Assessment of Tumor Infiltrating Lymphocytes in Predicting Stereotactic Ablative Radiotherapy (SABR) Response in Unresectable Breast Cancer

Background: Patients with advanced breast cancer (BC) may be treated with stereotactic ablative radiotherapy (SABR) for tumor control. Variable treatment responses are a clinical challenge and there is a need to predict tumor radiosensitivity a priori. There is evidence showing that tumor infiltrati...

Full description

Saved in:
Bibliographic Details
Main Authors: Mateusz Bielecki, Khadijeh Saednia, Fang-I Lu, Shely Kagan, Danny Vesprini, Katarzyna J. Jerzak, Roberto Salgado, Raffi Karshafian, William T. Tran
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Radiation
Subjects:
Online Access:https://www.mdpi.com/2673-592X/5/2/11
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850165044263780352
author Mateusz Bielecki
Khadijeh Saednia
Fang-I Lu
Shely Kagan
Danny Vesprini
Katarzyna J. Jerzak
Roberto Salgado
Raffi Karshafian
William T. Tran
author_facet Mateusz Bielecki
Khadijeh Saednia
Fang-I Lu
Shely Kagan
Danny Vesprini
Katarzyna J. Jerzak
Roberto Salgado
Raffi Karshafian
William T. Tran
author_sort Mateusz Bielecki
collection DOAJ
description Background: Patients with advanced breast cancer (BC) may be treated with stereotactic ablative radiotherapy (SABR) for tumor control. Variable treatment responses are a clinical challenge and there is a need to predict tumor radiosensitivity a priori. There is evidence showing that tumor infiltrating lymphocytes (TILs) are markers for chemotherapy response; however, this association has not yet been validated in breast radiation therapy. This pilot study investigates the computational analysis of TILs to predict SABR response in patients with inoperable BC. Methods: Patients with inoperable breast cancer (<i>n</i> = 22) were included for analysis and classified into partial response (<i>n</i> = 12) and stable disease (<i>n</i> = 10) groups. Pre-treatment tumor biopsies (<i>n</i> = 104) were prepared, digitally imaged, and underwent computational analysis. Whole slide images (WSIs) were pre-processed, and then a pre-trained convolutional neural network model (CNN) was employed to identify the regions of interest. The TILs were annotated, and spatial graph features were extracted. The clinical and spatial features were collected and analyzed using machine learning (ML) classifiers, including K-nearest neighbor (KNN), support vector machines (SVMs), and Gaussian Naïve Bayes (GNB), to predict the SABR response. The models were evaluated using receiver operator characteristics (ROCs) and area under the curve (AUC) analysis. Results: The KNN, SVM, and GNB models were implemented using clinical and graph features. Among the generated prediction models, the graph features showed higher predictive performances compared to the models containing clinical features alone. The highest-performing model, using computationally derived graph features, showed an AUC of 0.92, while the highest clinical model showed an AUC of 0.62 within unseen test sets. Conclusions: Spatial TIL models demonstrate strong potential for predicting SABR response in inoperable breast cancer. TILs indicate a higher independent predictive performance than clinical-level features alone.
format Article
id doaj-art-5d2c9c87c3bf46798233fd1036321125
institution OA Journals
issn 2673-592X
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Radiation
spelling doaj-art-5d2c9c87c3bf46798233fd10363211252025-08-20T02:21:50ZengMDPI AGRadiation2673-592X2025-04-01521110.3390/radiation5020011Assessment of Tumor Infiltrating Lymphocytes in Predicting Stereotactic Ablative Radiotherapy (SABR) Response in Unresectable Breast CancerMateusz Bielecki0Khadijeh Saednia1Fang-I Lu2Shely Kagan3Danny Vesprini4Katarzyna J. Jerzak5Roberto Salgado6Raffi Karshafian7William T. Tran8Biological Sciences Platform, Sunnybrook Research Institute, 2075 Bayview Ave., Room TB 097, Toronto, ON M4N 3M5, CanadaBiological Sciences Platform, Sunnybrook Research Institute, 2075 Bayview Ave., Room TB 097, Toronto, ON M4N 3M5, CanadaDepartment of Laboratory Medicine and Molecular Diagnostics, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaBiological Sciences Platform, Sunnybrook Research Institute, 2075 Bayview Ave., Room TB 097, Toronto, ON M4N 3M5, CanadaBiological Sciences Platform, Sunnybrook Research Institute, 2075 Bayview Ave., Room TB 097, Toronto, ON M4N 3M5, CanadaDivision of Medical Oncology and Hematology, Odette Cancer Centre, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Pathology, ZAS Hospitals, 2020 Antwerp, BelgiumDepartment of Physics, Toronto Metropolitan University, Toronto, ON M5B 2K3, CanadaBiological Sciences Platform, Sunnybrook Research Institute, 2075 Bayview Ave., Room TB 097, Toronto, ON M4N 3M5, CanadaBackground: Patients with advanced breast cancer (BC) may be