Contrast-enhanced magnetic resonance image segmentation based on improved U-Net and Inception-ResNet in the diagnosis of spinal metastases

Hai Wang; Shaohua Xu; Kai-Bin Fang; Zhang-Sheng Dai; Guo-Zhen Wei; Lu-Feng Chen

doi:10.1016/j.jbo.2023.100498

Contrast-enhanced magnetic resonance image segmentation based on improved U-Net and Inception-ResNet in the diagnosis of spinal metastases

J Bone Oncol. 2023 Aug 17:42:100498. doi: 10.1016/j.jbo.2023.100498. eCollection 2023 Oct.

Authors

Hai Wang^{1

2}, Shaohua Xu³, Kai-Bin Fang⁴, Zhang-Sheng Dai⁴, Guo-Zhen Wei^{1

2}, Lu-Feng Chen⁵

Affiliations

¹ Department of Orthopedics, The First Affiliated Hospital, Fujian Medical University, Fuzhou 350005, China.
² Department of Orthopedics, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou 350212,China.
³ Department of Hepatobiliary and Pancreatic Surgery, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou 350014, China.
⁴ Department of Orthopedics, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, China.
⁵ Department of Thoracic and Cardiovascular Surgery, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian 362000, China.

Abstract

Objective: The objective of this study was to investigate the use of contrast-enhanced magnetic resonance imaging (CE-MRI) combined with radiomics and deep learning technology for the identification of spinal metastases and primary malignant spinal bone tumor.

Methods: The region growing algorithm was utilized to segment the lesions, and two parameters were defined based on the region of interest (ROI). Deep learning algorithms were employed: improved U-Net, which utilized CE-MRI parameter maps as input, and used 10 layers of CE images as input. Inception-ResNet model was used to extract relevant features for disease identification and construct a diagnosis classifier.

Results: The diagnostic accuracy of radiomics was 0.74, while the average diagnostic accuracy of improved U-Net was 0.98, respectively. the PA of our model is as high as 98.001%. The findings indicate that CE-MRI based radiomics and deep learning have the potential to assist in the differential diagnosis of spinal metastases and primary malignant spinal bone tumor.

Conclusion: CE-MRI combined with radiomics and deep learning technology can potentially assist in the differential diagnosis of spinal metastases and primary malignant spinal bone tumor, providing a promising approach for clinical diagnosis.

Keywords: CE-MRI; Deep learning; Inception-ResNet; Radiomics; Spinal tumor; improved U-Net.