Dataset Information

Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation.

ABSTRACT: Surgical phase recognition (SPR) is a crucial element in the digital transformation of the modern operating theater. While SPR based on video sources is well-established, incorporation of interventional X-ray sequences has not yet been explored. This paper presents Pelphix, a first approach to SPR for X-ray-guided percutaneous pelvic fracture fixation, which models the procedure at four levels of granularity - corridor, activity, view, and frame value - simulating the pelvic fracture fixation workflow as a Markov process to provide fully annotated training data. Using added supervision from detection of bony corridors, tools, and anatomy, we learn image representations that are fed into a transformer model to regress surgical phases at the four granularity levels. Our approach demonstrates the feasibility of X-ray-based SPR, achieving an average accuracy of 99.2% on simulated sequences and 71.7% in cadaver across all granularity levels, with up to 84% accuracy for the target corridor in real data. This work constitutes the first step toward SPR for the X-ray domain, establishing an approach to categorizing phases in X-ray-guided surgery, simulating realistic image sequences to enable machine learning model development, and demonstrating that this approach is feasible for the analysis of real procedures. As X-ray-based SPR continues to mature, it will benefit procedures in orthopedic surgery, angiography, and interventional radiology by equipping intelligent surgical systems with situational awareness in the operating room.

SUBMITTER: Killeen BD

PROVIDER: S-EPMC11016332 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation.

Killeen Benjamin D BD Zhang Han H Mangulabnan Jan J Armand Mehran M Taylor Russell H RH Osgood Greg G Unberath Mathias M

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention 20231001

Surgical phase recognition (SPR) is a crucial element in the digital transformation of the modern operating theater. While SPR based on video sources is well-established, incorporation of interventional X-ray sequences has not yet been explored. This paper presents Pelphix, a first approach to SPR for X-ray-guided percutaneous pelvic fracture fixation, which models the procedure at four levels of granularity - corridor, activity, view, and frame value - simulating the pelvic fracture fixation wo ...[more]

PMID: 38617200

Similar Datasets

Project description:BackgroundThe management of hemodynamically unstable pelvic ring injuries necessitates surgical intervention, often involving procedures such as external fixation and percutaneous screw placement. Given the infrequent performance of these procedures, regular training is imperative to ensure readiness for emergencies. Our pre- post simulation study aimed to adapt and validate a realistic simulation model for stabilizing unstable pelvic ring injuries, facilitating participants' knowledge retention and procedural confidence enhancement.MethodsA standardized simulator of an unstable pelvic ring utilizing synthetic pelvic bones featuring complete disruption of the symphysis and sacroiliac joint was developed. Trauma surgeons of a level one academic hospital were invited to perform external fixation and emergency sacroiliac screw application under C-arm guidance. Prior to and following the simulation session, participants completed a subjective questionnaire assessing their confidence in emergency interventions on a 10-point Likert scale (10-LS). Objective parameters, such as intraoperative imaging quality, reduction accuracy, and the positioning of screws, wires, and external fixators, were also evaluated as secondary outcome measures.ResultsFifteen trauma surgeons (10 residents, 5 consultants) participated in the simulation over the course of one day. The mean total operation time was 20.34 ± 6.06 min, without significant differences between consultants and residents (p = 0.604). The confidence for emergency SI-Screw placement increased significantly after the simulator (10-LS: Before = 3.8 ± 3.08 vs. After = 5.67 ± 2.35; p = 0.002) as well as after external fixation (10-LS: Before = 3.93 ± 2.79 vs. After = 6.07 ± 2.52; p = 0.002). In addition, confidence in (intraoperative) pelvic imaging increased significantly (10-LS: Before = 4.60 ± 3.0 vs. After = 6.53 ± 2.39; p = 0.011). Overall, the model was rated as a realistic simulation of clinical practice (10-LS = 7.87 ± 1.13).ConclusionsOur unstable pelvis fracture model is a tool to practice emergency interventions such as external fixation and percutaneous techniques. Participants benefitted from this in terms of technical instrumentation as well as intraoperative imaging. Further studies are required to validate the objective benefits and improvements that participants undergo through frequent training.

Dataset Information

Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation.

Publications

Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets