Search

Background Nailfold videocapillaroscopy (NVC) captures high-magnification images of capillaries, allowing non-invasive assessment of systemic sclerosis [SSc] related microvascular disease. We have developed a state-of-the-art NVC system to enable faster and easier acquisition of high quality static images and produce video sequences in which red blood cell velocity can be measured. The system uses novel software to make fully automated quantitative estimates of capillary morphology and blood flow velocity, eliminating the need for (subjective) clinician input to image interpretation. Objectives To apply the new system in a case-control study to: 1) assess system usability 2) test how well automated measures of capillary morphology differentiate between healthy controls (HC), subjects with primary Raynaud9s phenomenon (PRP) and patients with SSc 3) investigate capillary blood flow velocity as a new quantitative measure for NVC. Methods 112 participants were recruited into the study (50 HC, 12 PRP, 50 SSc). Panoramic video sequences were taken for all 10 digits, each comprising 10,000 – 20,000 frames (size: 640x480 px, spatial resolution: 1μm/px, frame rate: 120 frames/s). The frames were processed and registered to produce a static panorama of the whole nailfold (∼2–5mm wide). The analysis software automatically detected and measured capillary structural properties in this image 1 , before using in-focus frames at each capillary to create video sequences for blood flow velocity estimation (Fig 1). Capillary-level measurements were averaged across all 10 nailfolds to produce subject-level parameters: capillary density, mean capillary width, maximum capillary width, shape score, derangement and mean flow velocity. For each parameter one-way ANOVA and Tukey9s range test were used to check for group differences, and the area under ROC curve (A z ) used to measure separation between HC/PRP and SSc. Results ANOVA tests showed significant group-wise differences for all parameters. Table 1 shows group means and A z for each parameter. Conclusions The new system successfully generated high-quality video sequences, and allowed fast panoramic imaging of the whole nailfold. Automatically extracted capillary morphology parameters matched both clinical expectations and previous study results 1,2 and show considerable promise as outcome measures for SSc. Preliminary flow results suggest reduced blood velocity is associated with abnormal morphology and thus lower in SSc patients, further work is needed to corroborate this. References Berks et al, MICCAI, 8673, 658–665, 2014 Murray et al, Arthritis Care Res, 61(8), 2009 Acknowledgement Funded by the Wellcome Trust Disclosure of Interest None declared

A recent study has shown that breast cancer risk can be reduced by taking Tamoxifen, but only if this results in at least a 10% point reduction in mammographic density. When mammographic density is quantified visually, it is impossible to assess reader accuracy using clinical images as the ground truth is unknown. Our aim was to compare three models of assessing density change and to determine reader accuracy in identifying reductions of 10% points or more. We created 100 synthetic, mammogram-like images comprising 50 pairs designed to simulate natural reduction in density within each pair. Model I: individual images were presented to readers and density assessed. Model II: pairs of images were displayed together, with readers assessing density for each image. Model III: pairs of images were displayed together, and readers asked whether there was at least a 10% point reduction in density. Ten expert readers participated. Readers' estimates of percentage density were significantly closer to the truth (6.8%-26.4%) when images were assessed individually rather than in pairs (9.6%-29.8%). Measurement of change was significantly more accurate in Model II than Model I (p

Mammographic density, defined as the proportion of the breast area in a mammogram that contains fibroglandular tissue, is associated with risk of breast cancer. However, measures of mammographic density are subject to variation in the underlying imaging process and in the assessments of observers. Automatic volumetric measures of breast density remove much of this variability, but their association with risk is less well established. We present density measurements produced using area-based visual analogue scales (VAS) and by volumetric assessment software (QuantraTM, Hologic Inc.) in the PROCAS study. The distributions of VAS scores (n = 22 327) and volumetric quantities (n = 11 653) are given, as are their relationships for subjects with results by both (n = 11 096), but these are not directly comparable as one is area-based and the other volumetric. Inter-observer variability in visual area-based estimation is examined by a scatter plot matrix.

We address the problem of evaluating the performance of algorithms for detecting curvilinear structures in medical images. As an exemplar we consider the detection of vessel trees which contain structures of variable width and contrast. Results for the conventional approach to evaluation, in which the detector output is compared directly with a ground-truth mask, tend to be dominated by the detection of large vessels and fail to capture adequately whether or not finer, lower contrast vessels have been detected successfully. We propose and investigate three alternative evaluation strategies. We demonstrate the use of the standard and new evaluation strategies to assess the performance of a novel method for detecting vessels in retinograms, using the publicly available DRIVE database.

The quantity and appearance of dense breast tissue in mammograms is related to the risk of developing breast cancer, the sensitivity of mammographic interpretation, and the likelihood of local recurrence of cancer following surgery. Visual assessment of breast density is widely used, often with readers indicating the percentage of dense tissue in a mammogram. Although real mammograms can be used to investigate intra- and inter-observer variability, ground truth is difficult to ascertain, so to investigate reader accuracy, we created 60 synthetic, mammogram-like images with densities comparable in area to those found in screening. The images contained either a single dense area, multiple or linear densities, or a variable breast size with a single density. The images were randomized and assessed by 9 expert and 6 non-expert readers who marked percentage area of density on a visual analogue scale. Non-expert readers' estimates of percentage area of density were closer to the truth (6-11% mean absolute difference) than the experts' estimates (10- 19%). The readers were most accurate when the density formed a single area in the image, and least accurate when the dense area was composed of linear structures. In almost every case, the dense area was overestimated by the expert readers. When experts were ranked according to the degree of overestimation, this broadly reflected their relative performance on real mammograms.

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 Az = 0.923 for curvilinear structure detection, and Az = 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.

Breast density is positively linked to the risk of developing breast cancer. We have developed a semi-automated, stepwedge-based method that has been applied to the mammograms of 1,289 women in the UK breast screening programme to measure breast density by volume and area. 116 images were analysed by three independent operators to assess inter-observer variability; 24 of these were analysed on 10 separate occasions by the same operator to determine intra-observer variability. 168 separate images were analysed using the stepwedge method and by two radiologists who independently estimated percentage breast density by area. There was little intra-observer variability in the stepwedge method (average coefficients of variation 3.49% - 5.73%). There were significant differences in the volumes of glandular tissue obtained by the three operators. This was attributed to variations in the operators' definition of the breast edge. For fatty and dense breasts, there was good correlation between breast density assessed by the stepwedge method and the radiologists. This was also observed between radiologists, despite significant inter-observer variation. Based on analysis of thresholds used in the stepwedge method, radiologists' definition of a dense pixel is one in which the percentage of glandular tissue is between 10 and 20% of the total thickness of tissue.

A method has been developed for generating synthetic masses that exhibit the appearance of real breast cancers in mammograms. To be clinically useful, the synthetic masses must appear sufficiently realistic, even to expert mammogram readers. This paper presents the results of an observer study in which 10 expert mammogram readers at the Nightingale Centre, Manchester attempted to distinguish between real and synthetically generated masses. Each reader rated a set of 30 real and 30 synthetics masses on a scale ranging from "definitely real" to "definitely synthetic". ROC curves were fitted to their responses and the area-under-curve (AUC) used to quantify the ability of a reader to identify synthetic masses. The mean AUC was 0.70±0.09, showing the readers were able to identify synthetic masses at a rate statistically better than chance and suggesting that further improvements must be made to the mass synthesis method. Analysis of individual AUC scores showed reader performance was not affected by job type (radiologist versus breast physician/radiographer) or experience.

Classification of linear structures, such as blood vessels, milk ducts, spiculations and fibrous tissue can be used to aid the automated detection and diagnosis of mammographic abnormalities We use a combination of dual-tree complex wavelet coefficients and random forest classification to detect and classify different types of linear structure Encouraging results are presented for synthetic linear structures added to real mammographic backgrounds, and spicules in real mammograms For spicule/non-spicule classification in real mammograms we report an area Az = 0.764 under the receiver operating characteristic.

21158 screening mammograms were obtained, 10024 acquired using full field digital mammography (FFDM) and 11134 acquired using film-screen mammography For each mammogram, data were collected on recall for further assessment due to detection of microcalcification, use of needle biopsy, and presence of microcalcifications in biopsy specimens 61.5% of women who had a core biopsy following digital mammography had microcalcifications detected, compared with 65.8% for analogue mammography but this difference was not significant (p=0.71) Rates of detection of microcalcifications in women screened by the two methods were similar It was also found that the recall rate for assessment for women screened digitally (6.1%) was significantly higher than the recall rate for those screened by analogue mammography (3.3%), 95% confidence interval 2.2% - 3.4% Screening using digital mammography leads to a higher recall rate for assessment than analogue mammography, although similar rates of detection of microcalcifications occur with both imaging modalities.

Breast density is positively linked to the risk of developing breast cancer Furthermore, the addition of breast density as an input to breast cancer risk prediction models has been shown to improve their predictive power Such models are used in the management of women at high risk but could potentially be used to determine screening strategy A stepwedge-based technique has been used to measure volumetric density from the mammograms of 1,289 women in the UK screening programme who additionally completed a questionnaire on risk-related factors The sample had a mean age of 60.1 (range 48.0 – 78.0), a mean breast thickness of 59mm (range 21 – 102mm) and a mean volumetric breast density of 11% (range 0.5 – 58%) Using Pearson's correlation coefficient, breast density was found to be significantly correlated with weight (r = -0.45), body mass index (r = -0.48), age (r = -0.13) and breast thickness (r =-0.65) at the p = 0.01 level Absolute glandular volume was also found to be significantly correlated with these parameters although the extent of correlation was weaker.

Using mammograms in which signs of breast cancer have been synthesised overcomes the problem of obtaining a sufficiently large volume of real data with known ground truth for training and test purposes This paper describes a fully automated method for generating synthetic spiculated masses Statistical methods are used to model the appearance and location of a training set of real masses and their effect on surrounding breast tissue The models are then used to synthesise the appearance of a malignant mass in an otherwise normal mammogram By virtue of using generative statistical models, the synthesis process can be fully automated In an observer study in which 10 expert mammogram readers attempted to distinguish between synthetic masses generated by the method and real masses, we report an area Az = 0.70±0.09 under the receiver operating characteristic.

This study compares visual assessment of density on full field digital mammograms using visual analogue scales (VAS) and written percentages Fifty normal digital screening mammograms were selected at random Nine readers viewed the images on two occasions, firstly indicating density on a VAS and then estimating the percentage of dense tissue in the breast Although the two methods were correlated, the degree of agreement between the density estimates varied considerably from reader to reader More experienced readers used a wider range of values, and inter-observer variability for both methods was higher for these readers The greatest difference between the methods was in mammograms with a mixed fatty-glandular appearance (density between 55% and 75%) Both methods are quick and convenient, although these results demonstrate a need for training to ensure they are used consistently by readers of different degrees of experience.

The appearance of breast tissue in mammograms is altered by the presence of a malignant mass Existing synthesis methods have not addressed this structural deformation We aim to use a set of mass background images that display altered breast tissue to simulate such deformations in regions of digital mammograms previously showing no signs of disease Regions are decomposed using the dual-tree complex wavelet transform (DT-CWT) to obtain a richer representation of local structure than provided by image grey-levels alone Synthesis is achieved by modifying the high-frequency DT-CWT coefficients of normal regions to match those in mass backgrounds Three methods for completing this task are described The results, advantages and current limitations of the methods are discussed.

If breast density is to be incorporated into breast cancer risk prediction models, the technique used for measurement must be quantitative, accurate, objective and reproducible We present a semi-automated method that has been used by three independent operators to measure glandular volume from the digitised mammograms of 29 women (116 images) Additionally, one operator used the method on 10 separate occasions on a sample of 24 images Intra-observer variability was found to be acceptably low, with coefficients of variation ranging from 3.5 – 5.7% depending on mammographic view (intra-class correlation coefficient close to 1 in all cases) However, inter-observer variability was greater with significant differences in glandular volume recorded between observers This was attributed to the method of breast edge detection The development of a new automatic breast edge detection algorithm has resolved the issue The average difference in glandular volume measurement between two independent operators in the cranio-caudal view is -0.89cm3 (95% confidence interval -2.77 – 0.99 cm3) using the new method, compared to 5.99cm3 (95% confidence interval 2.72 – 9.76 cm3) using the old method.

We present a method for building generative statistical appearance models of mammographic masses. We address several key issues that limited the performance of previous methods. In particular, we use MDL optimization to generate more compact shape correspondences; we describe a technique for the accurate estimation of the background tissue on which a mass is superimposed; and we highlight the importance of choosing suitable weighting between shape, texture and scale components in the final combined model. Improvements in the ability of the model to characterize a set of 101 mammographic masses are quantified using leave-one-out testing, showing a reduction in mean square error per pixel from 3.109 using a previous method to 1.262 using the new appearance model.

A link between increased breast density, as visualised in mammograms, and increased risk of developing breast cancer has been established. Recently, a number of objective, quantitative methods for measuring breast density have been described. One such method requires a calibration object to be imaged alongside the breast. However, it is important that this should not interfere with the routine imaging process. In this paper, we investigate the amount of space in mammographic images which is not currently occupied by the breast or existing patient labels and markers, and which would therefore be available for imaging an additional calibration device. We do this with a view to estimating the likelihood of failure of the method, and also to determining whether, without detriment to the imaging process, a device could be permanently fixed to the breast support platform. We also examine the impact of markers attached to the compression plate on the visibility of breast tissue. The results show that our existing calibration device may be used successfully without interfering with the routine imaging process, although permanently fixing such a device may present problems in a small minority of cases, and we demonstrate that the number of cases which would fail can be reduced by using a smaller stepwedge.

Increased mammographic density is a well-established risk factor for breast cancer; much of the evidence is based on semi-automated or visual assessment of analogue mammograms, although volumetric measures from digitally acquired mammograms are now being reported. It is also possible to quantify volumes of fat and gland from digitised analogue mammograms, given suitable calibration data. We have measured breast density in cancer cases and controls which had previous analogue screening mammograms in the PROCAS (Predicting Risk Of Cancer At Screening) study.