Landmark Regression with Attention U-Net for Assessing Breast Positioning Quality in MLO Mammography View


Denizoglu N., Tanyel T., Erkan E. C., Seker M. E., Meltem E., Aktufan Cerekci E., ...Daha Fazla

Diagnostics, cilt.16, sa.14, 2026 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 16 Sayı: 14
  • Basım Tarihi: 2026
  • Doi Numarası: 10.3390/diagnostics16142262
  • Dergi Adı: Diagnostics
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, EMBASE, Directory of Open Access Journals, Academic Search Ultimate (EBSCO), Biomedical Reference Collection: Corporate Edition (EBSCO)
  • Anahtar Kelimeler: breast cancer, deep learning, mammography, positioning quality
  • Acıbadem Mehmet Ali Aydınlar Üniversitesi Adresli: Evet

Özet

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.