Skip to main content

A multitask deep learning method in simultaneously predicting occult invasive disease in ductal carcinoma in-situ and segmenting microcalcifications in mammography

Publication ,  Conference
Hou, R; Grimm, LJ; Mazurowski, MA; Marks, JR; King, LM; Maley, CC; Hwang, ES; Lo, JY
Published in: Progress in Biomedical Optics and Imaging - Proceedings of SPIE
January 1, 2020

We proposed a two-branch multitask learning convolutional neural network to solve two different but related tasks at the same time. Our main task is to predict occult invasive disease in biopsy proven Ductal Carcinoma in-situ (DCIS), with an auxiliary task of segmenting microcalcifications (MCs). In this study, we collected digital mammography from 604 patients, 400 of which were DCIS. The model used patches with size of 512×512 extracted within a radiologist masked ROIs as input, with outputs including noisy MC segmentations obtained from our previous algorithms, and classification labels from final diagnosis at patients' definite surgery. We utilized a deep multitask model by combining both Unet segmentation networks and prediction classification networks, by sharing first several convolutional layers. The model achieved a patch-based ROC-AUC of 0.69, with a case-based ROC-AUC of 0.61. Segmentation results achieved a dice coefficient of 0.49.

Duke Scholars

Published In

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

DOI

ISSN

1605-7422

ISBN

9781510633957

Publication Date

January 1, 2020

Volume

11314
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Hou, R., Grimm, L. J., Mazurowski, M. A., Marks, J. R., King, L. M., Maley, C. C., … Lo, J. Y. (2020). A multitask deep learning method in simultaneously predicting occult invasive disease in ductal carcinoma in-situ and segmenting microcalcifications in mammography. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 11314). https://doi.org/10.1117/12.2549669
Hou, R., L. J. Grimm, M. A. Mazurowski, J. R. Marks, L. M. King, C. C. Maley, E. S. Hwang, and J. Y. Lo. “A multitask deep learning method in simultaneously predicting occult invasive disease in ductal carcinoma in-situ and segmenting microcalcifications in mammography.” In Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol. 11314, 2020. https://doi.org/10.1117/12.2549669.
Hou R, Grimm LJ, Mazurowski MA, Marks JR, King LM, Maley CC, et al. A multitask deep learning method in simultaneously predicting occult invasive disease in ductal carcinoma in-situ and segmenting microcalcifications in mammography. In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2020.
Hou, R., et al. “A multitask deep learning method in simultaneously predicting occult invasive disease in ductal carcinoma in-situ and segmenting microcalcifications in mammography.” Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 11314, 2020. Scopus, doi:10.1117/12.2549669.
Hou R, Grimm LJ, Mazurowski MA, Marks JR, King LM, Maley CC, Hwang ES, Lo JY. A multitask deep learning method in simultaneously predicting occult invasive disease in ductal carcinoma in-situ and segmenting microcalcifications in mammography. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2020.

Published In

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

DOI

ISSN

1605-7422

ISBN

9781510633957

Publication Date

January 1, 2020

Volume

11314