Spinal disease diagnosis assistant based on MRI images using deep transfer learning methods

Abstract

IntroductionIn 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.MethodsThe 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 the PP-YOLOv2 model achieved a 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, a visualization of the intelligent spine assistant diagnostic software based on the PP-YOLOv2 model was created and the software was made available to the doctors in the spine and osteopathic surgery at Guilin People's Hospital.Results and discussionThis software automatically provides auxiliary diagnoses in 14.5 s on a standard computer, is much faster than doctors in diagnosing human spines, which typically take 10 min, and its accuracy of 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 diagnoses and misdiagnoses, and demonstrates the efficacy of the developed intelligent spinal auxiliary diagnosis software.

Deep learning assisted diagnosis system: improving the diagnostic accuracy of distal radius fractures

“…Compared to traditional machine learning methods, deep learning has higher performance. In the field of medical image analysis, trained deep learning algorithms can simulate clinical doctors’ judgments and accurately detect fractures ( 31 ). Deep learning algorithms for fracture detection offer significant advantages in clinical settings.…”

A Critical Analysis on Vertebra Identification and Cobb Angle Estimation Using Deep Learning for Scoliosis Detection

“…The model achieved an impressive mAP of 90.7% and an Intersection Over Union (IOU) of 91.3%. J. Xuan et al [29] introduced a set of DL techniques for diagnosing spinal diseases using MRI images. In this work, the authors used YOLOv3, YOLOv5, and PP-YOLOv2 for the training.…”

“…This architecture uses preexisting knowledge about the target shapes and applies certain non-square kernels. 9.2 % SMAP [29] Clinically experienced doctors used the LableImg tool to label the MRIs of 604 patients. Then, deep transfer learning models of YOLOv3, YOLOv5, and PP-YOLOv2 were created and trained on the Baidu PaddlePaddle framework to select an appropriate object detection algorithm.…”