Investigation of scatter energy window width and count levels for deep learning-based attenuation map estimation in cardiac SPECT/CT imaging

OBJECTIVE

Deep learning (DL) is becoming increasingly important in generating attenuation maps for accurate attenuation correction in cardiac perfusion SPECT imaging. Typically, DL models take inputs from initial reconstructed SPECT images, which are performed on the photopeak window and often also on scatter windows. While prior studies have demonstrated improvements in DL performance when scatter window images are incorporated into the DL input, the comprehensive analysis of the impact of employing different scatter windows remains unassessed. Additionally, existing research mainly focuses on applying DL to SPECT scans obtained at clinical standard count levels. This study aimed to assess utilities of DL from two aspects: 1) investigating the impact when different scatter windows were used as input to DL, and 2) evaluating the performance of DL when applied on SPECT scans acquired at a reduced count level.

APPROACH

We utilized 1517 subjects, with 386 subjects for testing and the remaining 1131 for training and validation.

MAIN RESULTS

The results showed that as scatter window width increased from 4% to 30%, a slight improvement was observed in DL estimated attenuation maps. The application of DL models to quarter-count (¼-count) SPECT scans, compared to full-count scans, showed a slight reduction in performance. Nonetheless, discrepancies across different scatter window configurations and between count levels were minimal, with all normalized mean square error (NMSE) values remaining within 2.1% when comparing the different DL attenuation maps to the reference CT maps. For attenuation corrected SPECT slices using DL estimated maps, NMSE values were within 0.5% when compared to CT correction.

SIGNIFICANCE

This study, leveraging an extensive clinical dataset, showed that the performance of DL seemed to be consistent across the use of varied scatter window settings. Moreover, our investigation into reduced count studies indicated that DL could provide accurate attenuation correction even at a ¼-count level.

Quantitative reliability assessment of brain MRI volumetric measurements in type II GM1 gangliosidosis patients

Purpose

GM1-gangliosidosis (GM1) leads to extensive neurodegenerative changes and atrophy that precludes the use of automated MRI segmentation techniques for generating brain volumetrics. We developed a standardized segmentation protocol for brain MRIs of patients with type II GM1 and then assessed the inter- and intra-rater reliability of this methodology. The volumetric data may be used as a biomarker of disease burden and progression, and standardized methodology may support research into the natural history of the disease which is currently lacking in the literature.

Approach

Twenty-five brain MRIs were included in this study from 22 type II GM1 patients of which 8 were late-infantile subtype and 14 were juvenile subtype. The following structures were segmented by two rating teams on a slice-by-slice basis: whole brain, ventricles, cerebellum, lentiform nucleus, thalamus, corpus callosum, and caudate nucleus. The inter- and intra-rater reliability of the segmentation method was assessed with an intraclass correlation coefficient as well as Sorensen-Dice and Jaccard coefficients.

Results

Based on the Sorensen-Dice and Jaccard coefficients, the inter- and intra-rater reliability of the segmentation method was significantly better for the juvenile patients compared to late-infantile (p < 0.01). In addition, the agreement between the two rater teams and within themselves can be considered good with all p-values < 0.05.

Conclusions

The standardized segmentation approach described here has good inter- and intra-rater reliability and may provide greater accuracy and reproducibility for neuromorphological studies in this group of patients and help to further expand our understanding of the natural history of this disease.

Auto-segmentation of Adult-Type Diffuse Gliomas: Comparison of Transfer Learning-Based Convolutional Neural Network Model vs. Radiologists

Segmentation of glioma is crucial for quantitative brain tumor assessment, to guide therapeutic research and clinical management, but very time-consuming. Fully automated tools for the segmentation of multi-sequence MRI are needed. We developed and pretrained a deep learning (DL) model using publicly available datasets A (n = 210) and B (n = 369) containing FLAIR, T2WI, and contrast-enhanced (CE)-T1WI. This was then fine-tuned with our institutional dataset (n = 197) containing ADC, T2WI, and CE-T1WI, manually annotated by radiologists, and split into training (n = 100) and testing (n = 97) sets. The Dice similarity coefficient (DSC) was used to compare model outputs and manual labels. A third independent radiologist assessed segmentation quality on a semi-quantitative 5-scale score. Differences in DSC between new and recurrent gliomas, and between uni or multifocal gliomas were analyzed using the Mann-Whitney test. Semi-quantitative analyses were compared using the chi-square test. We found that there was good agreement between segmentations from the fine-tuned DL model and ground truth manual segmentations (median DSC: 0.729, std-dev: 0.134). DSC was higher for newly diagnosed (0.807) than recurrent (0.698) (p < 0.001), and higher for unifocal (0.747) than multi-focal (0.613) cases (p = 0.001). Semi-quantitative scores of DL and manual segmentation were not significantly different (mean: 3.567 vs. 3.639; 93.8% vs. 97.9% scoring ≥ 3, p = 0.107). In conclusion, the proposed transfer learning DL performed similarly to human radiologists in glioma segmentation on both structural and ADC sequences. Further improvement in segmenting challenging postoperative and multifocal glioma cases is needed.

Respiratory signal estimation for cardiac perfusion SPECT using deep learning

BACKGROUND

Respiratory motion induces artifacts in reconstructed cardiac perfusion SPECT images. Correction for respiratory motion often relies on a respiratory signal describing the heart displacements during breathing. However, using external tracking devices to estimate respiratory signals can add cost and operational complications in a clinical setting.

PURPOSE

We aim to develop a deep learning (DL) approach that uses only SPECT projection data for respiratory signal estimation.

