Human-AI Uncertainty Callibration for Improved Skin Lesion Segmentation

NCT07468357 | Not Yet Recruiting

• 1 other identifier: F-25076782
• Study Type: interventional
• Target: 50
• Locations: 0 countries
• Sites: N/A

Brief Summary

The goal of this randomized controlled study is to compare the effect of a new, personalized uncertainty-aware decision model (FDM) to a standard image recognition model in improving the diagnostic accuracy while reducing diagnostic uncertainty in experienced dermatologists tasked with differentiating between melanomas, moles and other benign skin lesions. The main question it aims to answer: Is the FDM a feasible method for an improved human AI partnership in which trust is build, misdiagnoses are avoided, and uncertainty is duly introduced or reduced. The investigators expect to see only a slight increase in collective diagnostic accuracy for both interventions as the the human participants are skilled dermatologist and thus have high accuracies pre-intervention. The investigators expect to see a higher increase in diagnostic certainty for the FDM intervention compared to the diagnostic certainty in the Base Model intervention. The investigators expect to see a higher amount of diagnosis changes from incorrect to correct in the FDM group compared to the Base Model group. The investigators do not expect any learning effect during the study. Participants will start by answering a series of training cases consisting of images of skin lesions. These are used to train their individual FDM (only for the FDM-intervention group). From here, the participants will be randomized into two arms determining which of the two interventions they are exposed to. The participants will solve each case withouth any intervention first, and this reply will act as a control.

Conditions

Skin Lesions

Keywords

Dermatology; AI; Artificial Intelligence; Uncertainty Calibration; Dermoscopy; Bayesian Deep Learning; Human-AI Decision Model

Outcome Measures

Primary Outcomes (1)

• Accuracy

  Diagnostic accuracy in differentiating between melanoma, nevus, and benign keratosis. Defined as the percentage of correct diagnoses. Ground truth is based on histopathologically verified diagnoses.

  Immediately after the intervention.

Secondary Outcomes (2)

• Uncertainty

  Immediately after the intervention.

• Cut-off uncertainty

  Immediately after the intervention.

Other Outcomes (1)

• Time

  Immediately after the intervention.

Study Arms (2)

Base Model

ACTIVE COMPARATOR

The study participant is presented with a patient case including patient demographics (gender, age, placement of lesion) and two lesion images: 1 overview image, and 1 dermoscopic image. They are asked first to indicate an initial diagnosis along with their self-perceived uncertainty for this specific case before they receive Intervention 1. This initial diagnosis will act as the control. Intervention 1 is AI-generated multi-class probabilities (from a model trained on a large dataset of dermoscopic and overview images similar to the ones used for testing) and only the most likely diagnosis is presented accompanied by uncertainty estimates in percent. After the AI input, the study participant is given the chance to change their diagnosis and indicate any potential shift in uncertainty.

Other: Base Model

FDM

EXPERIMENTAL

The initial diagnosis and indication of self-perceived uncertainty follows the same procedure as for Intervention 1. Intervention 2 is the most likely diagnosis accompanied by a calibrated uncertainty generated by the FDM model (i.e. trained on the study participants previous answers + the crowd annotations on the training data + the base model prediction). After the AI input, the study participant is given the chance to change their diagnosis and indicate any potential shift in uncertainty.

Other: FDM

Interventions

Base Model OTHER

See arm description.

Also known as: Intervention 1

Base Model

FDM OTHER

See arm description

Also known as: Final Decision Model, Intervention 2

FDM

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)

You may qualify if:

• Board certified dermatologists with clinical experience in dermoscopic diagnosis.

You may not qualify if:

• Doctors who have not yet finished their specialization and dermatologists.
• Dermatologists without clinical experience in dermoscopic diagnosis.

Sponsors & Collaborators

• Copenhagen Academy for Medical Education and Simulation: lead
• Technical University of Denmark: collaborator

Related Publications (1)

• Kampen, P.J.T. et al. (2026). Uncertainty-Aware Classification: A Human-Guided Bayesian Deep Learning Framework. In: Sudre, C.H., et al. Uncertainty for Safe Utilization of Machine Learning in Medical Imaging. UNSURE 2025. Lecture Notes in Computer Science, vol 16166. Springer, Cham. https://doi.org/10.1007/978-3-032-06593-3_19

  BACKGROUND

Study Officials

• Martin Tolsgaard, Professor

  Copenhagen Academy for Medical Education and Simulation

  STUDY CHAIR

Central Study Contacts

Julie Renata Bjerremand

CONTACT

+45 53593700; julierenata@outlook.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Model Details: Each participant will undergo the same training phase. Subsequently, the participants are randomized into one of the intervention arms. Each participant will be their own control.

Study Record Dates

• First Submitted: January 29, 2026
• First Posted: March 12, 2026
• Study Start: March 1, 2026
• Primary Completion: July 1, 2026
• Study Completion (Estimated): November 1, 2026
• Last Updated: March 12, 2026

Record last verified: 2026-03