Artificial Intelligence-Enabled Skin Perforator Segmentation

NCT06634472 | Recruiting

• 1 other identifier: UW 24-354
• Study Type: observational
• Target: 49
• Locations: 1 country
• Sites: 1

Brief Summary

Computer-assisted surgery has revolutionized reconstruction with more efficient, accurate, and predictable surgery, as reported in our previous studies. Skin perforators are vessels that travel through muscles and septa to supply the skin. The identification of skin perforators is crucial for a safe fibula osteocutaneous free flap harvest with computer-assisted surgery. Different methods have been proposed in the past, each of which has its own limitations. Traditionally, skin perforators are identified with a Doppler ultrasound. Berrone et al. measured the locations with a Doppler ultrasound and imported the information back to guide virtual surgical planning. However, their study showed imprecise concordance between handheld Doppler measurements and the actual perforator locations; good correlation between the location of perforators and bone segments was identified in only four out of six cases investigated. To improve on the accuracy, computed tomography angiography was used for skin perforator identification. Battaglia et al. manually marked the perforating vessel location at the subcutaneous level and reported good correlation. However, the manual segmentation of the perforator was at the subcutaneous level only. The course of the perforators, which would be more significant for the design of computer-assisted fibula osteocutaneous free flap harvest, was not shown. To incorporate the course of skin perforators into fibula osteocutaneous free flap virtual surgical planning, Ettinger et al. first described the technique of manual tracing from computed tomography angiography in 2018 and validated its accuracy in 2022. The median absolute difference between the computed tomography angiography and intraoperative measurements was 3 millimeters. However, reports quoted an average of 2 to 3 hours spent on tracing and modeling the course of the perforators depending on their number and anatomy; consequently, this adds a significant burden to healthcare professionals. Recently, United Imaging Intelligence has developed an artificial intelligence-based program that offers a potential solution for accurate and efficient localization of skin perforators to be incorporated into the current virtual surgical planning workflow. The proposed study aims to validate its performance in a prospective case series. This will be the first study to investigate the use of an artificial intelligence-enabled program for fibula skin paddle perforator identification.

Conditions

Microvascular Free Flap Transfer; Fibula Flap

Keywords

skin perforator identification with artificial intelligence-segmentation tool; computer-assisted surgery; jaw reconstruction; artificial intelligence; skin perforators

Outcome Measures

Primary Outcomes (1)

• predictive accuracy of the artificial intelligence tool in identifying the targeted skin perforators

  The primary endpoint is the predictive accuracy of the artificial intelligence-enabled skin perforator segmentation tool. When the skin perforator is identified by both the AI-segmentation tool and during the surgery, it will be counted as a true positive (TP). When the perforator is identified by the AI-segmentation tool, but not found during the surgery it is counted as a false positive (FP). When the perforator is seen during the surgery, but not shown by the AI tool, it is a false negative (FN). Finally, a true negative (TN) perforator count will be derived from those subjects, who do not exhibit an FN perforator. The predictive accuracy (PA) is identified as the percentage of true perforators among all the perforators, and is calculated as (TP +TN)/(TP+FP+TN+FN)\*100%.

  36 months

Study Arms (1)

Patients requiring computer-assisted jaw reconstruction with microvascular free flaps

Inclusion criteria 1. Age ≥18 years, both genders; 2. Provided signed and dated informed consent form; 3. Indicated for immediate or secondary reconstructive surgery with osteocutaneous fibula free flap. Exclusion criteria 1. Patients who are pregnant; 2. Patients who have medically compromised conditions and cannot tolerate surgery; 3. Patients who are unable to receive pre-operative computed tomography, computed tomography Aagiography scans, such as those with iodine allergy; 4. Patients who have anatomical variation preventing the safe harvest of fibula free flap;

Other: artificial intelligence

Interventions

artificial intelligence OTHER

Artificial intelligence-enabled skin perforator segmentation tool

Patients requiring computer-assisted jaw reconstruction with microvascular free flaps

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population will include patients with maxillary or mandibular neoplastic, inflammatory, and congenital diseases, who require immediate or secondary reconstructive surgery with osteocutaneous fibula free flap.

You may qualify if:

• Age ≥18 years, both genders;
• Provided signed and dated informed consent form;
• Indicated for immediate or secondary reconstructive surgery with osteocutaneous fibula free flap.

You may not qualify if:

• Patients who are pregnant;
• Patients who have medically compromised conditions and cannot tolerate surgery;
• Patients who are unable to receive pre-operative computed tomography angiogram scans, such as those with iodine allergy;
• Patients who have anatomical variation preventing the safe harvest of fibula free flap.

Sponsors & Collaborators

• The University of Hong Kong: lead

Study Sites (1)

The University of Hong Kong

Hong Kong, 999077, Hong Kong

RECRUITING

Related Publications (6)

• Pu JJ, Choi WS, Yang WF, Zhu WY, Su YX. Unexpected Change of Surgical Plans and Contingency Strategies in Computer-Assisted Free Flap Jaw Reconstruction: Lessons Learned From 98 Consecutive Cases. Front Oncol. 2022 Feb 4;12:746952. doi: 10.3389/fonc.2022.746952. eCollection 2022.

  PMID: 35186723 BACKGROUND

• Powcharoen W, Yang WF, Yan Li K, Zhu W, Su YX. Computer-Assisted versus Conventional Freehand Mandibular Reconstruction with Fibula Free Flap: A Systematic Review and Meta-Analysis. Plast Reconstr Surg. 2019 Dec;144(6):1417-1428. doi: 10.1097/PRS.0000000000006261.

  PMID: 31764662 BACKGROUND

• Pu JJ, Choi WS, Yu P, Wong MCM, Lo AWI, Su YX. Do predetermined surgical margins compromise oncological safety in computer-assisted head and neck reconstruction? Oral Oncol. 2020 Dec;111:104914. doi: 10.1016/j.oraloncology.2020.104914. Epub 2020 Jul 23.

  PMID: 32712577 BACKGROUND

• Pu JJ, Lo AWI, Wong MCM, Choi WS, Ho G, Yang WF, Su YX. A quantitative comparison of bone resection margin distances in virtual surgical planning versus histopathology: a prospective study. Int J Surg. 2024 Jan 1;110(1):111-118. doi: 10.1097/JS9.0000000000000780.

  PMID: 37737999 BACKGROUND

• Pu JJ, Hakim SG, Melville JC, Su YX. Current Trends in the Reconstruction and Rehabilitation of Jaw following Ablative Surgery. Cancers (Basel). 2022 Jul 7;14(14):3308. doi: 10.3390/cancers14143308.

  PMID: 35884369 BACKGROUND

• Su YR, Ganry L, Ozturk C, Lohman R, Al Afif A, McSpadden R, Frias V, Pu JJ. Fibula Flap Reconstruction for the Mandible: Why It Is Still the Workhorse? Atlas Oral Maxillofac Surg Clin North Am. 2023 Sep;31(2):121-127. doi: 10.1016/j.cxom.2023.04.005. No abstract available.

  PMID: 37500195 BACKGROUND

MeSH Terms

Interventions

Artificial Intelligence

Intervention Hierarchy (Ancestors)

Algorithms; Mathematical Concepts

Study Officials

• Jane J Pu, MDS

  The University of Hong Kong

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Jane J PU, MDS

CONTACT

852-28590534; drjanepu@hku.hk

Yuxiong Su, PhD

CONTACT

852-28590534; richsu@hku.hk

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Clinical Professor

Study Record Dates

• First Submitted: October 2, 2024
• First Posted: October 10, 2024
• Study Start: December 1, 2024
• Primary Completion (Estimated): September 30, 2027
• Study Completion (Estimated): December 31, 2027
• Last Updated: March 3, 2026

Record last verified: 2026-03

Locations

HK (1)