ABSTRACT. The current study investigates the feasibility of using texture analysis to quantify the heterogeneity of lesion enhancement kinetics in order to discriminate malignant from benign breast lesions. A total of 82 biopsy-proven breast lesions (51 malignant, 31 benign), originating from 74 women subjected to dynamic contrastenhanced magnetic resonance imaging (DCE-MRI) were analysed. Pixel-wise analysis of DCE-MRI lesion data was performed to generate initial enhancement, post-initial enhancement and signal enhancement ratio (SER) parametric maps; these maps were subsequently subjected to co-occurrence matrix texture analysis. The discriminating ability of texture features extracted from each parametric map was investigated using a least-squares minimum distance classifier and further compared with the discriminating ability of the same texture features extracted from the first post-contrast frame. Selected texture features extracted from the SER map achieved an area under receiver operating characteristic curve of 0.922 ¡ 0.029, a performance similar to post-initial enhancement map features (0.906 ¡ 0.032) and statistically significantly higher than for initial enhancement map (0.767 ¡ 0.053) and first post-contrast frame (0.756 ¡ 0.060) features. Quantifying the heterogeneity of parametric maps that reflect lesion washout properties could contribute to the computer-aided diagnosis of breast lesions in DCE-MRI. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) significantly complements mammography and is characterised by its high sensitivity in detecting breast cancer. However, its specificity in distinguishing malignant from benign lesions is highly varied: reported values range from 37 up to 90% [1]. This variation is mainly due to the variety of image acquisition protocols and interpretation schemes adopted in clinical practice [2].Diagnostic criteria in DCE-MRI of breast masses [3, 4] include assessment of morphological features such as lesion shape, margin and enhancement homogeneity (internal architecture), as well as analysis/assessment of signal intensity-time curves generated from manually selected regions of interest (ROIs) within the lesion area. The analysis of signal intensity-time curves can be performed qualitatively (i.e. visual inspection of the curve shape [5,6]), by means of empirical parameters (e.g. relative enhancement, time-to-peak enhancement, washout ratio [7]) or quantitatively through pharmacokinetic modelling techniques [8].The subjective selection of ROI within the lesion accounts for the increased intra-and interobserver variability in the interpretation of lesion enhancement kinetics and for the discrepancy of reported findings [9,10]. While the selection of an ROI that captures the entire lesion is less subjective [11], it provides average enhancement kinetics estimates and completely ignores the heterogeneity of tumour vascular characteristics, which is diagnostically important [12]. Pixel-wise analysis of enhancement kinetics (based either on pharmacokinetic ...
Intervertebral disc degeneration is an age-associated condition related to chronic back pain, while its consequences are responsible for over 90 % of spine surgical procedures. In clinical practice, MRI is the modality of reference for diagnosing disc degeneration. In this study, we worked toward 2-D semiautomatic segmentation of both normal and degenerated lumbar intervertebral discs from T2-weighted midsagittal MR images of the spine. This task is challenged by partial volume effects and overlapping gray-level values between neighboring tissue classes. To overcome these problems three variations of atlas-based segmentation using a probabilistic atlas of the intervertebral disc were developed and their accuracies were quantitatively evaluated against manually segmented data. The best overall performance, when considering the tradeoff between segmentation accuracy and time efficiency, was accomplished by the atlas-robust-fuzzy c-means approach, which combines prior anatomical knowledge by means of a rigidly registered probabilistic disc atlas with fuzzy clustering techniques incorporating smoothness constraints. The dice similarity indexes of this method were 91.6 % for normal and 87.2 % for degenerated discs. Research in progress utilizes the proposed approach as part of a computer-aided diagnosis system for quantification and characterization of disc degeneration severity. Moreover, this approach could be exploited in computer-assisted spine surgery.
Deep convolutional neural networks (CNNs) are investigated in the context of computer-aided diagnosis (CADx) of breast cancer. State-of-the-art CNNs are trained and evaluated on two mammographic datasets, consisting of ROIs depicting benign or malignant mass lesions. The performance evaluation of each examined network is addressed in two training scenarios: the first involves initializing the network with pre-trained weights, while for the second the networks are initialized in a random fashion. Extensive experimental results show the superior performance achieved in the case of fine-tuning a pretrained network compared to training from scratch.
A method aimed at minimizing image noise while optimizing contrast of image features is presented. The method is generic and it is based on local modification of multiscale gradient magnitude values provided by the redundant dyadic wavelet transform. Denoising is accomplished by a spatially adaptive thresholding strategy, taking into account local signal and noise standard deviation. Noise standard deviation is estimated from the background of the mammogram. Contrast enhancement is accomplished by applying a local linear mapping operator on denoised wavelet magnitude values. The operator normalizes local gradient magnitude maxima to the global maximum of the first scale magnitude subimage. Coefficient mapping is controlled by a local gain limit parameter. The processed image is derived by reconstruction from the modified wavelet coefficients. The method is demonstrated with a simulated image with added Gaussian noise, while an initial quantitative performance evaluation using 22 images from the DDSM database was performed. Enhancement was applied globally to each mammogram, using the same local gain limit value. Quantitative contrast and noise metrics were used to evaluate the quality of processed image regions containing verified lesions. Results suggest that the method offers significantly improved performance over conventional and previously reported global wavelet contrast enhancement methods. The average contrast improvement, noise amplification and contrast-to-noise ratio improvement indices were measured as 9.04, 4.86 and 3.04, respectively. In addition, in a pilot preference study, the proposed method demonstrated the highest ranking, among the methods compared. The method was implemented in C++ and integrated into a medical image visualization tool.
Diagnosis of microcalcifications (MCs) is challenged by the presence of dense breast parenchyma, resulting in low specificity values and thus in unnecessary biopsies. The current study investigates whether texture properties of the tissue surrounding MCs can contribute to breast cancer diagnosis. A case sample of 100 biopsy-proved MC clusters (46 benign, 54 malignant) from 85 dense mammographic images, included in the Digital Database for Screening Mammography, was analysed. Regions of interest (ROIs) containing the MCs were pre-processed using a wavelet-based contrast enhancement method, followed by local thresholding to segment MCs; the segmented MCs were excluded from original image ROIs, and the remaining area (surrounding tissue) was subjected to texture analysis. Four categories of textural features (first order statistics, co-occurrence matrices features, run length matrices features and Laws' texture energy measures) were extracted from the surrounding tissue. The ability of each feature category in discriminating malignant from benign tissue was investigated using a k-nearest neighbour (kNN) classifier. An additional classification scheme was performed by combining classification outputs of three textural feature categories (the most discriminating ones) with a majority voting rule. Receiver operating characteristic (ROC) analysis was conducted for classifier performance evaluation of the individual textural feature categories and of the combined classification scheme. The best performance was achieved by the combined classification scheme yielding an area under the ROC curve (A(z)) of 0.96 (sensitivity 94.4%, specificity 80.0%). Texture analysis of tissue surrounding MCs shows promising results in computer-aided diagnosis of breast cancer and may contribute to the reduction of unnecessary biopsies.
The current study investigates texture properties of the tissue surrounding microcalcification (MC) clusters on mammograms for breast cancer diagnosis. The case sample analyzed consists of 85 dense mammographic images, originating from the Digital Database for Screening Mammography. Mammograms analyzed contain 100 subtle MC clusters (46 benign and 54 malignant). The tissue surrounding MCs is defined on original and wavelet decomposed images, based on a redundant discrete wavelet transform. Gray-level texture and wavelet coefficient texture features at three decomposition levels are extracted from surrounding tissue regions of interest (ST-ROIs). Specifically, gray-level first-order statistics, gray-level cooccurrence matrices features, and Laws' texture energy measures are extracted from original image ST-ROIs. Wavelet coefficient first-order statistics and wavelet coefficient cooccurrence matrices features are extracted from subimages ST-ROIs. The ability of each feature set in differentiating malignant from benign tissue is investigated using a probabilistic neural network. Classification outputs of most discriminating feature sets are combined using a majority voting rule. The proposed combined scheme achieved an area under receiver operating characteristic curve ( A(z)) of 0.989. Results suggest that MCs' ST texture analysis can contribute to computer-aided diagnosis of breast cancer.
The first step in lung analysis by CT is the identification of the lung border. To deal with the increased number of sections per scan in thin-slice multidetector CT, it has been crucial to develop accurate and automated lung segmentation algorithms. In this study, an automated method for lung segmentation of thin-slice CT data is presented. The method exploits the advantages of a two-dimensional wavelet edge-highlighting step in lung border delineation. Lung volume segmentation is achieved with three-dimensional (3D) grey level thresholding, using a minimum error technique. 3D thresholding, combined with the wavelet pre-processing step, successfully deals with lung border segmentation challenges, such as anterior or posterior junction lines and juxtapleural nodules. Finally, to deal with mediastinum border under-segmentation, 3D morphological closing with a spherical structural element is applied. The performance of the proposed method is quantitatively assessed on a dataset originating from the Lung Imaging Database Consortium (LIDC) by comparing automatically derived borders with the manually traced ones. Segmentation performance, averaged over left and right lung volumes, for lung volume overlap is 0.983+/-0.008, whereas for shape differentiation in terms of mean distance it is 0.770+/-0.251 mm (root mean square distance is 0.520+/-0.008 mm; maximum distance is 3.327+/-1.637 mm). The effect of the wavelet pre-processing step was assessed by comparing the proposed method with the 3D thresholding technique (applied on original volume data). This yielded statistically significant differences for all segmentation metrics (p<0.01). Results demonstrate an accurate method that could be used as a first step in computer lung analysis by CT.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.