Generative Adversarial Network based Synthesis for Supervised Medical Image Segmentation. Neff, T., Payer, C., Štern, D., & Urschler, M. In Proceedings of the OAGM&ARW Joint Workshop 2017: Vision, Automation and Robotics, pages 140-145, 2017. Verlag der TU Graz.
abstract   bibtex   
— Modern deep learning methods achieve state-of-the-art results in many computer vision tasks. While these methods perform well when trained on large datasets, deep learning methods suffer from overfitting and lack of gener-alization given smaller datasets. Especially in medical image analysis, acquisition of both imaging data and corresponding ground-truth annotations (e.g. pixel-wise segmentation masks) as required for supervised tasks, is time consuming and costly, since experts are needed to manually annotate data. In this work we study this problem by proposing a new variant of Generative Adversarial Networks (GANs), which, in addition to synthesized medical images, also generates segmentation masks for the use in supervised medical image analysis applications. We evaluate our approach on a lung segmentation task involving thorax X-ray images, and show that GANs have the potential to be used for synthesizing training data in this specific application.
@inproceedings{
 title = {Generative Adversarial Network based Synthesis for Supervised Medical Image Segmentation},
 type = {inproceedings},
 year = {2017},
 identifiers = {[object Object]},
 pages = {140-145},
 publisher = {Verlag der TU Graz},
 city = {Vienna},
 id = {1fe014dc-3a7f-3585-a1ef-cee00d3c739b},
 created = {2018-02-08T16:32:04.839Z},
 file_attached = {false},
 profile_id = {53d1e3c7-2f16-3c81-9a84-dccd45be4841},
 last_modified = {2019-11-08T01:39:42.616Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Neff2017},
 notes = {Oral, Best Paper Award},
 folder_uuids = {0ec41d70-75f1-4a99-820b-0a83ccc37f54},
 private_publication = {false},
 abstract = {— Modern deep learning methods achieve state-of-the-art results in many computer vision tasks. While these methods perform well when trained on large datasets, deep learning methods suffer from overfitting and lack of gener-alization given smaller datasets. Especially in medical image analysis, acquisition of both imaging data and corresponding ground-truth annotations (e.g. pixel-wise segmentation masks) as required for supervised tasks, is time consuming and costly, since experts are needed to manually annotate data. In this work we study this problem by proposing a new variant of Generative Adversarial Networks (GANs), which, in addition to synthesized medical images, also generates segmentation masks for the use in supervised medical image analysis applications. We evaluate our approach on a lung segmentation task involving thorax X-ray images, and show that GANs have the potential to be used for synthesizing training data in this specific application.},
 bibtype = {inproceedings},
 author = {Neff, Thomas and Payer, Christian and Štern, Darko and Urschler, Martin},
 booktitle = {Proceedings of the OAGM&ARW Joint Workshop 2017: Vision, Automation and Robotics}
}
Downloads: 0