Comparison of Early Contrast Enhancement Models in Ultrafast Dynamic Contrast-Enhanced Magnetic Resonance Imaging of Prostate Cancer.

Tofts models have failed to produce reliable quantitative markers for prostate cancer. We examined the differences between prostate zones and lesion PI-RADS categories and grade group (GG) using regions of interest drawn in tumor and normal-appearing tissue for a two-compartment uptake (2CU) model (including plasma volume (vp), plasma flow (Fp), permeability surface area product (PS), plasma mean transit time (MTTp), capillary transit time (Tc), extraction fraction (E), and transfer constant (Ktrans)) and exponential (amplitude (A), arrival time (t0), and enhancement rate (α)), sigmoidal (amplitude (A0), center time relative to arrival time (A1 - T0), and slope (A2)), and empirical mathematical models, and time to peak (TTP) parameters fitted to high temporal resolution (1.695 s) DCE-MRI data. In 25 patients with 35 PI-RADS category 3 or higher tumors, we found Fp and α differed between peripheral and transition zones. Parameters Fp, MTTp, Tc, E, α, A1 - T0, and A2 and TTP all showed associations with PI-RADS categories and with GG in the PZ when normal-appearing regions were included in the non-cancer GG. PS and Ktrans were not associated with any PI-RADS category or GG. This pilot study suggests early enhancement parameters derived from ultrafast DCE-MRI may become markers of prostate cancer.

Contrast-agent-based perfusion MRI code repository and testing framework: ISMRM Open Science Initiative for Perfusion Imaging (OSIPI).

PURPOSE: Software has a substantial impact on quantitative perfusion MRI values. The lack of generally accepted implementations, code sharing and transparent testing reduces reproducibility, hindering the use of perfusion MRI in clinical trials. To address these issues, the ISMRM Open Science Initiative for Perfusion Imaging (OSIPI) aimed to establish a community-led, centralized repository for sharing open-source code for processing contrast-based perfusion imaging, incorporating an open-source testing framework. METHODS: A repository was established on the OSIPI GitHub website. Python was chosen as the target software language. Calls for code contributions were made to OSIPI members, the ISMRM Perfusion Study Group, and publicly via OSIPI websites. An automated unit-testing framework was implemented to evaluate the output of code contributions, including visual representation of the results. RESULTS: The repository hosts 86 implementations of perfusion processing steps contributed by 12 individuals or teams. These cover all core aspects of DCE- and DSC-MRI processing, including multiple implementations of the same functionality. Tests were developed for 52 implementations, covering five analysis steps. For T1 mapping, signal-to-concentration conversion and population AIF functions, different implementations resulted in near-identical output values. For the five pharmacokinetic models tested (Tofts, extended Tofts-Kety, Patlak, two-compartment exchange, and two-compartment uptake), differences in output parameters were observed between contributions. CONCLUSIONS: The OSIPI DCE-DSC code repository represents a novel community-led model for code sharing and testing. The repository facilitates the re-use of existing code and the benchmarking of new code, promoting enhanced reproducibility in quantitative perfusion imaging.

The ISMRM Open Science Initiative for Perfusion Imaging (OSIPI): Results from the OSIPI-Dynamic Contrast-Enhanced challenge.

PURPOSE: K trans $$ {K}^{\mathrm{trans}} $$ has often been proposed as a quantitative imaging biomarker for diagnosis, prognosis, and treatment response assessment for various tumors. None of the many software tools for K trans $$ {K}^{\mathrm{trans}} $$ quantification are standardized. The ISMRM Open Science Initiative for Perfusion Imaging-Dynamic Contrast-Enhanced (OSIPI-DCE) challenge was designed to benchmark methods to better help the efforts to standardize K trans $$ {K}^{\mathrm{trans}} $$ measurement. METHODS: A framework was created to evaluate K trans $$ {K}^{\mathrm{trans}} $$ values produced by DCE-MRI analysis pipelines to enable benchmarking. The perfusion MRI community was invited to apply their pipelines for K trans $$ {K}^{\mathrm{trans}} $$ quantification in glioblastoma from clinical and synthetic patients. Submissions were required to include the entrants' K trans $$ {K}^{\mathrm{trans}} $$ values, the applied software, and a standard operating procedure. These were evaluated using the proposed OSIP I gold $$ \mathrm{OSIP}{\mathrm{I}}_{\mathrm{gold}} $$ score defined with accuracy, repeatability, and reproducibility components. RESULTS: Across the 10 received submissions, the OSIP I gold $$ \mathrm{OSIP}{\mathrm{I}}_{\mathrm{gold}} $$ score ranged from 28% to 78% with a 59% median. The accuracy, repeatability, and reproducibility scores ranged from 0.54 to 0.92, 0.64 to 0.86, and 0.65 to 1.00, respectively (0-1 = lowest-highest). Manual arterial input function selection markedly affected the reproducibility and showed greater variability in K trans $$ {K}^{\mathrm{trans}} $$ analysis than automated methods. Furthermore, provision of a detailed standard operating procedure was critical for higher reproducibility. CONCLUSIONS: This study reports results from the OSIPI-DCE challenge and highlights the high inter-software variability within K trans $$ {K}^{\mathrm{trans}} $$ estimation, providing a framework for ongoing benchmarking against the scores presented. Through this challenge, the participating teams were ranked based on the performance of their software tools in the particular setting of this challenge. In a real-world clinical setting, many of these tools may perform differently with different benchmarking methodology.

First-in-human technique translation of oxygen-enhanced MRI to an MR Linac system in patients with head and neck cancer.

BACKGROUND AND PURPOSE: Tumour hypoxia is prognostic in head and neck cancer (HNC), associated with poor loco-regional control, poor survival and treatment resistance. The advent of hybrid MRI - radiotherapy linear accelerator or 'MR Linac' systems - could permit imaging for treatment adaptation based on hypoxic status. We sought to develop oxygen-enhanced MRI (OE-MRI) in HNC and translate the technique onto an MR Linac system. MATERIALS AND METHODS: MRI sequences were developed in phantoms and 15 healthy participants. Next, 14 HNC patients (with 21 primary or local nodal tumours) were evaluated. Baseline tissue longitudinal relaxation time (T1) was measured alongside the change in 1/T1 (termed ΔR1) between air and oxygen gas breathing phases. We compared results from 1.5 T diagnostic MR and MR Linac systems. RESULTS: Baseline T1 had excellent repeatability in phantoms, healthy participants and patients on both systems. Cohort nasal concha oxygen-induced ΔR1 significantly increased (p < 0.0001) in healthy participants demonstrating OE-MRI feasibility. ΔR1 repeatability coefficients (RC) were 0.023-0.040 s-1 across both MR systems. The tumour ΔR1 RC was 0.013 s-1 and the within-subject coefficient of variation (wCV) was 25% on the diagnostic MR. Tumour ΔR1 RC was 0.020 s-1 and wCV was 33% on the MR Linac. ΔR1 magnitude and time-course trends were similar on both systems. CONCLUSION: We demonstrate first-in-human translation of volumetric, dynamic OE-MRI onto an MR Linac system, yielding repeatable hypoxia biomarkers. Data were equivalent on the diagnostic MR and MR Linac systems. OE-MRI has potential to guide future clinical trials of biology guided adaptive radiotherapy.

A deep learning system for quantitative assessment of microvascular abnormalities in nailfold capillary images.

OBJECTIVES: Nailfold capillaroscopy is key to timely diagnosis of SSc, but is often not used in rheumatology clinics because the images are difficult to interpret. We aimed to develop and validate a fully automated image analysis system to fill this gap. METHODS: We mimicked the image interpretation strategies of SSc experts, using deep learning networks to detect each capillary in the distal row of vessels and make morphological measurements. We combined measurements from multiple fingers to give a subject-level probability of SSc.We trained the system using high-resolution images from 111 subjects (group A) and tested on images from subjects not in the training set: 132 imaged at high-resolution (group B); 66 imaged with a low-cost digital microscope (group C). Roughly half of each group had confirmed SSc, and half were healthy controls or had primary RP ('normal'). We also estimated the performance of SSc experts. RESULTS: We compared automated SSc probabilities with the known clinical status of patients (SSc versus 'normal'), generating receiver operating characteristic curves (ROCs). For group B, the area under the ROC (AUC) was 97% (94-99%) [median (90% CI)], with equal sensitivity/specificity 91% (86-95%). For group C, the AUC was 95% (88-99%), with equal sensitivity/specificity 89% (82-95%). SSc expert consensus achieved sensitivity 82% and specificity 73%. CONCLUSION: Fully automated analysis using deep learning can achieve diagnostic performance at least as good as SSc experts, and is sufficiently robust to work with low-cost digital microscope images.

Multispectral imaging of nailfold capillaries using light-emitting diode illumination.

Significance: The capillaries are the smallest blood vessels in the body, typically imaged using video capillaroscopy to aid diagnosis of connective tissue diseases, such as systemic sclerosis. Video capillaroscopy allows visualization of morphological changes in the nailfold capillaries but does not provide any physiological information about the blood contained within the capillary network. Extracting parameters such as hemoglobin oxygenation could increase sensitivity for diagnosis and measurement of microvascular disease progression. Aim: To design, construct, and test a low-cost multispectral imaging (MSI) system using light-emitting diode (LED) illumination to assess relative hemoglobin oxygenation in the nailfold capillaries. Approach: An LED ring light was first designed and modeled. The ring light was fabricated using four commercially available LED colors and a custom-designed printed circuit board. The experimental system was characterized and results compared with the illumination model. A blood phantom with variable oxygenation was used to determine the feasibility of using the illumination-based MSI system for oximetry. Nailfold capillaries were then imaged in a healthy subject. Results: The illumination modeling results were in close agreement with the constructed system. Imaging of the blood phantom demonstrated sensitivity to changing hemoglobin oxygenation, which was in line with the spectral modeling of reflection. The morphological properties of the volunteer capillaries were comparable to those measured in current gold standard systems. Conclusions: LED-based illumination could be used as a low-cost approach to enable MSI of the nailfold capillaries to provide insight into the oxygenation of the blood contained within the capillary network.

Photoacoustic imaging is a novel tool to measure finger artery structure and oxygenation in patients with SSc.

Systemic sclerosis (SSc)-related digital ischaemia is a major cause of morbidity, resulting from a combination of microvascular and digital artery disease. Photoacoustic imaging offers a newly available, non-invasive method of imaging digital artery structure and oxygenation. The aim of this study was to establish whether photoacoustic imaging could detect and measure vasculopathy in digital arteries, including the level of oxygenation, in patients with SSc and healthy controls. 22 patients with SSc and 32 healthy controls (HC) underwent photoacoustic imaging of the fingers. Vascular volume and oxygenation were assessed across eight fingers at the middle phalanx. In addition, oxygenation change during finger occlusion was measured at the non-dominant ring finger and the vascular network was imaged along the length of one finger for qualitative assessment. There was no statistically significant difference in vascular volume between patients with SSc and HC (mean of eight fingers; SSc, median 118.6 IQR [95.0-130.5] vs. HC 115.6 [97.8-158.9]) mm3. However, baseline oxygenation (mean 8 fingers) was lower in SSc vs. HC (0.373 [0.361-0.381] vs. 0.381 [0.373-0.385] arbitrary sO2 units respectively; p = 0.03). Hyperaemic oxygenation response following occlusion release was significantly lower in SSc compared to HC (0.379 [0.376-0.381] vs. 0.382 [0.377-0.385]; p = 0.03). Whilst vascular volume was similar between groups, digital artery oxygenation was decreased in patients with SSc as compared to HC, indicative of functional deficit. Photoacoustic imaging offers an exciting new method to image the vascular network in patients with SSc and the possibility to capture oxygenation as a functional measure.

A model selection framework to quantify microvascular liver function in gadoxetate-enhanced MRI: Application to healthy liver, diseased tissue, and hepatocellular carcinoma.

PURPOSE: We introduce a novel, generalized tracer kinetic model selection framework to quantify microvascular characteristics of liver and tumor tissue in gadoxetate-enhanced dynamic contrast-enhanced MRI (DCE-MRI). METHODS: Our framework includes a hierarchy of nested models, from which physiological parameters are derived in 2 regimes, corresponding to the active transport and free diffusion of gadoxetate. We use simulations to show the sensitivity of model selection and parameter estimation to temporal resolution, time-series duration, and noise. We apply the framework in 8 healthy volunteers (time-series duration up to 24 minutes) and 10 patients with hepatocellular carcinoma (6 minutes). RESULTS: The active transport regime is preferred in 98.6% of voxels in volunteers, 82.1% of patients' non-tumorous liver, and 32.2% of tumor voxels. Interpatient variations correspond to known co-morbidities. Simulations suggest both datasets have sufficient temporal resolution and signal-to-noise ratio, while patient data would be improved by using a time-series duration of at least 12 minutes. CONCLUSIONS: In patient data, gadoxetate exhibits different kinetics: (a) between liver and tumor regions and (b) within regions due to liver disease and/or tumor heterogeneity. Our generalized framework selects a physiological interpretation at each voxel, without preselecting a model for each region or duplicating time-consuming optimizations for models with identical functional forms.

Quantitative nailfold capillaroscopy-update and possible next steps.

We review the exciting potential (and challenges) of quantitative nailfold capillaroscopy, focusing on its role in systemic sclerosis. Quantifying abnormality, including automated analysis of nailfold images, overcomes the subjectivity of qualitative/descriptive image interpretation. First we consider the rationale for quantitative analysis, including the potential for precise discrimination between normal and abnormal capillaries and for reliable measurement of disease progression and treatment response. We discuss nailfold image acquisition and interpretation, and describe how early work on semi-quantitative and quantitative analysis paved the way for semi-automated and automated analysis. Measurement of red blood cell velocity is described briefly. Finally we give a personal view on 'next steps'. From a clinical perspective, increased uptake of nailfold capillaroscopy by general rheumatologists could be achieved via low-cost hand-held devices with cloud-based automated analysis. From a research perspective, automated analysis could facilitate large-scale prospective studies using capillaroscopic parameters as possible biomarkers of systemic sclerosis-spectrum disorders.

Comparison between low cost USB nailfold capillaroscopy and videocapillaroscopy: a pilot study.

OBJECTIVES: Universal serial bus (USB) microscopy (capillaroscopy) could provide all rheumatologists with an easy-to-use, low-cost tool to examine the nailfold capillaries to facilitate early diagnosis of SSc. The objectives of this pilot study were to examine the feasibility of acquiring and analysing images using USB microscopy and to compare results to videocapillaroscopy. METHODS: Videocapillaroscopy and USB microscope images were obtained from the right and left ring fingers of 20 patients with SSc and 20 healthy control subjects. In addition to generating panoramic capillary mosaics from across the whole nailbed, custom software made fully automated measurements of vessel structure including capillary width and density. The area under the receiver operating characteristic curve (AZ) was used to measure separation between the SSc and healthy control groups. RESULTS: High quality images could be generated from the USB microscope, with reconstructed USB images comparing very favourably with those obtained using videocapillaroscopy. Using USB microscope images, the receiver operating characteristic curve AZ for group separation based on mean width was 0.81 (standard error 0.120) compared with 0.81 (standard error 0.095) for the (gold standard) videocapillaroscopy. The receiver operating characteristic curve AZ for group separation using capillary density was 0.48 (standard error 0.16) for USB microscope images, compared with 0.70 (standard error 0.10) for videocapillaroscopy. CONCLUSION: In this pilot study, USB capillaroscopy was able to discriminate between patients with SSc and controls as well as videocapillaroscopy on the basis of capillary width. This finding, together with the high-quality images obtained, highlights the potential of USB capillaroscopy as a low-cost, easily accessible clinical and research tool.

Three-dimensional optoacoustic imaging of nailfold capillaries in systemic sclerosis and its potential for disease differentiation using deep learning.

