Educating the Healthcare Workforce to Support Digital Transformation.

Digital transformation of the healthcare workforce is a priority if we are to leverage the potential of digital technologies, artificial intelligence in clinical decision support and the potential of data captured within electronic health records. Educational programmes need to be diverse and support the digital novices through to the champions whom will be responsible for procuring and implementing digital solutions. In order to professionalise the workforce in this area, digital competencies need to be built into training from early on and be underpinned by frameworks that help to guide regulators and professional bodies and support educational providers to deliver them. Here we describe Manchester's involvement in the development of digital competency frameworks and our digital transformation education programmes that we have created, including a Massive Online Open Course and a professional development course for England's Topol Digital Fellows.

Understanding current UK practice for the incidental identification of vertebral fragility fractures from CT scans: an expert elicitation study.

BACKGROUND: There is an emerging interest in using automated approaches to enable the incidental identification of vertebral fragility fractures (VFFs) on existing medical images visualising the spine. AIM: To quantify values, and the degree of uncertainty associated with them, for the incidental identification of VFFs from computed tomography (CT) scans in current practice. METHODS: An expert elicitation exercise was conducted to generate point estimates and measures of uncertainty for four values representing the probability of: VFF being correctly reported by the radiologist; the absence of VFF being correctly assessed by the radiologist; being referred for management when a VFF is identified; having a dual-energy X-ray absorptiometry (DXA) scan after general practitioner (GP) referral. Data from a sample of seven experts in the diagnosis and management of people with VFFs were pooled using mathematical aggregation. RESULTS: The estimated mean values for each probability parameter were: VFF being correctly reported by the radiologist = 0.25 (standard deviation (SD): 0.21); absence of VFF being correctly assessed by the radiologist = 0.89 (0.10); being referred for management when a VFF is identified by the radiologist = 0.15 (0.12); having a DXA scan after GP referral = 0.66 (0.28). DISCUSSION: These estimates could be used to facilitate the subsequent early economic evaluation of potential new approaches to improve the health outcomes of people with VFFs. CONCLUSION: In the absence of epidemiological studies, this study produced point estimates and measures of uncertainty for key parameters needed to describe current pathways for the incidental diagnosis of VFFs.

Digital health interventions for osteoporosis and post-fragility fracture care.

The growing burden from osteoporosis and fragility fractures highlights a need to improve osteoporosis management across healthcare systems. Sub-optimal management of osteoporosis is an area suitable for digital health interventions. While fracture liaison services (FLSs) are proven to greatly improve care for people with osteoporosis, such services might benefit from technologies that enhance automation. The term 'Digital Health' covers a variety of different tools including clinical decision support systems, electronic medical record tools, patient decision aids, patient apps, education tools, and novel artificial intelligence (AI) algorithms. Within the scope of this review are AI solutions that use algorithms within health system registries to target interventions. Clinician-targeted, patient-targeted, or system-targeted digital health interventions could be used to improve management and prevent fragility fractures. This review was commissioned by The Royal Osteoporosis Society and Bone Research Academy during the production of the 2020 Research Roadmap (https://theros.org.uk), with the intention of identifying gaps where targeted research funding could lead to improved patient health. We explore potential uses of digital technology in the general management of osteoporosis. Evidence suggests that digital technologies can support multidisciplinary teams to provide the best possible patient care based on current evidence and to support patients in self-management. However, robust randomised controlled studies are still needed to assess the effectiveness and cost-effectiveness of these technologies.

Transfer learning for data-efficient abdominal muscle segmentation with convolutional neural networks.

BACKGROUND: Skeletal muscle segmentation is an important procedure for assessing sarcopenia, an emerging imaging biomarker of patient frailty. Data annotation remains the bottleneck for training deep learning auto-segmentation models. PURPOSE: There is a need to define methodologies for applying models to different domains (e.g., anatomical regions or imaging modalities) without dramatically increasing data annotation. METHODS: To address this problem, we empirically evaluate the generalizability of various source tasks for transfer learning: natural image classification, natural image segmentation, unsupervised image reconstruction, and self-supervised jigsaw solving. Axial CT slices at L3 were extracted from PET-CT scans for 204 oesophago-gastric cancer patients and the skeletal muscle manually delineated by an expert. Features were transferred and segmentation models trained on subsets ( n = 5 , 10 , 25 , 50 , 75 , 100 , 125 $n=5,10,25,50,75,100,125$ ) of the manually annotated training set. Four-fold cross-validation was performed to evaluate model generalizability. Human-level performance was established by performing an inter-observer study consisting of ten trained radiographers. RESULTS: We find that accurate segmentation models can be trained on a fraction of the data required by current approaches. The Dice similarity coefficient and root mean square distance-to-agreement were calculated for each prediction and used to assess model performance. Models pre-trained on a segmentation task and fine-tuned on 10 images produce delineations that are comparable to those from trained observers and extract reliable measures of muscle health. CONCLUSIONS: Appropriate transfer learning can generate convolutional neural networks for abdominal muscle segmentation that achieve human-level performance while decreasing the required data by an order of magnitude, compared to previous methods ( n = 160 → 10 $n=160 \rightarrow 10$ ). This work enables the development of future models for assessing skeletal muscle at other anatomical sites where large annotated data sets are scarce and clinical needs are yet to be addressed.

