Skip to content

Development of AI-powered Minimally Invasive Interventional Surgery for Pain Management

Development of AI-powered Minimally Invasive Interventional Surgery for Pain Management

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600119172
Enrollment
Unknown
Registered
2026-02-24
Start date
2026-02-24
Completion date
Unknown
Last updated
2026-03-02

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Degenerative spinal diseases such as herniated discs, spinal stenosis, or neuropathic pain

Interventions

Group of spinal cord stimulation surgery:None
Group of endoscopic spinal surgery:None

Sponsors

Shenzhen Nanshan People's Hospital
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1.Patients requiring endoscopic spinal surgery (ESS) or spinal cord stimulation (SCS). First, patients must be at least 18 years old and have signed informed consent. Second, they must be clinically diagnosed with degenerative spinal diseases such as herniated discs, spinal stenosis, or neuropathic pain, and their pain symptoms must have persisted for more than 3 months without response to standardized conservative treatment. In terms of imaging, patients are required to have preoperative thin-slice spinal MRI (slice thickness no greater than 1 mm) and concurrent CT data (interval within one week) to ensure the data quality of the multimodal fusion model. Furthermore, patients must have no prior history of spinal surgery in the target surgical segment to avoid interference from anatomical variations in the model segmentation. The study cohort was constructed using a combination of historical surgical data and prospective collection; 2.for example, 50 patients were included for each of ESS and SCS, all of whom had complete postoperative follow-up data and significant symptom improvement.

Exclusion criteria

Exclusion criteria: Cases of spinal fractures, spinal or intramedullary tumors were explicitly excluded, as they may disrupt the normal anatomical morphology of bones or nerves. Additionally, cases with severe imaging artifacts due to the presence of metal implants in or near the spine, or poor image quality caused by patient movement during scanning, were also excluded. Furthermore, cases with concomitant spinal skeletal developmental abnormalities or other congenital malformations were also excluded to ensure anatomical consistency for model training. For endoscopic video data, if instruments or anatomical landmarks could not be clearly identified in the intraoperative video due to bleeding, tissue obstruction, or other reasons, the data was considered invalid. During image registration, if CT and MRI could not achieve a satisfactory match through manual evaluation (e.g., significant misalignment of key points in the thoracic spine), the data was also not considered valid pairing samples.

Design outcomes

Primary

MeasureTime frame
Bland-Altman Consistency Bounds;Decompression range match degree;Mean absolute error (MAE) of surgical parameter prediction;visual analogue scale;Dice coefficient;Mean Hausdorf distance;

Secondary

MeasureTime frame
Planning time;Intraoperative fluoroscopy times;

Countries

China

Contacts

Public ContactXiang Liao

Shenzhen Nanshan People's Hospital

digitalxiang@163.com+86 137 2559 5056

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Mar 14, 2026