The autoimmune disease systemic sclerosis (SSc) causes microvascular changes that can be easily observed cutaneously at the finger nailfold. Optoacoustic imaging (OAI), a combination of optical and ultrasound imaging, specifically raster-scanning optoacoustic mesoscopy (RSOM), offers a non-invasive high-resolution 3D visualization of capillaries allowing for a better view of microvascular changes and an extraction of volumetric measures. In this study, nailfold capillaries of patients with SSc and healthy controls are imaged and compared with each other for the first time using OAI. The nailfolds of 23 patients with SSc and 19 controls were imaged using RSOM. The acquired images were qualitatively compared to images from state-of-the-art imaging tools for SSc, dermoscopy and high magnification capillaroscopy. The vascular volume in the nailfold capillaries were computed from the RSOM images. The vascular volumes differ significantly between both cohorts (0.216 ± 0.085 mm3 and 0.337 ± 0.110 mm3; p < 0.0005). In addition, an artificial neural network was trained to automatically differentiate nailfold images from both cohorts to further assess whether OAI is sensitive enough to visualize anatomical differences in the capillaries between the two cohorts. Using transfer learning, the model classifies images with an area under the ROC curve of 0.897, and a sensitivity of 0.783 and specificity of 0.895. In conclusion, this study demonstrates the capabilities of RSOM as an imaging tool for SSc and establishes it as a modality that facilitates more in-depth studies into the disease mechanisms and progression.

State-of-the-art technologies provide new insights linking skin and blood vessel abnormalities in SSc-related disorders.

OBJECTIVE: A key unanswered question in systemic sclerosis (SSc) is how microvascular abnormality and fibrosis inter-relate. Our aim was to use state-of-the-art non-invasive imaging methods to gain new insights into pathophysiology, comparing patients with different subtypes of SSc, including early dcSSc, not only to healthy controls but also to patients with causes of Raynaud's phenomenon not progressing to fibrosis. METHODS: Laser Doppler imaging, nailfold capillaroscopy, spectroscopy, and ultrasound measured (respectively) perfusion, microvascular structure, oxygenation/oxidative stress, and skin thickening in the hands of 265 subjects: 31 patients with primary Raynaud's phenomenon (PRP), 35 with undifferentiated connective tissue disease (UCTD), 93 with limited cutaneous SSc (lcSSc), 46 with diffuse cutaneous SSc (dcSSc, including 27 'early') and 60 healthy controls. RESULTS: Mean perfusion was reduced in SSc groups compared to controls (lcSSc 172 perfusion units [standard deviation 157], late-dcSSc 90 [145], early-dcSSc 68 [137] vs. controls 211 [146]; p = 0.0002) as was finger-oxygenation (lcSSc 12.1 [13.6] arbitrary units [AU], late-dcSSc 12.2 [8.4], early-dcSSc 11.1 [11.3] vs controls 14.9 [10.5]; p = 0.0049). Oxidative stress was increased at the hand-dorsum in SSc groups (p = 0.0007). Perfusion positively correlated with oxygenation (r = 0.23, p < 0.001), and capillary density negatively with skin thickness (r = -0.26, p < 0.001). CONCLUSION: Our findings lend support to the hypothesis that in SSc, particularly early dcSSc, (but not in PRP or UCTD), reduced perfusion (together with structural microvascular abnormality) associates with reduced oxygenation, with oxidative stress and with skin thickening/fibrosis, most likely driving a vicious cycle which ultimately results in irreversible tissue injury. Findings in skin may mirror alterations in internal organs.

Prediction of reader estimates of mammographic density using convolutional neural networks.

Mammographic density is an important risk factor for breast cancer. In recent research, percentage density assessed visually using visual analogue scales (VAS) showed stronger risk prediction than existing automated density measures, suggesting readers may recognize relevant image features not yet captured by hand-crafted algorithms. With deep learning, it may be possible to encapsulate this knowledge in an automatic method. We have built convolutional neural networks (CNN) to predict density VAS scores from full-field digital mammograms. The CNNs are trained using whole-image mammograms, each labeled with the average VAS score of two independent readers. Each CNN learns a mapping between mammographic appearance and VAS score so that at test time, they can predict VAS score for an unseen image. Networks were trained using 67,520 mammographic images from 16,968 women and for model selection we used a dataset of 73,128 images. Two case-control sets of contralateral mammograms of screen detected cancers and prior images of women with cancers detected subsequently, matched to controls on age, menopausal status, parity, HRT and BMI, were used for evaluating performance on breast cancer prediction. In the case-control sets, odd ratios of cancer in the highest versus lowest quintile of percentage density were 2.49 (95% CI: 1.59 to 3.96) for screen-detected cancers and 4.16 (2.53 to 6.82) for priors, with matched concordance indices of 0.587 (0.542 to 0.627) and 0.616 (0.578 to 0.655), respectively. There was no significant difference between reader VAS and predicted VAS for the prior test set (likelihood ratio chi square, p = 0.134 ). Our fully automated method shows promising results for cancer risk prediction and is comparable with human performance.

Nailfold capillaroscopy-how many fingers should be examined to detect abnormality?

Objectives: Nailfold capillaroscopy is being increasingly used by rheumatologists in the diagnosis of SSc. However, assessment of all nailfolds can be time-consuming in a busy outpatient clinic. Our aim was to answer the question as to how many (and which) fingers a clinician should routinely assess to capture accurately the true state. Methods: A total of 2994 assessments (by an international panel of expert observers) of 1600 images from 173 participants (101 with SSc, 22 with primary RP and 50 healthy controls) were included in this analysis. Seven single-finger or finger combinations (derived from the middle and ring fingers) were then tested for sensitivity for the presence of two markers of capillary abnormality [presence of giant capillaries and an SSc grade (early, active or late)] compared with assessment of all eight fingers. Results: For the eight-finger gold standard, sensitivity against the diagnostic criteria was 74.6% (53.0% for the presence of giants alone and 73.1% for image grade alone). Examining only one finger gave low sensitivity (ranging from right middle 31.7% to left ring 46.6%). Examining both ring fingers gave a sensitivity of 59.8%, whereas examining the four-finger combination of both ring and both middle fingers gave a sensitivity of 66.7%. Conclusion: During routine capillaroscopic examination, ideally all eight nailbeds (excluding thumbs) should be examined, otherwise some abnormalities will be missed. Examining only four fingers reduces capillaroscopy sensitivity.

Automated structure and flow measurement - a promising tool in nailfold capillaroscopy.

OBJECTIVES: Despite increasing interest in nailfold capillaroscopy, objective measures of capillary structure and blood flow have been little studied. We aimed to test the hypothesis that structural measurements, capillary flow, and a combined measure have the predictive power to separate patients with systemic sclerosis (SSc) from those with primary Raynaud's phenomenon (PRP) and healthy controls (HC). METHODS: 50 patients with SSc, 12 with PRP, and 50 HC were imaged using a novel capillaroscopy system that generates high-quality nailfold images and provides fully-automated measurements of capillary structure and blood flow (capillary density, mean width, maximum width, shape score, derangement and mean flow velocity). Population statistics summarise the differences between the three groups. Areas under ROC curves (AZ) were used to measure classification accuracy when assigning individuals to SSc and HC/PRP groups. RESULTS: Statistically significant differences in group means were found between patients with SSc and both HC and patients with PRP, for all measurements, e.g. mean width (µm) ±â€¯SE: 15.0 ±â€¯0.71, 12.7 ±â€¯0.74 and 11.8 ±â€¯0.23 for SSc, PRP and HC respectively. Combining the five structural measurements gave better classification (AZ = 0.919 ±â€¯0.026) than the best single measurement (mean width, AZ = 0.874 ±â€¯0.043), whilst adding flow further improved classification (AZ = 0.930 ±â€¯0.024). CONCLUSIONS: Structural and blood flow measurements are both able to distinguish patients with SSc from those with PRP/HC. Importantly, these hold promise as clinical trial outcome measures for treatments aimed at improving finger blood flow or microvascular remodelling.

Quantitative outcome measures for systemic sclerosis-related Microangiopathy - Reliability of image acquisition in Nailfold Capillaroscopy.

BACKGROUND: Nailfold capillaroscopic parameters hold increasing promise as outcome measures for clinical trials in systemic sclerosis (SSc). Their inclusion as outcomes would often naturally require capillaroscopy images to be captured at several time points during any one study. Our objective was to assess repeatability of image acquisition (which has been little studied), as well as of measurement. METHOD: 41 patients (26 with SSc, 15 with primary Raynaud's phenomenon) and 10 healthy controls returned for repeat high-magnification (300×) videocapillaroscopy mosaic imaging of 10 digits one week after initial imaging (as part of a larger study of reliability). Images were assessed in a random order by an expert blinded observer and 4 outcome measures extracted: (1) overall image grade and then (where possible) distal vessel locations were marked, allowing (2) vessel density (across the whole nailfold) to be calculated (3) apex width measurement and (4) giant vessel count. Intra-rater, intra-visit and intra-rater inter-visit (baseline vs. 1week) reliability were examined in 475 and 392 images respectively. A linear, mixed-effects model was used to estimate variance components, from which intra-class correlation coefficients (ICCs) were determined. RESULTS: Intra-visit and inter-visit reliability estimates (ICCs) were (respectively): overall image grade, 0.97 and 0.90; vessel density, 0.92 and 0.65; mean vessel width, 0.91 and 0.79; presence of giant capillary, 0.68 and 0.56. These estimates were conditional on each parameter being measurable. CONCLUSION: Within-operator image analysis and acquisition are reproducible. Quantitative nailfold capillaroscopy, at least with a single observer, provides reliable outcome measures for clinical studies including randomised controlled trials.

Intra-and inter-observer reliability of nailfold videocapillaroscopy - A possible outcome measure for systemic sclerosis-related microangiopathy.

OBJECTIVES: Our aim was to assess the reliability of nailfold capillary assessment in terms of image evaluability, image severity grade ('normal', 'early', 'active', 'late'), capillary density, capillary (apex) width, and presence of giant capillaries, and also to gain further insight into differences in these parameters between patients with systemic sclerosis (SSc), patients with primary Raynaud's phenomenon (PRP) and healthy control subjects. METHODS: Videocapillaroscopy images (magnification 300×) were acquired from all 10 digits from 173 participants: 101 patients with SSc, 22 with PRP and 50 healthy controls. Ten capillaroscopy experts from 7 European centres evaluated the images. Custom image mark-up software allowed extraction of the following outcome measures: overall grade ('normal', 'early', 'active', 'late', 'non-specific', or 'ungradeable'), capillary density (vessels/mm), mean vessel apical width, and presence of giant capillaries. RESULTS: Observers analysed a median of 129 images each. Evaluability (i.e. the availability of measures) varied across outcome measures (e.g. 73.0% for density and 46.2% for overall grade in patients with SSc). Intra-observer reliability for evaluability was consistently higher than inter- (e.g. for density, intra-class correlation coefficient [ICC] was 0.71 within and 0.14 between observers). Conditional on evaluability, both intra- and inter-observer reliability were high for grade (ICC 0.93 and 0.78 respectively), density (0.91 and 0.64) and width (0.91 and 0.85). CONCLUSIONS: Evaluability is one of the major challenges in assessing nailfold capillaries. However, when images are evaluable, the high intra- and inter-reliabilities suggest that overall image grade, capillary density and apex width have potential as outcome measures in longitudinal studies.

An automated system for detecting and measuring nailfold capillaries.

Nailfold capillaroscopy is an established qualitative technique in the assessment of patients displaying Raynaud's phenomenon. We describe a fully automated system for extracting quantitative biomarkers from capillaroscopy images, using a layered machine learning approach. On an unseen set of 455 images, the system detects and locates individual capillaries as well as human experts, and makes measurements of vessel morphology that reveal statistically significant differences between patients with (relatively benign) primary Raynaud's phenomenon, and those with potentially life-threatening systemic sclerosis.

Detecting and classifying linear structures in mammograms using random forests.

Detecting and classifying curvilinear structure is important in many image interpretation tasks. We focus on the challenging problem of detecting such structure in mammograms and deciding whether it is normal or abnormal. We adopt a discriminative learning approach based on a Dual-Tree Complex Wavelet representation and random forest classification. We present results of a quantitative comparison of our approach with three leading methods from the literature and with learning-based variants of those methods. We show that our new approach gives significantly better results than any of the other methods, achieving an area under the ROC curve A(z) = 0.923 for curvilinear structure detection, and A(z) = 0.761 for distinguishing between normal and abnormal structure (spicules). A detailed analysis suggests that some of the improvement is due to discriminative learning, and some due to the DT-CWT representation, which provides local phase information and good angular resolution.