Explainable Feature Extraction and Prediction Framework for 3D Image Recognition Applied to Pneumonia Detection

被引:5
|
作者
Pintelas, Emmanuel [1 ]
Livieris, Ioannis E. [1 ]
Pintelas, Panagiotis [1 ]
机构
[1] Univ Patras, Dept Math, GR 26500 Patras, Greece
关键词
medical and health applications; pneumonia detection; explainable machine learning; deep learning; 3D convolutional neural networks; 3D image classification;
D O I
10.3390/electronics12122663
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Explainable machine learning is an emerging new domain fundamental for trustworthy real-world applications. A lack of trust and understanding are the main drawbacks of deep learning models when applied to real-world decision systems and prediction tasks. Such models are considered as black boxes because they are unable to explain the reasons for their predictions in human terms; thus, they cannot be universally trusted. In critical real-world applications, such as in medical, legal, and financial ones, an explanation of machine learning (ML) model decisions is considered crucially significant and mandatory in order to acquire trust and avoid fatal ML bugs, which could disturb human safety, rights, and health. Nevertheless, explainable models are more than often less accurate; thus, it is essential to invent new methodologies for creating interpretable predictors that are almost as accurate as black-box ones. In this work, we propose a novel explainable feature extraction and prediction framework applied to 3D image recognition. In particular, we propose a new set of explainable features based on mathematical and geometric concepts, such as lines, vertices, contours, and the area size of objects. These features are calculated based on the extracted contours of every 3D input image slice. In order to validate the efficiency of the proposed approach, we apply it to a critical real-world application: pneumonia detection based on CT 3D images. In our experimental results, the proposed white-box prediction framework manages to achieve a performance similar to or marginally better than state-of-the-art 3D-CNN black-box models. Considering the fact that the proposed approach is explainable, such a performance is particularly significant.
引用
收藏
页数:15
相关论文
共 50 条
  • [21] Feature extraction method of 3D art creation based on deep learning
    Chen, Kaiqing
    Huang, Xiaoqin
    SOFT COMPUTING, 2020, 24 (11) : 8149 - 8161
  • [22] FeatureNet: Machining feature recognition based on 3D Convolution Neural Network
    Zhang, Zhibo
    Jaiswal, Prakhar
    Rai, Rahul
    COMPUTER-AIDED DESIGN, 2018, 101 : 12 - 22
  • [23] 3D model recognition and segmentation based on multi-feature fusion
    Dang J.
    Yang J.
    Yang, Jun (yangj@mail.lzjtu.cn), 1600, Science Press (47): : 149 - 157
  • [24] Local feature guidance framework for robust 3D point cloud registration
    Liu, Zikang
    He, Kai
    Zhang, Dazhuang
    Wang, Lei
    VISUAL COMPUTER, 2023, 39 (12) : 6459 - 6472
  • [25] Local feature guidance framework for robust 3D point cloud registration
    Zikang Liu
    Kai He
    Dazhuang Zhang
    Lei Wang
    The Visual Computer, 2023, 39 : 6459 - 6472
  • [26] FCNet: Stereo 3D Object Detection with Feature Correlation Networks
    Wu, Yingyu
    Liu, Ziyan
    Chen, Yunlei
    Zheng, Xuhui
    Zhang, Qian
    Yang, Mo
    Tang, Guangming
    ENTROPY, 2022, 24 (08)
  • [27] Stereo 3D Object Detection Using a Feature Attention Module
    Zhao, Kexin
    Jiang, Rui
    He, Jun
    ALGORITHMS, 2023, 16 (12)
  • [28] Comparison of 2D and 3D convolutional neural networks in hyperspectral image analysis of fruits applied to orange bruise detection
    Pourdarbani, Raziyeh
    Sabzi, Sajad
    Zohrabi, Reihaneh
    Garcia-Mateos, Gines
    Fernandez-Beltran, Ruben
    Molina-Martinez, Jose Miguel
    Rohban, Mohammad H.
    JOURNAL OF FOOD SCIENCE, 2023, 88 (12) : 5149 - 5163
  • [29] Multiscale feature fusion network for 3D head MRI image registration
    Yang, Shixin
    Li, Haojiang
    Chen, Shuchao
    Huang, Wenjie
    Liu, Demin
    Ruan, Guangying
    Huang, Qiangyang
    Gong, Qiong
    Liu, Lizhi
    Chen, Hongbo
    MEDICAL PHYSICS, 2023, 50 (09) : 5609 - 5620
  • [30] Comparing 2D and 3D Feature Extraction Methods for Lung Adenocarcinoma Prediction Using CT Scans: A Cross-Cohort Study
    Gouveia, Margarida
    Mendes, Tania
    Rodrigues, Eduardo M.
    Oliveira, Helder P.
    Pereira, Tania
    APPLIED SCIENCES-BASEL, 2025, 15 (03):