EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bilateral-Asymmetry-Aware Multiple-Instance Learning for Breast Cancer Classification on Chest CT

Ioana-Andreea Cîrlig iD, Lucian-Mihai Florescu, Mădălin Mămuleanu iD, Cristina-Mihaela Ciofiac, Mihai-Alexandru Ene iD, Aurelia-Ștefania Domenco, Alexandru-Marian Olaru, Alexandra-Gabriela-Cosmina Țâru, Raluca-Elena Nica iD, Rossy-Vlăduț Teică, Ioana-Andreea Gheonea iD

Life · 14.08.2026 · 16 (8) · 1337

DOI: 10.3390/life16081337 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Life, online erschienen am 14.08.2026. Verfasst von Ioana-Andreea Cîrlig und 10 weiteren Autor:innen. Beteiligte Einrichtung: Doctoral School, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Incidental breast abnormalities may be visible on chest computed tomography (CT), although breast tissue is frequently outside the primary diagnostic focus of these examinations. This proof-of-concept study developed and internally evaluated a bilateral-asymmetry-aware multiple-instance learning framework (BAA-MIL) for case-level discrimination between breast cancer and non-malignant control examinations using preselected breast-containing axial chest CT images. The retrospective single-center case–control dataset included 89 CT examinations from 89 unique patients: 49 histopathologically confirmed breast cancer cases and 40 non-malignant control cases established according to predefined case-level reference criteria. The dataset comprised 304 selected axial CT images, yielding 608 unilateral breast-region crops arranged as 304 bilateral crop pairs. Paired breast crops were processed by a shared convolutional encoder, combined through an explicit side-symmetric asymmetry descriptor, and aggregated across axial images using gated attention-based multiple-instance learning. Performance was assessed using exploratory five-fold stratified patient-level cross-validation and a nested patient-level validation analysis. Under the primary nested patient-level validation protocol, the compact-encoder BAA-MIL implementation achieved an accuracy of 0.528 (95% CI, 0.427–0.629), balanced accuracy of 0.555 (95% CI, 0.465–0.637), sensitivity of 0.286 (95% CI, 0.160–0.415), specificity of 0.825 (95% CI, 0.694–0.930), and ROC AUC of 0.547 (95% CI, 0.420–0.665). The original non-nested analysis yielded higher exploratory estimates, but this analysis used the held-out folds for early stopping and checkpoint selection and is therefore reported only as secondary exploratory analysis. These findings support technical feasibility for a constrained case-level classification task using preselected chest CT images, but do not demonstrate detection of unsuspected incidental breast cancer across complete CT examinations. Performance estimates remain uncertain, and external validation using complete volumetric CT data is required before clinical use.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencebilateral asymmetrybreast cancercase-level classificationchest CTdeep learningincidental findingsmultiple-instance learningopportunistic screening

Autor:innen und Institutionen

  • Doctoral School, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania.
  • Department of Radiology and Medical Imaging, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania.
  • Department of Automatic Control and Electronics, University of Craiova, 200585 Craiova, Romania.
  • Department of Radiology and Medical Imaging, Emergency Clinical County Hospital of Craiova, 200642 Craiova, Romania.

ORCID-Profile: Ioana-Andreea Cîrlig, Mădălin Mămuleanu, Mihai-Alexandru Ene, Raluca-Elena Nica, Ioana-Andreea Gheonea

Zitieren

APA

Cîrlig, I. A., Florescu, L. M., Mămuleanu, M., Ciofiac, C. M., Ene, M. A., Domenco, A. Ș., Olaru, A. M., Țâru, A. G., Nica, R. E., Teică, R. V., & Gheonea, I. A. (2026). Bilateral-Asymmetry-Aware Multiple-Instance Learning for Breast Cancer Classification on Chest CT. Life, 16(8), 1337. https://doi.org/10.3390/life16081337

Vancouver

Cîrlig IA, Florescu LM, Mămuleanu M, Ciofiac CM, Ene MA, Domenco AȘ, et al. Bilateral-Asymmetry-Aware Multiple-Instance Learning for Breast Cancer Classification on Chest CT. Life. 2026;16(8):1337. doi:10.3390/life16081337

BibTeX
@article{Crlig2026,
  author = {Cîrlig, Ioana-Andreea and Florescu, Lucian-Mihai and Mămuleanu, Mădălin and Ciofiac, Cristina-Mihaela and Ene, Mihai-Alexandru and Domenco, Aurelia-Ștefania and Olaru, Alexandru-Marian and Țâru, Alexandra-Gabriela-Cosmina and Nica, Raluca-Elena and Teică, Rossy-Vlăduț and Gheonea, Ioana-Andreea},
  title = {Bilateral-Asymmetry-Aware Multiple-Instance Learning for Breast Cancer Classification on Chest CT},
  journal = {Life},
  year = {2026},
  volume = {16},
  number = {8},
  pages = {1337},
  doi = {10.3390/life16081337}
}
Kostenlos starten →