Landmark Regression with Attention U-Net for Assessing Breast Positioning Quality in MLO Mammography View
Diagnostics · 20.07.2026 · 16 (14) · 2262
DOI: 10.3390/diagnostics16142262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 20.07.2026. Verfasst von Nurper Denizoglu und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Sultan 2. Abdulhamid Han Training and Research Hospital, Istanbul 34668, Turkey. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Scientific and Technological Research Council of Türkiye, Istanbul Technical University, Istanbul Technical University Scientific Research Projects (ITU BAP) funds.
Abstract (Originalsprache)
Background/Objectives: This study developed and evaluated a novel Attention U-Net regression model to assess MLO mammography positioning quality, comparing it against a plain U-Net regression baseline (architectural ablation) and a ResNeXt50 classification baseline.
Methods
We curated 1000 patient mammograms (2000 MLO images) from the public VinDr-Mammo dataset, with pectoral muscle line and nipple positions annotated by an expert breast radiologist. Three deep learning models were compared under a 10-fold stratified cross-validation protocol. Statistical significance was assessed with paired Wilcoxon signed-rank tests, McNemar’s test, Cochran’s Q, Wilson score confidence intervals, bootstrap confidence intervals, Holm–Bonferroni correction, and paired Cohen’s d effect sizes.
Results
Against the automated PNL reference, the Attention U-Net achieved 85.5% accuracy (Wilson 95% CI [83.9%, 87.0%]), 80.2% sensitivity, and 88.7% specificity, outperforming both the plain U-Net (71.8% accuracy) and ResNeXt50 (73.7% accuracy). (Cochran’s Q p < 0.001; pairwise McNemar p < 0.001). For landmark localization, the Attention U-Net produced significantly lower errors across all five evaluated landmark and geometric measures (nipple 3.44 mm vs. 7.02 mm; perpendicular intersection 5.93 mm vs. 9.81 mm; all comparisons remained significant after Holm–Bonferroni correction).
Conclusions
In this single-dataset, single-view study, an Attention U-Net landmark-regression model provided explicit landmark and PNL outputs for quantitative MLO mammography positioning assessment. The model showed improved accuracy and sensitivity compared with a plain U-Net regression baseline and a ResNeXt50 classification baseline.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Sultan 2. Abdulhamid Han Training and Research Hospital, Istanbul 34668, Turkey.
- Biomedical Engineering Graduate Program, Istanbul Technical University, Istanbul 34469, Turkey.
- Department of Radiology, School of Medicine, University of Wisconsin, Madison, WI 53792, USA.
- Department of Radiology, Istanbul Training and Research Hospital, University of Health Sciences, Istanbul 34098, Turkey.
- Department of Radiology, Sisli Hamidiye Etfal Training and Research Hospital, Istanbul 34371, Turkey.
- Department of Radiology, School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul 34684, Turkey.
ORCID-Profile: Nurper Denizoglu, Toygar Tanyel, Enes Can Erkan, Mustafa Ege Seker, Emine Meltem, Esma Aktufan Cerekci
Förderung
- The Scientific and Technological Research Council of Türkiye
- Istanbul Technical University
- Istanbul Technical University Scientific Research Projects (ITU BAP) funds
Zitieren
APA
Denizoglu, N., Tanyel, T., Erkan, E. C., Seker, M. E., Meltem, E., Aktufan Cerekci, E., Alis, D., Oksuz, I., Karaarslan, E., & Aribal, E. (2026). Landmark Regression with Attention U-Net for Assessing Breast Positioning Quality in MLO Mammography View. Diagnostics, 16(14), 2262. https://doi.org/10.3390/diagnostics16142262
Vancouver
Denizoglu N, Tanyel T, Erkan EC, Seker ME, Meltem E, Aktufan Cerekci E, et al. Landmark Regression with Attention U-Net for Assessing Breast Positioning Quality in MLO Mammography View. Diagnostics. 2026;16(14):2262. doi:10.3390/diagnostics16142262
BibTeX
@article{Denizoglu2026,
author = {Denizoglu, Nurper and Tanyel, Toygar and Erkan, Enes Can and Seker, Mustafa Ege and Meltem, Emine and Aktufan Cerekci, Esma and Alis, Deniz and Oksuz, Ilkay and Karaarslan, Ercan and Aribal, Erkin},
title = {Landmark Regression with Attention U-Net for Assessing Breast Positioning Quality in MLO Mammography View},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {14},
pages = {2262},
doi = {10.3390/diagnostics16142262}
}
EUVIMED