METHODS

A modified U-Net was implemented that takes temporally finely sampled SPECT sub-projection data (100 ms) as input. These sub-projections are obtained by reframing the 20-s list-mode data, resulting in 200 sub-projections, at each projection angle for each SPECT camera head. The network outputs a 200-time-point motion signal for each projection angle, which was later aggregated over all angles to give a full respiratory signal. The target signal for DL model training was from an external stereo-camera visual tracking system (VTS). In addition to comparing DL and VTS, we also included a data-driven approach based on the center-of-mass (CoM) strategy. This CoM method estimates respiratory signals by monitoring the axial changes of CoM for counts in the heart region of the sub-projections. We utilized 900 subjects with stress cardiac perfusion SPECT studies, with 302 subjects for testing and the remaining 598 subjects for training and validation.

RESULTS

The Pearson's correlation coefficient between the DL respiratory signal and the reference VTS signal was 0.90, compared to 0.70 between the CoM signal and the reference. For respiratory motion correction on SPECT images, all VTS, DL, and CoM approaches partially de-blured the heart wall, resulting in a thinner wall thickness and increased recovered maximal image intensity within the wall, with VTS reducing blurring the most followed by the DL approach. Uptake quantification for the combined anterior and inferior segments of polar maps showed a mean absolute difference from the reference VTS of 1.7% for the DL method for patients with motion >12 mm, compared to 2.6% for the CoM method and 8.5% for no correction.

CONCLUSION

We demonstrate the capability of a DL approach to estimate respiratory signal from SPECT projection data for cardiac perfusion imaging. Our results show that the DL based respiratory motion correction reduces artefacts and achieves similar regional quantification to that obtained using the stereo-camera VTS signals. This may enable fully automatic data-driven respiratory motion correction without relying on external motion tracking devices.

Observer studies of image quality of denoising reduced-count cardiac single photon emission computed tomography myocardial perfusion imaging by three-dimensional Gaussian post-reconstruction filtering and deep learning

BACKGROUND

The aim of this research was to asses perfusion-defect detection-accuracy by human observers as a function of reduced-counts for 3D Gaussian post-reconstruction filtering vs deep learning (DL) denoising to determine if there was improved performance with DL.

METHODS

SPECT projection data of 156 normally interpreted patients were used for these studies. Half were altered to include hybrid perfusion defects with defect presence and location known. Ordered-subset expectation-maximization (OSEM) reconstruction was employed with the optional correction of attenuation (AC) and scatter (SC) in addition to distance-dependent resolution (RC). Count levels varied from full-counts (100%) to 6.25% of full-counts. The denoising strategies were previously optimized for defect detection using total perfusion deficit (TPD). Four medical physicist (PhD) and six physician (MD) observers rated the slices using a graphical user interface. Observer ratings were analyzed using the LABMRMC multi-reader, multi-case receiver-operating-characteristic (ROC) software to calculate and compare statistically the area-under-the-ROC-curves (AUCs).

RESULTS

For the same count-level no statistically significant increase in AUCs for DL over Gaussian denoising was determined when counts were reduced to either the 25% or 12.5% of full-counts. The average AUC for full-count OSEM with solely RC and Gaussian filtering was lower than for the strategies with AC and SC, except for a reduction to 6.25% of full-counts, thus verifying the utility of employing AC and SC with RC.

CONCLUSION

We did not find any indication that at the dose levels investigated and with the DL network employed, that DL denoising was superior in AUC to optimized 3D post-reconstruction Gaussian filtering.

Assessment of thrombectomy procedure difficulty by neurointerventionalists based on vessel geometry parameters from carotid artery 3D reconstructions

BACKGROUND

Diagnosing and treating acute ischemic stroke patients within a narrow timeframe is challenging. Time needed to access the occluded vessel and initiate thrombectomy is dictated by the availability of information regarding vascular anatomy and trajectory. Absence of such information potentially impacts device selection, procedure success, and stroke outcomes. While the cervical vessels allow neurointerventionalists to navigate devices to the occlusion site, procedures are often encumbered due to tortuous pathways. The purpose of this retrospective study was to determine how neurointerventionalists consider the physical nature of carotid segments when evaluating a procedure's difficulty.

METHODS

Seven neurointerventionalists reviewed 3D reconstructions of CT angiograms of left and right carotid arteries from 49 subjects and rated the perceived procedural difficulty on a three-point scale (easy, medium, difficult) to reach the targeted M1. Twenty-two vessel metrics were quantified by dividing the carotids into 5 segments and measuring the radius of curvature, tortuosity, vessel radius, and vessel length of each segment.

RESULTS

The tortuosity and length of the arch-cervical and cervical regions significantly impacted difficulty ratings. Additionally, two-way interaction between the radius of curvature and tortuosity on the arch-cervical region was significant (p < 0.0001) wherein, for example, at a given arch-cervical tortuosity, an increased radius of curvature reduced the perceived case difficulty.

CONCLUSIONS

Examining the vessel metrics and providing detailed vascular data tailored to patient characteristics may result in better procedure preparation, facilitate faster vessel access time, and improve thrombectomy outcomes. Additionally, documenting these correlations can enhance device design to ensure they suitably function under various vessel conditions.

Silica-Coated Micrometer-Sized Latex Particles

A series of silica-coated micrometer-sized poly(methyl methacrylate) latex particles are prepared using a Stöber silica deposition protocol that employs tetraethyl orthosilicate (TEOS) as a soluble silica precursor. Given the relatively low specific surface area of the latex particles, silica deposition is best conducted at relatively high solids to ensure a sufficiently high surface area. Such conditions aid process intensification. Importantly, physical adsorption of chitosan onto the latex particles prior to silica deposition minimizes secondary nucleation and promotes the formation of silica shells: in the absence of chitosan, well-defined silica overlayers cannot be obtained. Thermogravimetry studies indicate that silica formation is complete within a few hours at 20 °C regardless of the presence or absence of chitosan. Kinetic data obtained using this technique suggest that the adsorbed chitosan chains promote surface deposition of silica onto the latex particles but do not catalyze its formation. Systematic variation of the TEOS/latex mass ratio enables the mean silica shell thickness to be tuned from 45 to 144 nm. Scanning electron microscopy (SEM) studies of silica-coated latex particles after calcination at 400 °C confirm the presence of hollow silica particles, which indicates the formation of relatively smooth (albeit brittle) silica shells under optimized conditions. Aqueous electrophoresis and X-ray photoelectron spectroscopy studies are also consistent with latex particles coated in a uniform silica overlayer. The silica deposition formulation reported herein is expected to be a useful generic strategy for the efficient coating of micrometer-sized particles at relatively high solids.

