Pedicle screw channel automatic planning system and method based on CBCT spine image

Abstract

The invention relates to a CBCT spine image-based pedicle screw channel automatic planning system, which comprises a segmentation planning neural network module and a feature extraction module, wherein the segmentation planning neural network module calculates a feature point heat map of a pedicle screw channel and a CBCT spine image segmentation map according to a CBCT spine image, and calculates feature values of the pedicle screw channel according to the feature point heat map and the CBCT spine image segmentation map; the feature values comprise an entry point, a target point, a length and a diameter of the pedicle screw channel, and the feature point heat map comprises a midpoint heat map and an entry point heat map. The invention further provides a pedicle screw channel automatic planning method based on the CBCT spine image. According to the automatic planning scheme of the pedicle screw channel based on the CBCT spine image, planning of the pedicle screw channel can be automatically obtained without manual intervention, the speed is high, and the effect is good.

Description

technical field [0001] The present application relates to the technical field of orthopedics, and in particular to a system and method for automatic planning of pedicle screw channels based on CBCT spinal images. Background technique [0002] Currently, placing screws in the vertebral body is a critical step in many spinal surgeries. Surgeons usually insert guide wires into the pedicles of the lumbar and coccygeal vertebrae to define a channel, and then place screws in the widened channel. However, there are many important nerves and organs around the spine, and spine surgery has the characteristics of high precision and low error tolerance. During the operation, it is very important for the surgeon to understand the structure of the spine. Once the screw is improperly placed and penetrates the upper and lower lamina, the misplaced screw will cause serious neurovascular damage, and also lead to early failure of fixation or formation of pseudarthrosis. [0003] In recent ye...

AI Technical Summary

Problems solved by technology

These protruding edge structures will distort the standard point set of the channel template when it is converted back to the image space, resulting in angular deviation of the fitted channel plan

[0006] Therefore, the current planning of spinal surgery needs to be done manually by doctors, which is very dependent on the experience of doctors, and the level of intelligence is low.

At the same time, the quality of CBCT images is low. Doctors need to check whether the planned channel is feasible on the 2D slices of each layer. The workload is heavy and the automation level is low.

Images