Related Experiment Video
Updated: Jan 11, 2026
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Characteristic changes in the fusion brain network are associated with bone metastasis pain in patients with lung
Jiahui Zheng1, Lin Tang1, Xiaoyu Zhou2
1Department of Radiology, Chongqing University Cancer Hospital, China.
Background:
Network neuroscience has revealed characteristic alterations associated with cancer pain in structural and functional brain networks. However, the mechanisms by which structural and functional networks interact and whether the interaction is related to cancer pain remain unclear.
Methods:
First, fusion brain networks were constructed based on structural and functional networks using an optimized self-attention mechanism algorithm. Next, the connectivity strength was analyzed at both regional and modular levels using network-based statistic (NBS) analysis and network connectivity analysis, respectively. Finally, relationships between connectivity strength and neuropsychological scales scores were evaluated.
Results:
NBS analysis demonstrated increased connectivities in both BMP+ and BMP- patients, spanning a wide range of brain regions. Additionally, four decreased connectivities were observed in BMP+ patients, involving the default mode network, limbic system, executive control network, and salience network. Network connectivity analysis demonstrated increased connectivity strengths in the feeder network in BMP- patients. Moreover, significant positive correlations were found between altered connectivity strength and neuropsychological scales scores.
Conclusions:
Characteristic changes in the fusion brain network were observed at both regional and modular levels in BMP+ patients, particularly in brain regions related to the descending modulation of cancer pain. Thus, abnormal brain fusion may contribute to cancer pain progression.
