Lesion-Location Supervision for Dual-Resolution Mammography Classification: A Patient-Grouped Evaluation on Mini-MIAS
Main Article Content
Abstract
This study evaluated whether lesion-location supervision improves benign-versus-malignant classification and lesion-center coverage in full mammograms. The analysis included 115 Mini-MIAS mammograms from 108 patients, comprising 63 benign and 52 malignant images. Two dual-resolution models combined a downsampled whole-mammogram view with 25 overlapping high-resolution tiles using a shared frozen ResNet-18 encoder. One model used lesion centers to guide tile weighting during training. Both were predicted from pixels alone on the same held-out patient folds. In the reference run, pooled area under the receiver operating characteristic curve (ROC-AUC) was 0.493 with location supervision and 0.491 with image labels alone (paired difference 0.002, 95% patient-bootstrap confidence interval −0.006 to 0.011). Across five training runs on fixed partitions, supervised ROC-AUC ranged from 0.480 to 0.511. Among 111 mammograms with usable coordinates, top-tile lesion-center coverage increased from 6.3% to 23.4% (gain 17.1 percentage points, 95% confidence interval 9.1 to 25.5). Uniform random and fixed central tile selection yielded 6.5% and 39.6% coverage, respectively. On the coordinate-eligible subset, reference ROC-AUC was 0.488 for the annotation-centered crop classifier and 0.508 for the supervised full-image model. Location supervision improved tile coverage, while full-image malignancy discrimination stayed near chance under the evaluated protocol.
Article Details
Issue
Section

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
[1] Shen, Y., Wu, N., Phang, J., Park, J., Kim, G., Moy, L., Cho, K., & Geras, K. J. (2019). Globally-aware multiple instance classifier for breast cancer screening. In Machine Learning in Medical Imaging (pp. 18–26). Springer. DOI: https://doi.org/10.1007/978-3-030-32692-0_3
[2] Logan, J., Kennedy, P. J., & Catchpoole, D. (2023). A review of the machine learning datasets in mammography, their adherence to the FAIR principles and the outlook for the future. Scientific Data, 10, Article 595. DOI: https://doi.org/10.1038/s41597-023-02430-6
[3] Kag, H., Kumar, D., & Diwan, A. (2026). Breast lesion classification: Leakage-free patch-based transfer learning with cross-dataset evaluation on CBIS-DDSM, MIAS, and INbreast. Jordanian Journal of Computers and Information Technology, 12(3), 388–411.
[4] Shen, Y., Wu, N., Phang, J., Park, J., Liu, K., Tyagi, S., Heacock, L., Kim, S. G., Moy, L., Cho, K., & Geras, K. J. (2021). An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization. Medical Image Analysis, 68, 101908. https://doi.org/10.1016/j.media.2020.101908 DOI: https://doi.org/10.1016/j.media.2020.101908
[5] Ribli, D., Horváth, A., Unger, Z., Pollner, P., & Csabai, I. (2018). Detecting and classifying lesions in mammograms with deep learning. Scientific Reports, 8, 4165. https://doi.org/10.1038/s41598-018-22437-z DOI: https://doi.org/10.1038/s41598-018-22437-z
[6] Lotter, W., Diab, A. R., Haslam, B., Kim, J. G., Grisot, G., Wu, E., Wu, K., Onieva Onieva, J., Boyer, Y., Boxerman, J. L., Wang, M., Bandler, M., Vijayaraghavan, G. R., & Sorensen, A. G. (2021). Robust breast cancer detection in mammography and digital breast tomosynthesis using an annotation-efficient deep learning approach. Nature Medicine, 27, 244–249. https://doi.org/10.1038/s41591-020-01174-9 DOI: https://doi.org/10.1038/s41591-020-01174-9
