计算机与现代化 ›› 2024, Vol. 0 ›› Issue (04): 43-47.doi: 10.3969/j.issn.1006-2475.2024.04.008

• 图像处理 • 上一篇    下一篇

基于Ghost卷积的高级别浆液性卵巢癌复发预测方法

  



  1. (1.重庆师范大学计算机与信息科学学院,重庆 401331; 2.重庆医科大学第一临床学院,重庆 401331)
  • 出版日期:2024-04-30 发布日期:2024-05-13
  • 作者简介:唐艺菠(1997—),男(羌族),四川乐山人,硕士研究生,研究方向:医学图像处理,E-mail: 543779362@qq.com; 通信作者:崔少国(1974—),男,重庆人,教授,博士,研究方向:大数据与人工智能,E-mail: csg@cqnu.edu.cn; 万皓明(1998—),男,浙江义乌人,硕士研究生,研究方向:医学图像处理,E-mail: 1260835131@qq.com; 王锐(1999—),男,云南昭通人,硕士研究生,研究方向:医学图像处理,E-mail: 1502400359@qq.com; 刘丽丽(1986—),女,重庆人,博士研究生,研究方向:医学影像,E-mail: 903689621@qq.com。
  • 基金资助:
    国家自然科学基金资助项目(62003065); 重庆市科技局自然科学基金资助项目(2022NSCQ-MSX2933, 2022TFII-OFX0262, cstc2019jscx-mbdxX0061); 教育部人文社科规划基金资助项目(22YJA870005); 重庆市教委重点项目(KJZD-K202200510); 重庆市社会科学规划项目(2022NDYB119); 重庆师范大学人才基金资助项目(20XLB004); 重庆市研究生科研创新项目(CYS22558, CYS22555); 重庆师范大学研究生科研创新项目(YKC22019)

Ghost Convolution Based Prediction Method for Recurrence of High Grade#br# Serous Ovarian Cancer



  1. (1. School of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China;
    2. The First Clinical College, Chongqing Medical University, Chongqing 401331, China)
  • Online:2024-04-30 Published:2024-05-13

摘要:
摘要:高级别浆液性卵巢癌是一种恶性肿瘤疾病,进行术前复发预测能帮助临床医生为患者提供个性化治疗方案,降低病人的死亡率。因该疾病的医学数据较少且难以获取,导致其深度学习模型难以得到充分的训练,复发预测准确率有待提高。针对此问题,本文设计了一种改进的低参数残差网络TGE-ResNet34,以ResNet34为主干网络,将传统卷积模块用Ghost卷积代替,完成病灶区特征的提取,降低模型的参数量,在2个Ghost卷积之间融入ECA(Efficient Channel Attention)注意力机制,抑制无用特征提取的干扰,最后通过5折交叉验证模型,避免数据随机划分的偶然性。实验结果表明,改进设计的TGE-ResNet34网络准确率为96.01%,相比原基线网络准确率提高4.52个百分点,参数量减少15.98 M。

关键词: 关键词:高级别浆液性卵巢癌, 残差网络, Ghost卷积, 注意力

Abstract:
Abstract: High grade serous ovarian cancer is a malignant tumor disease, and preoperative recurrence prediction can help clinical doctors provide personalized treatment plans for patients and reduce the mortality rate. Due to the less and difficult-to-obtain medical data of this disease, its deep learning model is difficult to obtain sufficient training, and the accuracy of recurrence prediction needs to be improved. To address this issue, this article proposes an improved low-parameter residual network TGE-ResNet34, which uses ResNet34 as the backbone network and replaces traditional convolution modules with Ghost convolutions to extract lesion area features and reduce the model’s parameter volume. The ECA (Efficient Channel Attention) attention mechanism is incorporated between two Ghost convolutions to suppress interference from useless feature extraction. Finally, the model is evaluated through a five-fold cross-validation to avoid the randomness of data partitioning. The experimental results show that the accuracy of the improved TGE-ResNet34 network is 96.01%, which is 4.52 percentage points higher than the original baseline network’s accuracy and reduces the parameter volume by 15.98 M.

Key words: Key words: high grade serous ovarian cancer, residual network, Ghost convolution, attention

中图分类号: