Table 5 Comparison of precision for orthopedic surgeons with and without CNN model assistance.

From: Automated fracture screening using an object detection algorithm on whole-body trauma computed tomography

Precision (%)

Without CNN model assistance

With CNN model assistance

Pelvic fracture

 Orthopedic surgeon 1

0.957

0.976

 Orthopedic surgeon 2

0.974

0.976

 Orthopedic surgeon 3

0.961

0.947

Rib fracture

 Orthopedic surgeon 1

0.962

0.942

 Orthopedic surgeon 2

0.949

0.885

 Orthopedic surgeon 3

0.935

0.984

Spine fracture

 Orthopedic surgeon 1

0.977

0.940

 Orthopedic surgeon 2

0.952

0.956

 Orthopedic surgeon 3

0.961

0.950

Mean

 Orthopedic surgeon 1

0.965

0.955

 Orthopedic surgeon 2

0.961

0.948

 Orthopedic surgeon 3

0.955

0.956

  1. Orthopedic surgeon 1 and 2 had 3 years of experience. Orthopedic surgeon 3 had 8 years of experience. CNN, convolutional neural network.
Back to article page