Evaluating the performance of artificial intelligence software for lung nodule detection on chest radiographs in a retrospective real-world UK population

OBJECTIVES

Early identification of lung cancer on chest radiographs improves patient outcomes. Artificial intelligence (AI) tools may increase diagnostic accuracy and streamline this pathway. This study evaluated the performance of commercially available AI-based software trained to identify cancerous lung nodules on chest radiographs.

DESIGN

This retrospective study included primary care chest radiographs acquired in a UK centre. The software evaluated each radiograph independently and outputs were compared with two reference standards: (1) the radiologist report and (2) the diagnosis of cancer by multidisciplinary team decision. Failure analysis was performed by interrogating the software marker locations on radiographs.

PARTICIPANTS

5722 consecutive chest radiographs were included from 5592 patients (median age 59 years, 53.8% women, 1.6% prevalence of cancer).

RESULTS

Compared with radiologist reports for nodule detection, the software demonstrated sensitivity 54.5% (95% CI 44.2% to 64.4%), specificity 83.2% (82.2% to 84.1%), positive predictive value (PPV) 5.5% (4.6% to 6.6%) and negative predictive value (NPV) 99.0% (98.8% to 99.2%). Compared with cancer diagnosis, the software demonstrated sensitivity 60.9% (50.1% to 70.9%), specificity 83.3% (82.3% to 84.2%), PPV 5.6% (4.8% to 6.6%) and NPV 99.2% (99.0% to 99.4%). Normal or variant anatomy was misidentified as an abnormality in 69.9% of the 943 false positive cases.

CONCLUSIONS

The software demonstrated considerable underperformance in this real-world patient cohort. Failure analysis suggested a lack of generalisability in the training and testing datasets as a potential factor. The low PPV carries the risk of over-investigation and limits the translation of the software to clinical practice. Our findings highlight the importance of training and testing software in representative datasets, with broader implications for the implementation of AI tools in imaging.

Validation of Artificial Intelligence Cardiac MRI Measurements: Relationship to Heart Catheterization and Mortality Prediction

Background Cardiac MRI measurements have diagnostic and prognostic value in the evaluation of cardiopulmonary disease. Artificial intelligence approaches to automate cardiac MRI segmentation are emerging but require clinical testing. Purpose To develop and evaluate a deep learning tool for quantitative evaluation of cardiac MRI functional studies and assess its use for prognosis in patients suspected of having pulmonary hypertension. Materials and Methods A retrospective multicenter and multivendor data set was used to develop a deep learning-based cardiac MRI contouring model using a cohort of patients suspected of having cardiopulmonary disease from multiple pathologic causes. Correlation with same-day right heart catheterization (RHC) and scan-rescan repeatability was assessed in prospectively recruited participants. Prognostic impact was assessed using Cox proportional hazard regression analysis of 3487 patients from the ASPIRE (Assessing the Severity of Pulmonary Hypertension In a Pulmonary Hypertension Referral Centre) registry, including a subset of 920 patients with pulmonary arterial hypertension. The generalizability of the automatic assessment was evaluated in 40 multivendor studies from 32 centers. Results The training data set included 539 patients (mean age, 54 years ± 20 [SD]; 315 women). Automatic cardiac MRI measurements were better correlated with RHC parameters than were manual measurements, including left ventricular stroke volume (r = 0.72 vs 0.68; P = .03). Interstudy repeatability of cardiac MRI measurements was high for all automatic measurements (intraclass correlation coefficient range, 0.79-0.99) and similarly repeatable to manual measurements (all paired t test P > .05). Automated right ventricle and left ventricle cardiac MRI measurements were associated with mortality in patients suspected of having pulmonary hypertension. Conclusion An automatic cardiac MRI measurement approach was developed and tested in a large cohort of patients, including a broad spectrum of right ventricular and left ventricular conditions, with internal and external testing. Fully automatic cardiac MRI assessment correlated strongly with invasive hemodynamics, had prognostic value, were highly repeatable, and showed excellent generalizability. Clinical trial registration no. NCT03841344 Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Ambale-Venkatesh and Lima in this issue. An earlier incorrect version appeared online. This article was corrected on June 27, 2022.

MO012: Development of an Accurate Automated Segmentation Algorithm to Measure Total Kidney Volume in ADPKD Suitable for Clinical Application (The Cystvas Study)

BACKGROUND AND AIMS

A major barrier to the routine adoption of total kidney volume (TKV) as a clinical biomarker of disease for autosomal dominant polycystic disease (ADPKD) is the significant human operator time required even by experienced analysts (typically, 45–90 min per patient). Several groups have investigated automated and semi-automated kidney segmentation methods to either reduce or eliminate the human interaction required. However, such tools have mostly been developed using data from single centers, which may not translate well to other centers. To date, there has been little attempt to develop or validate algorithms using multi-center and multi-scanner data.

Here, we report an automated segmentation tool capable of high performance across different patient populations and scanner sequences using 1.5 T MRI data from four centers (the CYSTic consortium). The algorithm was subsequently tested in a separate clinical cohort to assess its likely performance during routine clinical use.

METHOD

All 1.5 T studies from the CYSTic trial were downloaded (acquired from Siemens Avanto, GE Optima and Siemens Aera, using different sequences). Cases with poor image quality or with sections of kidney missing from the field of view were excluded. A single, experienced operator selected the most appropriate image series for segmentation and manually segmented each patient's kidneys using a commercial software program (MIM Encore). There were 454 kidneys segmented from 227 scans. These data were used for algorithm training and validation.

In addition, 48 routine clinical scans from the Sheffield 3D Lab were extracted from the archives along with their original segmentations (performed by six different analysts), to use as a test set. None of the patients in the clinical test set were included in the training set.

An ensemble U-net algorithm was created using the nnUNet approach Isensee et al. (nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Meth 2021; 18(2): 203–211), whereby the CYSTic data were used in a 5-fold cross-validation, with stratification across the four centers (i.e. each center contributed 80% of the available data to algorithm training in each fold). Algorithm training proceeded according to the standard heuristic nnUnet functions, using a 3D architecture, for 100 epochs. Segmented kidneys were split into left and right sides during post-processing, through analysis of the position of the center of gravity of segmented regions. Once trained, the five algorithms from cross-validation were applied in an ensemble to the clinical test cohort.

RESULTS

In both cross-validation and clinical testing phases, the median DICE score was 0.96 for each kidney (IQR of 0.95–0.97 in cross-validation on both sides, And 0.95–0.97 on the left side for clinical testing and 0.96 for the right). The median total kidney volume error was −0.46% (−2.02 to 1.27) for the left side in cross-validation and −0.82% (−2.55 to 0.86) for the right. In the clinical testing phase, the median volume errors were −1.8% (−3.69 to 1.29), left and −1.79% (−3.95 to 0.65), right.

The mean time taken to manually segment kidneys in the CYSTIc dataset was 54 min per scan (SD of 31 min). Use of the algorithm as a first pass segmentation, with subsequent checking and editing by an operator, would significantly reduce human input time to a few minutes per case

CONCLUSION

Our new algorithm demonstrates high accuracy compared to the gold standard of manual TKV segmentation and performs well in a wide range of patients with ADPKD imaged using different scanners at several European centers. Its high performance in a real-world clinical dataset demonstrates that such tools can provide a reliable means of measuring TKV in routine practice and reduces the previous barrier of analyst time and experience.

Computed tomography lung parenchymal descriptions in routine radiological reporting have diagnostic and prognostic utility in patients with idiopathic pulmonary arterial hypertension and pulmonary hypertension associated with lung disease

BACKGROUND

Patients with pulmonary hypertension (PH) and lung disease may pose a diagnostic dilemma between idiopathic pulmonary arterial hypertension (IPAH) and PH associated with lung disease (PH-CLD). The prognostic impact of common computed tomography (CT) parenchymal features is unknown.

METHODS

660 IPAH and PH-CLD patients assessed between 2001 and 2019 were included. Reports for all CT scans 1 year prior to diagnosis were analysed for common lung parenchymal patterns. Cox regression and Kaplan-Meier analysis were performed.

RESULTS

At univariate analysis of the whole cohort, centrilobular ground-glass (CGG) changes (hazard ratio, HR 0.29) and ground-glass opacification (HR 0.53) predicted improved survival, while honeycombing (HR 2.79), emphysema (HR 2.09) and fibrosis (HR 2.38) predicted worse survival (all p<0.001). Fibrosis was an independent predictor after adjusting for baseline demographics, PH severity and diffusing capacity of the lung for carbon monoxide (HR 1.37, p<0.05). Patients with a clinical diagnosis of IPAH who had an absence of reported parenchymal lung disease (IPAH-noLD) demonstrated superior survival to patients diagnosed with either IPAH who had coexistent CT lung disease or PH-CLD (2-year survival of 85%, 60% and 46%, respectively, p<0.05). CGG changes were present in 23.3% of IPAH-noLD and 5.8% of PH-CLD patients. There was no significant difference in survival between IPAH-noLD patients with or without CGG changes. PH-CLD patients with fibrosis had worse survival than those with emphysema.

INTERPRETATION

Routine clinical reports of CT lung parenchymal disease identify groups of patients with IPAH and PH-CLD with significantly different prognoses. Isolated CGG changes are not uncommon in IPAH but are not associated with worse survival.

Fully automatic cardiac four chamber and great vessel segmentation on CT pulmonary angiography using deep learning

Introduction

Computed tomography pulmonary angiography (CTPA) is an essential test in the work-up of suspected pulmonary vascular disease including pulmonary hypertension and pulmonary embolism. Cardiac and great vessel assessments on CTPA are based on visual assessment and manual measurements which are known to have poor reproducibility. The primary aim of this study was to develop an automated whole heart segmentation (four chamber and great vessels) model for CTPA.

Methods

A nine structure semantic segmentation model of the heart and great vessels was developed using 200 patients (80/20/100 training/validation/internal testing) with testing in 20 external patients. Ground truth segmentations were performed by consultant cardiothoracic radiologists. Failure analysis was conducted in 1,333 patients with mixed pulmonary vascular disease. Segmentation was achieved using deep learning via a convolutional neural network. Volumetric imaging biomarkers were correlated with invasive haemodynamics in the test cohort.

Results

Dice similarity coefficients (DSC) for segmented structures were in the range 0.58-0.93 for both the internal and external test cohorts. The left and right ventricle myocardium segmentations had lower DSC of 0.83 and 0.58 respectively while all other structures had DSC >0.89 in the internal test cohort and >0.87 in the external test cohort. Interobserver comparison found that the left and right ventricle myocardium segmentations showed the most variation between observers: mean DSC (range) of 0.795 (0.785-0.801) and 0.520 (0.482-0.542) respectively. Right ventricle myocardial volume had strong correlation with mean pulmonary artery pressure (Spearman's correlation coefficient = 0.7). The volume of segmented cardiac structures by deep learning had higher or equivalent correlation with invasive haemodynamics than by manual segmentations. The model demonstrated good generalisability to different vendors and hospitals with similar performance in the external test cohort. The failure rates in mixed pulmonary vascular disease were low (<3.9%) indicating good generalisability of the model to different diseases.

Conclusion

Fully automated segmentation of the four cardiac chambers and great vessels has been achieved in CTPA with high accuracy and low rates of failure. DL volumetric biomarkers can potentially improve CTPA cardiac assessment and invasive haemodynamic prediction.

OUP accepted manuscript

Background

Everolimus is a potential alternative to embolization and nephrectomy for managing tuberous sclerosis complex (TSC)-associated renal angiomyolipoma (AML). In 2016, National Health Service England approved its use through regional centres for renal AML ≥30 mm showing interval growth. Evidence of lesion stabilization or reduction after 6 months is mandated for continuation of long-term treatment.

Methods

From November 2016 to June 2021, all potentially eligible adult TSC patients with AML across Yorkshire and Humber were referred for assessment and monitoring. Eligible patients underwent baseline renal magnetic resonance imaging (MRI) assessment and a follow-up MRI scan after 6 months on everolimus. Dose titration was guided by trough levels and lesion responsiveness using a new 3D MRI volumetric protocol.

Results

Of 28 patients commencing treatment, 19 tolerated everolimus for >3 months. Overall, 11 patients (40%) discontinued treatment, mostly due to recurrent infections (42%) and allergic reactions (25%). Sixty-eight percent required dose adjustments from the initiating dose (10 mg) due to sub-optimal trough levels (38%), minimal AML response (15%) or adverse events (47%). 3D volumetric assessment confirmed a reduction in AML volume of a pre-selected index lesion in all treatment-naïve cases (n = 14), showing superiority over 2D measurements of lesion diameter.

Conclusion

In this cohort, everolimus promoted AML regression in all patients who tolerated the drug for >6 months with stabilization observed over 3 years. Trough levels enabled individual dose titration to maximize responsiveness and minimize side effects. The use of 3D MRI assessment of lesion volume was superior to 2D measurements of lesion diameter in monitoring treatment response.

Cardiac stereotactic ablative radiotherapy for control of refractory ventricular tachycardia: initial UK multicentre experience

Background

Options for patients with ventricular tachycardia (VT) refractory to antiarrhythmic drugs and/or catheter ablation remain limited. Stereotactic radiotherapy has been described as a novel treatment option.

Methods

Seven patients with recurrent refractory VT, deemed high risk for either first time or redo invasive catheter ablation, were treated across three UK centres with non-invasive cardiac stereotactic ablative radiotherapy (SABR). Prior catheter ablation data and non-invasive mapping were combined with cross-sectional imaging to generate radiotherapy plans with aim to deliver a single 25 Gy treatment. Shared planning and treatment guidelines and prospective peer review were used.

Results

Acute suppression of VT was seen in all seven patients. For five patients with at least 6 months follow-up, overall reduction in VT burden was 85%. No high-grade radiotherapy treatment-related side effects were documented. Three deaths (two early, one late) occurred due to heart failure.

Conclusions

Cardiac SABR showed reasonable VT suppression in a high-risk population where conventional treatment had failed.

COVID-19: A systematic evaluation of personal protective equipment (PPE) performance during restraint

BACKGROUND

Restraint is widely practised within inpatient mental health services and is considered a higher-risk procedure for patients and staff. There is a sparsity of evidence in respect of the efficacy of personal protective equipment (PPE) used during restraint for reducing risk of infection.

METHODS

A series of choreographed restraint episodes were used to simulate contact contamination in research participants playing the roles of staff members and a patient. For comparison, one episode of simulated recording of physical observations was taken. Ultraviolet (UV) fluorescent material was used to track the simulated contact contamination, with analysis undertaken using established image registration techniques of UV photographs. This was repeated for three separate sets of PPE.

RESULTS

All three PPE sets showed similar performance in protecting against contamination transfer. For teams not utilising coveralls, this was dependent upon effective cleansing as part of doffing. There were similar patterns of contamination for restraint team members assigned to specific roles, with hands and upper torso appearing to be higher-risk areas. The restraint-related contamination was 23 times higher than that observed for physical observations.

DISCUSSION

A second layer of clothing that can be removed showed efficacy in reducing contact contamination. PPE fit to individual is important. Post-restraint cleansing procedures are currently inadequate, with new procedures for face and neck cleansing required. These findings leave scope for staff to potentially improve their appearance when donning PPE and engaging with distressed patients.

High interstudy repeatability of automatic deep learnt biventricular CMR measurements

Funding Acknowledgements

Type of funding sources: Foundation. Main funding source(s): Wellcome Trust (UK), NIHR (UK)

Introduction

Cardiac magnetic resonance (CMR) measurements have significant diagnostic and prognostic value. Accurate and repeatable measurements are essential to assess disease severity, evaluate therapy response and monitor disease progression. Deep learning approaches have shown promise for automatic left ventricular (LV) segmentation on CMR, however fully automatic right ventricular (RV) segmentation remains challenging. We aimed to develop a biventricular automatic contouring model and evaluate the interstudy repeatability of the model in a prospectively recruited cohort.