[7] Chen, Y., Liu, Y., Wang, C., Elliott, M., Kwok, C. F., Peña-Solorzano, C., Tian, Y., Liu, F., Frazer, H., McCarthy, D. J., & Carneiro, G. (2024). BRAIxDet: Learning to detect malignant breast lesions with incomplete annotations. Medical Image Analysis, 96, 103192. DOI: https://doi.org/10.1016/j.media.2024.103192
[8] Lee, R. S., Gimenez, F., Hoogi, A., Miyake, K. K., Gorovoy, M., & Rubin, D. L. (2017). A curated mammography data set for use in computer-aided detection and diagnosis research. Scientific Data, 4, 170177. https://doi.org/10.1038/sdata.2017.177 DOI: https://doi.org/10.1038/sdata.2017.177
[9] Moreira, I. C., Amaral, I., Domingues, I., Cardoso, A., Cardoso, M. J., & Cardoso, J. S. (2012). INbreast: Toward a full-field digital mammographic database. Academic Radiology, 19(2), 236–248. https://doi.org/10.1016/j.acra.2011.09.014 DOI: https://doi.org/10.1016/j.acra.2011.09.014
[10] Zhu, M., Zhang, L., Wang, L., Wang, Z., Wang, Y., & Qian, G. (2025). Local extremum mapping for weak supervision learning on mammogram classification and localization. Bioengineering, 12(4), 325. DOI: https://doi.org/10.3390/bioengineering12040325
[11] Mahmood, T., Li, J., Pei, Y., Akhtar, F., Rehman, M. U., & Wasti, S. H. (2022). Breast lesions classifications of mammographic images using a deep convolutional neural network-based approach. PLOS ONE, 17(1), e0263126. DOI: https://doi.org/10.1371/journal.pone.0263126
[12] Avcı, H., & Karakaya, J. (2024). Segmentation techniques in mammography: Their value in breast cancer diagnosis. Journal of Clinical Practice and Research, 46(6), 548–556. DOI: https://doi.org/10.14744/cpr.2024.38483
[13] Teoh, J. R., Hasikin, K., Lai, K. W., Wu, X., & Li, C. (2024). Enhancing early breast cancer diagnosis through automated microcalcification detection using an optimized ensemble deep learning framework. PeerJ Computer Science, 10, e2082. DOI: https://doi.org/10.7717/peerj-cs.2082
[14] Zebari, D. A., Ibrahim, D. A., Zeebaree, D. Q., Haron, H., Salih, M. S., Damaševičius, R., & Mohammed, M. A. (2021). Systematic review of computing approaches for breast cancer detection based on computer-aided diagnosis using mammogram images. Applied Artificial Intelligence, 35(15), 2157–2203. DOI: https://doi.org/10.1080/08839514.2021.2001177
[15] Zebari, D. A., Ibrahim, D. A., Zeebaree, D. Q., Mohammed, M. A., Haron, H., Zebari, N. A., Damaševičius, R., & Maskeliūnas, R. (2021). Breast cancer detection using mammogram images with improved multi-fractal dimension approach and feature fusion. Applied Sciences, 11(24), 12122. https://doi.org/10.3390/app112412122 DOI: https://doi.org/10.3390/app112412122
[16] Zebari, D. A., Haron, H., Sulaiman, D. M., Yusoff, Y., & Othman, M. N. M. (2022). CNN-based deep transfer learning approach for detecting breast cancer in mammogram images. In 2022 IEEE 10th Conference on Systems, Process & Control (ICSPC) (pp. 256–261). IEEE. DOI: https://doi.org/10.1109/ICSPC55597.2022.10001781
[17] Zebari, D. A., Ibrahim, D. A., & Al-Zebari, A. (2022). Suspicious region segmentation using deep features in breast cancer mammogram images. In 2022 International Conference on Computer Science and Software Engineering (CSASE) (pp. 253–258). IEEE. DOI: https://doi.org/10.1109/CSASE51777.2022.9759633
[18] Qian, L., Bai, J., Huang, Y., Zeebaree, D. Q., Saffari, A., & Zebari, D. A. (2024). Breast cancer diagnosis using evolving deep convolutional neural network based on hybrid extreme learning machine technique and improved chimp optimization algorithm. Biomedical Signal Processing and Control, 87, 105492. https://doi.org/10.1016/j.bspc.2023.105492 DOI: https://doi.org/10.1016/j.bspc.2023.105492
[19] Cao, J., Zeebaree, D. Q., Chen, Q., & Zebari, D. A. (2023). Breast cancer diagnosis using hybrid AlexNet-ELM and chimp optimization algorithm evolved by Nelder–Mead simplex approach. Biomedical Signal Processing and Control, 85, 105053. https://doi.org/10.1016/j.bspc.2023.105053 DOI: https://doi.org/10.1016/j.bspc.2023.105053
[20] Zebari, N. A., Alkurdi, A. A. H., Marqas, R. B., & Salih, M. S. (2023). Enhancing brain tumor classification with data augmentation and DenseNet121. Academic Journal of Nawroz University, 12(4). https://journals.nawroz.edu.krd/files/article/view/864 DOI: https://doi.org/10.25007/ajnu.v12n4a1985
[21] Zebari, D. A., Sulaiman, D. M., Sadiq, S. S., Zebari, N. A., & Salih, M. S. (2022). Automated detection of COVID-19 from X-ray using SVM. 2022 4th International Conference on Advanced Science and Engineering (ICOASE), 130–135. IEEE. https://doi.org/10.1109/ICOASE56293.2022.10075586 DOI: https://doi.org/10.1109/ICOASE56293.2022.10075586
[22] Salih, M. S., Zebari, N. A., & Doski, H. (2025). A hybrid LBP and CNN-based approach for COVID-19 detection using chest X-ray images. Artificial Intelligence & Robotics Development Journal, 5(4), 396–408. https://doi.org/10.52098/airdj.20255465 DOI: https://doi.org/10.52098/airdj.20255465
[23] Suckling, J., et al. (1994). The Mammographic Image Analysis Society Digital Mammogram Database. International Congress Series, 1069, 375–378. https://www.andrew.cmu.edu/course/15-440-s12/applications/labs/lab4/mias.html
[24] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778. https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html DOI: https://doi.org/10.1109/CVPR.2016.90
[25] Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. International Conference on Learning Representations. https://openreview.net/forum?id=Bkg6RiCqY7
[26] Youden, W. J. (1950). Index for rating diagnostic tests. Cancer, 3(1), 32–35. https://pubmed.ncbi.nlm.nih.gov/15405679/ DOI: https://doi.org/10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3
[27] Salim, M., Wåhlin, E., Dembrower, K., Azavedo, E., Foukakis, T., Liu, Y., Smith, K., Eklund, M., & Strand, F. (2020). External evaluation of 3 commercial artificial intelligence algorithms for independent assessment of screening mammograms. JAMA Oncology, 6(10), 1581–1588. https://doi.org/10.1001/jamaoncol.2020.3321 DOI: https://doi.org/10.1001/jamaoncol.2020.3321
[28] Freeman, K., Geppert, J., Stinton, C., Todkill, D., Johnson, S., Clarke, A., & Taylor-Phillips, S. (2021). Use of artificial intelligence for image analysis in breast cancer screening programs: Systematic review of test accuracy. BMJ, 374, n1872. https://doi.org/10.1136/bmj.n1872 DOI: https://doi.org/10.1136/bmj.n1872
[29] Nguyen, H. T., Nguyen, H. Q., Pham, H. H., Lam, K., Le, L. T., Dao, M., & Vu, V. (2023). VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography. Scientific Data, 10, 277. https://doi.org/10.1038/s41597-023-02100-7 DOI: https://doi.org/10.1038/s41597-023-02100-7
[30] Tejani, A. S., Klontzas, M. E., CLAIM 2024 Update Panel, Gatti, A. A., Mongan, J. T., Moy, L., Park, S. H., & Kahn, C. E., Jr. (2024). Checklist for Artificial Intelligence in Medical Imaging (CLAIM): 2024 update. Radiology: Artificial Intelligence, 6(4), e240300. https://doi.org/10.1148/ryai.240300 DOI: https://doi.org/10.1148/ryai.240300