Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Mouse Models of Cancer Study

Mouse Models of Cancer Study

Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...

Mouse Models of Cancer Study

Mouse Models of Cancer Study

Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...

You might also read

Related Articles

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

Sort by

Same author

[<sup>18</sup>F]FDG PET/CT Radiomics for Predicting Pathological Risk Subtypes of Thymic Epithelial Tumors: A Bicentric Study.

Cancers·2026

Same author

Systematic Review of Paraspinal Muscle Changes in Lumbar Spondylolisthesis: MRI and CT Insights.

Orthopaedic surgery·2026

Same author

Radiologic and Lipid Metabolism Imaging Features Associated with FABP2 Expression in Clear Cell Renal Cell Carcinoma: An Interpretable Supervised Machine Learning Radiogenomic Study.

Archivos espanoles de urologia·2026

Same author

Mediastinal adipose tissue as an active player in cardiovascular disease: a multimodality imaging narrative review.

Quantitative imaging in medicine and surgery·2026

Same author

Multimodal clinical data integration for prognosis of pulmonary embolism: A comparative study.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Same author

Interventional radiology in the management of complications after pancreatic surgery: a single-center experience.

Abdominal radiology (New York)·2026

Search research articles

Related Experiment Video

Updated: Jul 9, 2026

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

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

Published on: October 10, 2018

Augmented intelligence for multimodal virtual biopsy in breast cancer using generative artificial intelligence.

Aurora Rofena¹, Claudia Lucia Piccolo², Bruno Beomonte Zobel³

¹Unit of Artificial Intelligence and Computer Systems, University Campus Bio-Medico of Roma, Rome, Italy.

Journal of Biomedical Informatics

|December 28, 2025

Summary

This study introduces a generative AI approach to create synthetic Contrast-Enhanced Spectral Mammography (CESM) images, improving non-invasive breast cancer virtual biopsy when real CESM data is missing. The AI-enhanced method offers better lesion classification than using only Full-Field Digital Mammography (FFDM).

Keywords:

Breast cancer CESM Generative artificial intelligence Missing modality Multimodal deep learning Virtual biopsy

More Related Videos

Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis

Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis

Published on: February 6, 2020

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

Related Experiment Videos

Last Updated: Jul 9, 2026

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

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

Published on: October 10, 2018

Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis

Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis

Published on: February 6, 2020

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

Area of Science:

Medical Imaging
Artificial Intelligence in Healthcare
Oncology

Background:

Breast cancer diagnosis relies on imaging techniques like Full-Field Digital Mammography (FFDM) and Contrast-Enhanced Spectral Mammography (CESM).
Missing CESM data can disrupt diagnostic workflows and impact classification accuracy.
Virtual biopsy offers a non-invasive method for classifying breast lesions.

Purpose of the Study:

To develop a multimodal, multi-view deep learning approach for breast cancer virtual biopsy.
To integrate FFDM and CESM data for improved lesion classification.
To address missing CESM data using generative AI for image synthesis.

Main Methods:

A CycleGAN model synthesized missing CESM images from FFDM inputs.
Three Convolutional Neural Networks (ResNet18, ResNet50, VGG16) were used for classification.
A two-stage late fusion strategy combined view-specific and modality-specific probabilities, weighted by the Matthews Correlation Coefficient (MCC).

Main Results:

Generative AI achieved high-fidelity synthesis of CESM images (PSNR > 24 dB, SSIM > 0.8).
The multimodal approach (FFDM + CESM) outperformed unimodal FFDM-only classification.
Even with fully synthetic CESM images, the multimodal approach improved performance over FFDM alone.

Conclusions:

Generative AI effectively synthesizes CESM images, overcoming data gaps in breast cancer diagnostics.
Incorporating synthetic CESM images enhances FFDM-based virtual biopsy performance.
This non-invasive approach supports clinical decision-making and contributes a valuable dataset (CESM@UCBM).