Research Group CAMMA's repositories
MVOR
Multi-View Operating Room (MVOR) dataset consists of synchronized multi-view frames recorded by three RGB-D cameras in a hybrid OR during real clinical interventions. We provide camera calibration parameters, color and depth frames, human bounding boxes, and 2D/3D pose annotations. The MVOR was released in the MICCAI-LABELS 2018 workshop.
SelfSupSurg
Official repository for "Dissecting Self-Supervised Learning Methods for Surgical Computer Vision"
Endoscapes
Official Repository for the Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment
TF-Cholec80
Library packaging the Cholec80 dataset for easy handling with Tensorflow.
rendezvous
A transformer-inspired neural network for surgical action triplet recognition from laparoscopic videos.
AI4surgery
Short tutorial supplementing the Neural Networks and Deep Learning chapter from Artificial Intelligence in Surgery: An AI Primer for Surgical Practice designed to offer hands-on experience with artificial neural networks to surgeons with little to no coding experience.
SurgLatentGraph
This repository contains the code associated with our 2023 TMI paper "Latent Graph Representations for Critical View of Safety Assessment" and our MICCAI 2023 paper "Encoding Surgical Videos as Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning".
ivtmetrics
A Python evaluation metrics package for surgical action triplet recognition
Surgical-Phase-Recognition
Demo for surgical phase recognition on videos of laparoscopic cholecystectomy using a CNN-biLSTM-CRF model presented in "Learning from a tiny dataset of manual annotations: a teacher/student approach for surgical phase recognition" (IPCAI 2019)
ORPose-Color
Inference demo for the MICCAI-2020 paper "Self-supervision on Unlabelled OR Data for Multi-person 2D/3D Human Pose Estimation"
SelfPose3d
Official code for "SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation"
cholectriplet2022
CholecTriplet 2022 challenge on surgical action triplet detection
rendezvous-in-time
rendezvous-in-time
out-of-body-detector
Application for classifying out-of-body images in endoscopic videos
HPE-AdaptOR
Code for Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the OR
cvs_annotator
Application for reviewing and annotating frames with critical view of safety (CVS) criteria and other relevant information