Mesh modeling of system geometry and anatomy phantoms for realistic GATE simulations and their inclusion in SPECT reconstruction

Objective.Monte-Carlo simulation studies have been essential for advancing various developments in single photon emission computed tomography (SPECT) imaging, such as system design and accurate image reconstruction. Among the simulation software available, Geant4 application for tomographic emission (GATE) is one of the most used simulation toolkits in nuclear medicine, which allows building systems and attenuation phantom geometries based on the combination of idealized volumes. However, these idealized volumes are inadequate for modeling free-form shape components of such geometries. Recent GATE versions alleviate these major limitations by allowing users to import triangulated surface meshes.Approach.In this study, we describe our mesh-based simulations of a next-generation multi-pinhole SPECT system dedicated to clinical brain imaging, called AdaptiSPECT-C. To simulate realistic imaging data, we incorporated in our simulation the XCAT phantom, which provides an advanced anatomical description of the human body. An additional challenge with the AdaptiSPECT-C geometry is that the default voxelized XCAT attenuation phantom was not usable in our simulation due to intersection of objects of dissimilar materials caused by overlap of the air containing regions of the XCAT beyond the surface of the phantom and the components of the imaging system.Main results.We validated our mesh-based modeling against the one constructed by idealized volumes for a simplified single vertex configuration of AdaptiSPECT-C through simulated projection data of123I-activity distributions. We resolved the overlap conflict by creating and incorporating a mesh-based attenuation phantom following a volume hierarchy. We then evaluated our reconstructions with attenuation and scatter correction for projections obtained from simulation consisting of mesh-based modeling of the system and the attenuation phantom for brain imaging. Our approach demonstrated similar performance as the reference scheme simulated in air for uniform and clinical-like123I-IMP brain perfusion source distributions.Significance.This work enables the simulation of complex SPECT acquisitions and reconstructions for emulating realistic imaging data close to those of actual patients.

Chronic Wound Image Augmentation and Assessment Using Semi-Supervised Progressive Multi-Granularity EfficientNet

Goal: Augment a small, imbalanced, wound dataset by using semi-supervised learning with a secondary dataset. Then utilize the augmented wound dataset for deep learning-based wound assessment. Methods: The clinically-validated Photographic Wound Assessment Tool (PWAT) scores eight wound attributes: Size, Depth, Necrotic Tissue Type, Necrotic Tissue Amount, Granulation Tissue type, Granulation Tissue Amount, Edges, Periulcer Skin Viability to comprehensively assess chronic wound images. A small corpus of 1639 wound images labeled with ground truth PWAT scores was used as reference. A Semi-Supervised learning and Progressive Multi-Granularity training mechanism were used to leverage a secondary corpus of 9870 unlabeled wound images. Wound scoring utilized the EfficientNet Convolutional Neural Network on the augmented wound corpus. Results: Our proposed Semi-Supervised PMG EfficientNet (SS-PMG-EfficientNet) approach estimated all 8 PWAT sub-scores with classification accuracies and F1 scores of about 90% on average, and outperformed a comprehensive list of baseline models and had a 7% improvement over the prior state-of-the-art (without data augmentation). We also demonstrate that synthetic wound image generation using Generative Adversarial Networks (GANs) did not improve wound assessment. Conclusions: Semi-supervised learning on unlabeled wound images in a secondary dataset achieved impressive performance for deep learning-based wound grading.

A Smartphone Physical Activity App for Patients in Alcohol Treatment: Single-Arm Feasibility Trial

BACKGROUND

Alcohol use disorder (AUD) is a significant public health concern worldwide. Alcohol consumption is a leading cause of death in the United States and has a significant negative impact on individuals and society. Relapse following treatment is common, and adjunct intervention approaches to improve alcohol outcomes during early recovery continue to be critical. Interventions focused on increasing physical activity (PA) may improve AUD treatment outcomes. Given the ubiquity of smartphones and activity trackers, integrating this technology into a mobile app may be a feasible, acceptable, and scalable approach for increasing PA in individuals with AUD.

OBJECTIVE

This study aims to test the Fit&Sober app developed for patients with AUD. The goals of the app were to facilitate self-monitoring of PA engagement and daily mood and alcohol cravings, increase awareness of immediate benefits of PA on mood and cravings, encourage setting and adjusting PA goals, provide resources and increase knowledge for increasing PA, and serve as a resource for alcohol relapse prevention strategies.

METHODS

To preliminarily test the Fit&Sober app, we conducted an open pilot trial of patients with AUD in early recovery (N=22; 13/22, 59% women; mean age 43.6, SD 11.6 years). At the time of hospital admission, participants drank 72% of the days in the last 3 months, averaging 9 drinks per drinking day. The extent to which the Fit&Sober app was feasible and acceptable among patients with AUD during early recovery was examined. Changes in alcohol consumption, PA, anxiety, depression, alcohol craving, and quality of life were also examined after 12 weeks of app use.

RESULTS

Participants reported high levels of satisfaction with the Fit&Sober app. App metadata suggested that participants were still using the app approximately 2.5 days per week by the end of the intervention. Pre-post analyses revealed small-to-moderate effects on increase in PA, from a mean of 5784 (SD 2511) steps per day at baseline to 7236 (SD 3130) steps per day at 12 weeks (Cohen d=0.35). Moderate-to-large effects were observed for increases in percentage of abstinent days (Cohen d=2.17) and quality of life (Cohen d=0.58) as well as decreases in anxiety (Cohen d=-0.71) and depression symptoms (Cohen d=-0.58).

CONCLUSIONS

The Fit&Sober app is an acceptable and feasible approach for increasing PA in patients with AUD during early recovery. A future randomized controlled trial is necessary to determine the efficacy of the Fit&Sober app for long-term maintenance of PA, ancillary mental health, and alcohol outcomes. If the efficacy of the Fit&Sober app could be established, patients with AUD would have a valuable adjunct to traditional alcohol treatment that can be delivered in any setting and at any time, thereby improving the overall health and well-being of this population.

TRIAL REGISTRATION

ClinicalTrials.gov NCT02958280; https://www.clinicaltrials.gov/ct2/show/NCT02958280.

Cumulative effect of simvastatin, L-arginine, and tetrahydrobiopterin on cerebral blood flow and cognitive function in Alzheimer's disease

BACKGROUND AND OBJECTIVES

Vascular disease is a known risk factor for Alzheimer's disease (AD). Endothelial dysfunction has been linked to reduced cerebral blood flow. Endothelial nitric oxide synthase pathway (eNOS) upregulation is known to support endothelial health. This single-center, proof-of-concept study tested whether the use of three medications known to augment the eNOS pathway activity improves cognition and cerebral blood flow (CBF).

METHODS

Subjects with mild AD or mild cognitive impairment (MCI) were sequentially treated with the HMG-CoA reductase synthesis inhibitor simvastatin (weeks 0-16), L-arginine (weeks 4-16), and tetrahydrobiopterin (weeks 8-16). The primary outcome of interest was the change in CBF as measured by MRI from baseline to week 16. Secondary outcomes included standard assessments of cognition.

RESULTS

A total of 11 subjects were deemed eligible and enrolled. One subject withdrew from the study after enrollment, leaving 10 subjects for data analysis. There was a significant increase in CBF from baseline to week 8 by ~13% in the limbic and ~15% in the cerebral cortex. Secondary outcomes indicated a modest but significant increase in the MMSE from baseline (24.2±3.2) to week 16 (26.0±2.7). Exploratory analysis indicated that subjects with cognitive improvement (reduction of the ADAS-cog 13) had a significant increase in their respective limbic and cortical CBF.

CONCLUSIONS

Treatment of mild AD/MCI subjects with medications shown to augment the eNOS pathway was well tolerated and associated with modestly increased cerebral blood flow and cognitive improvement.

TRIAL REGISTRATION

This study is registered in https://www.

CLINICALTRIALS

gov ; registration identifier: NCT01439555; date of registration submitted to registry: 09/23/2011; date of first subject enrollment: 11/2011.

Exploring Factors Associated With Mobile Phone Behaviors and Attitudes Toward Technology Among Adults With Alcohol Use Disorder and Implications for mHealth Interventions: Exploratory Study

BACKGROUND

Alcohol use disorder (AUD) is associated with severe chronic medical conditions and premature mortality. Expanding the reach or access to effective evidence-based treatments to help persons with AUD is a public health objective. Mobile phone or smartphone technology has the potential to increase the dissemination of clinical and behavioral interventions (mobile health interventions) that increase the initiation and maintenance of sobriety among individuals with AUD. Studies about how this group uses their mobile phone and their attitudes toward technology may have meaningful implications for participant engagement with these interventions.

OBJECTIVE

This exploratory study examined the potential relationships among demographic characteristics (race, gender, age, marital status, and income), substance use characteristics (frequency of alcohol and cannabis use), and clinical variables (anxiety and depression symptoms) with indicators of mobile phone use behaviors and attitudes toward technology.

METHODS

A sample of 71 adults with AUD (mean age 42.9, SD 10.9 years) engaged in an alcohol partial hospitalization program completed 4 subscales from the Media Technology Usage and Attitudes assessment: Smartphone Usage measures various mobile phone behaviors and activities, Positive Attitudes and Negative Attitudes measure attitudes toward technology, and the Technological Anxiety/Dependence measure assesses level of anxiety when individuals are separated from their phone and dependence on this device. Participants also provided demographic information and completed the Epidemiologic Studies Depression Scale (CES-D) and the Generalized Anxiety Disorder (GAD-7) scale. Lastly, participants reported their frequency of alcohol use over the past 3 months using the Drug Use Frequency Scale.

RESULTS

Results for the demographic factors showed a significant main effect for age, Smartphone Usage (P=.003; ηp2=0.14), and Positive Attitudes (P=.01; ηp2=0.07). Marital status (P=.03; ηp2=0.13) and income (P=.03; ηp2=0.14) were associated only with the Technological Anxiety and Dependence subscale. Moreover, a significant trend was found for alcohol use and the Technological Anxiety/Dependence subscale (P=.06; R2=0.02). Lastly, CES-D scores (P=.03; R2=0.08) and GAD symptoms (P=.004; R2=0.13) were significant predictors only of the Technological Anxiety/Dependence subscale.

CONCLUSIONS

Findings indicate differences in mobile phone use patterns and attitudes toward technology across demographic, substance use, and clinical measures among patients with AUD. These results may help inform the development of future mHealth interventions among this population.

Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN With Context-Preserving Attention

Goal: Chronic wounds affect 6.5 million Americans. Wound assessment via algorithmic analysis of smartphone images has emerged as a viable option for remote assessment. Methods: We comprehensively score wounds based on the clinically-validated Photographic Wound Assessment Tool (PWAT), which comprehensively assesses clinically important ranges of eight wound attributes: Size, Depth, Necrotic Tissue Type, Necrotic Tissue Amount, Granulation Tissue type, Granulation Tissue Amount, Edges, Periulcer Skin Viability. We proposed a DenseNet Convolutional Neural Network (CNN) framework with patch-based context-preserving attention to assess the 8 PWAT attributes of four wound types: diabetic ulcers, pressure ulcers, vascular ulcers and surgical wounds. Results: In an evaluation on our dataset of 1639 wound images, our model estimated all 8 PWAT sub-scores with classification accuracies and F1 scores of over 80%. Conclusions: Our work is the first intelligent system that autonomously grades wounds comprehensively based on criteria in the PWAT rubric, alleviating the significant burden that manual wound grading imposes on wound care nurses.

Transitioning a cardiovascular health and rehabilitation programme to a virtual platform during covid 19

Funding Acknowledgements

Type of funding sources: None.

OnBehalf

Our Hearts Our Minds

Purpose

Can a virtual cardiovascular prevention and rehabilitation programme be as effective as face-to-face programme.

Background

The Our Hearts Our Minds (OHOM) prevention and rehabilitation programme rapidly transitioned to a virtual platform in the covid era.  Here we compare if a virtual programme potentially could offer the same standard of the nursing intervention (education, smoking cessation, medical risk factor management and psychosocial health) as the previous face to face programme

Methods

Both the initial assessment (IA) and end of programme (EOP) assessments were conducted via telephone/video as per patient preference. The following measures were recorded at both time points (home blood pressure (BP) monitors were provided)

Smoking (self report) BP/Heart rate, Lipids/HbA1c (facilitated by phlebotomy hub), cardio protective drugs (doses, adherence), Hospital Anxiety and Depression score, EuroQoL

Nursing Intervention Smoking cessation counselling and pharmacotherapy where appropriate

Weekly meeting with cardiologist to optimise BP and lipid management and up titration cardio protective drugs

Bimonthly virtual coaching consultation for monitoring/goal resetting

Bimonthly group video education sessions

Results

From April to November 2020, of the 432 referrals received 400 were eligible with 377 accepting the offer of an IA (94% response rate). 262 have had an IA with the remaining 115 awaiting an assessment date.  Of the completed IA’s 257 were willing to attend the programme (98% uptake).  120 had been offered an end of programme assessment with 114 attending (96% of those offered). The results for the virtual programme were then compared to the same period one year previously when the programme was fully face to face and are outlined in the table below.

The comparison of results delivered via remote delivery are remarkably similar to those achieved in the previous year delivered via face to face.

Conclusion

Initial data has shown that virtual delivery of the nursing component of the OHOM prevention/rehabilitation programme was highly acceptable to patients and was as effective as that of the traditional face to face service.

Table 1 below exhibits the clinical and patient-reported outcomes.

OP0229 THE GROUP FOR RESEARCH AND ASSESSMENT OF PSORIASIS AND PSORIATIC ARTHRITIS (GRAPPA) TREATMENT RECOMMENDATIONS 2021

Background:

Since the 2015 GRAPPA treatment recommendations were published, therapeutic options and management strategies for psoriatic arthritis (PsA) have advanced considerably.

Objectives:

The goal of the GRAPPA recommendations update is to develop high quality, evidence-based recommendations for the treatment of PsA, including related conditions and comorbidities.

Methods:

GRAPPA rheumatologists, dermatologists and patient research partners (PRPs) updated overarching principles for the management of adults with PsA by consensus. Principles considering use of biosimilars and tapering/discontinuing of therapy were added to this update. Systematic literature searches based on data publicly available from three databases (MEDLINE, EMBASE, and Cochrane CENTRAL) were conducted from the end of the previous recommendations’ searches through August 2020. Additional abstract searches were performed for conference presentations in 2017-2020. Searches covered PsA treatments (peripheral arthritis, axial arthritis, enthesitis, dactylitis, skin, and nail disease). Additional searches were performed for related conditions (uveitis and IBD) and comorbidities evaluating their impact on safety and treatment outcomes. Individual groups assessed the risk of bias and applied the GRADE system to generate strong or conditional recommendations for therapies within the domain groups and for the management of comorbidities and related conditions. These recommendations were then incorporated into an overall treatment schema.

Results:

Updated, evidence-based treatment recommendations are shown (Table 1). Since 2015, many new medications have been incorporated. Additional results for older medications, such as methotrexate, have been published across PsA domains. Based on the evidence, the treatment recommendations developed by individual groups were incorporated into the overall schema including principles for management of arthritis, spondylitis, enthesitis, dactylitis, skin, and nail disease in PsA, and associated conditions (Figure 1). Choice of therapy for an individual should ideally address all of the domains that impact on that patient, supporting shared decision making with the patient involved. Additional consideration in the recommendations was given to key associated conditions and comorbidities as these often impact on therapy choice.

Conclusion:

These GRAPPA treatment recommendations provide up to date, evidence-based guidance to providers who manage and treat adult patients with PsA. These recommendations are based on domain-based strategy for PsA and supplemented by overarching principles developed by consensus of GRAPPA members.

IndicationStrongForConditional ForConditionalAgainstStrongAgainstInsufficient evidencePeripheral Arthritis DMARD NaïvecsDMARDs, TNFi, PDE4i, IL-12/23i, IL-17i, IL-23i, JAKiNSAIDs, oral CS, IA CS,IL-6i,Peripheral Arthritis DMARD IRTNFi, IL-12/23i, IL-17i, IL-23i, JAKiPDE4i, other csDMARD, NSAIDs, oral CS, IA CS,IL-6i,Peripheral ArthritisbDMARD IRTNFi, IL-17i, IL-23i, JAKi,NSAIDs, oral CS, IA CS, IL-12/23i, PDE4i, CTLA-4-IgIL-6i,Axial arthritis, Biologic NaïveNSAIDs, Physiotherapy, simple analgesia, TNFi, IL-17i, JAKiCS SIJ injections, bisphosphonatescsDMARDs, IL-6i,IL-12/23i, IL-23iAxial PsA, Biologic IRNSAIDs, Physiotherapy, simple analgesia, TNFi, IL-17i, JAKi csDMARDs, IL-6i,IL-12/23i, IL-23iEnthesitisTNFi, IL-12/23i, IL-17i, PDE4i, IL-23i, JAKiNSAIDs, physiotherapy, CS injections, MTXIL-6i,Other csDMARDsDactylitisTNFi IL-12/23i, IL-17i, IL-23i, JAKi, PDE4iNSAIDs, CS injections, MTXOther csDMARDsPsoriasisTopicals, phototherapy, csDMARDs, TNFi, IL-12/23i, IL-17i, IL-23i, PDE4i, JAKi AcitretinNail psoriasisTNFi, IL12/23i, IL17i, IL23i, PDE4iTopical CS, tacrolimus and calcipotriol combination or individual therapies, Pulsed dye laser, csDMARDs, acitretin, JAKiTopical Cyclosporine / Tazarotene, Fumarate, Fumaric Acid Esters, UVA and UVB Phototherapy, AlitretinoinIBDTNFi (not ETN), IL-12/23i, JAKiIL-17iUveitisTNFi (not ETN)

Disclosure of Interests:

Laura C Coates Speakers bureau: AbbVie, Amgen, Biogen, Celgene, Gilead, Eli Lilly, Janssen, Medac, Novartis, Pfizer, and UCB, Consultant of: AbbVie, Amgen, Boehringer Ingelheim, Bristol-Myers Squibb, Celgene, Eli Lilly, Gilead, Janssen, Novartis, Pfizer, and UCB, Grant/research support from: AbbVie, Amgen, Celgene, Eli Lilly, Pfizer, and Novartis, Enrique Soriano Speakers bureau: AbbVie, Amgen, Bristol-Myers Squibb,GSK, Genzyme, Janssen, Lilly, Novartis, Pfizer, Roche, Sandoz, Sanofi, UCB, Consultant of: AbbVie, Amgen, Bristol-Myers Squibb,GSK, Genzyme, Janssen, Lilly, Novartis, Pfizer, Roche, Sandoz, Sanofi, UCB, Grant/research support from: AbbVie, Janssen, Novartis Pharma, Pfizer, Roche, and UCB, Nadia Corp: None declared, Heidi Bertheussen Consultant of: Pfizer, Kristina Callis-Duffin Consultant of: AbbVie, Amgen, Bristol-Myers Squibb, Celgene, Lilly, Janssen, Novartis, Pfizer, Sienna Biopharmaceuticals, Stiefel Laboratories, UCB, Ortho Dermatologics, Inc, Regeneron Pharmaceuticals, Inc., Anaptys Bio, Boehringer Ingelheim., Cristiano Barbosa Campanholo Speakers bureau: AbbVie, Eli Lilly, Janssen, Novartis, Pfizer, and UCB, Consultant of: AbbVie, Bristol-Myers Squibb, Eli Lilly, Janssen, Novartis, Pfizer, and UCB, Jeffrey Chau: None declared, Lihi Eder Consultant of: Abbvie, UCB, Janssen, Eli Lily, Pfizer, Novartis, Grant/research support from: Abbvie, UCB, Janssen, Eli Lily, Pfizer, Novartis, Daniel Fernandez Consultant of: Abbvie, UCB, Roche, Janssen, Pfizer, Amgen and Brystol, Grant/research support from: Abbvie, UCB, Roche, Janssen, Pfizer, Amgen and Brystol, Oliver FitzGerald Speakers bureau: AbbVie, Janssen and Pfizer Inc, Consultant of: BMS, Celgene, Eli Lilly, Janssen and Pfizer Inc, Grant/research support from: AbbVie, BMS, Eli Lilly, Novartis and Pfizer Inc, Amit Garg Consultant of: Abbvie, Amgen, Asana Biosciences, Bristol Myers Squibb, Boehringer Ingelheim, Incyte, InflaRx, Janssen, Pfizer, UCB, Viela Biosciences, Grant/research support from: Abbvie, Dafna D Gladman Consultant of: Abbvie, Amgen, BMS, Eli Lilly, Galapagos, Gilead, Jansen, Novartis, Pfizer and UCB, Grant/research support from: Abbvie, Amgen, Eli Lilly, Jansen, Novartis, Pfizer and UCB, Niti Goel: None declared, Suzanne Grieb: None declared, Philip Helliwell Speakers bureau: Janssen, Novartis, Pfizer, Consultant of: Eli Lilly, M Elaine Husni Consultant of: Abbvie, Amgen, Janssen, Novartis, Lilly, UCB, Regeneron, and Pfizer, Deepak Jadon Speakers bureau: AbbVie, Amgen, Celgene, Eli Lilly, Gilead, Healthcare Celltrion, Janssen, MSD, Novartis, Pfizer, Roche, Sandoz, UCB, Consultant of: AbbVie, Amgen, Celgene, Eli Lilly, Gilead, Healthcare Celltrion, Janssen, MSD, Novartis, Pfizer, Roche, Sandoz, UCB, Grant/research support from: AbbVie, Amgen, Celgene, Eli Lilly, Gilead, Healthcare Celltrion, Janssen, MSD, Novartis, Pfizer, Roche, Sandoz, UCB, Arnon Katz: None declared, Dhruvkumar Laheru: None declared, John Latella: None declared, Ying Ying Leung Speakers bureau: Novartis, AbbVie, Eli Lilly, Janssen, Consultant of: Pfizer and Boehringer Ingelheim, Grant/research support from: Pfizer and conference support from AbbVie, Christine Lindsay Shareholder of: Amgen, Employee of: Aurinia pharmaceuticals, Ennio Lubrano Speakers bureau: Alfa-Sigma, Abbvie, Galapagos, Janssen Cilag, Lilly., Consultant of: Alfa-Sigma, Abbvie, Galapagos, Janssen Cilag, Lilly., Luis Mazzuoccolo Speakers bureau: Abbvie, Amgen, Novartis, Elli Lilly, Jansen, Consultant of: Abbvie, Amgen, Novartis, Elli Lilly, Jansen, Roland McDonald: None declared, Philip J Mease Speakers bureau: AbbVie, Amgen, Eli Lilly, Janssen, Novartis, Pfizer and UCB, Consultant of: AbbVie, Amgen, Boehringer Ingelheim, Bristol-Myers Squibb, Eli Lilly, Galapagos, Gilead Sciences, GlaxoSmithKline, Janssen, Novartis, Pfizer, SUN and UCB, Grant/research support from: AbbVie, Amgen, Bristol-Myers Squibb, Celgene, Eli Lilly, Galapagos, Gilead Sciences, Janssen, Novartis, Pfizer, SUN and UCB, Denis O’Sullivan: None declared, Alexis Ogdie Consultant of: AbbVie, Amgen, BMS, Celgene, Corrona, Gilead, Janssen, Lilly, Novartis, and Pfizer, Grant/research support from: Novartis and Pfizer and Amgen, Wendy Olsder: None declared, Lori Schick: None declared, Ingrid Steinkoenig: None declared, Maarten de Wit Consultant of: AbbVie, BMS, Celgene, Janssen, Lilly, Novartis, Pfizer, Roche, Danielle van der Windt: None declared, Arthur Kavanaugh Speakers bureau: AbbVie, Amgen, BMS, Eli Lilly, Gilead Janssen, Novartis, Pfizer, UCB, Consultant of: AbbVie, Amgen, BMS, Eli Lilly, Gilead Janssen, Novartis, Pfizer, UCB

