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

Sponsor

Maastricht University Medical Center (Other)

Overall Status

Recruiting

CT.gov ID

NCT05817279

Collaborator

(none)

124

Enrollment

Location

8.7

Anticipated Duration (Months)

14.2

Patients Per Site Per Month

Study Details

Study Description

Brief Summary

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.

Condition or Disease	Intervention/Treatment	Phase
Basal Cell Carcinoma Optical Coherence Tomography	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:

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

Study Design

Study Type:

Observational

Anticipated Enrollment :

124 participants

Observational Model:

Case-Control

Time Perspective:

Retrospective

Official Title:

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

Anticipated Study Start Date :

Apr 10, 2023

Anticipated Primary Completion Date :

Dec 31, 2023

Anticipated Study Completion Date :

Dec 31, 2023

Arms and Interventions

Arm	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

Arm

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

Other Names:

3mm punch biopsy

Outcome Measures

Primary Outcome Measures

Proportion of high-confidence diagnoses [31-12-2023]
The difference in percentage of high-confidence diagnoses will be evaluated between AI-OCT and unaided OCT.

Secondary Outcome Measures

Diagnostic accuracy of high-confidence diagnoses [31-12-2023]
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.
Diagnostic parameters for BCC subtyping [31-12-2023]
Differences in diagnostic parameters for BCC subtyping (sBCC/nBCC/iBCC) will be evaluated (explorative)