Page 110 - Read Online

Page 56 Ambati et al. Art Int Surg. 2025;5:53-64 https://dx.doi.org/10.20517/ais.2024.45

Figure 1. (A) Example of preoperative planning software. Yellow boxes highlight automated spinopelvic parameters and Cobb angle
measurements performed by the software. Purple boxes indicate AI-recommended surgical plans and predicted postoperative
spinopelvic parameters. The green box demonstrates the predicted postoperative sagittal standing X-ray with the recommended
surgical plan; (B) Postoperative standing sagittal and coronal long-cassette radiographs. AI: Artificial intelligence.

[28]
[27]
[29]
musculature . The extent of osteoporosis and associated fractures can also be diagnosed by AI.
Building upon algorithms that segment spinal imaging, others can interpret degrees of neural element
compression and estimate parameters of spinal deformity. In particular, these applications are promising as
they are tedious, time-consuming, and subject to error and variability when performed by humans. For
example, deep learning can estimate the degree of cervical central and foraminal stenosis and can detect
[30]
lumbar spondylolisthesis and other important aspects of degeneration, such as the degree of disc
[31]
degeneration and central canal stenosis with high accuracy . For deformity parameter calculation, AI has
[32]
been applied to calculate coronal [33,34] , sagittal [35,36] , and combined coronal-sagittal parameters . By
[37]
incorporating AI into deformity parameter calculation, clinicians can more accurately and efficiently
perform both large deformity surgeries and use deformity principles in more limited surgery to ensure
patients achieve the best anatomic and physiologic outcomes. These applications represent an ideal area for
the strengths of AI to address current challenges in preoperative spine surgical evaluation, and indeed, these
technologies have been among the first to reach clinical practice [Table 1].

Intraoperative tools
During surgery, a number of promising AI technologies may help clinicians optimize operative technique
and efficiency. Compared to tools designed for pre- or postoperative settings, bringing AI into the OR
requires algorithms that can deploy in real time and run on equipment that can interface with the
patient, surgeon, and available intraoperative data streams.