Breaking boundaries in radiology: redefining AI diagnostics via raw data ahead of reconstruction.

Journal: Physics in medicine and biology
Published Date: Mar 18, 2024

Abstract

In the realm of utilizing artificial intelligence (AI) for medical image analysis, the paradigm of 'signal-image-knowledge' has remained unchanged. However, the process of 'signal to image' inevitably introduces information distortion, ultimately leading to irrecoverable biases in the 'image to knowledge' process. Our goal is to skip reconstruction and build a diagnostic model directly from the raw data (signal).. This study focuses on computed tomography (CT) and its raw data (sinogram) as the research subjects. We simulate the real-world process of 'human-signal-image' using the workflow 'CT-simulated data- reconstructed CT,' and we develop a novel AI predictive model directly targeting raw data (RCTM). This model comprises orientation, spatial, and global analysis modules, embodying the fusion of local to global information extraction from raw data. We selected 1994 patients with retrospective cases of solid lung nodules and modeled different types of data.. We employed predefined radiomic features to assess the diagnostic feature differences caused by reconstruction. The results indicated that approximately 14% of the features had Spearman correlation coefficients below 0.8. These findings suggest that despite the increasing maturity of CT reconstruction algorithms, they still introduce perturbations to diagnostic features. Moreover, our proposed RCTM achieved an area under the curve (AUC) of 0.863 in the diagnosis task, showcasing a comprehensive superiority over models constructed from secondary reconstructed CTs (0.840, 0.822, and 0.825). Additionally, the performance of RCTM closely resembled that of models constructed from original CT scans (0.868, 0.878, and 0.866).. The diagnostic and therapeutic approach directly based on CT raw data can enhance the precision of AI models and the concept of 'signal-to-image' can be extended to other types of imaging. AI diagnostic models tailored to raw data offer the potential to disrupt the traditional paradigm of 'signal-image-knowledge', opening up new avenues for more accurate medical diagnostics.

Authors

  • Bingxi He
    CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Institute of Automation, Beijing, 100190, China; University of Chinese Academy of Sciences, Beijing, 100190, China.
  • Caixia Sun
    CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China; Beijing Advanced Innovation Centre for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Beijing, China; Key Laboratory of Big Data-Based Precision Medicine, Ministry of Industry and Information Technology, Beihang University, Beijing, China.
  • Hailin Li
    School of Bioscience and Bioengineering, South China University of Technology, Guangzhou, China.
  • Yongbo Wang
    School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, People's Republic of China. Guangzhou Key Laboratory of Medical Radiation Imaging and Detection Technology, Southern Medical University, Guangdong 510515, People's Republic of China. These authors contributed equally.
  • Yunlang She
    Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China.
  • Mengmeng Zhao
    MOE Key Laboratory of Analysis and Detection for Food Safety, Fujian Provincial Key Laboratory of Analysis and Detection Technology for Food Safety, College of Chemistry, Fuzhou University, Fuzhou, Fujian 350108, China.
  • Mengjie Fang
    CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China; University of Chinese Academy of Sciences, Beijing, 100080, China.
  • Yongbei Zhu
  • Kun Wang
    CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
  • Zhenyu Liu
    School of Electronic Information, Hangzhou Dianzi University, Hangzhou 310018, China.
  • Ziqi Wei
    CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, People's Republic of China.
  • Wei Mu
    Key Laboratory of Pesticide Toxicology&Application Technique, College of Plant Protection, Shandong Agricultural University, Tai'an 271018, China.
  • Shuo Wang
    College of Tea & Food Science, Anhui Agricultural University, Hefei, China.
  • Zhenchao Tang
  • Jingwei Wei
    Animal Reproduction Institute, State Key Laboratory for Conservation and Utilization of Subtropical Agro-Bioresources, Guangxi University, Nanning, China.
  • Lizhi Shao
    CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Computer Science and Engineering, Southeast University, Nanjing, China.
  • Lixia Tong
    Neusoft Medical Systems Co. Ltd, Shenyang, People's Republic of China.
  • Feng Huang
    Beijing Hospital of TCM, Capital Medical University, Beijing 100010, China; Institution of Acupuncture and Moxibustion, China Academy of Chinese Medical Sciences, Beijing 100700.
  • Mingze Tang
    School of Mechanical and Materials Engineering, North China University of Technology, Beijing, People's Republic of China.
  • Yu Guo
    Animal Disease Control Center of Inner Mongolia, Hohhot, China.
  • Huimao Zhang
    Department of Radiology, The First Hospital of Jilin University, No.1, Xinmin Street, Changchun 130021, China (Y.W., M.L., Z.M., J.W., K.H., Q.Y., L.Z., L.M., H.Z.). Electronic address: huimao@jlu.edu.cn.
  • Di Dong
    The Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
  • Chang Chen
    Biomass Energy and Environmental Engineering Research Center, College of Chemical Engineering, Beijing University of Chemical Technology, 505 Zonghe Building A, 15 North 3rd Ring East Road, Beijing, 100029, China. chenchang@mail.buct.edu.cn.
  • Jianhua Ma
  • Jie Tian
    CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.

Keywords

External Resources

Popular Topics
Recent Journals