AI in General Surgery and surgical specialties
AI in surgery is mostly about video and data. Systems that recognise surgical phases, instruments and anatomy in laparoscopic video are moving from research towards early use. Evidence for real-time decision support in the operating room is still thin, and most studies come from a few centres.
What AI does in General Surgery and surgical specialties
Platforms record and analyse operations so surgeons can review cases and compare technique.
Examples: Theator, Proximie, Touch Surgery
Robotic systems that record data and add software assistance. AI features vary by vendor.
Examples: Intuitive da Vinci
Models label the steps of an operation from video. Reported accuracy in a 2025 systematic review ran from 81% to 93.2%.
Examples: Cholec80-trained models, Theator
Overlays that mark structures such as the bile duct or vessels to support safe dissection.
Examples: Academic cholecystectomy models
Detects which instrument is in the field and where, for workflow and skill analysis.
Examples: Cholec80 tool-presence models
Machine learning on clinical data to estimate risk of complications after surgery.
Examples: Local hospital models
routine = in everyday use in many centres · early adoption = in use at some sites, evidence still building · research = studies only
Key ideas for this specialty
New to the basics? Start with the theory lessons.
Tools
Platform for recording, sharing and remotely assisting operations.
Regulatory status: Not listed
Robotic surgery systems and surgeon data tools.
Regulatory status: Not listed
Public laparoscopic video datasets from Strasbourg for phase and tool recognition research.
Regulatory status: Not listed
A listing here is not an endorsement. Ask any vendor for its CDSCO licence and class before clinical use.
Where to learn
Plain survey of what phase, instrument and anatomy models achieve.
Three courses on image diagnosis, prognosis and treatment models. Needs basic Python.
No-maths introduction to what AI can and cannot do. Good first step.
India's own ethics framework. Useful before you plan a thesis using AI.
Talks and symposium recordings on medical AI.
9-hour beginner course on AI in surgery. Taught in German.
Do it yourself
Request access to Cholec80 from the CAMMA page. Plot how long each of the seven phases lasts across the 80 videos. Compare with your own unit's cholecystectomies.
Open the dataset or tool →Install MedSAM from GitHub. Draw a box around an organ on a de-identified image and see how well it outlines it. Note where it fails.
Open the dataset or tool →Use public or properly de-identified data only, and get ethics approval before any project on your own patients.
Papers worth reading
- Artificial intelligence in the operating room: A systematic review of AI models for surgical phase, instruments and anatomical structure identification Acta Obstetricia et Gynecologica Scandinavica, 2025
- Surgical computer vision for intraoperative decision-support: a scoping review on performance metrics and readiness Artificial Intelligence Surgery, 2026
Societies and guidance
Runs surgeon-focused AI education; check its learning portal.
Recent updates
Lancet: full MASAI results show AI-supported mammography screening lowered interval cancers by 12%
In the Swedish randomised trial of over 100,000 women, AI-supported screening cut interval cancer diagnoses by 12% with similar false positives (1.5% vs 1.4%). It also found 16% fewer invasive and 27% fewer aggressive-subtype cancers between screens.
Source: ecancerLinks checked 3 October 2026. “Not listed” means we could not confirm the detail, not that it is absent. Educational material, not clinical advice.