Methods

A deep learning CMR contouring model was developed in a retrospective multi-vendor (Siemens and General Electric), multi-pathology cohort of patients, predominantly with heart failure, pulmonary hypertension and lung diseases (n = 400, ASPIRE registry). Biventricular segmentations were made on all CMR studies across cardiac phases. To test the accuracy of the automatic segmentation, 30 ASPIRE CMRs were segmented independently by two CMR experts. Each segmentation was compared to the automatic contouring with agreement assessed using the Dice similarity coefficient (DSC). 

A prospective validation cohort of 46 subjects (10 healthy volunteers and 36 patients with pulmonary hypertension) were recruited to assess interstudy agreement of automatic and manual CMR assessments. Two CMR studies were performed during separate sessions on the same day. Interstudy repeatability was assessed using intraclass correlation coefficient (ICC) and Bland-Altman plots. 

Results

DSC showed high agreement (figure 1) comparing automatic and expert CMR readers, with minimal bias towards either CMR expert. The scan-scan repeatability CMR measurements were higher for all automatic RV measurements (ICC 0.89 to 0.98) compared to manual RV measurements (0.78 to 0.98). LV automatic and manual measurements were similarly repeatable (figure 2). Bland-Altman plots showed strong agreement with small mean differences between the scan-scan measurements (figure 2).

Conclusion

Fully automatic biventricular short-axis segmentations are comparable with expert manual segmentations, and have shown excellent interstudy repeatability.

Fully automated CMR derived stroke volume correlates with right heart catheter measurements in patients with suspected pulmonary hypertension

Funding Acknowledgements

Type of funding sources: Foundation. Main funding source(s): Welcome Trust (UK), NIHR (UK)

Introduction

Cardiac magnetic resonance (CMR) assessment plays a significant role in the diagnosis, prognosis and monitoring of patients with pulmonary hypertension (PH). We developed a deep learning model to automatically generate biventricular contours and validated its result in a prospective cohort of patients with suspected PH who underwent right heart catheterization (RHC).

Methods

A deep learning CMR contouring model was developed in a retrospective multi-vendor (Siemens and General Electric), multi-pathology cohort of patients, predominantly with heart failure, lung disease and PH (n = 400, ASPIRE registry). Biventricular segmentations were made on all CMR studies across cardiac phases. A prospective validation cohort of 102 suspected PH patients was recruited and they had RHC within 24 hours  of the CMR. To test the accuracy of the automatic segmentation, the RHC-thermodilution and CMR-derived measures of stroke volume (SV) were compared for manual and automated measurements. 

Results

The mean and standard deviation for the derived SV was 59 ml ± 21 measured by RHC and 75 ml ± 25 for automated and 79 ml ± 26 for manual CMR measurements. Automatic and manual CMR measurement correlated strongly with RHC derived SV; 0.73, 95% CI [0.62, 0.81] and 0.78, 95% CI [0.69, 0.85], respectively (figure 1).  The agreement between automatic and manual SV was high; interclass correlation coefficient (ICC) = 0.88, 95% CI [0.83, 0.92] and Bland-Altman plots showed a narrow spread of mean differences between manual and automatic measurements (figure 2).

Conclusion

In a prospective cohort, fully automatic CMR assessments corresponded accurately to invasive hemodynamics performed within 24 hours of a CMR study.