Machine learning models for synthesizing actionable care decisions on lower extremity wounds

Lower extremity chronic wounds affect 4.5 million Americans annually. Due to inadequate access to wound experts in underserved areas, many patients receive non-uniform, non-standard wound care, resulting in increased costs and lower quality of life. We explored machine learning classifiers to generate actionable wound care decisions about four chronic wound types (diabetic foot, pressure, venous, and arterial ulcers). These decisions (target classes) were: (1) Continue current treatment, (2) Request non-urgent change in treatment from a wound specialist, (3) Refer patient to a wound specialist. We compare classification methods (single classifiers, bagged & boosted ensembles, and a deep learning network) to investigate (1) whether visual wound features are sufficient for generating a decision and (2) whether adding unstructured text from wound experts increases classifier accuracy. Using 205 wound images, the Gradient Boosted Machine (XGBoost) outperformed other methods when using both visual and textual wound features, achieving 81% accuracy. Using only visual features decreased the accuracy to 76%, achieved by a Support Vector Machine classifier. We conclude that machine learning classifiers can generate accurate wound care decisions on lower extremity chronic wounds, an important step toward objective, standardized wound care. Higher decision-making accuracy was achieved by leveraging clinical comments from wound experts.

Semantic Segmentation of Smartphone Wound Images: Comparative Analysis of AHRF and CNN-Based Approaches

Smartphone wound image analysis has recently emerged as a viable way to assess healing progress and provide actionable feedback to patients and caregivers between hospital appointments. Segmentation is a key image analysis step, after which attributes of the wound segment (e.g. wound area and tissue composition) can be analyzed. The Associated Hierarchical Random Field (AHRF) formulates the image segmentation problem as a graph optimization problem. Handcrafted features are extracted, which are then classified using machine learning classifiers. More recently deep learning approaches have emerged and demonstrated superior performance for a wide range of image analysis tasks. FCN, U-Net and DeepLabV3 are Convolutional Neural Networks used for semantic segmentation. While in separate experiments each of these methods have shown promising results, no prior work has comprehensively and systematically compared the approaches on the same large wound image dataset, or more generally compared deep learning vs non-deep learning wound image segmentation approaches. In this paper, we compare the segmentation performance of AHRF and CNN approaches (FCN, U-Net, DeepLabV3) using various metrics including segmentation accuracy (dice score), inference time, amount of training data required and performance on diverse wound sizes and tissue types. Improvements possible using various image pre- and post-processing techniques are also explored. As access to adequate medical images/data is a common constraint, we explore the sensitivity of the approaches to the size of the wound dataset. We found that for small datasets (< 300 images), AHRF is more accurate than U-Net but not as accurate as FCN and DeepLabV3. AHRF is also over 1000x slower. For larger datasets (> 300 images), AHRF saturates quickly, and all CNN approaches (FCN, U-Net and DeepLabV3) are significantly more accurate than AHRF.

Do Novice and Expert Users of Clinical Decision Support Tools Need Different Explanations?

A key requirement for the successful adoption of clinical decision support systems (CDSS) is their ability to provide users with reliable explanations for any given recommendation which can be challenging for some tasks such as wound management decisions. Despite the abundance of decision guidelines, wound non-expert (novice hereafter) clinicians who usually provide most of the treatments still have decision uncertainties. Our goal is to evaluate the use of a Wound CDSS smartphone App that provides explanations for recommendations it produces. The App utilizes wound images taken by the novice clinician using smartphone camera. This study experiments with two proposed variations of rule-tracing explanations called verbose-based and gist-based. Deriving upon theories of decision making, and unlike prior literature that says rule-tracing explanations are only preferred by novices, we hypothesize that, rule-tracing explanations are preferred by both clinicians but in different forms: novices prefer verbose-based rule-tracing and experts prefer gist-based rule-tracing.

