Vendor-independent soft tissue lesion detection using weakly supervised and unsupervised adversarial domain adaptation

Joris van Vugt; Elena Marchiori; Ritse Mann; Albert Gubern-Mérida; Nikita Moriakov; Jonas Teuwen

doi:10.1117/12.2512940

Translator Disclaimer

13 March 2019 Vendor-independent soft tissue lesion detection using weakly supervised and unsupervised adversarial domain adaptation

Joris van Vugt, Elena Marchiori, Ritse Mann, Albert Gubern-Mérida, Nikita Moriakov, Jonas Teuwen

Author Affiliations +

Proceedings Volume 10950, Medical Imaging 2019: Computer-Aided Diagnosis; 1095002 (2019) https://doi.org/10.1117/12.2512940
Event: SPIE Medical Imaging, 2019, San Diego, California, United States

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.

Conference Presentation

Citation Download Citation

Joris van Vugt, Elena Marchiori, Ritse Mann, Albert Gubern-Mérida, Nikita Moriakov, and Jonas Teuwen "Vendor-independent soft tissue lesion detection using weakly supervised and unsupervised adversarial domain adaptation", Proc. SPIE 10950, Medical Imaging 2019: Computer-Aided Diagnosis, 1095002 (13 March 2019); https://doi.org/10.1117/12.2512940

ACCESS THE FULL ARTICLE