Roman Janer

Four image interpolation techniques for ultrasound breast phantom data acquired using Fischer's full field digital mammography and ultrasound system (FFDMUS): a comparative approach

In computer-aided analysis of mammograms, a fast processing analysis for mammograms benefits and facilitate the real time application and is also useful for radiologist to do on-line diagnosis. Down sampling is widely applied to reduce the size of large images and improve the processing speed. This paper presents the performance evaluations among several interpolation techniques (bilinear, bicubic, wavelet and Lanczos) for ultrasound breast phantom data. We also compared lesion segmentation results of down sampled images with the results of original images. Two major metrics: the Hausdorff distance measure (HDM) and polyline distance measure (PDM) were applied to measure the performance of the segmentation. We conclude that without scarifying the quality of ultrasound images, we increase the speed of system processing using our down sampling strategies. Moreover, among the four different technologies, the Lanczos algorithm can achieve the best performance.

Image quality assessment via segmentation of breast lesion in X-ray and ultrasound phantom images from Fischer's full field digital mammography and ultrasound (FFDMUS) system.

Fischer has been developing a fused full-field digital mammography and ultrasound (FFDMUS) system funded by the National Institute of Health (NIH). In FFDMUS, two sets of acquisitions are performed: 2-D X-ray and 3-D ultrasound. The segmentation of acquired lesions in phantom images is important: (i) to assess the image quality of X-ray and ultrasound images; (ii) to register multi-modality images; and (iii) to establish an automatic lesion detection methodology to assist the radiologist. In this paper we developed lesion segmentation strategies for ultrasound and X-ray images acquired using FFDMUS. For ultrasound lesion segmentation, a signal-to-noise (SNR)-based method was adapted. For X-ray segmentation, we used gradient vector flow (GVF)-based deformable model. The performance of these segmentation algorithms was evaluated. We also performed partial volume correction (PVC) analysis on the segmentation of ultrasound images. For X-ray lesion segmentation, we also studied the effect of PDE smoothing on GVFs ability to segment the lesion. We conclude that ultrasound image qualities from FFDMUS and Hand-Held ultrasound (HHUS) are comparable. The mean percentage error with PVC was 4.56% (4.31%) and 6.63% (5.89%) for 5 mm lesion and 3 mm lesion respectively. The mean average error from the segmented X-ray images with PDE yielded an average error of 9.61%. We also tested our program on synthetic datasets. The system was developed for Linux workstation using C/C++.

Effect of Adaptive-Neighborhood Contrast Enhancement on the Extraction of the Breast Skin-Line in Mammograms

Extraction of the breast skin-line is crucial in computer-aided analysis of mammograms. This paper presents an analysis of the effect of adaptive-neighborhood contrast enhancement (ANCE) on skin-line extraction. ANCE is used to enhance the parenchyma of the breast and suppress the background noise. Suppression of the background noise can improve skin-line extraction. Our skin-line extraction method is based on the work by Ojala et al (2001). We use the Hausdorff distance for quantitative comparison of the skin-lines. Our work shows that ANCE improves the skin-line extraction due to its ability of suppressing noise while improving the contrast. We have defined an improvement factor based on the Hausdorff distance. The metric allows us to spot automatically the mammograms with significant improvement in the detection of the skin-line because of ANCE. We tested 83 images from the MIAS database, with the ground-truth skin-lines hand-drawn by a radiologist. The average Hausdorff distance improvement with ANCE was 11 pixels (2.2 mm)

Relationship between the stroma edge and skin-air boundary for generating a dependency approach to skin-line estimation in screening mammograms

Breast area segmentation or skin-line extraction in mammograms is very important in many aspects. Prior segmentation can reduce the effects of background noise and artifacts on the analysis of mammograms. In this paper, we investigate a novel method to estimate the breast skin-line in mammograms. Adaptive thresholding [1] yields a nearly perfect skin-line at the center of the image and around the nipple area with images from the MIAS database [2], but the upper and lower portions of the extracted boundary have been observed to be erroneous due to noise and artifacts. Because the distance from the edge of the stroma to the actual skin-line is usually uniform, we propose a method to estimate the skin-line from the edge of the stroma, with the information provided by the center portion around the nipple from adaptive thresholding. The results are compared with the ground-truth boundaries drawn by a radiologist [3] using polyline distance measure and shape smoothness measure. The results on 83 mammograms from the MIAS database are demonstrated. The proposed methods led to a decrease in a shape smoothness measure based upon curvature, on the average, from 65.6 to 20.0 over the 83 mammograms tested, resulting in an improvement of 69.5%.

