Augmented Reality in Surgery (ARS)

Artificial Intelligence-Based Identification of the Target Zone on Arthroscopic Images During Knee Anterior Cruciate Ligament Reconstruction: An Observational Study

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.

Study Overview

• Status: Recruiting
• Conditions: Anterior Cruciate Ligament (ACL) Tear
• Intervention / Treatment: Procedure: Primary arthroscopic anterior cruciate ligament reconstruction

Detailed Description

Background and rationale. Anterior cruciate ligament (ACL) reconstruction is one of the most frequently performed orthopaedic procedures worldwide. A well-documented determinant of long-term clinical outcome is the anatomical accuracy of femoral bone tunnel placement, whose centre must reproduce the native ACL footprint on the lateral wall of the intercondylar notch. Femoral tunnel malposition is recognised in the literature as a contributing factor to recurrent instability, graft failure and revision surgery. Anatomic tunnel placement is guided arthroscopically by the visual identification of bony and cartilaginous landmarks - most notably the resident's ridge (lateral intercondylar ridge) and the posterior cartilaginous margin of the lateral femoral condyle. These landmarks must be discriminated from the surrounding tissue on the 2D arthroscopic monitor image; their identification depends on operator experience and on the quality of the visual field, which can be degraded by soft-tissue debris, bleeding or suboptimal camera orientation. The reported association between surgeon case volume and surgical outcome reflects, in part, the learning curve associated with this visual task. Computer vision and artificial intelligence methods applied to surgical video offer a route to automated, reproducible recognition of these landmarks on the existing arthroscopic image stream, without modifying the hardware already present in the operating room.

Investigational system. The ARS (Augmented Reality in Surgery) software pipeline analyses arthroscopic video acquired from the standard arthroscopic camera column. Two functional modules are evaluated: a binary classifier that determines whether the field of view is sufficiently free of debris and adequately oriented to allow landmark identification, and a semantic segmentation module that delineates the resident's ridge, the posterior cartilaginous margin of the lateral femoral condyle and the candidate anatomical footprint zone for femoral tunnel placement. The algorithmic core is built by fine-tuning surgical vision foundation models on a dataset specifically curated for this task. The intended future deployment paradigm - outside the scope of the present study - is an unobtrusive visual overlay on the existing arthroscopic monitor, supporting the surgeon's visual interpretation. By design, the system is a decision-support tool: it does not pilot instruments, does not take autonomous decisions, and does not substitute the surgeon's judgement at any step of the procedure.

Study design. The study is a prospective, single-centre observational study conducted at IRCCS Galeazzi-Sant'Ambrogio (Milan, Italy). A retrospective component, based on previously acquired arthroscopic video material from ACL reconstructions performed within the same Unit and managed under applicable data-protection and consent provisions, is used for additional independent validation of the algorithms. The prospective component is fully integrated into the standard clinical pathway: no additional surgical step, device or instrument is introduced, no operative time is added, and the system is not used to guide any intraoperative decision during enrolment. The algorithm operates offline on the recorded material.

Video acquisition protocol. For each enrolled patient, six 5-second video segments are extracted from a single continuous intra-operative recording captured from the existing arthroscopic camera column at native 1920×1080 resolution and 60 frames per second. Five segments document the state of the intercondylar notch at progressive cleaning steps - corresponding to approximately 0%, 25%, 50%, 75% and 100% completion of soft-tissue debridement of the lateral wall - and the sixth segment is acquired with the surgical probe positioned on the posterior cartilaginous margin, without occluding the candidate footprint zone, in order to capture the instrument-anatomy spatial relationship in the same anatomical frame. During the procedure the surgeon verbally announces each stability moment to facilitate post-operative segment extraction. Cleaning of the lateral wall in the resident's ridge region is performed exclusively with radiofrequency ablation; motorised instrumentation is avoided in this region during enrolment to preserve the integrity of the bony ridge as a visual landmark.

