Cancers (Oct 2023)
Deep Learning for Fully Automatic Tumor Segmentation on Serially Acquired Dynamic Contrast-Enhanced MRI Images of Triple-Negative Breast Cancer
- Zhan Xu,
- David E. Rauch,
- Rania M. Mohamed,
- Sanaz Pashapoor,
- Zijian Zhou,
- Bikash Panthi,
- Jong Bum Son,
- Ken-Pin Hwang,
- Benjamin C. Musall,
- Beatriz E. Adrada,
- Rosalind P. Candelaria,
- Jessica W. T. Leung,
- Huong T. C. Le-Petross,
- Deanna L. Lane,
- Frances Perez,
- Jason White,
- Alyson Clayborn,
- Brandy Reed,
- Huiqin Chen,
- Jia Sun,
- Peng Wei,
- Alastair Thompson,
- Anil Korkut,
- Lei Huo,
- Kelly K. Hunt,
- Jennifer K. Litton,
- Vicente Valero,
- Debu Tripathy,
- Wei Yang,
- Clinton Yam,
- Jingfei Ma
Affiliations
- Zhan Xu
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- David E. Rauch
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Rania M. Mohamed
- Department of Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Sanaz Pashapoor
- Department of Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Zijian Zhou
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Bikash Panthi
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Jong Bum Son
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Ken-Pin Hwang
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Benjamin C. Musall
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Beatriz E. Adrada
- Department of Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Rosalind P. Candelaria
- Department of Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Jessica W. T. Leung
- Department of Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Huong T. C. Le-Petross
- Department of Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Deanna L. Lane
- Department of Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Frances Perez
- Department of Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Jason White
- Department of Breast Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Alyson Clayborn
- Department of Breast Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Brandy Reed
- Department of Clinical Research Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Huiqin Chen
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Jia Sun
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Peng Wei
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Alastair Thompson
- Section of Breast Surgery, Baylor College of Medicine, Houston, TX 77030, USA
- Anil Korkut
- Department of Bioinformatics & Computational Biology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Lei Huo
- Department of Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Kelly K. Hunt
- Department of Breast Surgical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Jennifer K. Litton
- Department of Breast Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Vicente Valero
- Department of Breast Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Debu Tripathy
- Department of Breast Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Wei Yang
- Department of Breast Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Clinton Yam
- Department of Breast Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Jingfei Ma
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- DOI
- https://doi.org/10.3390/cancers15194829
- Journal volume & issue
-
Vol. 15,
no. 19
p. 4829
Abstract
Accurate tumor segmentation is required for quantitative image analyses, which are increasingly used for evaluation of tumors. We developed a fully automated and high-performance segmentation model of triple-negative breast cancer using a self-configurable deep learning framework and a large set of dynamic contrast-enhanced MRI images acquired serially over the patients’ treatment course. Among all models, the top-performing one that was trained with the images across different time points of a treatment course yielded a Dice similarity coefficient of 93% and a sensitivity of 96% on baseline images. The top-performing model also produced accurate tumor size measurements, which is valuable for practical clinical applications.
Keywords
