Prognostic Factors and Tumor Infiltrating Lymphocytes in Triple Negative Breast Cancer

Dülgar, Özgecan; İlvan, Şennur; Turna, Zeynep Hande

doi:10.5152/ejbh.2020.5305

Cited by 6 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the postoperative pathological results of patients in this study, TILs were correlated with pathological grade, peritumor vascular invasion, molecular typing and other factors, which were in agreement with the conclusions of previous studies (Pruneri et al, 2016b;Criscitiello et al, 2020;Dülgar et al, 2020). In addition, this study innovatively found that BRCA peri-tumor nerve invasion was also negatively correlated with TILs, providing another influencing factor as a reference, although the specific mechanism still needs to be further explored.…”

Section: Validation Of Nomogram In Nat Patientssupporting

confidence: 90%

Nomogram to Predict Tumor-Infiltrating Lymphocytes in Breast Cancer Patients

Feng

Huang

et al. 2021

Front. Mol. Biosci.

View full text Add to dashboard Cite

Background: Tumor-infiltrating lymphocytes (TILs) play important roles in the prediction of prognosis and neoadjuvant therapy (NAT) efficacy in breast cancer (BRCA) patients, in this study, we identified clinicopathological factors related to BRCA TILs, then to construct and validate nomogram to predict high density of TILs.Methods: A total of 826 patients diagnosed with BRCA in Sun Yat-Sen University cancer center were enrolled in nomogram cohort. TILs were assessed using hematoxylin-eosin (H&E) staining by two pathologists. Complete clinical data were collected for analysis. Then the enrolled patients were split into a training set and validation set at a ratio of 8:2. and the backward multivariate binary logistic regression model was used to establish nomogram for predicting BRCA TILs, which were further evaluated and validated using the C-index, receiver operating characteristic (ROC) curves and calibration curves. Then another independent NAT cohort of 106 patients was established for verifying this nomogram in NAT efficacy prediction.Results: TILs were significantly correlated with body mass index (BMI), tumor differentiation, ER, PR, HER2 expression, Ki67, blood biochemical indicators including total bilirubin (TBIL), indirect bilirubin (IBIL), total protein (TP), Globulin (GLOB), inorganic phosphorus (IP), calcium (Ca). In which ER expression level [OR = 0.987, 95%CI (0.982–0.992), p < 0.001], IP [OR = 4.462, 95%CI (1.171∼17.289), p = 0.029], IBIL [OR = 0.906, 95%CI (0.845–0.966), p = 0.004] and TP [OR = 1.053, 95%CI (1.010–1.098, p = 0.016)] were independent predictors of TILs. Then nomogram was established, for which calibration curves (C-index = 0.759) and ROC curve (AUC = 0.759, 95%CI 0.717–0.801) in training sets, calibration curves (C-index = 0.708) and ROC curve (AUC = 0.708, 95%CI 0.617–0.800) in validation sets demonstrated great evaluation efficiency. Besides, independent NAT cohort verified this nomogram can distinguish patients with greater NAT efficacy (p = 0.041).Conclusion: The finds of clinicopathological factors associated with TILs could help clinicians to understand the tumor immunity of BRCA and improve treatment system for patients, and the established nomogram with high evaluation efficiency may be used as a complement tool for distinguishing patients with better NAT efficacy.

show abstract

Section: Validation Of Nomogram In Nat Patientssupporting

confidence: 90%

Nomogram to Predict Tumor-Infiltrating Lymphocytes in Breast Cancer Patients

Feng

Huang

et al. 2021

Front. Mol. Biosci.

View full text Add to dashboard Cite

show abstract

“…Several studies have shown that histopathological TME components, particularly TILs, can be used to predict pCR because increased counts of sTILs and tTILs have been correlated with pCR in TNBC patients [30,31]. TILs mirror the local immune response, and high TIL counts are associated with favorable OS in patients with TNBC [32][33][34]. Although H&E WSIs can be used to enumerate TILs, they do not provide information on the various types of TILs in the TME.…”

Section: Discussionmentioning

confidence: 99%

Predicting Neoadjuvant Treatment Response in Triple-Negative Breast Cancer Using Machine Learning