treated with stereotactic ablative radiotherapy (SABR) for tumor control. Variable treatment responses are a clinical challenge and there is a need to predict tumor radiosensitivity a priori. There is evidence showing that tumor infiltrating lymphocytes (TILs) are markers for chemotherapy response; however, this association has not yet been validated in breast radiation therapy. This pilot study investigates the computational analysis of TILs to predict SABR response in patients with inoperable BC. Methods: Patients with inoperable breast cancer (<i>n</i> = 22) were included for analysis and classified into partial response (<i>n</i> = 12) and stable disease (<i>n</i> = 10) groups. Pre-treatment tumor biopsies (<i>n</i> = 104) were prepared, digitally imaged, and underwent computational analysis. Whole slide images (WSIs) were pre-processed, and then a pre-trained convolutional neural network model (CNN) was employed to identify the regions of interest. The TILs were annotated, and spatial graph features were extracted. The clinical and spatial features were collected and analyzed using machine learning (ML) classifiers, including K-nearest neighbor (KNN), support vector machines (SVMs), and Gaussian Naïve Bayes (GNB), to predict the SABR response. The models were evaluated using receiver operator characteristics (ROCs) and area under the curve (AUC) analysis. Results: The KNN, SVM, and GNB models were implemented using clinical and graph features. Among the generated prediction models, the graph features showed higher predictive performances compared to the models containing clinical features alone. The highest-performing model, using computationally derived graph features, showed an AUC of 0.92, while the highest clinical model showed an AUC of 0.62 within unseen test sets. Conclusions: Spatial TIL models demonstrate strong potential for predicting SABR response in inoperable breast cancer. TILs indicate a higher independent predictive performance than clinical-level features alone.https://www.mdpi.com/2673-592X/5/2/11stereotactic ablative radiotherapyadvanced inoperable breast cancertumor infiltrating lymphocytes
spellingShingle Mateusz Bielecki
Khadijeh Saednia
Fang-I Lu
Shely Kagan
Danny Vesprini
Katarzyna J. Jerzak
Roberto Salgado
Raffi Karshafian
William T. Tran
Assessment of Tumor Infiltrating Lymphocytes in Predicting Stereotactic Ablative Radiotherapy (SABR) Response in Unresectable Breast Cancer
Radiation
stereotactic ablative radiotherapy
advanced inoperable breast cancer
tumor infiltrating lymphocytes
title Assessment of Tumor Infiltrating Lymphocytes in Predicting Stereotactic Ablative Radiotherapy (SABR) Response in Unresectable Breast Cancer
title_full Assessment of Tumor Infiltrating Lymphocytes in Predicting Stereotactic Ablative Radiotherapy (SABR) Response in Unresectable Breast Cancer
title_fullStr Assessment of Tumor Infiltrating Lymphocytes in Predicting Stereotactic Ablative Radiotherapy (SABR) Response in Unresectable Breast Cancer
title_full_unstemmed Assessment of Tumor Infiltrating Lymphocytes in Predicting Stereotactic Ablative Radiotherapy (SABR) Response in Unresectable Breast Cancer
title_short Assessment of Tumor Infiltrating Lymphocytes in Predicting Stereotactic Ablative Radiotherapy (SABR) Response in Unresectable Breast Cancer
title_sort assessment of tumor infiltrating lymphocytes in predicting stereotactic ablative radiotherapy sabr response in unresectable breast cancer
topic stereotactic ablative radiotherapy
advanced inoperable breast cancer
tumor infiltrating lymphocytes
url https://www.mdpi.com/2673-592X/5/2/11
work_keys_str_mv AT mateuszbielecki assessmentoftumorinfiltratinglymphocytesinpredictingstereotacticablativeradiotherapysabrresponseinunresectablebreastcancer
AT khadijehsaednia assessmentoftumorinfiltratinglymphocytesinpredictingstereotacticablativeradiotherapysabrresponseinunresectablebreastcancer
AT fangilu assessmentoftumorinfiltratinglymphocytesinpredictingstereotacticablativeradiotherapysabrresponseinunresectablebreastcancer
AT shelykagan assessmentoftumorinfiltratinglymphocytesinpredictingstereotacticablativeradiotherapysabrresponseinunresectablebreastcancer
AT dannyvesprini assessmentoftumorinfiltratinglymphocytesinpredictingstereotacticablativeradiotherapysabrresponseinunresectablebreastcancer
AT katarzynajjerzak assessmentoftumorinfiltratinglymphocytesinpredictingstereotacticablativeradiotherapysabrresponseinunresectablebreastcancer
AT robertosalgado assessmentoftumorinfiltratinglymphocytesinpredictingstereotacticablativeradiotherapysabrresponseinunresectablebreastcancer
AT raffikarshafian assessmentoftumorinfiltratinglymphocytesinpredictingstereotacticablativeradiotherapysabrresponseinunresectablebreastcancer
AT williamttran assessmentoftumorinfiltratinglymphocytesinpredictingstereotacticablativeradiotherapysabrresponseinunresectablebreastcancer