Shin Seung Yeon, Lee Sungwon, Summers Ronald M
Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA.
Med Image Comput Comput Assist Interv. 2021 Sep-Oct;12903:282-292. doi: 10.1007/978-3-030-87199-4_27. Epub 2021 Sep 21.
We present a novel unsupervised domain adaptation method for small bowel segmentation based on feature disentanglement. To make the domain adaptation more controllable, we disentangle intensity and non-intensity features within a unique two-stream auto-encoding architecture, and selectively adapt the non-intensity features that are believed to be more transferable across domains. The segmentation prediction is performed by aggregating the disentangled features. We evaluated our method using intravenous contrast-enhanced abdominal CT scans with and without oral contrast, which are used as source and target domains, respectively. The proposed method showed clear improvements in terms of three different metrics compared to other domain adaptation methods that are without the feature disentanglement. The method brings small bowel segmentation closer to clinical application.
我们提出了一种基于特征解缠的新型无监督域适应方法用于小肠分割。为了使域适应更可控，我们在独特的双流自动编码架构中解缠强度特征和非强度特征，并选择性地适应那些被认为在不同域之间更具可迁移性的非强度特征。分割预测通过聚合解缠后的特征来执行。我们使用分别作为源域和目标域的有静脉注射对比剂的腹部CT扫描（有口服对比剂）和无口服对比剂的腹部CT扫描来评估我们的方法。与其他没有特征解缠的域适应方法相比，所提出的方法在三种不同指标方面有明显改进。该方法使小肠分割更接近临床应用。
