Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography

Md Atik Ahamed; Braxton McFarland; Xiaoqin Wang; Jin Chen; Abdullah Al Zubaer Imran

doi:10.1117/12.3025407

Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography

Md Atik Ahamed, Braxton McFarland, Xiaoqin Wang, Jin Chen, Abdullah Al Zubaer Imran

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Complete removal of cancer tumors with a negative specimen margin during lumpectomy is essential to reduce breast cancer recurrence. However, 2D radiography, the current method used to assess intraoperative specimen margin status, has limited accuracy, resulting in nearly one in four patients needing repeat surgery. This study aims to develop a deep learning model that improves the detection of positive margins in intraoperative breast lumpectomy specimens on radiographs. We annotated the lumpectomy radiograph images with masking that denotes regions of known malignancy, non-malignant tissue, and the areas of pathology-confirmed positive margin. We propose a pretraining strategy, namely Forward-Forward Contrastive Learning (FFCL) with both local and global-level contrastive learning. Experimental results on our annotated breast radiographs demonstrate the effectiveness of our FFCL method in detecting positive margins from intraoperative radiographs of breast lumpectomy specimens.

Original language	English
Title of host publication	17th International Workshop on Breast Imaging, IWBI 2024
Editors	Maryellen L. Giger, Heather M. Whitney, Karen Drukker, Hui Li
ISBN (Electronic)	9781510680203
DOIs	https://doi.org/10.1117/12.3025407
State	Published - 2024
Event	17th International Workshop on Breast Imaging, IWBI 2024 - Chicago, United States Duration: Jun 9 2024 → Jun 12 2024

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	13174
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	17th International Workshop on Breast Imaging, IWBI 2024
Country/Territory	United States
City	Chicago
Period	6/9/24 → 6/12/24

Bibliographical note

Publisher Copyright:
© 2024 SPIE.

Keywords

Breast cancer
Contrastive learning
Forward-Forward
Lumpectomy specimen
Radiography

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1117/12.3025407

Cite this

Ahamed, M. A., McFarland, B., Wang, X., Chen, J., & Imran, A. A. Z. (2024). Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography. In M. L. Giger, H. M. Whitney, K. Drukker, & H. Li (Eds.), 17th International Workshop on Breast Imaging, IWBI 2024 Article 131741S (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13174). https://doi.org/10.1117/12.3025407

Ahamed, Md Atik ; McFarland, Braxton ; Wang, Xiaoqin et al. / Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography. 17th International Workshop on Breast Imaging, IWBI 2024. editor / Maryellen L. Giger ; Heather M. Whitney ; Karen Drukker ; Hui Li. 2024. (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{5a04ae7dbc654297a98177df6134f624,

title = "Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography",

abstract = "Complete removal of cancer tumors with a negative specimen margin during lumpectomy is essential to reduce breast cancer recurrence. However, 2D radiography, the current method used to assess intraoperative specimen margin status, has limited accuracy, resulting in nearly one in four patients needing repeat surgery. This study aims to develop a deep learning model that improves the detection of positive margins in intraoperative breast lumpectomy specimens on radiographs. We annotated the lumpectomy radiograph images with masking that denotes regions of known malignancy, non-malignant tissue, and the areas of pathology-confirmed positive margin. We propose a pretraining strategy, namely Forward-Forward Contrastive Learning (FFCL) with both local and global-level contrastive learning. Experimental results on our annotated breast radiographs demonstrate the effectiveness of our FFCL method in detecting positive margins from intraoperative radiographs of breast lumpectomy specimens.",

keywords = "Breast cancer, Contrastive learning, Forward-Forward, Lumpectomy specimen, Radiography",

author = "Ahamed, {Md Atik} and Braxton McFarland and Xiaoqin Wang and Jin Chen and Imran, {Abdullah Al Zubaer}",

note = "Publisher Copyright: {\textcopyright} 2024 SPIE.; 17th International Workshop on Breast Imaging, IWBI 2024 ; Conference date: 09-06-2024 Through 12-06-2024",

