AUTHOR=Xuan Junbo , Ke Baoyi , Ma Wenyu , Liang Yinghao , Hu Wei TITLE=Spinal disease diagnosis assistant based on MRI images using deep transfer learning methods JOURNAL=Frontiers in Public Health VOLUME=Volume 11 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2023.1044525 DOI=10.3389/fpubh.2023.1044525 ISSN=2296-2565 ABSTRACT=In light of the potential problems of missed diagnosis and misdiagnosis in the diagnosis of spinal diseases caused by experience differences and fatigue, this paper investigates the use of artificial intelligence technology for auxiliary diagnosis of spinal diseases.The LableImg tool was used to label the MRIs of 604 patients by clinically experienced doctors. Then, in order to select an appropriate object detection algorithm,deep transfer learning models of YOLOv3, YOLOv5, and PP-YOLOv2 were created and trained on the Baidu PaddlePaddle framework. The experimental results showed that PP-YOLOv2 model achieved 90.08% overall accuracy in the diagnosis of Normal,IVD bulges and Spondylolisthesis,which were 27.5% and 3.9% higher than YOLOv3 and YOLOv5,respectively.Finally,visualization of intelligence spine assistant diagnostic software based on the PP-YOLOv2 model were created and the software are made it available to the doctors of spine and osteopathic surgery at Guilin People's Hospital.This software automatically provides auxiliary diagnoses in 14.5 seconds on a standard computer,much faster than doctors diagnose human spines,which typically take 10 minutes,and its accuracy about 98% can be compared to that of experienced doctors in the comparison of various diagnostic methods.It significantly improves doctors' working efficiency,reduces the phenomenon of missed diagnosis and misdiagnosis,and demonstrates the efficacy of the developed intelligent spinal auxiliary diagnosis software.