skblv/yolov12m-surgvu-instruments

YOLOv12-m — SurgVU instrument recognition

Supervised YOLOv12-m detector trained for the 17 SurgVU instruments, then scored as multi-label presence.

This is the “YOLOv12-m” row on the Instruments tab of the SDSC × Chicago Booth surgical video understanding leaderboard.

Prompt example

This closed-set example mirrors the leaderboard format, not a text-input API for this checkpoint.

[surgical frame]

Which instruments are visible in this robotic surgical frame?
Select every matching label.

- bipolar dissector
- bipolar forceps
- cadiere forceps
- clip applier
- force bipolar
- grasping retractor
- monopolar curved scissors
- needle driver
- permanent cautery hook/spatula
- potts scissors
- prograsp forceps
- stapler
- suction irrigator
- synchroseal
- tenaculum forceps
- tip-up fenestrated grasper
- vessel sealer

Evaluation

Full SurgVU validation split (95% bootstrap CI):

Metric	Value
Exact match	51.75% (50.97–52.51)
Micro-averaged F1	75.34% (74.87–75.82)

License note

Derived from Ultralytics YOLO weights; distributed under AGPL-3.0.

References

• Skobelev, K., Fithian, E., Baranovski, Y., et al. A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling. arXiv:2603.27341, 2026.
• Dataset: Zia, A., Berniker, M., Nespolo, R., et al. Surgical Visual Understanding (SurgVU) Dataset. arXiv:2501.09209, 2025.

Limitations

Research baseline only. Not a medical device.