Data management. Footage is pseudonymised at the point of acquisition; only intra-articular content is recorded, and no patient-identifying frames are produced. A structured naming convention is applied at ingestion. All study data are stored on institutional infrastructure under the governance of IRCCS Galeazzi-Sant'Ambrogio, processed in accordance with Regulation (EU) 2016/679 (GDPR) and applicable Italian implementing legislation. Each video segment is traceable to a single enrolment record on the institutional study management system, supporting source-data verification.

Annotation workflow. Annotation is performed on a self-hosted instance of the CVAT Community Edition platform, deployed on institutional infrastructure. Three annotation workstreams are configured: a field-classification workstream, in which each segment is assigned a class corresponding to the cleaning step; an anatomical-segmentation workstream, in which every extracted frame of the fully-cleaned segment is densely annotated with polyline labels for the resident's ridge and the posterior cartilaginous margin and with a polygon label for the candidate perforation zone; and an instrument-plus-anatomy workstream addressing the segment recorded with the surgical probe in position. An AI-collaborative labelling pipeline is employed, in which a vision foundation model generates mask proposals that the expert surgeon annotator subsequently refines. The reference standard is established by a senior surgeon with sub-specialty expertise in knee arthroscopy; a subset of cases is independently re-annotated to estimate inter-rater agreement, and discrepancies are adjudicated by consensus.

Algorithm training and performance assessment. Models are trained on the annotated prospective dataset, supplemented by the retrospective material where applicable, and evaluated on a held-out subset. Algorithm performance is summarised by classification accuracy, sensitivity, specificity and F1 score for the field-quality classifier, and by intersection-over-union (IoU) and Dice similarity coefficient at the per-frame level for the anatomical-segmentation outputs, reported with bootstrap confidence intervals. Pre-specified sensitivity analyses include stratification by cleaning step, by camera orientation and by surgical phase.

Quality assurance. Standard Operating Procedures cover video acquisition, file management and annotation. Each procedure is version-controlled and distributed to all study personnel. Automated data validation rules check naming-convention compliance, segment duration, resolution and frame rate at ingestion. Video segments failing technical quality checks - for example, due to excessive motion blur or to instrument occlusion of the candidate footprint zone in segments where the instrument should not be present - are excluded from the analysis dataset, and exclusions are documented at segment level. Adverse events are not anticipated as a direct consequence of the observational procedure; any clinical event occurring during the standard ACL reconstruction is documented in the institutional clinical record according to routine practice and is not part of the study endpoints.

Sample size and missing data. The required sample size is driven by the technical objective of training and validating image-analysis algorithms rather than by a clinical-effect estimate, and is specified in the study protocol. Handling of missing data and the segment-level exclusion criteria for technical inadequacy are pre-defined in the analysis plan.

Statistical analysis. The statistical analysis plan is developed in collaboration with an institutional biostatistician and is documented in the study protocol. Algorithm performance metrics are reported as point estimates with bootstrap confidence intervals; comparisons across strata, where applicable, use non-parametric tests appropriate to the per-frame or per-patient unit of analysis.

Regulatory positioning. The investigational software is used in this study under a research protocol and is not employed to guide intraoperative decisions during enrolment. Any future clinical deployment is anticipated under the European Medical Device Regulation framework as a decision-support software intended to assist the surgeon's visual interpretation, without autonomous guidance.

Ethics. The study is conducted in accordance with the Declaration of Helsinki, with applicable European and Italian regulations on observational research with health data, and with Regulation (EU) 2016/679 (GDPR). Approval by the competent Ethics Committee is obtained prior to study initiation.

• Study Type: Observational
• Enrollment (Estimated): 100

Contacts and Locations

• Study Contact: Name: Andrea Cusumano, MD; Phone Number: 0039 3483733690; Email: dr.andreacusumano@gmail.com

Study Locations

• Italy
  • Michigan
    • Milan, Michigan, Italy, 20157
      • Recruiting
      • IRCCS Ospedale Galeazzi-Sant'Ambrogio
      • Contact: Andrea Cusumano, MD; Phone Number: 0039 3483733690; Email: dr.andreacusumano@gmail.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study 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.

