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
  • [41] 68 landmarks are efficient for 3D face alignment: what about more?3D face alignment method applied to face recognition
    Marwa Jabberi
    Ali Wali
    Bidyut Baran Chaudhuri
    Adel M. Alimi
    Multimedia Tools and Applications, 2023, 82 : 41435 - 41469
  • [42] 68 landmarks are efficient for 3D face alignment: what about more? 3D face alignment method applied to face recognition
    Jabberi, Marwa
    Wali, Ali
    Chaudhuri, Bidyut Baran
    Alimi, Adel M.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (27) : 41435 - 41469
  • [43] LIVE-Net: Comprehensive 3D vessel extraction framework in CT angiography
    Sun, Qi
    Yang, Jinzhu
    Zhao, Sizhe
    Chen, Chen
    Hou, Yang
    Yuan, Yuliang
    Ma, Shuang
    Huang, Yan
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 159
  • [44] A 3D Occlusion Facial Recognition Network Based on a Multi-Feature Combination Threshold
    Zhu, Kaifeng
    He, Xin
    Lv, Zhuang
    Zhang, Xin
    Hao, Ruidong
    He, Xu
    Wang, Jun
    He, Jiawei
    Zhang, Lei
    Mu, Zhiya
    APPLIED SCIENCES-BASEL, 2023, 13 (10):
  • [45] Night Pedestrian Detection Using Thermal Image Feature Extraction Enhanced YOLOv3 (TIFEEY)
    Tian, Liang
    Chin, Chi-Te
    Cheng, Ching-Hsiang
    Huang, Rong-Peng
    2022 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, COMPUTER VISION AND MACHINE LEARNING (ICICML), 2022, : 80 - 89
  • [46] Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition
    Hui, Le
    Cheng, Mingmei
    Xie, Jin
    Yang, Jian
    Cheng, Ming-Ming
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 1258 - 1270
  • [47] A stroke image recognition model based on 3D residual network and attention mechanism
    Hou, Yingan
    Su, Junguang
    Liang, Jun
    Chen, Xiwen
    Liu, Qin
    Deng, Liang
    Liao, Jiyuan
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2022, 43 (04) : 5205 - 5214
  • [48] ETS-3D: An Efficient Two-Stage Framework for Stereo 3D Object Detection
    Ji, Chaofeng
    Liu, Guizhong
    Zhao, Dan
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2022, 88
  • [49] Badminton Shot Event Detection and Feature Calculation from 3D Rally Video
    Liu, Po-Yu
    Chiu, Hui-Chieh
    Chiu, Tzu-Chen
    Ik, Tsi-Ui
    PROCEEDINGS OF THE 52ND INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING WORKSHOPS PROCEEDINGS, ICPP-W 2023, 2023, : 22 - 29
  • [50] 3D detection transformer: Set prediction of objects using point clouds
    Thon, Tan
    Lim, Joanne Mun-Yee
    Jinn, Foo Ji
    Muniandy, Ramachandran
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2023, 236