Bhattarai,

Saini,

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Background: Neoadjuvant chemotherapy (NAC) is the standard treatment for early-stage triple negative breast cancer (TNBC). The primary endpoint of NAC is a pathological complete response (pCR). NAC results in pCR in only 30–40% of TNBC patients. Tumor-infiltrating lymphocytes (TILs), Ki67 and phosphohistone H3 (pH3) are a few known biomarkers to predict NAC response. Currently, systematic evaluation of the combined value of these biomarkers in predicting NAC response is lacking. In this study, the predictive value of markers derived from H&E and IHC stained biopsy tissue was comprehensively evaluated using a supervised machine learning (ML)-based approach. Identifying predictive biomarkers could help guide therapeutic decisions by enabling precise stratification of TNBC patients into responders and partial or non-responders. Methods: Serial sections from core needle biopsies (n = 76) were stained with H&E and immunohistochemically for the Ki67 and pH3 markers, followed by whole-slide image (WSI) generation. The serial section stains in H&E stain, Ki67 and pH3 markers formed WSI triplets for each patient. The resulting WSI triplets were co-registered with H&E WSIs serving as the reference. Separate mask region-based CNN (MRCNN) models were trained with annotated H&E, Ki67 and pH3 images for detecting tumor cells, stromal and intratumoral TILs (sTILs and tTILs), Ki67+, and pH3+ cells. Top image patches with a high density of cells of interest were identified as hotspots. Best classifiers for NAC response prediction were identified by training multiple ML models and evaluating their performance by accuracy, area under curve, and confusion matrix analyses. Results: Highest prediction accuracy was achieved when hotspot regions were identified by tTIL counts and each hotspot was represented by measures of tTILs, sTILs, tumor cells, Ki67+, and pH3+ features. Regardless of the hotspot selection metric, a complementary use of multiple histological features (tTILs, sTILs) and molecular biomarkers (Ki67 and pH3) resulted in top ranked performance at the patient level. Conclusions: Overall, our results emphasize that prediction models for NAC response should be based on biomarkers in combination rather than in isolation. Our study provides compelling evidence to support the use of ML-based models to predict NAC response in patients with TNBC.

show abstract

“…Several studies have shown that histopathological TME components, particularly TILs, can be used to predict pCR because increased counts of sTILs and tTILs have been correlated with pCR in TNBC patients (27,28). TILs mirror the local immune response, and high TIL counts are associated with favorable OS in patients with TNBC (29)(30)(31).…”

Section: Discussionmentioning

confidence: 99%

Predicting neoadjuvant treatment response in triple-negative breast cancer using machine learning

Bhattarai

Saini

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Neoadjuvant chemotherapy (NAC) is the standard treatment for early-stage triple negative breast cancer (TNBC). The primary endpoint of NAC is a pathological complete response (pCR). NAC results in pCR in only 30% to 40% of TNBC patients. Tumor-infiltrating lymphocytes (TILs), Ki67 and phosphohistone H3 (pH3) are a few known biomarkers to predict NAC response. Currently, systematic evaluation of the combined value of these biomarkers in predicting NAC response is lacking. In this study, the predictive value of markers derived from H&E and IHC stained biopsy tissue was comprehensively evaluated using a supervised machine learning (ML)-based approach. Identifying predictive biomarkers could help guide therapeutic decisions by enabling precise stratification of TNBC patients into responders and partial or non-responders. Methods: Serial sections from core needle biopsies (n=76) were stained with H&E, and immunohistochemically for the Ki67 and pH3 markers, followed by whole slide image (WSI) generation. The resulting WSI triplets were co-registered with H&E WSIs serving as the reference. Separate mask region-based CNN (MRCNN) models were trained with annotated H&E, Ki67 and pH3 images for detecting tumor cells, stromal and intratumoral TILs (sTILs and tTILs), Ki67+, and pH3+ cells. Top image patches with a high density of cells of interest were identified as hotspots. Best classifiers for NAC response prediction were identified by training multiple ML models, and evaluating their performance by accuracy, area under curve, and confusion matrix analyses. Results: Highest prediction accuracy was achieved when hotspot regions were identified by tTIL counts and each hotspot was represented by measures of tTILs, sTILs, tumor cells, Ki67+, and pH3+ features. Regardless of the hotspot selection metric, a complementary use of multiple histological features (tTILs, sTILs) and molecular biomarkers (Ki67 and pH3) resulted in top ranked performance at the patient level. Conclusions: Overall, our results emphasize that prediction models for NAC response should be based on biomarkers in combination rather than in isolation. Our study provides compelling evidence to support the use of ML-based models to predict NAC response in patients with TNBC.

show abstract

Prognostic Factors and Tumor Infiltrating Lymphocytes in Triple Negative Breast Cancer

Cited by 6 publications

References 22 publications

Nomogram to Predict Tumor-Infiltrating Lymphocytes in Breast Cancer Patients

Nomogram to Predict Tumor-Infiltrating Lymphocytes in Breast Cancer Patients

Predicting Neoadjuvant Treatment Response in Triple-Negative Breast Cancer Using Machine Learning

Predicting neoadjuvant treatment response in triple-negative breast cancer using machine learning

Contact Info

Product

Resources

About