Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Approach to mediastinal cytopathology: a diagnostic overview.

Mediastinum (Hong Kong, China)·2026
Same author

Merlin deficiency supports an immunosuppressive milieu in breast cancer.

Cell death discovery·2026
Same author

Weakly Supervised Teacher-Student Framework with Progressive Pseudo-mask Refinement for Gland Segmentation.

Journal of clinical and translational pathology·2026
Same author

Postradiation angiosarcoma of the breast: a 25-year single-institution analysis of clinicopathological characteristics and immunohistochemical biomarker study.

Biotechnic & histochemistry : official publication of the Biological Stain Commission·2026
Same author

Molecular Classification of Endometrial Carcinomas: Review and Recent Updates.

Cancers·2026
Same author

Concurrent <i>MYC</i>-Amplified Secondary Angiosarcoma and Recurrent Carcinoma in the Breast: A Rare Presentation With Unique Clinical Features and Distinct <i>MYC</i> Amplification Patterns.

International journal of surgical pathology·2025

Related Experiment Video

Updated: Sep 11, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Predicting Neoadjuvant Chemotherapy Response in Triple-Negative Breast Cancer Using Pre-Treatment Histopathologic

Hikmat Khan1, Ziyu Su1, Huina Zhang2

  • 1Department of Pathology, College of Medicine, Wexner Medical Center, The Ohio State University, Columbus, OH 43210, USA.

Cancers
|August 14, 2025
PubMed
Summary

An AI model predicts neoadjuvant chemotherapy (NACT) response in triple-negative breast cancer (TNBC) using H&E slides. Attention maps highlight immune cells, improving interpretability and guiding personalized oncology.

Keywords:
artificial intelligence (AI)neoadjuvant chemotherapy (NACT)pathologic complete response (pCR)treatment response predictiontriple-negative breast cancer (TNBC)

More Related Videos

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment &#8212; Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.5K
Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model
09:29

Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model

Published on: March 20, 2020

18.1K

Related Experiment Videos

Last Updated: Sep 11, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment &#8212; Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.5K
Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model
09:29

Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model

Published on: March 20, 2020

18.1K

Area of Science:

  • Computational pathology
  • Digital oncology
  • Biomarker discovery

Background:

  • Triple-negative breast cancer (TNBC) presents significant treatment challenges due to its aggressive nature and limited targeted therapies.
  • Predicting response to neoadjuvant chemotherapy (NACT) is crucial for tailoring treatment and improving outcomes in TNBC patients.
  • Hematoxylin and eosin (H&E)-stained biopsy slides offer a rich source of histological information for predictive modeling.

Purpose of the Study:

  • To develop and validate an attention-based multiple instance learning (MIL) framework for predicting pathologic complete response (pCR) to NACT in TNBC.
  • To assess the model's generalizability using external validation data.
  • To enhance model interpretability by correlating attention maps with immune cell biomarkers.

Main Methods:

  • An attention-based MIL framework was developed to analyze pre-treatment H&E-stained biopsy slides.
  • The model was trained on a retrospective TNBC cohort (n=174) and validated on an independent cohort (n=30).
  • Spatial co-registration of model attention maps with multiplex immunohistochemistry (mIHC) data for PD-L1, CD8+ T cells, and CD163+ macrophages was performed.

Main Results:

  • The MIL model achieved a mean AUC of 0.85 in cross-validation and 0.78 in external testing, demonstrating robust predictive performance.
  • Attention maps showed moderate spatial overlap with immune-enriched areas (IoU: 0.47 for PD-L1, 0.45 for CD8+, 0.46 for CD163+).
  • The overlap suggests biological relevance of immune biomarkers in high-attention regions for NACT response prediction.

Conclusions:

  • The attention-based MIL framework accurately predicts NACT response in TNBC directly from H&E slides.
  • Model interpretability is enhanced by linking attention regions to specific immune cell populations.
  • This approach holds potential for identifying histological biomarkers and advancing precision oncology for TNBC.