significant clinical challenge, with over 50% of patients experiencing poor clinical outcomes in the form of early recurrence or progression following treatment with Bacillus Calmette-Guerin (BCG) immunotherapy. The pre-treatment tumor immune microenvironment (TIME) is an established determinant of response to BCG. This study explores the spatial profiles of CD79a+ B cells, CD163+ M2-like macrophages, proliferating and tissue-resident phenotypes of T cells, along with PD-1/PD-L1 checkpoint expression in pre-BCG treatment tumors of 173 patients (139 males, 34 females). Multiplex immunofluorescence staining of a tumor tissue microarray, revealed elevated infiltration of CD79a+ B cells, CD163+ M2-like macrophages, CD103+ cells, and CD8+ T cells at the tumor invasive margins. Increased epithelial PD-L1 immune-checkpoint expression in tumors was observed in female and male patients who exhibited significantly shorter recurrence-free survival (RFS). Importantly, high CD79a+ B cell density in BCG-treated females in both stromal and epithelial compartments exhibited significantly shorter RFS and progression-free survival compared to males. Stromal CD79a+ B cell density was positively correlated with M2-like macrophages, CD8+ T cells, CD103+ cells and PD-1 expressing cells. CD79a+ B cells, CD103+ cells, and M2-like macrophage density were associated with higher grade and enriched in basal subtype tumor. This study highlights the significance of an understudied role of B cells and their cellular neighborhoods in the pre-treatment TIME and BCG-therapy response. Overall, findings from this study underscore the importance of considering sex-related immunobiological differences in the stromal compartments of bladder tumors towards the development of optimal therapeutic targeting strategies.

show abstract

Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics

Cited by 6 publications

References 54 publications

Predictive Factors of Immunotherapy in Gastric Cancer: A 2024 Update

Predictive Factors of Immunotherapy in Gastric Cancer: A 2024 Update

Development and interpretation of a pathomics-driven ensemble model for predicting the response to immunotherapy in gastric cancer

Increased stromal densities of B cells, CD103+ cells, and CD163+ M2-like macrophages associate with poor clinical outcomes in BCG treated non-muscle invasive bladder cancer

Contact Info

Product

Resources

About