From 2D to 3D Without Extra Baggage: Data-Efficient Cancer Detection in Digital Breast Tomosynthesis

Yen Nhi Truong Vu, Dan Guo, Sripad Joshi, Harshit Kumar, Jason Su, Thomas Paul Matthews
Proceedings of the Fifth Machine Learning for Health Symposium, PMLR 297:1346-1359, 2026.

Abstract

Digital Breast Tomosynthesis ({DBT}) enhances finding visibility for breast cancer detection by providing volumetric information that reduces the impact of overlapping tissues; however, limited annotated data has constrained the development of deep learning models for {DBT}. To address data scarcity, existing methods attempt to reuse {2D} full-field digital mammography ({FFDM}) models by either flattening {DBT} volumes or processing slices individually, thus discarding volumetric information. Alternatively, {3D} reasoning approaches introduce complex architectures that require more {DBT} training data. Tackling these drawbacks, we propose {M&M-3D}, an architecture that enables learnable {3D} reasoning while remaining parameter-free relative to its {FFDM} counterpart, {M&M}. {M&M-3D} constructs malignancy-guided {3D} features, and {3D} reasoning is learned through repeatedly mixing these {3D} features with slice-level information. This is achieved by modifying operations in {M&M} without adding parameters, thus enabling direct weight transfer from {FFDM}. Extensive experiments show that {M&M-3D} surpasses {2D} projection and {3D} slice-based methods by 11–54% for localization and 3–10% for classification. Additionally, {M&M-3D} outperforms complex {3D} reasoning variants by 20–47% for localization and 2–10% for classification in the low-data regime, while matching their performance in high-data regime. On the popular {BCS-DBT} benchmark, {M&M-3D} outperforms previous top baseline by 4% for classification and 10% for localization.

Cite this Paper

BibTeX
@InProceedings{pmlr-v297-vu26a, title = {From {2D} to {3D} Without Extra Baggage: Data-Efficient Cancer Detection in Digital Breast Tomosynthesis}, author = {Vu, Yen Nhi Truong and Guo, Dan and Joshi, Sripad and Kumar, Harshit and Su, Jason and Matthews, Thomas Paul}, booktitle = {Proceedings of the Fifth Machine Learning for Health Symposium}, pages = {1346--1359}, year = {2026}, editor = {Argaw, Peniel and Zhang, Haoran and Jabbour, Sarah and Chandak, Payal and Ji, Jerry and Mukherjee, Sumit and Salaudeen, Olawale and Chang, Trenton and Healey, Elizabeth and Gröger, Fabian and Adibi, Amin and Hegselmann, Stefan and Wild, Benjamin and Noori, Ayush}, volume = {297}, series = {Proceedings of Machine Learning Research}, month = {13--14 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v297/main/assets/vu26a/vu26a.pdf}, url = {https://proceedings.mlr.press/v297/vu26a.html}, abstract = {Digital Breast Tomosynthesis ({DBT}) enhances finding visibility for breast cancer detection by providing volumetric information that reduces the impact of overlapping tissues; however, limited annotated data has constrained the development of deep learning models for {DBT}. To address data scarcity, existing methods attempt to reuse {2D} full-field digital mammography ({FFDM}) models by either flattening {DBT} volumes or processing slices individually, thus discarding volumetric information. Alternatively, {3D} reasoning approaches introduce complex architectures that require more {DBT} training data. Tackling these drawbacks, we propose {M&M-3D}, an architecture that enables learnable {3D} reasoning while remaining parameter-free relative to its {FFDM} counterpart, {M&M}. {M&M-3D} constructs malignancy-guided {3D} features, and {3D} reasoning is learned through repeatedly mixing these {3D} features with slice-level information. This is achieved by modifying operations in {M&M} without adding parameters, thus enabling direct weight transfer from {FFDM}. Extensive experiments show that {M&M-3D} surpasses {2D} projection and {3D} slice-based methods by 11–54% for localization and 3–10% for classification. Additionally, {M&M-3D} outperforms complex {3D} reasoning variants by 20–47% for localization and 2–10% for classification in the low-data regime, while matching their performance in high-data regime. On the popular {BCS-DBT} benchmark, {M&M-3D} outperforms previous top baseline by 4% for classification and 10% for localization.} }
Endnote
%0 Conference Paper %T From 2D to 3D Without Extra Baggage: Data-Efficient Cancer Detection in Digital Breast Tomosynthesis %A Yen Nhi Truong Vu %A Dan Guo %A Sripad Joshi %A Harshit Kumar %A Jason Su %A Thomas Paul Matthews %B Proceedings of the Fifth Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2026 %E Peniel Argaw %E Haoran Zhang %E Sarah Jabbour %E Payal Chandak %E Jerry Ji %E Sumit Mukherjee %E Olawale Salaudeen %E Trenton Chang %E Elizabeth Healey %E Fabian Gröger %E Amin Adibi %E Stefan Hegselmann %E Benjamin Wild %E Ayush Noori %F pmlr-v297-vu26a %I PMLR %P 1346--1359 %U https://proceedings.mlr.press/v297/vu26a.html %V 297 %X Digital Breast Tomosynthesis ({DBT}) enhances finding visibility for breast cancer detection by providing volumetric information that reduces the impact of overlapping tissues; however, limited annotated data has constrained the development of deep learning models for {DBT}. To address data scarcity, existing methods attempt to reuse {2D} full-field digital mammography ({FFDM}) models by either flattening {DBT} volumes or processing slices individually, thus discarding volumetric information. Alternatively, {3D} reasoning approaches introduce complex architectures that require more {DBT} training data. Tackling these drawbacks, we propose {M&M-3D}, an architecture that enables learnable {3D} reasoning while remaining parameter-free relative to its {FFDM} counterpart, {M&M}. {M&M-3D} constructs malignancy-guided {3D} features, and {3D} reasoning is learned through repeatedly mixing these {3D} features with slice-level information. This is achieved by modifying operations in {M&M} without adding parameters, thus enabling direct weight transfer from {FFDM}. Extensive experiments show that {M&M-3D} surpasses {2D} projection and {3D} slice-based methods by 11–54% for localization and 3–10% for classification. Additionally, {M&M-3D} outperforms complex {3D} reasoning variants by 20–47% for localization and 2–10% for classification in the low-data regime, while matching their performance in high-data regime. On the popular {BCS-DBT} benchmark, {M&M-3D} outperforms previous top baseline by 4% for classification and 10% for localization.
APA
Vu, Y.N.T., Guo, D., Joshi, S., Kumar, H., Su, J. & Matthews, T.P.. (2026). From 2D to 3D Without Extra Baggage: Data-Efficient Cancer Detection in Digital Breast Tomosynthesis. Proceedings of the Fifth Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 297:1346-1359 Available from https://proceedings.mlr.press/v297/vu26a.html.

Related Material