Augmented Reality in Surgery
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorI.R.C.C.S Ospedale Galeazzi-Sant'Ambrogio
About this trial
The goal of this observational study is to learn whether an artificial-intelligence software can reliably recognise the anatomical landmarks used to guide femoral bone tunnel placement on the arthroscopic monitor image during anterior cruciate ligament (ACL) reconstruction in adults. The main questions it aims to answer are:
Can the software automatically tell when the arthroscopic image is clean enough to allow identification of these landmarks? Can the software accurately outline the key bony and cartilaginous landmarks on the femur that guide correct tunnel positioning?
Participants will undergo their clinically indicated ACL reconstruction without modifications: short video sequences of the operative field will be recorded from the arthroscopic camera already used in routine practice, and used to train and validate the algorithms. No additional devices, manoeuvres or operative time are required.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Age 18 years or older
Scheduled for primary arthroscopic anterior cruciate ligament reconstruction at IRCCS Galeazzi-Sant'Ambrogio
Signed written informed consent
Disqualifiers
Revision anterior cruciate ligament reconstruction
Arthroscopic video quality judged inadequate by the investigator (artefacts, insufficient illumination, uninterpretable images)
Failure to sign informed consent, or withdrawal of consent
Trial population
Patients referred to and treated at the Knee Surgery and Sports Traumatology Unit of IRCCS Galeazzi-Sant'Ambrogio in Milan, Italy. The institution is a tertiary orthopaedic referral hospital and a recognised Italian Scientific Hospital for Research and Care (Istituto di Ricovero e Cura a Carattere Scientifico), dedicated to the musculoskeletal system and performing a very high yearly volume of orthopaedic procedures. Within the institution, the Knee Surgery and Sports Traumatology Unit is a homogeneous surgical team with a substantial annual caseload of arthroscopic anterior cruciate ligament reconstructions. Enrolment is single-centre, prospective and consecutive across the study period.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
Primary arthroscopic anterior cruciate ligament reconstruction
Procedure/SurgeryArthroscopic reconstruction of the anterior cruciate ligament performed per institutional surgical protocol. Cleaning of the lateral wall of the intercondylar notch in the resident's ridge region uses exclusively radiofrequency ablation; motorised instrumentation is avoided in this region to preserve the integrity of the bony landmark. Per enrolled patient, a continuous intra-operative recording is obtained from the unmodified standard arthroscopic camera column at 1920x1080 resolution and 60 fps; six 5-second segments are extracted, five documenting progressive cleaning steps of the lateral wall (0%, 25%, 50%, 75%, 100% completion) and one acquired with the surgical probe positioned on the posterior cartilaginous margin without occluding the candidate femoral footprint zone. The investigational software is not used to guide any intraoperative decision during enrolment; the algorithm operates offline on the recorded material.
Treatment groups
100 Participants
are divided into 1 treatment groupGroup A: Adult patients undergoing primary arthroscopic ACL reconstruction1 intervention
Trial outcomes
Primary outcomes
1
Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of the binary classification of arthroscopic field cleanliness
Area under the receiver operating characteristic curve (AUC-ROC) of the deep learning model trained to perform binary classification of arthroscopic frames into "fully cleaned" (corresponding to 100% completion of soft-tissue debridement of the lateral wall of the intercondylar notch) versus "not fully cleaned" (corresponding to 0%, 25%, 50% and 75% completion). AUC-ROC is computed on the independent validation cohort (frames extracted from the second 50 subjects, not used during training), with 95% confidence interval estimated by bootstrap. Additional descriptive performance metrics - overall classification accuracy, sensitivity, specificity, positive predictive value and F1-score - are pre-specified in the study protocol and reported as supportive.
Time frame
Through study completion, an average of 12 monthsSecondary outcomes
1
Mean Dice similarity coefficient of the semantic segmentation of anatomical landmarks on arthroscopic frames
Mean Dice similarity coefficient (Sorensen-Dice coefficient) at the per-frame level for the deep learning model trained to perform semantic segmentation of anatomical landmarks on arthroscopic frames acquired at full cleaning of the lateral wall of the intercondylar notch. The segmentation targets are the resident's ridge area (bony landmark) and the candidate perforation zone for femoral tunnel placement. The Dice coefficient is computed on the independent validation cohort (frames extracted from the second 50 subjects, not used during training), with 95% confidence interval estimated by bootstrap. Additional descriptive performance metrics - Intersection over Union, pixel accuracy and mean pixel accuracy per class - are pre-specified in the study protocol and reported as supportive.
Time frame
Through study completion, an average of 12 monthsSponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov