Share Email Print

Proceedings Paper • new

Vendor-independent soft tissue lesion detection using weakly supervised and unsupervised adversarial domain adaptation
Author(s): Joris van Vugt; Elena Marchiori; Ritse Mann; Albert Gubern-Mérida; Nikita Moriakov; Jonas Teuwen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Computer-aided detection aims to improve breast cancer screening programs by helping radiologists to evaluate digital mammography (DM) exams. DM exams are generated by devices from different vendors, with diverse characteristics between and even within vendors. Physical properties of these devices and postprocessing of the images can greatly influence the resulting mammogram. This results in the fact that a deep learning model trained on data from one vendor cannot readily be applied to data from another vendor. This paper investigates the use of tailored transfer learning methods based on adversarial learning to tackle this problem. We consider a database of DM exams (mostly bilateral and two views) generated by Hologic and Siemens vendors. We analyze two transfer learning settings: 1) unsupervised transfer, where Hologic data with soft lesion annotation at pixel level and Siemens unlabelled data are used to annotate images in the latter data; 2) weak supervised transfer, where exam level labels for images from the Siemens mammograph are available. We propose tailored variants of recent state-of-the-art methods for transfer learning which take into account the class imbalance and incorporate knowledge provided by the annotations at exam level. Results of experiments indicate the beneficial effect of transfer learning in both transfer settings. Notably, at 0.02 false positives per image, we achieve a sensitivity of 0.37, compared to 0.30 of a baseline with no transfer. Results indicate that using exam level annotations gives an additional increase in sensitivity.

Paper Details

Date Published: 13 March 2019
PDF: 4 pages
Proc. SPIE 10950, Medical Imaging 2019: Computer-Aided Diagnosis, 1095002 (13 March 2019); doi: 10.1117/12.2512940
Show Author Affiliations
Joris van Vugt, Radboud Univ. Nijmegen (Netherlands)
Elena Marchiori, Radboud Univ. Nijmegen (Netherlands)
Ritse Mann, Radboud Univ. Medical Ctr. (Netherlands)
Albert Gubern-Mérida, ScreenPoint Medical (Netherlands)
Nikita Moriakov, Radboud Univ. Medical Ctr. (Netherlands)
Jonas Teuwen, Radboud Univ. Medical Ctr. (Netherlands)
Delft Univ. of Technology (Netherlands)

Published in SPIE Proceedings Vol. 10950:
Medical Imaging 2019: Computer-Aided Diagnosis
Kensaku Mori; Horst K. Hahn, Editor(s)

© SPIE. Terms of Use
Back to Top