Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 58 min ago
Peer-reviewedCC BY 4.0Current Medical Imaging

AI-assisted Decision-support Framework for Breast Density and Background Parenchymal Enhancement Assessment in Contrast-enhanced Mammography

  • Graziella Di Grezia1
  • Antonio Nazzaro2
  • Luigi Schiavone3
  • Elisa Cisternino4
  • Alessandro Galiano4
  • Vincenzo Cuccurullo5
  • Gianluca Gatta3
5 affiliations
  1. 1Department of Life Sciences, Health, and Healthcare Professions, Link Campus University, Rome, Italy
  2. 2REPRISE - Register of Expert Peer Reviewers for Italian Scientific Evaluation, Italy
  3. 3Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, Naples, Italy
  4. 4Department of Radiology, P.O. ‘A. Perrino’ Hospital, Brindisi, Italy
  5. 5Department of Advanced Medical and Surgical Sciences, “University of Campania “Luigi Vanvitelli”, Naples, Italy
Read full textPDFDOICite

Abstract

Introduction/Objectives: Interobserver variability in breast density and Background Parenchymal Enhancement (BPE) assessment remains a major limitation in Contrast-Enhanced Mammography (CEM) reporting consistency. Building on the BPE-CEM Standard Scale (BCSS) framework introduced in Part 1, this study aimed to evaluate whether a structured artificial intelligence-assisted decision-support model based on expert-derived variables could improve consistency in BCSS-related interpretation, particularly in disagreement-prone dense breast categories, rather than function as an autonomous image-based grading system.

Methods: We retrospectively analyzed 213 consecutive CEM examinations with BI-RADS 4-5 lesions and histologically confirmed malignancy. A multilayer perceptron model operating on expert-derived patient-level variables (BPE grade, breast density category, and age) generated continuous BCSS-related estimates intended as structured decision-support outputs rather than autonomous image grading. Inter-reader agreement analyses were based on multi-reader expert assessment with consensus reference labeling, and external testing on the VinDr-Mammo dataset was limited to density-related robustness evaluation. Model performance was compared with conventional radiologist assessment. Primary endpoints were prediction error and inter-reader agreement (Fleiss’ κ). Secondary analyses included Area Under the Receiver-Operating-Characteristic Curve (AUC), precision, and recall across predefined BCSS categorization thresholds. External testing using the VinDr-Mammo dataset evaluated robustness of density-related predictions across independent imaging populations.

Results: Relative to conventional assessment, the predictive framework was associated with a 26% reduction in categorization disagreement and with higher agreement estimates within the structured evaluation setting, particularly in dense breasts (BI-RADS C/D), where interpretative variability is greatest. Overall performance supported feasibility within a decision-support context (AUC 0.75; precision 0.72; recall 0.69).

Discussion: AI-assisted modeling of structured BCSS variables showed potential to improve reporting consistency while preserving a human-in-the-loop workflow. Findings emphasize interpretative support rather than diagnostic automation. The retrospective single-center design and enriched malignant cohort limit generalizability to screening populations and warrant prospective multicenter validation.

Conclusion: A structured AI-assisted predictive framework showed preliminary potential to enhance consistency of BCSS interpretation in CEM, particularly in dense breasts, while requiring prospective multicenter validation before broader clinical adoption. These results support the role of transparent decision-support tools aimed at reducing observer variability while maintaining radiologist oversight.