AB0794 CLINICAL TRIAL DISCRIMINATION OF PHYSICAL FUNCTION INSTRUMENTS FOR PSORIATIC ARTHRITIS: A SYSTEMATIC REVIEW

Background:

Physical function is a core domain to be measured in randomized controlled trials (RCTs) of psoriatic arthritis (PsA). The discriminative performance of patient reported outcome measures (PROMs) for physical function (PF) in RCTs has not been evaluated systematically.

Objectives:

In this systematic review, the GRAPPA-OMERACT working group aimed to evaluate the clinical trial discrimination of PF-PROMs in PsA RCTs.

Methods:

We searched PubMed and Scopus databases in English to identify all original RCTs conducted in PsA. We limited the review to RCTs of biologic and targeted synthetic DMARDs. Groups of two researchers extracted data independently for PF-PROMs. We assessed quality in each article using the OMERACT good method checklist. Effect sizes (ES) for the PF-PROMs were calculated and appraised usinga priorihypotheses. Evidence supporting clinical trial discrimination for each PF-PROM was summarized to derive recommendations.

Results:

32 articles were included (Figure 1). Four PF-PROMs had data for evaluation: HAQ-Disability Index (DI), HAQ-Spondyloarthritis (S), Short Form 36-item Health Survey Physical Component Summary (SF-36 PCS), and the Physical Functioning domain (SF-36 PF) (Table 1). The ES for intervention versus (vs.) control arms for HAQ-DI ranged from -0.55 to -1.81 vs. 0.24 to -0.52; and for SF-36 PCS ranged from 0.30 to 1.86 vs. -0.02 to 0.63.

Table 1.

Summary of Measurement Properties Table for clinical trial discrimination

ArticlesHAQ-DIHAQ-SSF-36 PCSSF-36 PFAntoni 2005 (IMPACT); Gottlieb 2009 (UST)+Antoni 2005 (IMPACT2)++Kavanaugh 2006 (IMPACT2)+Mease 2005 (ADEPT); Genovese 2007 (ADA); Mease 2010 (ETN); Kavanaugh 2009 (GO-REVEAL); Kavanaugh 2017 (GO-VIBRANT); Gladman 2014 (RAPID-PsA); Mease 2015 (FUTURE1); McInnes 2015 (FUTURE2); Kavanaugh, 2016 (FUTURE2)-subgroup; Nash 2018 (FUTURE3); Mease 2017 (SPIRIT-P1); Nash 2017 (SPIRIT-P2); Deodhar 2018 (GUS); Mease 2016 (CLZ)++Mease 2000 (ETN); McInne, 2013 (PSUMMIT 1); Ritchlin 2014 (PSUMMIT 2); Araugo 2019 (ECLIPSA)++Gniadecki 2012 (PRESTA)+Mease 2019 (SEAM-PsA)+/-+McInnes 2014 (SEC)++Mease 2014 (BRO)++Mease 2011 (ABT)+/-+Mease 2017 (ASTRAEA)++Mease 2006 (ALC)+/-Mease 2017 (OPAL Broaden); Gladman 2017 (OPAL Beyond)++Mease 2018 (EQUATOR)++Mease 2018 (ABT-122)+Total available articles311244Total articles for evidence synthesis291232Overall rating+++

Color code in each box indicate study quality by OMERACT good methods. GREEN: “likely low risk of bias”; AMBER: “some cautions but can be used as evidence”; RED: “don’t use as evidence”. WHITE (empty boxes): absence of information from that study. (+): findings had adequate performance of the instrument; (+/-): equivocal performance; (-): poor performance (less than adequate).

Conclusion:

Clinical trial discrimination was supported for HAQ-DI and SF-36 PCS in PsA with low risk of bias; and for SF-36 PF with some caution. More studies are required for HAQ-S.

Disclosure of Interests:

Ying Ying Leung Speakers bureau: Novartis, Janssen, Eli Lilly, Richard Holland: None declared, Ashish Mathew: None declared, Christine Lindsay Employee of: Previously employed (worked) for pharmaceutical company., Niti Goel Shareholder of: UCB and Galapagos, Consultant of: VielaBio, Mallinckrodt, and IMMVention, Alexis Ogdie Grant/research support from: Novartis, Pfizer – grant/research support, Consultant of: AbbVie, BMS, Eli Lilly, Novartis, Pfizer, Takeda – consultant, Ana-Maria Orbai Grant/research support from: Abbvie, Eli Lilly and Company, Celgene, Novartis, Janssen, Horizon, Consultant of: Eli Lilly; Janssen; Novartis; Pfizer; UCB. Ana-Maria Orbai was a private consultant or advisor for Sun Pharmaceutical Industries, Inc, not in her capacity as a Johns Hopkins faculty member and was not compensated for this service., Pil Hoejgaard: None declared, Jeffrey Chau: None declared, Laura C Coates: None declared, Vibeke Strand: None declared, Dafna D Gladman Grant/research support from: AbbVie, Amgen Inc., BMS, Celgene Corporation, Janssen, Novartis, Pfizer, UCB – grant/research support, Consultant of: AbbVie, Amgen Inc., BMS, Celgene Corporation, Janssen, Novartis, Pfizer, UCB – consultant, Robin Christensen: None declared, William Tillett: None declared, Philip J Mease Grant/research support from: Abbott, Amgen, Biogen Idec, BMS, Celgene Corporation, Eli Lilly, Novartis, Pfizer, Sun Pharmaceutical, UCB – grant/research support, Consultant of: Abbott, Amgen, Biogen Idec, BMS, Celgene Corporation, Eli Lilly, Novartis, Pfizer, Sun Pharmaceutical, UCB – consultant, Speakers bureau: Abbott, Amgen, Biogen Idec, BMS, Eli Lilly, Genentech, Janssen, Pfizer, UCB – speakers bureau