Custom-made 3D printed masks for children using non-invasive ventilation: a comparison of 3D scanning technologies and specifications for future clinical service use, guided by patient and professional experience

Non-invasive ventilation (NIV) is assisted mechanical ventilation delivered via a facemask for people with chronic conditions that affect breathing. Mass-produced masks are available for both the adult and paediatric markets but masks that fit well are difficult to find for children who are small or have asymmetrical facial features. A good fit between the mask and the patient's face to minimise unintentional air leakage is essential to deliver the treatment effectively. We present an innovative use of 3D assessment and manufacturing technologies to deliver novel custom-made facemasks for children for whom a well-fitting standard mask is not available. This paper aims to describe the processes undertaken to investigate and compare currently available technologies for 3D scanning children and to explore the design of a system for creating custom-made paediatric NIV masks within the NHS. The paper therefore considers not only the quality and accuracy of the data, but also other factors such as the time and ease of process. Searches for all currently available scanning technologies were made. Photogrammetry image stitch using a smartphone and a digital camera, and two structured light scanners were selected and compared in the laboratory, in discussion with user groups, and in adult volunteers. Using the processes described, it became apparent that the optimal 3D scanning system for this purpose was the handheld structured light scanner. This option offered both superior accuracy and convenience and was more cost effective.

Pulmonary Hypertension in Association with Lung Disease: Quantitative CT and Artificial Intelligence to the Rescue? State-of-the-Art Review

Accurate phenotyping of patients with pulmonary hypertension (PH) is an integral part of informing disease classification, treatment, and prognosis. The impact of lung disease on PH outcomes and response to treatment remains a challenging area with limited progress. Imaging with computed tomography (CT) plays an important role in patients with suspected PH when assessing for parenchymal lung disease, however, current assessments are limited by their semi-qualitative nature. Quantitative chest-CT (QCT) allows numerical quantification of lung parenchymal disease beyond subjective visual assessment. This has facilitated advances in radiological assessment and clinical correlation of a range of lung diseases including emphysema, interstitial lung disease, and coronavirus disease 2019 (COVID-19). Artificial Intelligence approaches have the potential to facilitate rapid quantitative assessments. Benefits of cross-sectional imaging include ease and speed of scan acquisition, repeatability and the potential for novel insights beyond visual assessment alone. Potential clinical benefits include improved phenotyping and prediction of treatment response and survival. Artificial intelligence approaches also have the potential to aid more focused study of pulmonary arterial hypertension (PAH) therapies by identifying more homogeneous subgroups of patients with lung disease. This state-of-the-art review summarizes recent QCT developments and potential applications in patients with PH with a focus on lung disease.

A machine learning cardiac magnetic resonance approach to extract disease features and automate pulmonary arterial hypertension diagnosis

AIMS

Pulmonary arterial hypertension (PAH) is a progressive condition with high mortality. Quantitative cardiovascular magnetic resonance (CMR) imaging metrics in PAH target individual cardiac structures and have diagnostic and prognostic utility but are challenging to acquire. The primary aim of this study was to develop and test a tensor-based machine learning approach to holistically identify diagnostic features in PAH using CMR, and secondarily, visualize and interpret key discriminative features associated with PAH.

METHODS AND RESULTS

Consecutive treatment naive patients with PAH or no evidence of pulmonary hypertension (PH), undergoing CMR and right heart catheterization within 48 h, were identified from the ASPIRE registry. A tensor-based machine learning approach, multilinear subspace learning, was developed and the diagnostic accuracy of this approach was compared with standard CMR measurements. Two hundred and twenty patients were identified: 150 with PAH and 70 with no PH. The diagnostic accuracy of the approach was high as assessed by area under the curve at receiver operating characteristic analysis (P < 0.001): 0.92 for PAH, slightly higher than standard CMR metrics. Moreover, establishing the diagnosis using the approach was less time-consuming, being achieved within 10 s. Learnt features were visualized in feature maps with correspondence to cardiac phases, confirming known and also identifying potentially new diagnostic features in PAH.

CONCLUSION

A tensor-based machine learning approach has been developed and applied to CMR. High diagnostic accuracy has been shown for PAH diagnosis and new learnt features were visualized with diagnostic potential.

Left ventricular fibrosis and hypertrophy are associated with mortality in heart failure with preserved ejection fraction

Cardiac magnetic resonance (CMR) is emerging as an important tool in the assessment of heart failure with preserved ejection fraction (HFpEF). This study sought to investigate the prognostic value of multiparametric CMR, including left and right heart volumetric assessment, native T1-mapping and LGE in HFpEF. In this retrospective study, we identified patients with HFpEF who have undergone CMR. CMR protocol included: cines, native T1-mapping and late gadolinium enhancement (LGE). The mean follow-up period was 3.2 ± 2.4 years. We identified 86 patients with HFpEF who had CMR. Of the 86 patients (85% hypertensive; 61% males; 14% cardiac amyloidosis), 27 (31%) patients died during the follow up period. From all the CMR metrics, LV mass (area under curve [AUC] 0.66, SE 0.07, 95% CI 0.54-0.76, p = 0.02), LGE fibrosis (AUC 0.59, SE 0.15, 95% CI 0.41-0.75, p = 0.03) and native T1-values (AUC 0.76, SE 0.09, 95% CI 0.58-0.88, p < 0.01) were the strongest predictors of all-cause mortality. The optimum thresholds for these were: LV mass > 133.24 g (hazard ratio [HR] 1.58, 95% CI 1.1-2.2, p < 0.01); LGE-fibrosis > 34.86% (HR 1.77, 95% CI 1.1-2.8, p = 0.01) and native T1 > 1056.42 ms (HR 2.36, 95% CI 0.9-6.4, p = 0.07). In multivariate cox regression, CMR score model comprising these three variables independently predicted mortality in HFpEF when compared to NTproBNP (HR 4 vs HR 1.65). In non-amyloid HFpEF cases, only native T1 > 1056.42 ms demonstrated higher mortality (AUC 0.833, p < 0.01). In patients with HFpEF, multiparametric CMR aids prognostication. Our results show that left ventricular fibrosis and hypertrophy quantified by CMR are associated with all-cause mortality in patients with HFpEF.

Custom-made 3D printed masks for children using non-invasive ventilation: a feasibility study of production method and testing of outcomes in adult volunteers

Non-invasive ventilation (NIV) is assisted mechanical ventilation delivered via a facemask for people with chronic conditions that affect breathing. NIV is most commonly delivered via an interface (mask) covering the nose (nasal mask) or the nose and mouth (oronasal mask). The number of children in the UK requiring NIV is currently estimated to be around 5000. Mass-produced masks are available for both the adult and paediatric markets but masks that fit well are difficult to find for children who are small or have asymmetrical facial features. A good conforming fit between the mask and the patient's face to minimise unintentional air leakage is essential to deliver the treatment effectively; most ventilators will trigger an alarm requiring action if such leakage is detected. We present an innovative use of 3D scanning and manufacturing technologies to deliver novel mask-face interfaces to optimise mask fit to the needs of individual patients. Ahead of planned user trials with paediatric patients, the project team trialled the feasibility of the process of creating and printing bespoke masks from 3D scan data and carried out testing of the masks in adult volunteers to select the strongest design concept for the paediatric trial. The evaluation of the process of designing a bespoke mask from scan data, arranging for its manufacture and carrying out user testing has been invaluable in gaining knowledge and discovering the pitfalls and timing bottlenecks in the processes. This allowed the team to iteratively refine the techniques and methods involved, informing user trials later on in the project. It has also provided indicative cost estimates for 3D printed mask prototype components which are useful in project decision making and trial planning. The value of the process extends to considerations for future implementation of the process within a clinical pathway.

A rapid high-performance semi-automated tool to measure total kidney volume from MRI in autosomal dominant polycystic kidney disease

Objectives

To develop a high-performance, rapid semi-automated method (Sheffield TKV Tool) for measuring total kidney volume (TKV) from magnetic resonance images (MRI) in patients with autosomal dominant polycystic kidney disease (ADPKD).

Methods

TKV was initially measured in 61 patients with ADPKD using the Sheffield TKV Tool and its performance compared to manual segmentation and other published methods (ellipsoidal, mid-slice, MIROS). It was then validated using an external dataset of MRI scans from 65 patients with ADPKD.

Results

Sixty-one patients (mean age 45 ± 14 years, baseline eGFR 76 ± 32 ml/min/1.73 m²) with ADPKD had a wide range of TKV (258–3680 ml) measured manually. The Sheffield TKV Tool was highly accurate (mean volume error 0.5 ± 5.3% for right kidney, − 0.7 ± 5.5% for left kidney), reproducible (intra-operator variability − 0.2 ± 1.3%; inter-operator variability 1.1 ± 2.9%) and outperformed published methods. It took less than 6 min to execute and performed consistently with high accuracy in an external MRI dataset of T2-weighted sequences with TKV acquired using three different scanners and measured using a different segmentation methodology (mean volume error was 3.45 ± 3.96%, n = 65).

Conclusions

The Sheffield TKV Tool is operator friendly, requiring minimal user interaction to rapidly, accurately and reproducibly measure TKV in this, the largest reported unselected European patient cohort with ADPKD. It is more accurate than estimating equations and its accuracy is maintained at larger kidney volumes than previously reported with other semi-automated methods. It is free to use, can run as an independent executable and will accelerate the application of TKV as a prognostic biomarker for ADPKD into clinical practice.

Key Points

• This new semi-automated method (Sheffield TKV Tool) to measure total kidney volume (TKV) will facilitate the routine clinical assessment of patients with ADPKD.

• Measuring TKV manually is time consuming and laborious.

• TKV is a prognostic indicator in ADPKD and the only imaging biomarker approved by the FDA and EMA.

Electronic supplementary material

The online version of this article (10.1007/s00330-018-5918-9) contains supplementary material, which is available to authorized users.

Can we optimize electrode placement for impedance pneumography?

In this paper, we discuss issues involved in defining an optimum placement of four electrodes for impedance pneumography. We observed a general trend where the change in impedance (delta Z) decreased while the sensitivity (delta Z/Z) increased with distance between the drive and receive electrode pairs. However, the theoretical study indicated that delta Z/Z should decrease with distance. The scatter of points in the plots indicated that sensitivity was influenced by factors other than distance. The correlation coefficient between the theoretical and measured delta Z/Z was low, but significant. This suggested that the best electrode configuration can be derived from the theoretical data. High delta Z/Z was obtained when the drive and receive electrode pairs were placed close to the lungs and in different horizontal planes.

Three-dimensional electrical impedance tomography

The electrical resistivity of mammalian tissues varies widely and is correlated with physiological function. Electrical impedance tomography (EIT) can be used to probe such variations in vivo, and offers a non-invasive means of imaging the internal conductivity distribution of the human body. But the computational complexity of EIT has severe practical limitations, and previous work has been restricted to considering image reconstruction as an essentially two-dimensional problem. This simplification can limit significantly the imaging capabilities of EIT, as the electric currents used to determine the conductivity variations will not in general be confined to a two-dimensional plane. A few studies have attempted three-dimensional EIT image reconstruction, but have not yet succeeded in generating images of a quality suitable for clinical applications. Here we report the development of a three-dimensional EIT system with greatly improved imaging capabilities, which combines our 64-electrode data-collection apparatus with customized matrix inversion techniques. Our results demonstrate the practical potential of EIT for clinical applications, such as lung or brain imaging and diagnostic screening.

Posture control using electrical stimulation biofeedback: a pilot study

The investigation studied the effects of biofeedback on the sitting posture of a 14 year old girl with cerebral palsy. The subject's posture was quantified using a video analysis technique which established the threshold of poor posture at 30 degrees from the vertical plane. A stimulator system was designed using an adapted drop foot stimulator and a custom made controller with a mercury tilt switch as the posture angle transducer. If posture became greater than 30 degrees tactile electrical stimulation was administered to the subject's lower back. Repetitive stimuli occurred on non-correction of posture, with a maximum of 4 consecutive stimuli, upon which an alarm was activated. 10 training sessions of 20 min duration were completed over a 4 week period, monitored using a data logger. Following initial improvement the daily results show a gradual deterioration in posture, whilst post-trial video analysis indicates a significant improvement in posture. An improved response to the alarm stimulus is observed. Reasons for these conflicting findings are discussed.