Zhang Huiting, Yang Xiaotang, Li Dengao, Cui Yanfen, Zhao Jumin, Qiu Shuang
College of Data Science, Taiyuan University of Technology, Jinzhong 030600, China; Technology Research Centre of Spatial Information Network Engineering of Shanxi, Jinzhong 030600, China; Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province, Taiyuan, China, 030024.
Department of Radiology, Shanxi Province Cancer Hospital, Shanxi Medical University, Taiyuan 030013, China.
J Biomed Inform. 2023 Mar;139:104304. doi: 10.1016/j.jbi.2023.104304. Epub 2023 Feb 2.
Segmentation of rectal cancerous regions from Magnetic Resonance (MR) images can help doctor define the extent of the rectal cancer and judge the severity of rectal cancer, so rectal tumor segmentation is crucial to improve the accuracy of rectal cancer diagnosis. However, accurate segmentation of rectal cancerous regions remains a challenging task due to the shape of rectal tumor has significant variations and the tumor and surrounding tissue are indistinguishable. In addition, in the early research on rectal tumor segmentation, most deep learning methods were based on convolutional neural networks (CNNs), and traditional CNN have small receptive field, which can only capture local information while ignoring the global information of the image. Nevertheless, the global information plays a crucial role in rectal tumor segmentation, so traditional CNN-based methods usually cannot achieve satisfactory segmentation results. In this paper, we propose an encoder-decoder network named Dual Parallel Net (DuPNet), which fuses transformer and classical CNN for capturing both global and local information. Meanwhile, as for capture features at different scales as well as to avoid accuracy loss and parameters reduction, we design a feature adaptive block (FAB) in skip connection between encoder and decoder. Furthermore, in order to utilize the apriori information of rectal tumor shape effectively, we design a Gaussian Mixture prior and embed it in self-attention mechanism of the transformer, leading to robust feature representation and accurate segmentation results. We have performed extensive ablation experiments to verify the effectiveness of our proposed dual parallel encoder, FAB and Gaussian Mixture prior on the dataset from the Shanxi Cancer Hospital. In the experimental comparison with the state-of-the-art methods, our method achieved a Mean Intersection over Union (MIoU) of 89.34% on the test set. In addition to that, we evaluated the generalizability of our method on the dataset from Xinhua Hospital, the promising results verify the superiority of our method.
从磁共振（MR）图像中分割直肠癌区域有助于医生确定直肠癌的范围并判断其严重程度，因此直肠肿瘤分割对于提高直肠癌诊断的准确性至关重要。然而，由于直肠肿瘤形状变化显著且肿瘤与周围组织难以区分，准确分割直肠癌区域仍然是一项具有挑战性的任务。此外，在早期的直肠肿瘤分割研究中，大多数深度学习方法基于卷积神经网络（CNN），而传统CNN的感受野较小，只能捕捉局部信息而忽略了图像的全局信息。然而，全局信息在直肠肿瘤分割中起着至关重要的作用，因此基于传统CNN的方法通常无法取得令人满意的分割结果。在本文中，我们提出了一种名为双并行网络（DuPNet）的编码器 - 解码器网络，它融合了Transformer和经典CNN以同时捕捉全局和局部信息。同时，为了在不同尺度上捕捉特征并避免精度损失和参数减少，我们在编码器和解码器之间的跳跃连接中设计了一个特征自适应块（FAB）。此外，为了有效利用直肠肿瘤形状的先验信息，我们设计了一个高斯混合先验并将其嵌入到Transformer的自注意力机制中，从而获得强大的特征表示和准确的分割结果。我们在山西医科大学附属肿瘤医院的数据集中进行了广泛的消融实验，以验证我们提出的双并行编码器、FAB和高斯混合先验的有效性。在与现有最先进方法的实验比较中，我们的方法在测试集上实现了89.34%的平均交并比（MIoU）。除此之外，我们还在新华医院的数据集中评估了我们方法的泛化能力，有前景的结果验证了我们方法的优越性。
