arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.09288eess.IVcs.CV
收藏

CT-SGAN:计算机断层扫描合成GAN

CT-SGAN: Computed Tomography Synthesis GAN

Imagia Inc.(Imagia公司);Quebec AI Institute (Mila)(魁北克人工智能研究所(Mila));McGill University(麦吉尔大学);University of Waterloo(滑铁卢大学)

Ahmad Pesaranghader, Yiping Wang, Mohammad Havaei

摘要:

数据的多样性对于成功训练深度学习模型至关重要。利用一个循环生成对抗网络,我们提出了CT-SGAN模型,该模型在胸部CT扫描的小数据集上训练时生成大规模3D合成CT扫描体积($\geq 224\times224\times224$)。CT-SGAN为医学成像中机器学习面临的两大挑战提供了有吸引力的解决方案:少量给定的i.i.d.训练数据,以及围绕患者数据共享的限制,阻止快速获得更大和更多样化的数据集。我们使用各种度量标准(包括Fréchet Inception Distance和Inception Score)定性和定量地评估生成图像的保真度。我们进一步表明,CT-SGAN可以通过在大量合成数据上预训练分类器来显着提高肺结节检测的准确性。

英文摘要:

Diversity in data is critical for the successful training of deep learning models. Leveraged by a recurrent generative adversarial network, we propose the CT-SGAN model that generates large-scale 3D synthetic CT-scan volumes ($\geq 224\times224\times224$) when trained on a small dataset of chest CT-scans. CT-SGAN offers an attractive solution to two major challenges facing machine learning in medical imaging: a small number of given i.i.d. training data, and the restrictions around the sharing of patient data preventing to rapidly obtain larger and more diverse datasets. We evaluate the fidelity of the generated images qualitatively and quantitatively using various metrics including Fréchet Inception Distance and Inception Score. We further show that CT-SGAN can significantly improve lung nodule detection accuracy by pre-training a classifier on a vast amount of synthetic data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