Opportunistic diagnosis of osteoporosis, fragile bone strength and vertebral fractures from routine CT scans; a review of approved technology systems and pathways to implementation.

Osteoporosis causes bones to become weak, porous and fracture more easily. While a vertebral fracture is the archetypal fracture of osteoporosis, it is also the most difficult to diagnose clinically. Patients often suffer further spine or other fractures, deformity, height loss and pain before diagnosis. There were an estimated 520,000 fragility fractures in the United Kingdom (UK) in 2017 (costing £4.5 billion), a figure set to increase 30% by 2030. One way to improve both vertebral fracture identification and the diagnosis of osteoporosis is to assess a patient's spine or hips during routine computed tomography (CT) scans. Patients attend routine CT for diagnosis and monitoring of various medical conditions, but the skeleton can be overlooked as radiologists concentrate on the primary reason for scanning. More than half a million CT scans done each year in the National Health Service (NHS) could potentially be screened for osteoporosis (increasing 5% annually). If CT-based screening became embedded in practice, then the technique could have a positive clinical impact in the identification of fragility fracture and/or low bone density. Several companies have developed software methods to diagnose osteoporosis/fragile bone strength and/or identify vertebral fractures in CT datasets, using various methods that include image processing, computational modelling, artificial intelligence and biomechanical engineering concepts. Technology to evaluate Hounsfield units is used to calculate bone density, but not necessarily bone strength. In this rapid evidence review, we summarise the current literature underpinning approved technologies for opportunistic screening of routine CT images to identify fractures, bone density or strength information. We highlight how other new software technologies have become embedded in NHS clinical practice (having overcome barriers to implementation) and highlight how the novel osteoporosis technologies could follow suit. We define the key unanswered questions where further research is needed to enable the adoption of these technologies for maximal patient benefit.

Artificial intelligence projects in healthcare: 10 practical tips for success in a clinical environment.

There is much discussion concerning 'digital transformation' in healthcare and the potential of artificial intelligence (AI) in healthcare systems. Yet it remains rare to find AI solutions deployed in routine healthcare settings. This is in part due to the numerous challenges inherent in delivering an AI project in a clinical environment. In this article, several UK healthcare professionals and academics reflect on the challenges they have faced in building AI solutions using routinely collected healthcare data.These personal reflections are summarised as 10 practical tips. In our experience, these are essential considerations for an AI healthcare project to succeed. They are organised into four phases: conceptualisation, data management, AI application and clinical deployment. There is a focus on conceptualisation, reflecting our view that initial set-up is vital to success. We hope that our personal experiences will provide useful insights to others looking to improve patient care through optimal data use.

Diagnostic performance of morphometric vertebral fracture analysis (MXA) in children using a 33-point software program.

BACKGROUND: There is significant inter and intraobserver variability in diagnosing vertebral fractures in children. PURPOSE: We aimed to evaluate the diagnostic accuracy of morphometric vertebral fracture analysis (MXA) using a 33-point software program designed for adults, on dual-energy x-ray absorptiometry (DXA) images of children. MATERIALS AND METHODS: Lateral spine DXA images of 420 children aged between 5 and 18 years were retrospectively reviewed. Vertebral fracture assessment (VFA) by an expert pediatric radiologist using Genant's semiquantitative scoring system served as the gold standard. All 420 DXA scans were analyzed by a trained radiographer, using semi-automated software (33-point morphometry). VFA of a random sample of 100 DXA was performed by an experienced pediatric clinical scientist. MXA of a random sample of 30 DXA images were analyzed by three pediatric radiologists and the pediatric clinical scientist. Diagnostic accuracy and inter and intraobserver agreement (kappa statistics) were calculated. RESULTS: Overall sensitivity, specificity, false positive (FP) and false negative (FN) rates for the radiographer using the MXA software were 80%, 90%, 10%, and 20% respectively and for mild fractures alone were 46%, 92%, 8%, and 54% respectively. Overall sensitivity, specificity, FP, and FN rates for the four additional observers using MXA were 89%, 79%, 21%, and 11% respectively and for mild fractures alone were 36%, 86%, 14%, and 64% respectively. Agreement between two expert observers was fair to good for VFA and MXA [kappa = 0·29 to 0·76 (95% CI: 0·17-0·88) and 0·29 to 0·69 (95% CI: 0·17-0·83)] respectively. CONCLUSION: MXA using a 33-point technique developed for adults is not a reliable method for the identification of mild vertebral fractures in children. A pediatric standard is required which not only incorporates specific vertebral body height ratios but also the age-related physiological changes in vertebral shape that occur throughout childhood.

Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting.

A widely used approach for locating points on deformable objects in images is to generate feature response images for each point, and then to fit a shape model to these response images. We demonstrate that Random Forest regression-voting can be used to generate high quality response images quickly. Rather than using a generative or a discriminative model to evaluate each pixel, a regressor is used to cast votes for the optimal position of each point. We show that this leads to fast and accurate shape model matching when applied in the Constrained Local Model framework. We evaluate the technique in detail, and compare it with a range of commonly used alternatives across application areas: the annotation of the joints of the hands in radiographs and the detection of feature points in facial images. We show that our approach outperforms alternative techniques, achieving what we believe to be the most accurate results yet published for hand joint annotation and state-of-the-art performance for facial feature point detection.

Quantitative shape analysis with weighted covariance estimates for increased statistical efficiency.

BACKGROUND: The introduction and statistical formalisation of landmark-based methods for analysing biological shape has made a major impact on comparative morphometric analyses. However, a satisfactory solution for including information from 2D/3D shapes represented by 'semi-landmarks' alongside well-defined landmarks into the analyses is still missing. Also, there has not been an integration of a statistical treatment of measurement error in the current approaches. RESULTS: We propose a procedure based upon the description of landmarks with measurement covariance, which extends statistical linear modelling processes to semi-landmarks for further analysis. Our formulation is based upon a self consistent approach to the construction of likelihood-based parameter estimation and includes corrections for parameter bias, induced by the degrees of freedom within the linear model. The method has been implemented and tested on measurements from 2D fly wing, 2D mouse mandible and 3D mouse skull data. We use these data to explore possible advantages and disadvantages over the use of standard Procrustes/PCA analysis via a combination of Monte-Carlo studies and quantitative statistical tests. In the process we show how appropriate weighting provides not only greater stability but also more efficient use of the available landmark data. The set of new landmarks generated in our procedure ('ghost points') can then be used in any further downstream statistical analysis. CONCLUSIONS: Our approach provides a consistent way of including different forms of landmarks into an analysis and reduces instabilities due to poorly defined points. Our results suggest that the method has the potential to be utilised for the analysis of 2D/3D data, and in particular, for the inclusion of information from surfaces represented by multiple landmark points.

TINA manual landmarking tool: software for the precise digitization of 3D landmarks.

BACKGROUND: Interest in the placing of landmarks and subsequent morphometric analyses of shape for 3D data has increased with the increasing accessibility of computed tomography (CT) scanners. However, current computer programs for this task suffer from various practical drawbacks. We present here a free software tool that overcomes many of these problems. RESULTS: The TINA Manual Landmarking Tool was developed for the digitization of 3D data sets. It enables the generation of a modifiable 3D volume rendering display plus matching orthogonal 2D cross-sections from DICOM files. The object can be rotated and axes defined and fixed. Predefined lists of landmarks can be loaded and the landmarks identified within any of the representations. Output files are stored in various established formats, depending on the preferred evaluation software. CONCLUSIONS: The software tool presented here provides several options facilitating the placing of landmarks on 3D objects, including volume rendering from DICOM files, definition and fixation of meaningful axes, easy import, placement, control, and export of landmarks, and handling of large datasets. The TINA Manual Landmark Tool runs under Linux and can be obtained for free from http://www.tina-vision.net/tarballs/.

Endoscopic third ventriculostomy: predicting outcome with phase-contrast MR imaging.

PURPOSE: To determine whether phase-contrast magnetic resonance (MR) imaging measurements of preoperative cerebral blood and cerebrospinal fluid (CSF) hydrodynamics can be used as a biomarker of response to endoscopic third ventriculostomy (ETV). MATERIALS AND METHODS: Approval from the local research ethics committee and written informed consent were obtained for this prospective study. Thirteen patients (six female patients, seven male patients; median age, 43 years) with chronic obstructive hydrocephalus, 12 of whom went on to undergo ETV, were imaged with phase-contrast MR imaging at 1.5 T to determine rates of total cerebral blood flow (CBF) and ventriculostomy defect, foramen magnum (FM), and cerebral aqueduct CSF flow. Ten control subjects (10 men; median age, 37 years) were similarly imaged. Correlations between measured values were assessed by means of Pearson correlation coefficients. Measurements were compared between groups with a Mann-Whitney test, and measurements before and after surgical intervention were compared with a Wilcoxon test for paired samples. RESULTS: Rates of CBF (356 mL . min(-1) +/- 73 [standard deviation] vs 518 mL . min(-1) +/- 79, P < .001) and CSF flow in the FM (17.62 mL . min(-1) +/- 13.12 vs 36.35 mL . min(-1) +/- 8, P < .05) were significantly lower in patients than in control subjects. CONCLUSION: ETV induces changes in brain volume and CBF that can be predicted by using simple metrics. These pilot results support a formal trial of these techniques in a larger prospective study.