Evidence map›Paper›PMID 41374377›Full record

ReviewDiagnostics (Basel, Switzerland)2025

The Role of Synthetic Data and Generative AI in Breast Imaging: Promise, Pitfalls, and Pathways Forward.

Filippo Pesapane, Lucrezia D'Amelio, Luca Nicosia, Carmen Mallardi, Anna Bozzini, Lorenza Meneghetti, Gianpaolo Carrafiello, Enrico Cassano, Sonia Santicchia

Abstract readReview
In one paragraph

Review in Diagnostics (Basel, Switzerland), 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 2 papers.

0numbers the graph read from it
0cells of the map it votes in
2citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

2 citing papers in PubMed.

  1. Article
  2. Review
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

9 authors.

Filippo PesapaneBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy.ORCID 0000-0002-0374-5054
Lucrezia D'AmelioRadiology Unit, Sant'Andrea University Hospital, Department of Medical Surgical Sciences and Translational Medicine, Sapienza University of Rome, 00189 Rome, Italy.
Luca NicosiaBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy.ORCID 0000-0003-3979-8075
Carmen MallardiBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy.
Anna BozziniBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy.
Lorenza MeneghettiBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy.
Gianpaolo CarrafielloRadiology Department, Foundation IRCCS Ca' Granda, Ospedale Maggiore Policlinico, Università Degli Studi di Milano, Via Festa del Perdono 7, 20122 Milan, Italy.
Enrico CassanoBreast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy.ORCID 0000-0002-3437-8939
Sonia SanticchiaRadiology Department, Foundation IRCCS Ca' Granda, Ospedale Maggiore Policlinico, Università Degli Studi di Milano, Via Festa del Perdono 7, 20122 Milan, Italy.

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

Artificial intelligence is reshaping breast imaging, yet progress is constrained by data scarcity, privacy restrictions, and uneven representation. This narrative review synthesizes evidence (2020-April 2025) on synthetic data and generative AI-principally GANs and diffusion models-in mammography and related modalities. We examine how synthetic images enable data augmentation, class balancing, external validation, and simulation-based training; summarize reported gains in detection performance; and assess their potential to mitigate or, if misapplied, amplify bias across subgroups (age, density, ethnicity). We analyze threats to validity, including enriched cohorts, distribution shift, and unverifiable realism, and address medico-legal exposure, image provenance, and deepfake risks. Finally, we outline task-specific validation and reporting practices, equity auditing across density and demographics, and governance pathways aligned with EU/US regulatory expectations. Synthetic data and generative AI can enhance performance, training, and data sharing; however, responsible clinical adoption requires rigorous validation, transparency on failure modes, tamper-evident provenance, and shared accountability models.

Indexed as

artificial intelligence in radiologybreast imagingdiffusion modelsgenerative adversarial networks (GANs)generative AImammographysynthetic data

Identifiers

PMID41374377
PMCPMC12691509

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.