AI-aided Optical Coherence Tomography for the Detection of Basal Cell Carcinoma

Basal cell carcinoma (BCC) is the most common form of cancer among the Caucasian population. A BCC diagnosis is commonly establish by means of an invasive punch biopsy (golden standard). Optical coherence tomography (OCT) is a safe non-invasive diagnostic modality which may replace biopsy if an OCT assessor is able to establish a high confidence BCC diagnosis. Hence, for clinical implementation of OCT, diagnostic certainty should be as high as possible. Artificial intelligence in the form of a clinical decision support system (CDSS) may improve the diagnostic certainty of newly trained OCT assessors by highlighting suspicious areas on OCT scans and by providing diagnostic suggestions (classification). This study will evaluate the effect of a CDSS on the diagnostic certainty and accuracy of OCT assessors.

Study Overview

• Status: Recruiting
• Conditions: Basal Cell Carcinoma; Optical Coherence Tomography
• Intervention / Treatment: Diagnostic test: Optical coherence tomography

Detailed Description

In this diagnostic case control design, OCT assessors will retrospectively evaluate OCT scans of equivocal BCC lesions twice (once with, and once without the help of the CDSS). A total of 124 scans (62 BCC/62 non-BCC) will be included in the study. Cases will be shuffled to prevent recall bias. AI-aided OCT scans and unaided OCT scans will be presented in alternating order. The assessors will express their certainty level on a 5-point confidence scale. The diagnostic certainty and diagnostic accuracy of OCT assessment with CDSS and without CDSS will be compared.

Research questions:

1. Does AI-aided OCT assessment result in an increase in high-confidence diagnoses compared to unaided OCT assessment?
2. Does AI-aided OCT assessment result in a significant increase in sensitivity for BCC detection without compromising specificity compared to unaided OCT assessment?
3. Does AI-aided OCT assessment result in more accurate BCC subtyping compared to unaided OCT assessment (explorative)

• Study Type: Observational
• Enrollment (Estimated): 124

Contacts and Locations

Study Locations

• Netherlands
  • Limbrug
    • Maastricht, Limbrug, Netherlands, 6202AZ
      • Recruiting
      • Maastricht University Medical Center+
      • Contact: Tom Wolswijk, MD, MSc; Phone Number: +31(0)42-3877295; Email: tom.wolswijk@mumc.nl

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: N/A

• Sampling Method: Probability Sample

Study Population

Scans of patients with equivocal BCC lesions will be included. Patients previously underwent an OCT scan and punch biopsy for their lesion. Patients signed informed consent for the use of the OCT scans made and patient information for the sake of answering research questions regarding OCT.

Description

Inclusion Criteria:

• Patients (18+ years)
• Patient underwent OCT scan and punch biopsy for an equivocal BCC lesion

Exclusion Criteria:

- Patient unable to sign informed consent

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
AI-OCT; Group of 124 patients with equivocal BCC lesions. Of these lesions, OCT scans have been obtained in the past. These scans will be evaluated with AI-assistance.	Diagnostic test: Optical coherence tomography; Optical coherence tomography: OCT is a non-invasive CE-certified diagnostic modality based on light interferometry. An OCT scan visualizes an area with a diameter of 6mm thereby revealing the skin and adnexal structures with a depth of approximately 1.5mm. 3mm punch biopsy: the patients included in this study underwent a 3mm punch biopsy conform regular care. The subsequent histopathological examination of the biopsy specimen serves as ground truth diagnosis of the lesions (gold standard); Other Names: 3mm punch biopsy
Unaided OCT; Group of 124 patients with equivocal BCC lesions (same patients as in AI-OCT group). Of these lesions, OCT scans have been obtained in the past. These scans will be evaluated without AI-assistance.	Diagnostic test: Optical coherence tomography; Optical coherence tomography: OCT is a non-invasive CE-certified diagnostic modality based on light interferometry. An OCT scan visualizes an area with a diameter of 6mm thereby revealing the skin and adnexal structures with a depth of approximately 1.5mm. 3mm punch biopsy: the patients included in this study underwent a 3mm punch biopsy conform regular care. The subsequent histopathological examination of the biopsy specimen serves as ground truth diagnosis of the lesions (gold standard); Other Names: 3mm punch biopsy

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of high-confidence diagnoses	The difference in percentage of high-confidence diagnoses will be evaluated between AI-OCT and unaided OCT.	31-12-2023

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy of high-confidence diagnoses	Diagnostic parameters (sensitivity, specificity, positive predictive value, negative predicted value, diagnostic odds ratio) will be estimated for high-confidence diagnoses made by AI-OCT and unaided OCT.	31-12-2023
Diagnostic parameters for BCC subtyping	Differences in diagnostic parameters for BCC subtyping (sBCC/nBCC/iBCC) will be evaluated (explorative)	31-12-2023

Collaborators and Investigators

• Sponsor: Maastricht University Medical Center

Study record dates

Study Major Dates

• Study Start (Actual): April 10, 2023
• Primary Completion (Estimated): December 31, 2024
• Study Completion (Estimated): December 31, 2024

Study Registration Dates

• First Submitted: April 4, 2023
• First Submitted That Met QC Criteria: April 4, 2023
• First Posted (Actual): April 18, 2023

Study Record Updates

• Last Update Posted (Actual): February 16, 2024
• Last Update Submitted That Met QC Criteria: February 15, 2024
• Last Verified: February 1, 2024

More Information

Terms related to this study

• Keywords: OCT; Imaging; Optical coherence tomography; Artificial intelligence; Basal cell carcinoma; BCC; Machine learning
• Additional Relevant MeSH Terms: Neoplasms by Histologic Type; Neoplasms; Neoplasms, Glandular and Epithelial; Neoplasms, Basal Cell; Carcinoma; Carcinoma, Basal Cell
• Other Study ID Numbers: 2022-3517

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No