Methodology to create 3D models of COVID-19 pathologies for virtual clinical trials

Development and validation of a 3D anthropomorphic phantom for dental CBCT imaging research

BACKGROUND

Optimization of dental cone beam computed tomography (CBCT) imaging is still in a preliminary stage and should be addressed using task-based methods. Dedicated models containing relevant clinical tasks for image quality studies have yet to be developed.

PURPOSE

To present a methodology to develop and validate a virtual adult anthropomorphic voxel phantom for use in task-based image quality optimization studies in dental CBCT imaging research, focusing on root fracture (RF) detection tasks in the presence of metal artefacts.

METHODS

The phantom was developed from a CBCT scan with an isotropic voxel size of 0.2 mm, from which the main dental structures, mandible and maxilla were segmented. The missing large anatomical structures, including the spine, skull and remaining soft tissues, were segmented from a lower resolution full skull scan. Anatomical abnormalities were absent in the areas of interest. Fine detailed dental structures, that could not be segmented due to the limited resolution and noise in the clinical data, were modelled using a-priori anatomical knowledge. Model resolution of the teeth was therefore increased to 0.05 mm. Models of RFs as well as dental restorations to create the artefacts, were developed, and could be inserted in the phantom in any desired configuration. Simulated CBCT images of the models were generated using a newly developed multi-resolution simulation framework that incorporated the geometry, beam quality, noise and spatial resolution characteristics of a real dental CBCT scanner. Ray-tracing and Monte Carlo techniques were used to create the projection images, which were reconstructed using the classical FDK algorithm. Validation of the models was assessed by measurements of different tooth lengths, the pulp volume and the mandible, and comparison with reference values. Additionally, the simulated images were used in a reader study in which two oral radiologists had to score the realism level of the model's normal anatomy, as well as the modelled RFs and restorations.

RESULTS

A model of an adult head, as well as models of RFs and different types of dental restorations were created. Anatomical measurements were consistent with ranges reported in literature. For the tooth length measurements, the deviations from the mean reference values were less than 20%. In 77% of all the measurements, the deviations were within 10.1%. The pulp volumes, and mandible measurements were within one standard deviation of the reference values. Regarding the normal anatomy, both readers considered the realism level of the dental structures to be good. Background structures received a lower realism score due to the lack of detailed enough trabecular bone structure, which was expected but not the focus of this study. All modelled RFs were scored at least adequate by at least one of the readers, both in appearance and position. The realism level of the modelled restorations was considered to be good.

CONCLUSIONS

A methodology was proposed to develop and validate an anthropomorphic voxel phantom for image quality optimization studies in dental CBCT imaging, with a main focus on RF detection tasks. The methodology can be extended further to create more models representative of the clinical population.

Procurement, commissioning and QA of AI based solutions: An MPE's perspective on introducing AI in clinical practice

PURPOSE

In this study, we propose a framework to help the MPE take up a unique and important role at the introduction of AI solutions in clinical practice, and more in particular at procurement, acceptance, commissioning and QA.

MATERIAL AND METHODS

The steps for the introduction of Medical Radiological Equipment in a hospital setting were extrapolated to AI tools. Literature review and in-house experience was added to prepare similar, yet dedicated test methods.

RESULTS

Procurement starts from the clinical cases to be solved and is usually a complex process with many stakeholders and possibly many candidate AI solutions. Specific KPIs and metrics need to be defined. Acceptance testing follows, to verify the installation and test for critical exams. Commissioning should test the suitability of the AI tool for the intended use in the local institution. Results may be predicted from peer reviewed papers that treat representative populations. If not available, local data sets can be prepared to assess the KPIs, or 'virtual clinical trials' could be used to create large, simulated test data sets. Quality assurance must be performed periodically to verify if KPIs are stable, especially if the software is upscaled or upgraded, and as soon as self-learning AI tools would enter the medical practice.

DISCUSSION

MPEs are well placed to bridge between manufacturer and medical team and help from procurement up to reporting to the management board. More work is needed to establish consolidated test protocols.