Segmentation of bladder tumors from medical radiographic images is of great significance for early detection, diagnosis and prognosis evaluation of bladder cancer. Deep Convolution Neural Networks (DCNNs) have been successfully used for bladder tumor segmentation, but the segmentation based on DCNN is data-hungry for model training and ignores clinical knowledge. From the clinical view, bladder tumors originate from the mucosal surface of bladder and must rely on the bladder wall to survive and grow. This clinical knowledge of tumor location is helpful to improve the bladder tumor segmentation. To achieve this, we propose a novel bladder tumor segmentation method, which incorporates the clinical logic rules of bladder tumor and bladder wall into DCNNs to harness the tumor segmentation. Clinical logical rules provide a semantic and human-readable knowledge representation and are easy for knowledge acquisition from clinicians. In addition, incorporating logical rules of clinical knowledge helps to reduce the data dependency of the segmentation network, and enables precise segmentation results even with limited number of annotated images. Experiments on bladder MR images collected from the collaborating hospital validate the effectiveness of the proposed bladder tumor segmentation method.

中文翻译：

---

将逻辑临床知识融入深度神经网络以改善膀胱肿瘤分割


从医学放射图像中分割膀胱肿瘤对于膀胱癌的早期发现、诊断和预后评估具有重要意义。深度卷积神经网络（DCNN）已成功用于膀胱肿瘤分割，但基于 DCNN 的分割模型训练需要大量数据，并且忽略了临床知识。从临床上看，膀胱肿瘤起源于膀胱粘膜表面，必须依赖膀胱壁才能生存和生长。这种肿瘤位置的临床知识有助于改善膀胱肿瘤分割。为了实现这一目标，我们提出了一种新颖的膀胱肿瘤分割方法，该方法将膀胱肿瘤和膀胱壁的临床逻辑规则纳入DCNN中以利用肿瘤分割。临床逻辑规则提供语义和人类可读的知识表示，并且易于临床医生获取知识。此外，结合临床知识的逻辑规则有助于减少分割网络的数据依赖性，即使在带注释的图像数量有限的情况下也能获得精确的分割结果。对从合作医院收集的膀胱 MR 图像进行的实验验证了所提出的膀胱肿瘤分割方法的有效性。