分离病变与正常组织特征，提升PET图像病灶分割准确性
Disentangled PET Lesion Segmentation
- 采用3D解耦架构，分离病变与健康组织特征
- 在多个数据集上降低假阳性率，尤其减少高摄取正常区域误判
- 适合医学影像分析、放射组学及临床辅助诊断场景
PET成像在临床中至关重要，能反映正常组织和肿瘤病灶的功能活性。开发自动化的PET图像病灶分割方法十分关键，因为人工分割费时且存在观察者间与观察者内差异。本文提出PET-Disentangler，一种基于3D UNet-like编码器-解码器结构的3D解耦方法，通过分割损失、重建损失和健康成分合理性损失，分离疾病与健康解剖特征。引入判别网络，使健康潜在特征分布匹配健康样本，从而避免其包含病变相关特征。定量结果表明，PET-Disentangler更不易将健康组织或高示踪剂摄取区域误判为癌灶，因这些模式被分配至解耦后的健康组件。
原文摘要 · Abstract (English)
PET imaging is an invaluable tool in clinical settings as it captures the functional activity of both healthy anatomy and cancerous lesions. Developing automatic lesion segmentation methods for PET images is crucial since manual lesion segmentation is laborious and prone to inter- and intra-observer variability. We propose PET-Disentangler, a 3D disentanglement method that uses a 3D UNet-like encoder-decoder architecture to disentangle disease and normal healthy anatomical features with losses for segmentation, reconstruction, and healthy component plausibility. A critic network is used to encourage the healthy latent features to match the distribution of healthy samples and thus encourages these features to not contain any lesion-related features. Our quantitative results show that PET-Disentangler is less prone to incorrectly declaring healthy and high tracer uptake regions as cancerous lesions, since such uptake pattern would be assigned to the disentangled healthy component.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。