Related

  1. Background parenchymal enhancement in ultrafast MRI: Inter-reader agreement before and after training, and correlations with prognostic factors of breast cancer.
    Ken Yamaguchi, Kanto Ichinohe, Takahiko Nakazono +6
    European journal of radiology openPeer-reviewedCC BYFull textMedical imaging & radiologyEurope PMC
  2. Contralateral Breast Background Parenchymal Enhancement: A Physiologic Marker, not a Predictor of ER Status
    Dana Haddad, Stephanie B Shamir, Zoha Baig +7
    Current Medical ImagingPeer-reviewedCC BY 4.0Full textMedical imaging & radiologyPMC
  3. Intratracheal microspray delivery of iohexol for sustained lung-parenchymal enhancement in preclinical micro-computed tomography: A feasibility and acute-safety study in mice
    Sheng-Chieh Lin, Kuo-Kai Lin, Kevin Aristyo +4
    PLOS OnePeer-reviewedCC BYFull textMedical imaging & radiologyPharmacology & toxicologyPLOSEurope PMC
  4. Intraoperative specimen ultrasonography for margin assessment in breast conserving surgery in comparison with specimen mammography
    Alexia Mensah, Sendhil Rajan, Lukschana Senathirajah +4
    Surgery in practice and sciencePeer-reviewedCC BY-NCFull textGeneral medicineEurope PMC
  5. Deep-Learning-Based Assessment of Breast Arterial Calcification on Mammography: Technical Validation, Cardiovascular Prognostic Value, and Clinical Translation—A Narrative Review
    Alexandru Carauleanu, Amelian M. Bobu, Elena Porumb-Andrese +8
    Medical sciences (Basel, Switzerland)Peer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{grezia2026aiassisted,
  title = {{AI-assisted Decision-support Framework for Breast Density and Background Parenchymal Enhancement Assessment in Contrast-enhanced Mammography}},
  author = {Graziella Di Grezia and Antonio Nazzaro and Luigi Schiavone and Elisa Cisternino and Alessandro Galiano and Vincenzo Cuccurullo and Gianluca Gatta},
  journal = {Current Medical Imaging},
  year = {2026},
  month = jul,
  doi = {10.2174/0115734056444815260715111252},
  url = {https://doi.org/10.2174/0115734056444815260715111252},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - AI-assisted Decision-support Framework for Breast Density and Background Parenchymal Enhancement Assessment in Contrast-enhanced Mammography
AU  - Graziella Di Grezia
AU  - Antonio Nazzaro
AU  - Luigi Schiavone
AU  - Elisa Cisternino
AU  - Alessandro Galiano
AU  - Vincenzo Cuccurullo
AU  - Gianluca Gatta
PY  - 2026
DA  - 2026/07/22
JO  - Current Medical Imaging
DO  - 10.2174/0115734056444815260715111252
UR  - https://doi.org/10.2174/0115734056444815260715111252
AB  - Introduction/Objectives: Interobserver variability in breast density and Background Parenchymal Enhancement (BPE) assessment remains a major limitation in Contrast-Enhanced Mammography (CEM) reporting consistency. Building on the BPE-CEM Standard Scale (BCSS) framework introduced in Part 1, this study aimed to evaluate whether a structured artificial intelligence-assisted decision-support model based on expert-derived variables could improve consistency in BCSS-related interpretation, particularly in disagreement-prone dense breast categories, rather than function as an autonomous image-based grading system.  Methods: We retrospectively analyzed 213 consecutive CEM examinations with BI-RADS 4-5 lesions and histologically confirmed malignancy. A multilayer perceptron model operating on expert-derived patient-level variables (BPE grade, breast density category, and age) generated continuous BCSS-related estimates intended as structured decision-support outputs rather than autonomous image grading. Inter-reader agreement analyses were based on multi-reader expert assessment with consensus reference labeling, and external testing on the VinDr-Mammo dataset was limited to density-related robustness evaluation. Model performance was compared with conventional radiologist assessment. Primary endpoints were prediction error and inter-reader agreement (Fleiss’ κ). Secondary analyses included Area Under the Receiver-Operating-Characteristic Curve (AUC), precision, and recall across predefined BCSS categorization thresholds. External testing using the VinDr-Mammo dataset evaluated robustness of density-related predictions across independent imaging populations.  Results: Relative to conventional assessment, the predictive framework was associated with a 26% reduction in categorization disagreement and with higher agreement estimates within the structured evaluation setting, particularly in dense breasts (BI-RADS C/D), where interpretative variability is greatest. Overall performance supported feasibility within a decision-support context (AUC 0.75; precision 0.72; recall 0.69).  Discussion: AI-assisted modeling of structured BCSS variables showed potential to improve reporting consistency while preserving a human-in-the-loop workflow. Findings emphasize interpretative support rather than diagnostic automation. The retrospective single-center design and enriched malignant cohort limit generalizability to screening populations and warrant prospective multicenter validation.  Conclusion: A structured AI-assisted predictive framework showed preliminary potential to enhance consistency of BCSS interpretation in CEM, particularly in dense breasts, while requiring prospective multicenter validation before broader clinical adoption. These results support the role of transparent decision-support tools aimed at reducing observer variability while maintaining radiologist oversight.
SN  - 1573-4056
ER  -