EUVIMEDEUVIMED entdecken
Open Access

BREAST AI-PLAN: Prompt-Driven AI Assistance for Breast Surgery Planning – A Retrospective Single-center Study

Martina Cossu, Letizia Cuniolo, Raquel Diaz, Martino Oliva, Chiara Cornacchia, Federica Murelli, Francesca Depaoli, Marco Gipponi, Cecilia Margarino, Chiara Boccardo, Simonetta Franchelli, Marianna Pesce und 4 weitere

In Vivo · 2025

DOI: 10.21873/invivo.14126 ↗

Kurz gefasst

Fachartikel in der Zeitschrift In Vivo, 2025. Verfasst von Martina Cossu und 15 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, University of Genoa, Genoa, Italy. Hauptthemen laut MEDLINE: Breast Neoplasms, Artificial Intelligence, Mammaplasty. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND/AIM: Preoperative planning in oncoplastic and reconstructive breast surgery requires synthesizing patient- and tumor-specific variables with aesthetic considerations. Variability in documentation and expertise may hinder reproducibility across centers. Large language models (LLMs) can process structured data into consistent outputs. We assessed whether a prompt-engineered artificial intelligence (AI) assistant (BREAST AI-PLAN) could replicate multidisciplinary team (MDT) decisions and aesthetic scores from routinely collected clinical data. PATIENTS AND METHODS: This single-center retrospective study included 30 women undergoing breast cancer surgery. Each case was recorded in a standardized form covering demographics, comorbidities, breast anatomy, tumor biology, and staging. This form was used to generate structured prompts for the AI assistant. The AI returned eight outputs: 1) neoadjuvant therapy suitability; 2) planned surgery; 3) surgical approach; 4) reconstruction type; 5) direct-to-implant feasibility; 6) implant type; 7) adjuvant therapy; and 8) an aesthetic score (BCCT.core-aligned). Clinical MDT decisions were the reference standard. Agreement was measured using Cohen's κ, with linear and quadratic weights for aesthetics. RESULTS: Mean age was 59.2±9.8 years; median body mass index (BMI) 24.2 (20.9-26.8). One patient carried a BRCA2 mutation; 13.3% had prior radiotherapy; 33.3% were smokers. Tumors were mainly Luminal A (43.3%) and Luminal B (26.7%). Agreement was very good for neoadjuvant therapy (κ=0.91; observed 96.7%) and good/moderate for planned surgery (κ=0.58; observed 70.0%), surgical approach (κ=0.43; observed 60.0%), reconstruction (κ=0.36; observed 57.1%), and adjuvant therapy (κ=0.29; observed 64.3%). Aesthetic scoring showed high observed concordance (0.778-0.896) but only slight weighted κ (0.14-0.16). CONCLUSION: BREAST AI-PLAN reproduced MDT planning elements and aesthetic assessments with moderate-to-very-good agreement. Transparent, auditable AI assistance may standardize surgical planning and support training. Prospective validation with imaging integration is warranted.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsArtificial IntelligenceMammaplastyHumansFemaleMiddle AgedRetrospective StudiesAgedMastectomyNeoadjuvant Therapy

Stichwörter der Autor:innen

Breast cancerCohen’s kappa (κ)aestheticsartificial intelligencebreast reconstructionclinical decision supportoncoplastic surgery

Autor:innen und Institutionen

  • School of Medicine, University of Genoa, Genoa, Italy.
  • Department of Surgical Sciences and Integrated Diagnostic (DISC), University of Genoa, Genoa, Italy; letiziacuniolo@gmail.com.
  • Breast Surgery Unit, IRCCS Ospedale Policlinico San Martino, Genoa, Italy.
  • Department of Surgical Sciences and Integrated Diagnostic (DISC), University of Genoa, Genoa, Italy.
  • Department of Health Sciences, University of Genova, Genoa, Italy.

Zitieren

APA

Cossu, M., Cuniolo, L., Diaz, R., Oliva, M., Cornacchia, C., Murelli, F., Depaoli, F., Gipponi, M., Margarino, C., Boccardo, C., Franchelli, S., Pesce, M., Allievi, R., D'Agraives, A. C., Abdallah, S., & Fregatti, P. (2025). BREAST AI-PLAN: Prompt-Driven AI Assistance for Breast Surgery Planning – A Retrospective Single-center Study. In Vivo. https://doi.org/10.21873/invivo.14126

Vancouver

Cossu M, Cuniolo L, Diaz R, Oliva M, Cornacchia C, Murelli F, et al. BREAST AI-PLAN: Prompt-Driven AI Assistance for Breast Surgery Planning – A Retrospective Single-center Study. In Vivo. 2025. doi:10.21873/invivo.14126

BibTeX
@article{Cossu2025,
  author = {Cossu, Martina and Cuniolo, Letizia and Diaz, Raquel and Oliva, Martino and Cornacchia, Chiara and Murelli, Federica and Depaoli, Francesca and Gipponi, Marco and Margarino, Cecilia and Boccardo, Chiara and Franchelli, Simonetta and Pesce, Marianna and Allievi, Rebecca and D'Agraives, Amandine Causse and Abdallah, Saad and Fregatti, Piero},
  title = {BREAST AI-PLAN: Prompt-Driven AI Assistance for Breast Surgery Planning – A Retrospective Single-center Study},
  journal = {In Vivo},
  year = {2025},
  doi = {10.21873/invivo.14126}
}
Kostenlos starten →