Bram Platel

Volumetric breast density estimation from Full-Field Digital Mammograms: A validation study

A method is presented for estimation of dense breast tissue volume from mammograms obtained with full-field digital mammography (FFDM). The thickness of dense tissue mapping to a pixel is determined by using a physical model of image acquisition. This model is based on the assumption that the breast is composed of two types of tissue, fat and parenchyma. Effective linear attenuation coefficients of these tissues are derived from empirical data as a function of tube voltage (kVp), anode material, filtration, and compressed breast thickness. By employing these, tissue composition at a given pixel is computed after performing breast thickness compensation, using a reference value for fatty tissue determined by the maximum pixel value in the breast tissue projection. Validation has been performed using 22 FFDM cases acquired with a GE Senographe 2000D by comparing the volume estimates with volumes obtained by semi-automatic segmentation of breast magnetic resonance imaging (MRI) data. The correlation between MRI and mammography volumes was 0.94 on a per image basis and 0.97 on a per patient basis. Using the dense tissue volumes from MRI data as the gold standard, the average relative error of the volume estimates was 13.6%.

A Novel Approach to Contrast-enhanced Breast Magnetic Resonance Imaging for Screening: High-resolution Ultrafast Dynamic Imaging

ObjectivesThe use of breast magnetic resonance imaging (MRI) as screening tool has been stalled by high examination costs. Scan protocols have lengthened to optimize specificity. Modern view-sharing sequences now enable ultrafast dynamic whole-breast MRI, allowing much shorter and more cost-effective procedures. This study evaluates whether dynamic information from ultrafast breast MRI can be used to replace standard dynamic information to preserve accuracy. Materials and MethodsWe interleaved 20 ultrafast time-resolved angiography with stochastic trajectory (TWIST) acquisitions (0.9 × 1 × 2.5 mm, temporal resolution, 4.3 seconds) during contrast inflow in a regular high-resolution dynamic MRI protocol. A total of 160 consecutive patients with 199 enhancing abnormalities (95 benign and 104 malignant) were included. The maximum slope of the relative enhancement versus time curve (MS) obtained from the TWIST and curve type obtained from the regular dynamic sequence as defined in the breast imaging reporting and data system (BIRADS) lexicon were recorded. Diagnostic performance was compared using receiver operating characteristic analysis. ResultsAll lesions were visible on both the TWIST and standard series. Maximum slope allows discrimination between benign and malignant disease with high accuracy (area under the curve, 0.829). Types of MS were defined in analogy to BIRADS curve types: MS type 3 implies a high risk of malignancy (MS >13.3%/s; specificity, 85%), MS type 2 yields intermediate risk (MS <13.3%/s and >6.4%/s), and MS type 1 implies a low risk (MS <6.4%/s; sensitivity, 90%). This simplification provides a much higher accuracy than the much lengthier BIRADS curve type analysis does (area under the curve, 0.812 vs 0.692; P = 0.0061). ConclusionsUltrafast dynamic breast MRI allows detection of breast lesions and classification with high accuracy using MS. This allows substantial shortening of scan protocols and hence reduces imaging costs, which is beneficial especially for screening.

Computer-Aided Lesion Diagnosis in Automated 3-D Breast Ultrasound Using Coronal Spiculation

A computer-aided diagnosis (CAD) system for the classification of lesions as malignant or benign in automated 3-D breast ultrasound (ABUS) images, is presented. Lesions are automatically segmented when a seed point is provided, using dynamic programming in combination with a spiral scanning technique. A novel aspect of ABUS imaging is the presence of spiculation patterns in coronal planes perpendicular to the transducer. Spiculation patterns are characteristic for malignant lesions. Therefore, we compute spiculation features and combine them with features related to echotexture, echogenicity, shape, posterior acoustic behavior and margins. Classification experiments were performed using a support vector machine classifier and evaluation was done with leave-one-patient-out cross-validation. Receiver operator characteristic (ROC) analysis was used to determine performance of the system on a dataset of 201 lesions. We found that spiculation was among the most discriminative features. Using all features, the area under the ROC curve (Az) was 0.93, which was significantly higher than the performance without spiculation features (Az=0.90, p=0.02). On a subset of 88 cases, classification performance of CAD (Az=0.90) was comparable to the average performance of 10 readers (Az=0.87).

Parameter Sensitivity Visualization for DTI Fiber Tracking

Fiber tracking of diffusion tensor imaging (DTI) data offers a unique insight into the three-dimensional organisation of white matter structures in the living brain. However, fiber tracking algorithms require a number of user-defined input parameters that strongly affect the output results. Usually the fiber tracking parameters are set once and are then re-used for several patient datasets. However, the stability of the chosen parameters is not evaluated and a small change in the parameter values can give very different results. The user remains completely unaware of such effects. Furthermore, it is difficult to reproduce output results between different users. We propose a visualization tool that allows the user to visually explore how small variations in parameter values affect the output of fiber tracking. With this knowledge the user cannot only assess the stability of commonly used parameter values but also evaluate in a more reliable way the output results between different patients. Existing tools do not provide such information. A small user evaluation of our tool has been done to show the potential of the technique.

Automated localization of breast cancer in DCE-MRI

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is increasingly being used for the detection and diagnosis of breast cancer. Compared to mammography, DCE-MRI provides higher sensitivity, however its specificity is variable. Moreover, DCE-MRI data analysis is time consuming and depends on reader expertise. The aim of this work is to propose a novel automated breast cancer localization system for DCE-MRI. Such a system can be used to support radiologists in DCE-MRI analysis by marking suspicious areas. The proposed method initially corrects for motion artifacts and segments the breast. Subsequently, blob and relative enhancement voxel features are used to locate lesion candidates. Finally, a malignancy score for each lesion candidate is obtained using region-based morphological and kinetic features computed on the segmented lesion candidate. We performed experiments to compare the use of different classifiers in the region classification stage and to study the effect of motion correction in the presented system. The performance of the algorithm was assessed using free-response operating characteristic (FROC) analysis. For this purpose, a dataset of 209 DCE-MRI studies was collected. It is composed of 95 DCE-MRI studies with 105 breast cancers (55 mass-like and 50 non-mass-like malignant lesions) and 114 DCE-MRI studies from women participating in a screening program which were diagnosed to be normal. At 4 false positives per normal case, 89% of the breast cancers (91% and 86% for mass-like and non-mass-like malignant lesions, respectively) were correctly detected.

Computer-Aided Detection of Cancer in Automated 3-D Breast Ultrasound

Automated 3-D breast ultrasound (ABUS) has gained a lot of interest and may become widely used in screening of dense breasts, where sensitivity of mammography is poor. However, reading ABUS images is time consuming, and subtle abnormalities may be missed. Therefore, we are developing a computer aided detection (CAD) system to help reduce reading time and prevent errors. In the multi-stage system we propose, segmentations of the breast, the nipple and the chestwall are performed, providing landmarks for the detection algorithm. Subsequently, voxel features characterizing coronal spiculation patterns, blobness, contrast, and depth are extracted. Using an ensemble of neural-network classifiers, a likelihood map indicating potential abnormality is computed. Local maxima in the likelihood map are determined and form a set of candidates in each image. These candidates are further processed in a second detection stage, which includes region segmentation, feature extraction and a final classification. On region level, classification experiments were performed using different classifiers including an ensemble of neural networks, a support vector machine, a k-nearest neighbors, a linear discriminant, and a gentle boost classifier. Performance was determined using a dataset of 238 patients with 348 images (views), including 169 malignant and 154 benign lesions. Using free response receiver operating characteristic (FROC) analysis, the system obtains a view-based sensitivity of 64% at 1 false positives per image using an ensemble of neural-network classifiers.

Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities

The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).

Fully automatic breast segmentation in 3D breast MRI

In computer-aided diagnosis of breast MRI, a precise segmentation of the breast is often required as a fundamental step to facilitate further diagnostic tasks, e.g., breast density measurement, lesion detection and automatic reporting. In this work, a fully automatic method dedicated to breast segmentation is proposed, which comprises four major steps: sheet-like structures enhancement, pectoralis muscle boundary segmentation, breast-air boundary segmentation and breast extraction. To validate the proposed method, the segmented breast boundaries of 84 breast MR images, acquired in five different sites with variant imaging protocols, were compared to the manual segmentation. An average distance of 2.56mm with a standard deviation of 3.26mm was achieved.

Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin

Lacunes of presumed vascular origin (lacunes) are associated with an increased risk of stroke, gait impairment, and dementia and are a primary imaging feature of the small vessel disease. Quantification of lacunes may be of great importance to elucidate the mechanisms behind neuro-degenerative disorders and is recommended as part of study standards for small vessel disease research. However, due to the different appearance of lacunes in various brain regions and the existence of other similar-looking structures, such as perivascular spaces, manual annotation is a difficult, elaborative and subjective task, which can potentially be greatly improved by reliable and consistent computer-aided detection (CAD) routines. In this paper, we propose an automated two-stage method using deep convolutional neural networks (CNN). We show that this method has good performance and can considerably benefit readers. We first use a fully convolutional neural network to detect initial candidates. In the second step, we employ a 3D CNN as a false positive reduction tool. As the location information is important to the analysis of candidate structures, we further equip the network with contextual information using multi-scale analysis and integration of explicit location features. We trained, validated and tested our networks on a large dataset of 1075 cases obtained from two different studies. Subsequently, we conducted an observer study with four trained observers and compared our method with them using a free-response operating characteristic analysis. Shown on a test set of 111 cases, the resulting CAD system exhibits performance similar to the trained human observers and achieves a sensitivity of 0.974 with 0.13 false positives per slice. A feasibility study also showed that a trained human observer would considerably benefit once aided by the CAD system.

Longitudinal multiple sclerosis lesion segmentation: Resource and challenge

Abstract In conjunction with the ISBI 2015 conference, we organized a longitudinal lesion segmentation challenge providing training and test data to registered participants. The training data consisted of five subjects with a mean of 4.4 time‐points, and test data of fourteen subjects with a mean of 4.4 time‐points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. Eleven teams submitted results using state‐of‐the‐art lesion segmentation algorithms to the challenge, with ten teams presenting their results at the conference. We present a quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms. The challenge presented three unique opportunities: (1) the sharing of a rich data set; (2) collaboration and comparison of the various avenues of research being pursued in the community; and (3) a review and refinement of the evaluation metrics currently in use. We report on the performance of the challenge participants, as well as the construction and evaluation of a consensus delineation. The image data and manual delineations will continue to be available for download, through an evaluation website2 as a resource for future researchers in the area. This data resource provides a platform to compare existing methods in a fair and consistent manner to each other and multiple manual raters. HighlightsPublic lesion data base of 21 training data sets and 61 testing data sets.Fully automated evaluation website.Comparison between 14 state‐of‐the‐art algorithms and 2 manual delineators.