Related Experiment Video
Updated: Jul 31, 2025
Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
Published on: April 12, 2024
Whole slide image features predict pathologic complete response and poor clinical outcomes in triple-negative breast
Sean M Hacking1, Julie Karam2, Kamaljeet Singh3
1Department of Pathology and Laboratory Medicine, Rhode Island Hospital and Lifespan Medical Center, Providence, RI, United States; Department of Pathology and Laboratory Medicine, Warren Alpert Medical School of Brown University, Providence, RI, United States.
Introduction:
Breast cancers are complex ecosystem like networks of malignant cells and their associated microenvironment. Applications for machine intelligence and the tumoral microenvironment are expanding frontiers in pathology. Previously, computational approaches have been developed to quantify and spatially analyze immune cells, proportionate stroma, and detect tumor budding. Little work has been done to analyze different types of tumor-associated stromata both quantitatively and computationally in relation to clinical endpoints.
Methods:
We aimed to quantify stromal features from whole slide images (WSI) including stromata (myxoid, collagenous, immune) and tumoral components and combined them with traditional clinical and pathologic parameters in 120 triple-negative breast cancer (TNBC) patients treated with neoadjuvant chemotherapy (NAC) to predict pathologic complete response (pCR) and poor clinical outcomes.
Results:
High collagenous stroma on WSI was best associated with lower rates of pCR, while combined high proportionated stroma (myxoid, collagenous, and immune) most optimally predicted worse clinical survival outcomes. When combining clinical, pathologic, and WSI features, Receiver Operator Characteristics (ROC) curves for LASSO features was up to 0.67 for pCR and 0.77 for poor outcomes.
Conclusion:
The techniques demonstrated in the present study can be performed with appropriate quality assurance. Future trials are needed to demonstrate whether coupling applications for machine intelligence, inclusive of the tumor mesenchyme, can improve outcomes prediction for patients with breast cancer.