year = "2024",

doi = "10.1117/12.3025407",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

editor = "Giger, {Maryellen L.} and Whitney, {Heather M.} and Karen Drukker and Hui Li",

booktitle = "17th International Workshop on Breast Imaging, IWBI 2024",

}

Ahamed, MA, McFarland, B, Wang, X, Chen, J & Imran, AAZ 2024, Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography. in ML Giger, HM Whitney, K Drukker & H Li (eds), 17th International Workshop on Breast Imaging, IWBI 2024., 131741S, Proceedings of SPIE - The International Society for Optical Engineering, vol. 13174, 17th International Workshop on Breast Imaging, IWBI 2024, Chicago, United States, 6/9/24. https://doi.org/10.1117/12.3025407

Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography. / Ahamed, Md Atik; McFarland, Braxton; Wang, Xiaoqin et al.
17th International Workshop on Breast Imaging, IWBI 2024. ed. / Maryellen L. Giger; Heather M. Whitney; Karen Drukker; Hui Li. 2024. 131741S (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13174).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography

AU - Ahamed, Md Atik

AU - McFarland, Braxton

AU - Wang, Xiaoqin

AU - Chen, Jin

AU - Imran, Abdullah Al Zubaer

PY - 2024

Y1 - 2024

N2 - Complete removal of cancer tumors with a negative specimen margin during lumpectomy is essential to reduce breast cancer recurrence. However, 2D radiography, the current method used to assess intraoperative specimen margin status, has limited accuracy, resulting in nearly one in four patients needing repeat surgery. This study aims to develop a deep learning model that improves the detection of positive margins in intraoperative breast lumpectomy specimens on radiographs. We annotated the lumpectomy radiograph images with masking that denotes regions of known malignancy, non-malignant tissue, and the areas of pathology-confirmed positive margin. We propose a pretraining strategy, namely Forward-Forward Contrastive Learning (FFCL) with both local and global-level contrastive learning. Experimental results on our annotated breast radiographs demonstrate the effectiveness of our FFCL method in detecting positive margins from intraoperative radiographs of breast lumpectomy specimens.

AB - Complete removal of cancer tumors with a negative specimen margin during lumpectomy is essential to reduce breast cancer recurrence. However, 2D radiography, the current method used to assess intraoperative specimen margin status, has limited accuracy, resulting in nearly one in four patients needing repeat surgery. This study aims to develop a deep learning model that improves the detection of positive margins in intraoperative breast lumpectomy specimens on radiographs. We annotated the lumpectomy radiograph images with masking that denotes regions of known malignancy, non-malignant tissue, and the areas of pathology-confirmed positive margin. We propose a pretraining strategy, namely Forward-Forward Contrastive Learning (FFCL) with both local and global-level contrastive learning. Experimental results on our annotated breast radiographs demonstrate the effectiveness of our FFCL method in detecting positive margins from intraoperative radiographs of breast lumpectomy specimens.

KW - Breast cancer

KW - Contrastive learning

KW - Forward-Forward

KW - Lumpectomy specimen

KW - Radiography

UR - http://www.scopus.com/inward/record.url?scp=85195428263&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85195428263&partnerID=8YFLogxK

U2 - 10.1117/12.3025407

DO - 10.1117/12.3025407

M3 - Conference contribution

AN - SCOPUS:85195428263

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - 17th International Workshop on Breast Imaging, IWBI 2024

A2 - Giger, Maryellen L.

A2 - Whitney, Heather M.

A2 - Drukker, Karen

A2 - Li, Hui

T2 - 17th International Workshop on Breast Imaging, IWBI 2024

Y2 - 9 June 2024 through 12 June 2024

ER -

Ahamed MA, McFarland B, Wang X, Chen J, Imran AAZ. Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography. In Giger ML, Whitney HM, Drukker K, Li H, editors, 17th International Workshop on Breast Imaging, IWBI 2024. 2024. 131741S. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.3025407

Automatic Detection of Breast Cancer Lumpectomy Margin from Intraoperative Specimen Mammography

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this