Description

Inclusion Criteria:

• Age 18 years or older
• Scheduled for primary arthroscopic anterior cruciate ligament reconstruction at IRCCS Galeazzi-Sant'Ambrogio
• Signed written informed consent

Exclusion Criteria:

• 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

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

Adult patients undergoing primary arthroscopic ACL reconstruction; Adult patients (age 18 years or older) consecutively enrolled at IRCCS Galeazzi-Sant'Ambrogio (Milan, Italy) for primary arthroscopic anterior cruciate ligament reconstruction. The procedure follows the institutional standard of care; no investigational device, additional intraoperative manoeuvre or operative-time extension is introduced for study purposes. During surgery, a continuous arthroscopic video is recorded from the standard arthroscopic camera column already in clinical use, and short segments are extracted to document the lateral wall of the intercondylar notch at progressive cleaning steps and the instrument-anatomy relationship at the fully-cleaned step. The recorded material is pseudonymised and used to train and validate computer vision algorithms for landmark identification on the arthroscopic image. The first 50 enrolled subjects contribute to algorithm training; the subsequent 50 to independent validation.

Procedure: Primary arthroscopic anterior cruciate ligament reconstruction; Arthroscopic 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.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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.	Through study completion, an average of 12 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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.	Through study completion, an average of 12 months

Collaborators and Investigators

• Sponsor: I.R.C.C.S Ospedale Galeazzi-Sant'Ambrogio

Publications and helpful links

General Publications

• Hashimoto DA, Rosman G, Rus D, Meireles OR. Artificial Intelligence in Surgery: Promises and Perils. Ann Surg. 2018 Jul;268(1):70-76. doi: 10.1097/SLA.0000000000002693.
• Kayaalp ME, Konstantinou E, Karaismailoglu B, Lucidi GA, Kaymakoglu M, Vieider R, Giusto JD, Inoue J, Hirschmann MT. The metaverse in orthopaedics: Virtual, augmented and mixed reality for advancing surgical training, arthroscopy, arthroplasty and rehabilitation. Knee Surg Sports Traumatol Arthrosc. 2025 Aug;33(8):3039-3050. doi: 10.1002/ksa.12723. Epub 2025 Jul 7.
• Bian D, Lin Z, Lu H, Zhong Q, Wang K, Tang X, Zang J. The application of extended reality technology-assisted intraoperative navigation in orthopedic surgery. Front Surg. 2024 Feb 5;11:1336703. doi: 10.3389/fsurg.2024.1336703. eCollection 2024.
• Chen H. Application progress of artificial intelligence and augmented reality in orthopaedic arthroscopy surgery. J Orthop Surg Res. 2023 Oct 14;18(1):775. doi: 10.1186/s13018-023-04280-9.

Study record dates

Study Major Dates

• Study Start (Actual): May 26, 2026
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): May 31, 2027

Study Registration Dates

• First Submitted: May 23, 2026
• First Submitted That Met QC Criteria: June 3, 2026
• First Posted (Actual): June 9, 2026

Study Record Updates

• Last Update Posted (Actual): June 9, 2026
• Last Update Submitted That Met QC Criteria: June 3, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: Anterior Cruciate Ligament Reconstruction; Artificial Intelligence; Deep Learning; Augmented Reality; Arthroscopy; Surgery, Computer-Assisted; Image Processing; Computer Vision; Decision Support Systems; Semantic Segmentation; Femoral Tunnel
• Additional Relevant MeSH Terms: Wounds and Injuries; Lacerations
• Other Study ID Numbers: ARS

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: The arthroscopic video material and derived annotations collected in this study are owned by IRCCS Galeazzi-Sant'Ambrogio, which acts as data controller, in accordance with institutional research and intellectual property policy and with applicable data protection legislation. The data constitute an institutional research asset and contain sensitive surgical material that, although pseudonymised at the point of acquisition, requires controlled access to ensure compliance with data protection obligations and to safeguard the legitimate interests of the data controller. Any future external access or transfer would require explicit authorisation by the institution and would be governed by a dedicated data access agreement and, where applicable, by additional ethical review. At the time of registration, no individual participant data sharing plan with external researchers is in place.