He, B., Guo, Y., Zhu, Y., Tong, L., Kong, B., Wang, K., Sun, C., Li, H., Huang, F., Wu, L., Wang, M., Meng, F., Dou, L., Sun, K., Tong, T., Liu, Z., Wei, Z., Mu, W., Wang, S., ... Tian, J. (2024). From Signal to Knowledge: The Diagnostic Value of Raw Data in the Artificial Intelligence Prediction of Human Data for the First Time. Engineering, 34, 60-69. https://doi.org/10.1016/j.eng.2023.02.013
@article{b7fd80b1ebaf41c491ef59fb73b0b4f5,
title = "From Signal to Knowledge: The Diagnostic Value of Raw Data in the Artificial Intelligence Prediction of Human Data for the First Time",
abstract = "Encouraging and astonishing developments have recently been achieved in image-based diagnostic technology. Modern medical care and imaging technology are becoming increasingly inseparable. However, the current diagnosis pattern of signal to image to knowledge inevitably leads to information distortion and noise introduction in the procedure of image reconstruction (from signal to image). Artificial intelligence (AI) technologies that can mine knowledge from vast amounts of data offer opportunities to disrupt established workflows. In this prospective study, for the first time, we develop an AI-based signal-to-knowledge diagnostic scheme for lung nodule classification directly from the computed tomography (CT) raw data (the signal). We find that the raw data achieves almost comparable performance with CT, indicating that it is possible to diagnose diseases without reconstructing images. Moreover, the incorporation of raw data through three common convolutional network structures greatly improves the performance of the CT models in all cohorts (with a gain ranging from 0.01 to 0.12), demonstrating that raw data contains diagnostic information that CT does not possess. Our results break new ground and demonstrate the potential for direct signal-to-knowledge domain analysis.",
keywords = "Computed tomography, Deep learning, Diagnosis, Lung cancer, Raw data",
author = "Bingxi He and Yu Guo and Yongbei Zhu and Lixia Tong and Boyu Kong and Kun Wang and Caixia Sun and Hailin Li and Feng Huang and Liwei Wu and Meng Wang and Fanyang Meng and Le Dou and Kai Sun and Tong Tong and Zhenyu Liu and Ziqi Wei and Wei Mu and Shuo Wang and Zhenchao Tang and Shuaitong Zhang and Jingwei Wei and Lizhi Shao and Mengjie Fang and Juntao Li and Shouping Zhu and Lili Zhou and Di Dong and Huimao Zhang and Jie Tian",
note = "Publisher Copyright: {\textcopyright} 2023 THE AUTHORS",
year = "2024",
month = mar,
doi = "10.1016/j.eng.2023.02.013",
language = "English",
volume = "34",
pages = "60--69",
journal = "Engineering",
issn = "2095-8099",
publisher = "Elsevier Ltd.",
}
He, B, Guo, Y, Zhu, Y, Tong, L, Kong, B, Wang, K, Sun, C, Li, H, Huang, F, Wu, L, Wang, M, Meng, F, Dou, L, Sun, K, Tong, T, Liu, Z, Wei, Z, Mu, W, Wang, S, Tang, Z, Zhang, S, Wei, J, Shao, L, Fang, M, Li, J, Zhu, S, Zhou, L, Dong, D, Zhang, H & Tian, J 2024, 'From Signal to Knowledge: The Diagnostic Value of Raw Data in the Artificial Intelligence Prediction of Human Data for the First Time', Engineering, vol. 34, pp. 60-69. https://doi.org/10.1016/j.eng.2023.02.013
TY - JOUR
T1 - From Signal to Knowledge
T2 - The Diagnostic Value of Raw Data in the Artificial Intelligence Prediction of Human Data for the First Time
AU - He, Bingxi
AU - Guo, Yu
AU - Zhu, Yongbei
AU - Tong, Lixia
AU - Kong, Boyu
AU - Wang, Kun
AU - Sun, Caixia
AU - Li, Hailin
AU - Huang, Feng
AU - Wu, Liwei
AU - Wang, Meng
AU - Meng, Fanyang
AU - Dou, Le
AU - Sun, Kai
AU - Tong, Tong
AU - Liu, Zhenyu
AU - Wei, Ziqi
AU - Mu, Wei
AU - Wang, Shuo
AU - Tang, Zhenchao
AU - Zhang, Shuaitong
AU - Wei, Jingwei
AU - Shao, Lizhi
AU - Fang, Mengjie
AU - Li, Juntao
AU - Zhu, Shouping
AU - Zhou, Lili
AU - Dong, Di
AU - Zhang, Huimao
AU - Tian, Jie
N1 - Publisher Copyright:
© 2023 THE AUTHORS
PY - 2024/3
Y1 - 2024/3
N2 - Encouraging and astonishing developments have recently been achieved in image-based diagnostic technology. Modern medical care and imaging technology are becoming increasingly inseparable. However, the current diagnosis pattern of signal to image to knowledge inevitably leads to information distortion and noise introduction in the procedure of image reconstruction (from signal to image). Artificial intelligence (AI) technologies that can mine knowledge from vast amounts of data offer opportunities to disrupt established workflows. In this prospective study, for the first time, we develop an AI-based signal-to-knowledge diagnostic scheme for lung nodule classification directly from the computed tomography (CT) raw data (the signal). We find that the raw data achieves almost comparable performance with CT, indicating that it is possible to diagnose diseases without reconstructing images. Moreover, the incorporation of raw data through three common convolutional network structures greatly improves the performance of the CT models in all cohorts (with a gain ranging from 0.01 to 0.12), demonstrating that raw data contains diagnostic information that CT does not possess. Our results break new ground and demonstrate the potential for direct signal-to-knowledge domain analysis.
AB - Encouraging and astonishing developments have recently been achieved in image-based diagnostic technology. Modern medical care and imaging technology are becoming increasingly inseparable. However, the current diagnosis pattern of signal to image to knowledge inevitably leads to information distortion and noise introduction in the procedure of image reconstruction (from signal to image). Artificial intelligence (AI) technologies that can mine knowledge from vast amounts of data offer opportunities to disrupt established workflows. In this prospective study, for the first time, we develop an AI-based signal-to-knowledge diagnostic scheme for lung nodule classification directly from the computed tomography (CT) raw data (the signal). We find that the raw data achieves almost comparable performance with CT, indicating that it is possible to diagnose diseases without reconstructing images. Moreover, the incorporation of raw data through three common convolutional network structures greatly improves the performance of the CT models in all cohorts (with a gain ranging from 0.01 to 0.12), demonstrating that raw data contains diagnostic information that CT does not possess. Our results break new ground and demonstrate the potential for direct signal-to-knowledge domain analysis.
KW - Computed tomography
KW - Deep learning
KW - Diagnosis
KW - Lung cancer
KW - Raw data
UR - http://www.scopus.com/inward/record.url?scp=85175494757&partnerID=8YFLogxK
U2 - 10.1016/j.eng.2023.02.013
DO - 10.1016/j.eng.2023.02.013
M3 - Article
AN - SCOPUS:85175494757
SN - 2095-8099
VL - 34
SP - 60
EP - 69
JO - Engineering
JF - Engineering
ER -
He B, Guo Y, Zhu Y, Tong L, Kong B, Wang K et al. From Signal to Knowledge: The Diagnostic Value of Raw Data in the Artificial Intelligence Prediction of Human Data for the First Time. Engineering. 2024 Mar;34:60-69. doi: 10.1016/j.eng.2023.02.013
