A training tool for clinicians in segmenting medical images to make 3D models

Ann Surg Open. 2023 May 23;4(2):e275. doi: 10.1097/AS9.0000000000000275.

Abstract

Introduction: 3D models produced from medical imaging can be used to plan treatment, design prosthesis, teach and for communication. Despite the clinical benefit, few clinicians have experience of how 3D models are produced.This is the first study evaluating a training tool to teach clinicians to produce 3D models and reporting the perceived impact on their clinical practice.

Method: Following ethical approval, 10 clinicians completed a bespoke training tool, comprising written and video material alongside online support. Each clinician and 2 technicians (included as control) were sent 3 CT scans and asked to produce 6 fibula 3D models using an open-source software (3Dslicer). The produced models were compared to those produced by the technicians using Hausdorff distance calculation. Thematic analysis was used to study the post-intervention questionnaire.

Results: The mean Hausdorff distance between the final model produced by the clinicians and technicians was 0.65mm SD0.54mm. The first model made by clinicians took a mean time of 1hr 25mins and the final model took 16:04mins (5:00-46:00mins). 100% of learners reported finding the training tool useful and will employ it in future practice.

Discussion: The training tool described in this paper is able to successfully train clinicians to produce fibula models from CT scans. Learners were able to produce comparable models to technicians within an acceptable timeframe. This does not replace technicians. However, the learners perceived this training will allow them to use this technology in more cases, with appropriate case selection and they appreciate the limits of this technology.