《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (2): 662-669.DOI: 10.11772/j.issn.1001-9081.2024020185

• 多媒体计算与计算机仿真 • 上一篇    

受腹侧通路启发的脂肪肝超声图像分类方法VPNet

丁丹妮1, 彭博2, 吴锡1()   

  1. 1.成都信息工程大学 计算机学院,成都 610225
    2.西南交通大学 计算机与人工智能学院,成都 611756
  • 收稿日期:2024-02-27 修回日期:2024-05-17 接受日期:2024-05-27 发布日期:2024-07-19 出版日期:2025-02-10
  • 通讯作者: 吴锡
  • 作者简介:丁丹妮(1999—),女,湖北松滋人,硕士研究生,主要研究方向:图像处理、生物视觉
    彭博(1980—),女,四川成都人,教授,博士,CCF会员,主要研究方向:计算机视觉、模式识别;
  • 基金资助:
    四川省科技创新苗子工程培育项目(MZGC20230077);四川省重点研发计划项目(2023YFG0125);四川省中央引导地方科技发展专项(2022ZYD0117)

VPNet: fatty liver ultrasound image classification method inspired by ventral pathway

Danni DING1, Bo PENG2, Xi WU1()   

  1. 1.School of Computer Science,Chengdu University of Information Technology,Chengdu Sichuan 610225,China
    2.School of Computing and Artificial Intelligence,Southwest Jiaotong University,Chengdu Sichuan 611756,China
  • Received:2024-02-27 Revised:2024-05-17 Accepted:2024-05-27 Online:2024-07-19 Published:2025-02-10
  • Contact: Xi WU
  • About author:DING Danni, born in 1999, M. S. candidate. Her research interests include image processing, biological vision.
    PENG Bo, born in 1980, Ph. D., professor. Her research interests include computer vision, pattern recognition.
  • Supported by:
    Cultivation Project of Sichuan Scientific and Technological Innovation Seedlings Project(MZGC20230077);Key Research and Development Program in Sichuan Province(2023YFG0125);Sichuan Provincial Central Guidance for Local Science and Technology Development Special Project(2022ZYD0117)

摘要:

考虑腹侧通路在视觉信息处理中的核心作用,提出一种基于腹侧通路的脂肪肝分类方法。通过整合卷积神经网络(CNN)和生物视觉认知模型,模拟从初级视觉皮层(V1)到下颞叶皮层(IT Cortex)的层次化信息加工流程,从而构建全新的神经网络架构——VPNet (Ventral Pathway Network)。此外,受生物视觉机制中非经典感受野(nCRF)抑制机制在背景噪声抑制方面的启发,模拟该机制以应对超声图像中斑点噪声的挑战,进而增强模型的特征识别能力。在自制数据集上进行四类别的脂肪肝变异程度识别时,VPNet达到88.37%的准确率;在公开数据集上进行二类别的脂肪肝诊断时,VPNet的准确率、敏感性和特异性均达到100%的最佳性能。实验结果表明,与已知公开数据集研究中较优的ResNet101-SVM相比,VPNet的准确率分别在自制数据集和公开数据集上提升了11.63和0.7个百分点,证明了所提方法在脂肪肝疾病诊断中的有效性。

关键词: 超声图像分类, 脂肪肝变性, 生物视觉, 腹侧通路, 非经典感受野抑制, 深度学习

Abstract:

An innovative fatty liver classification method based on ventral pathway was developed due to the crucial role of ventral pathway in visual information processing. By integrating Convolutional Neural Network (CNN) and biological visual cognition model, hierarchical information processing process from primary visual cortex (V1) to Inferior Temporal Cortex (IT Cortex) was simulated, resulting in the creation of a new neural network architecture named VPNet (Ventral Pathway Network). Besides, inspired by non-Classical Receptive Field (nCRF) inhibition mechanism in biological vision, which aids in background noise suppression, this mechanism was simulated to address the challenge of speckle noise in ultrasound images, thereby enhancing the feature recognition capability of the model. An accuracy of 88.37% was achieved by VPNet in identifying four categories of fatty liver variation degree on the self-made dataset, and best performance of 100% accuracy, sensitivity, and specificity was achieved by VPNet in diagnosing two categories of fatty liver on the public dataset. The experimental results show that, compared with the superior ResNet101-SVM in the existing public dataset research, the accuracy of VPNet increases by 11.63 and 0.7 percentage points on the self-made dataset and public dataset respectively, which proves the effectiveness of the proposed method in the diagnosis of fatty liver diseases.

Key words: ultrasound image classification, fatty liver degeneration, biological vision, ventral pathway, non-Classical Receptive Field (nCRF) inhibition, deep learning

中图分类号: