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.

Virtual anatomical reconstruction of large acetabular bone defects using a statistical shape model.

Custom implants are used to treat patients with large acetabular bone defects. To quantify the bone defect and to initialize the implant design, a virtual anatomical reconstruction of the bone needs to be performed. Our SSM-based reconstruction approach was used to overcome the limitations of the mirrored contralateral method and improves upon other SSM reconstruction techniques. The reconstruction errors for the acetabular direction, the hip joint center and the acetabular radius were, respectively: [Formula: see text], 2.6 mm and 0.7 mm. We believe that our method can be an essential tool in the planning and the design of custom implants.

Computed tomography-based joint locations affect calculation of joint moments during gait when compared to scaling approaches.

Hip joint moments are an important parameter in the biomechanical evaluation of orthopaedic surgery. Joint moments are generally calculated using scaled generic musculoskeletal models. However, due to anatomical variability or pathology, such models may differ from the patient's anatomy, calling into question the accuracy of the resulting joint moments. This study aimed to quantify the potential joint moment errors caused by geometrical inaccuracies in scaled models, during gait, for eight test subjects. For comparison, a semi-automatic computed tomography (CT)-based workflow was introduced to create models with subject-specific joint locations and inertial parameters. 3D surface models of the femora and hemipelves were created by segmentation and the hip joint centres and knee axes were located in these models. The scaled models systematically located the hip joint centre (HJC) up to 33.6 mm too inferiorly. As a consequence, significant and substantial peak hip extension and abduction moment differences were recorded, with, respectively, up to 23.1% and 15.8% higher values in the image-based models. These findings reaffirm the importance of accurate HJC estimation, which may be achieved using CT- or radiography-based subject-specific modelling. However, obesity-related gait analysis marker placement errors may have influenced these results and more research is needed to overcome these artefacts.

Quantitative Computerized Assessment of the Degree of Acetabular Bone Deficiency: Total radial Acetabular Bone Loss (TrABL).

A novel quantitative, computerized, and, therefore, highly objective method is presented to assess the degree of total radical acetabular bone loss. The method, which is abbreviated to "TrABL", makes use of advanced 3D CT-based image processing and effective 3D anatomical reconstruction methodology. The output data consist of a ratio and a graph, which can both be used for direct comparison between specimens. A first dataset of twelve highly deficient hemipelves, mainly Paprosky types IIIB, is used as illustration. Although generalization of the findings will require further investigation on a larger population, it can be assumed that the presented method has the potential to facilitate the preoperative use of existing classifications and related decision schemes for treatment selection in complex revision cases.

A custom-made guide-wire positioning device for hip surface replacement arthroplasty: description and first results.

BACKGROUND: Hip surface replacement arthroplasty (SRA) can be an alternative for total hip arthroplasty. The short and long-term outcome of hip surface replacement arthroplasty mainly relies on the optimal size and position of the femoral component. This can be defined before surgery with pre-operative templating. Reproducing the optimal, templated femoral implant position during surgery relies on guide wire positioning devices in combination with visual inspection and experience of the surgeon. Another method of transferring the templated position into surgery is by navigation or Computer Assisted Surgery (CAS). Though CAS is documented to increase accurate placement particularly in case of normal hip anatomy, it requires bulky equipment that is not readily available in each centre. METHODS: A custom made neck jig device is presented as well as the results of a pilot study. The device is produced based on data pre-operatively acquired with CT-scan. The position of the guide wire is chosen as the anatomical axis of the femoral neck. Adjustments to the design of the jig are made based on the orthopedic surgeon's recommendations for the drill direction. The SRA jig is designed as a slightly more-than-hemispherical cage to fit the anterior part of the femoral head. The cage is connected to an anterior neck support. Four knifes are attached on the central arch of the cage. A drill guide cylinder is attached to the cage, thus allowing guide wire positioning as pre-operatively planned. Custom made devices were tested in 5 patients scheduled for total hip arthroplasty. The orthopedic surgeons reported the practical aspects of the use of the neck-jig device. The retrieved femoral heads were analyzed to assess the achieved drill place in mm deviation from the predefined location and orientation compared to the predefined orientation. RESULTS: The orthopedic surgeons rated the passive stability, full contact with neck portion of the jig and knife contact with femoral head, positive. There were no guide failures. The jig unique position and the number of steps required to put the guide in place were rated 1, while the complexity to put the guide into place was rated 1-2. In all five cases the guide wire was accurately positioned. Maximum angular deviation was 2.9 degrees and maximum distance between insertion points was 2.1 mm. CONCLUSIONS: Pilot testing of a custom made jig for use during SRA indicated that the device was (1) successfully applied and user friendly and (2) allowed for accurate guide wire placement according to the preoperative plan.

Accuracy and repeatability of cone-beam computed tomography (CBCT) measurements used in the determination of facial indices in the laboratory setup.

AIM: To assess the three dimensional (3D) surface accuracy of a phantom's face acquired from a cone-beam computed tomography (CBCT) scan and to determine the reliability of selected cephalometric measurements performed with Maxilim software (Medicim N.V., Mechelen, Belgium). MATERIAL AND METHODS: A mannequin head was imaged with a CBCT (I-CAT, Imaging Sciences International, Inc., Hatfield, USA). The data were used to produce 3D surface meshes (Maxilim and Mimics, Materialise N.V., Leuven, Belgium) which were compared with an optical surface scan of the head using Focus Inspection software (Metris N.V., Leuven, Belgium). The intra- and inter-observer reliability for the measurement of distances between facial landmarks with Maxilim 3D cephalometry were determined by calculating Pearson correlation coefficients and intraclass correlation (ICC). The Dahlberg formula was used to assess the method error (ME). RESULTS: (1) The maximal range of the 3D mesh deviations was 1.9 mm for Maxilim, and 1.8mm for Mimics segmentation. (2) Test-retest and inter-observer reliability were high; Pearson's correlation coefficient was 1.000 and the ICC was 0.9998. The ME of the vertical measurements was a little larger than that calculated for the width measurements. Maximum ME was 1.33 mm. CONCLUSIONS: The 3D surface accuracy of CBCT scans segmented with Maxilim and Mimics software is high. Maxilim also shows satisfactory intra- and inter-assessor reliability for measurement of distances on a rigid facial surface.

Skull reconstruction planning transfer to the operation room by thin metallic templates: clinical results.

INTRODUCTION: Craniofacial malformations implicate a risk of medical complications and a negative psychological impact on the patient. In order to correct functional and aesthetic aspects of these malformations, skull reconstruction is required. Because of the complexity of the surgery, pre-operative planning is unavoidable. Current and previously developed planning environments often lack the opportunity to transfer the simulated surgery to the operation room on a cheap but accurate, and easy to handle basis. MATERIALS AND METHODS: This study applies an automated filter procedure, implemented in Matlab, to generate a set of adapted contours from which a surface mesh can be directly deduced. Skull reconstruction planning is performed on the generated outer bone surface model. For each resected/osteotomized bone part, the presented semi-automatic Matlab procedure generates surface based bone cutting guides, also denoted bone segment templates. Autoclaved aluminium templates transfer the surgical plan to the operation room. RESULTS: The clinical feasibility is demonstrated by the successful pre-operative planning and surgical correction of three skull reconstruction cases in which the proposed procedure leads to considerable reduction in surgery time and good results. CONCLUSION: A cost-efficient and planning-environment-independent solution is generated for an accurate and fast transfer of a complex cranial surgery plan to the operation room.