DepthParkNet: A 3D Convolutional Neural Network with Depth-Aware Coordinate Attention for PET-Based Parkinson's Disease Diagnosis

被引:0
|
作者
Li, Maoyuan [1 ,2 ]
Chen, Ling [3 ]
Chu, Jianmin [3 ]
Shi, Xinchong [4 ]
Zhang, Xiangsong [4 ]
Zhao, Gansen [1 ,2 ]
Tang, Hua [1 ,2 ]
机构
[1] South China Normal Univ, Sch Comp Sci, Guangzhou, Peoples R China
[2] Key Lab Cloud Secur & Assessment Technol Guangzho, Guangzhou, Peoples R China
[3] Sun Yat Sen Univ, Affiliated Hosp 1, Dept Neurol, Guangzhou, Peoples R China
[4] Sun Yat Sen Univ, Affiliated Hosp 1, Dept Nucl Med, Guangzhou, Peoples R China
来源
ADVANCED INTELLIGENT COMPUTING IN BIOINFORMATICS, PT I, ICIC 2024 | 2024年 / 14881卷
基金
中国国家自然科学基金;
关键词
Parkinson's disease; Deep learning; 3D convolutional neural network; Attention mechanism; Class imbalance;
D O I
10.1007/978-981-97-5689-6_6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Positron Emission Tomography (PET) imaging is essential for accurately diagnosing Parkinson's Disease (PD). With the advancement of deep convolutional networks, 3D convolutional neural networks (CNNs) have been extensively utilized to analyze PET images. However, the limited availability of PET imaging data represents a significant bottleneck in this field. Training on small datasets could restrict the performance of 3D CNNs. Moreover, models trained on small datasets tend to exhibit weak generalizability, making it challenging to handle variations in PET images caused by clinical factors. This paper proposes depth-aware coordinate attention that integrates clinical prior knowledge. It's composed of two modules: the coordinate attention module and the depth-aware attention module. The coordinate attention module could preserve positional information while capturing long-range dependencies. Meanwhile, the depth-aware attention module aims to reveal the relationships among various depths within a PET image. These innovations enable our DepthParkNet to extract critical features from limited PET imaging data, thus enhancing its performance. Additionally, this paper proposes an augmentation pipeline named PDaug, which includes three transformations aimed at improving the generalizability of the model. The proposed model is validated on two datasets, demonstrating outstanding performance with balanced accuracy of 99.17% and 98.13%.
引用
收藏
页码:61 / 72
页数:12
相关论文
共 50 条
  • [21] 3D Face Reconstruction Based on Convolutional Neural Network
    Li Fangmin
    Chen Ke
    Liu Xinhua
    2017 10TH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTATION TECHNOLOGY AND AUTOMATION (ICICTA 2017), 2017, : 71 - 74
  • [22] Parkinson's severity diagnosis explainable model based on 3D multi-head attention residual network
    Huang, Jiehui
    Lin, Lishan
    Yu, Fengcheng
    He, Xuedong
    Song, Wenhui
    Lin, Jiaying
    Tang, Zhenchao
    Yuan, Kang
    Li, Yucheng
    Huang, Haofan
    Pei, Zhong
    Xian, Wenbiao
    Chen, Calvin Yu-Chian
    COMPUTERS IN BIOLOGY AND MEDICINE, 2024, 170
  • [23] Spatial Attention-Based 3D Graph Convolutional Neural Network for Sign Language Recognition
    Al-Hammadi, Muneer
    Bencherif, Mohamed A.
    Alsulaiman, Mansour
    Muhammad, Ghulam
    Mekhtiche, Mohamed Amine
    Abdul, Wadood
    Alohali, Yousef A.
    Alrayes, Tareq S.
    Mathkour, Hassan
    Faisal, Mohammed
    Algabri, Mohammed
    Altaheri, Hamdi
    Alfakih, Taha
    Ghaleb, Hamid
    SENSORS, 2022, 22 (12)
  • [24] Attention-based 3D convolutional recurrent neural network model for multimodal emotion recognition
    Du, Yiming
    Li, Penghai
    Cheng, Longlong
    Zhang, Xuanwei
    Li, Mingji
    Li, Fengzhou
    FRONTIERS IN NEUROSCIENCE, 2024, 17
  • [25] Diagnosing Parkinson's disease with speech signal based on convolutional neural network
    Zhang, Tao
    Zhang, Yajuan
    Cao, Yuyang
    Li, Lin
    Hao, Lianwang
    INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY, 2020, 63 (04) : 348 - 353
  • [26] DEEP CONVOLUTIONAL NEURAL NETWORK FOR PARKINSON'S DISEASE BASED HANDWRITING SCREENING
    Shaban, Mohamed
    2020 IEEE 17TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING WORKSHOPS (IEEE ISBI WORKSHOPS 2020), 2020,
  • [27] 3D Convolutional Neural Networks for Diagnosis of Alzheimer's Disease via structural MRI
    Yagis, Ekin
    Citi, Luca
    Diciotti, Stefano
    Marzi, Chiara
    Atnafu, Selamawet Workalemahu
    De Herrera, Alba G. Seco
    2020 IEEE 33RD INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS(CBMS 2020), 2020, : 65 - 70
  • [28] EEG-Based Parkinson's Disease Recognition via Attention-Based Sparse Graph Convolutional Neural Network
    Chang, Hongli
    Liu, Bo
    Zong, Yuan
    Lu, Cheng
    Wang, Xuenan
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2023, 27 (11) : 5216 - 5224
  • [29] Instance importance-Aware graph convolutional network for 3D medical diagnosis
    Chen, Zhen
    Liu, Jie
    Zhu, Meilu
    Woo, Peter Y. M.
    Yuan, Yixuan
    MEDICAL IMAGE ANALYSIS, 2022, 78
  • [30] 3D face recognition using depth filtering and deep convolutional neural network
    Dorofeev, Konstantin
    Ruchay, Alexey
    Kober, Anastasia
    Kober, Vitaly
    APPLICATIONS OF DIGITAL IMAGE PROCESSING XLII, 2019, 11137