13.3: MTF and NPS Study of High-Resolution LCDs and CRTs for Mammography

This paper presents a closer look on the link between the physical parameters (MTF and NPS) that characterize the performance of a liquid crystal display (LCD) and the architecture that generates the images. Understanding the major architectural difference between the cathode ray tube (CRT) and LCD displays can lead to better image quality analysis and characterization of the LCD displays. The aim of this research is to quantify two major image quality control parameters namely, modulation transfer function (MTF) and noise power spectrum (NPS) and understand their significance with respect to the architecture of the LCD and CRT displays. The experimentation was performed at Fischer Imaging Corporation research and development division in Denver, CO. We conclude the following: (1) The MTF of LCD is higher than that of CRT, and (2) LCD has higher NPS. The results thus infer that the LCD is better suitable display compared to CRT displays for mammography applications particularly considering its superior resolution.

P‐186: A Study of CRT (5‐Mpixel) vs. LCD (9‐Mpixel) Displays for Breast Lesion Detection in Full‐Field Digital Mammography and Ultrasound (FFDMUS) Data Sets via Image‐Enhancement Algorithms

The latest technological changes are fast replacing the conventional cathode ray tube (CRT) displays with liquid crystal displays (LCDs). It is thus important to understand and evaluate them. The novelty of our evaluation strategy comes from the usage of computer aided diagnostics-based on pixel intensities. This evaluation system combines both lesion segmentation and quantification. Hence it is an integrated approach. The FFDMUS ultrasound data was acquired and then displayed on LCD and CRT displays. The FFDMUS ultrasound images were segmented using the signal-to-noise ratio (SNR) algorithm. We use Hausdoff distance measure (HDM) and polyline distance metric (PDM) for performance evaluation. Our results using the HDM method on FFDMUS ultrasound images show that lesions quantified from LCD images show a 29% improvement compared to lesions quantified from CRT images. A similar behavior was observed using PDM method. Hence we conclude that use of LCD displays for mammography applications with image enhancement techniques will have a greater diagnostic accuracy compared to the CRT displays.

Effect of PDE-based noise removal on GVF-based deformation model on lesion detection in breast phantom x-ray images from Fischer’s fused FFDM and ultrasound (FFDMUS) imaging system

It has been recently established that fusion of multi-modalities has led to better diagnostic capability and increased sensitivity and specificity. Fischer has been developing fused full-field digital mammography and ultrasound (FFDMUS) system. In FFDMUS, two sets of acquisitions are performed: 2-D X-ray and 3-D ultrasound. The segmentation of acquired lesions in phantom images is important: (1) to assess the image quality of X-ray and ultrasound images; (2) to register multi-modality images, and (3) to establish an automatic lesion detection methodology to assist the radiologist. In this paper, we studied the effect of PDE-based smoother on the gradient vector flow (GVF)-based active contour model for breast lesion detection. CIRS X-ray phantom images were acquired using FFDMUS, and region of interest (ROI) samples were extracted. PDE-based smoother was implemented to generate noise free images. The GVF-based strategy was then implemented on these noise free samples. Initial contours were set as default, and GVF snake then converged to extract lesion topology. The performance index was calculated by computing the difference between estimated lesion area and ideal lesion area. Our performance index with GVF (without PDE smoothing) yielded an average percentage error of 10.32%, while GVF with PDE yielded an average error of 9.61%, an improvement of 7%. We also optimized our PDE smoother for least GVF error estimation, and to our observation, we found the optimal number of iteration was 140. We also tested our program written in C++ on synthetic datasets.