Department of Electronic Engineering, Fudan University, Shanghai, China.
Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai, China.
Technol Health Care. 2022;30(6):1475-1487. doi: 10.3233/THC-213655.
The incidence of liver tumors is among the top three in China. The treatments of benign and malignant tumors are different. Accurate diagnosis plays an important role in guiding the treatment of tumors.
The aim of this study is to solve the following: (1) blurred boundary between the liver tumor and other organs causes incorrect segmentation of liver tumor boundaries; (2) large difference in tumor size and the diversity in texture and grayscale are major challenges in liver tumor classification tasks.
Firstly, the liver tumor is segmented from the original CT images by a tumor segmentation network, UNet++ with fusion loss and atrous spatial pyramid pooling (FLAS-UNet++). The proposed segmentation method can solve the problem of tumor edge segmentation error by learning the tumor edge information. Secondly they are adaptively cropped according to the tumor volume to reduce the over-fitting and over-sensitivity of the deep network. Thirdly an improved Dense Block is designed to pay more attention to the changes in grayscale and texture between benign and malignant tumors. Finally, the features extracted from the network combined with tumor volume, patient's sex and age, are sent to a classifier for diagnosis.
Liver tumor segmentation results show that the dice, HD95 reached 71.9%, 12.1 mm, respectively. The classification results show that the accuracy, specificity, sensitivity and area under curve reached 82.4%, 79.8%, 84.4%, 87.5%, respectively. The segmentation and classification results are both better than other's methods and mainstream networks.
In order to solve existing problems of liver tumor CT image classification methods, our method realizes the accurate segmentation and classification of liver tumors in CT images and has important clinical application value.
肝脏肿瘤的发病率居中国前三位。良性和恶性肿瘤的治疗方法不同。准确的诊断对指导肿瘤的治疗起着重要作用。
本研究旨在解决以下问题：（1）肝脏肿瘤与其他器官之间的边界模糊导致肝脏肿瘤边界的分割不正确；（2）肿瘤大小差异大和纹理、灰度多样性是肝脏肿瘤分类任务的主要挑战。
首先，通过肿瘤分割网络 UNet++融合融合损失和空洞空间金字塔池化（FLAS-UNet++）对原始 CT 图像进行肝脏肿瘤分割。所提出的分割方法可以通过学习肿瘤边缘信息来解决肿瘤边缘分割错误的问题。其次，根据肿瘤体积自适应裁剪，减少深度网络的过拟合和过灵敏度。第三，设计了改进的密集块，以更加关注良恶性肿瘤之间灰度和纹理的变化。最后，将网络提取的特征与肿瘤体积、患者性别和年龄相结合，送入分类器进行诊断。
肝脏肿瘤分割结果表明，Dice、HD95 分别达到 71.9%、12.1mm。分类结果表明，准确率、特异性、灵敏度和曲线下面积分别达到 82.4%、79.8%、84.4%、87.5%。分割和分类结果均优于其他方法和主流网络。
为了解决现有的肝脏肿瘤 CT 图像分类方法存在的问题，我们的方法实现了 CT 图像中肝脏肿瘤的精确分割和分类，具有重要的临床应用价值。
