南方医科大学学报

南方医科大学学报 ›› 2023, Vol. 43 ›› Issue (5): 755-763.doi: 10.12122/j.issn.1673-4254.2023.05.11

• • 上一篇    下一篇

aFaster RCNN：一种基于平扫 CT 的多疾病阶段胰腺病灶检测模型

梁利渡，张浩杰，鲁 倩，周陈杰，李淑龙   

  1. 南方医科大学生物医学工程学院//广东省医学图像处理重点实验室，广东 广州 510515；南方医科大学珠江医院普通外科中心肝胆外科二//广东省人工器官与组织工程研究中心，广东 广州 510280；盐城市第三人民医院超声科，江苏 盐城 224008
  • 出版日期:2023-05-20 发布日期:2023-06-12

Advanced Faster RCNN: a non-contrast CT-based algorithm for detecting pancreatic lesions in multiple disease stages

LIANG Lidu, ZHANG Haojie, LU Qian, ZHOU Chenjie, LI Shulong   

  1. School of Biomedical Engineering, Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou 510515, China; General Surgery Center, Second Department of Hepatobiliary Surgery, Guangdong Provincial Research Center for Artificial Organ and Tissue Engineering, Zhujiang Hospital, Southern Medical University, Guangzhou 510280, China; Department of Ultrasound, Yancheng Third People's Hospital, Yancheng 224008, China
  • Online:2023-05-20 Published:2023-06-12

RichHTML

13

PDF

131

摘要： 目的 研究基于平扫CT的胰腺病灶检测算法，实现低成本和精准的胰腺病灶自动检测。方法 以Faster RCNN为基准模型，构建了名为advanced Faster RCNN（aFaster RCNN）的基于平扫CT胰腺病灶检测模型。该模型使用残差连接网络Resnet50为特征提取模块来提取胰腺病灶的深层图像特征；并针对胰腺病灶形态重新设计了9种检测锚框尺寸来构建RPN模块；同时，提出一种综合考虑病灶形状和解剖结构约束的新型Bounding Box回归损失函数来约束RPN模块回归子网络的训练过程；最后，利用第二阶段的检测器来生成检测框。模型使用来自国内四家临床中心的728例胰腺疾病患者进行训练（518例，约占71.15%）和测试（210例，约占28.85%）；并通过消融实验，以及与3种经典目标检测模型SSD、YOLO和CenterNet进行比较的对比实验来验证aFaster RCNN的性能。结果 aFaster RCNN胰腺病灶检测模型在测试集图像水平和病人水平上分别获得了73.64%、92.38%的召回率以及45.29%、53.80%的平均精度，均高于所有被比较模型。结论 本文方法可以有效提取平扫CT中的胰腺病灶特征来检测胰腺病灶区域。

关键词: 平扫CT；胰腺癌；病灶检测

Abstract: Objective To propose a non-contrast CT-based algorithm for automated and accurate detection of pancreatic lesions at a low cost. Methods With Faster RCNN as the benchmark model, an advanced Faster RCNN (aFaster RCNN) model for pancreatic lesions detection based on plain CT was constructed. The model uses the residual connection network Resnet50 as the feature extraction module to extract the deep image features of pancreatic lesions. According to the morphology of pancreatic lesions, 9 anchor frame sizes were redesigned to construct the RPN module. A new Bounding Box regression loss function was proposed to constrain the training process of RPN module regression subnetwork by comprehensively considering the constraints of the lesion shape and anatomical structure. Finally, a detection frame was generated using the detector in the second stage. The data from a total of 728 cases of pancreatic diseases from 4 clinical centers in China were used for training (518 cases, 71.15%) and testing (210 cases, 28.85%) of the model. The performance of aFaster RCNN was verified through ablation experiments and comparison experiments with 3 classical target detection models SSD, YOLO and CenterNet. Results The aFaster RCNN model for pancreatic lesion detection achieved recall rates of 73.64% at the image level and 92.38% at the patient level, with an average precision of 45.29% and 53.80% at the image and patient levels, respectively, which were higher than those of the 3 models for comparison. Conclusion The proposed method can effectively extract the imaging features of pancreatic lesions from non-contrast CT images to detect the pancreatic lesions.

Key words: non-contrast CT; pancreatic cancer; lesion detection