Search

Purpose: Segmentation of microcalcification (MC) clusters in x-ray mammography is a difficult task for radiologists. Accurate segmentation is prerequisite for quantitative image analysis of MC clusters and subsequent feature extraction and classification in computer-aided diagnosis schemes. Methods: In this study, a two-stage semiautomated segmentation method of MC clusters is investigated. The first stage is targeted to accurate and time efficient segmentation of the majority of the particles of a MC cluster, by means of a level set method. The second stage is targeted to shape refinement of selected individual MCs, by means of an active contour model. Both methods are applied in the framework of a rich scale-space representation, provided by the wavelet transform at integer scales. Segmentation reliability of the proposed method in terms of inter and intraobserver agreements was evaluated in a case sample of 80 MC clusters originating from the digital database for screening mammography, corresponding to 4 morphology types (punctate: 22, fine linear branching: 16, pleomorphic: 18, and amorphous: 24) of MC clusters, assessing radiologists’ segmentations quantitatively by two distance metrics (Hausdorff distance—HDIST{sub cluster}, average of minimum distance—AMINDIST{sub cluster}) and the area overlap measure (AOM{sub cluster}). The effect of the proposed segmentation method on MC clustermore » characterization accuracy was evaluated in a case sample of 162 pleomorphic MC clusters (72 malignant and 90 benign). Ten MC cluster features, targeted to capture morphologic properties of individual MCs in a cluster (area, major length, perimeter, compactness, and spread), were extracted and a correlation-based feature selection method yielded a feature subset to feed in a support vector machine classifier. Classification performance of the MC cluster features was estimated by means of the area under receiver operating characteristic curve (Az ± Standard Error) utilizing tenfold cross-validation methodology. A previously developed B-spline active rays segmentation method was also considered for comparison purposes. Results: Interobserver and intraobserver segmentation agreements (median and [25%, 75%] quartile range) were substantial with respect to the distance metrics HDIST{sub cluster} (2.3 [1.8, 2.9] and 2.5 [2.1, 3.2] pixels) and AMINDIST{sub cluster} (0.8 [0.6, 1.0] and 1.0 [0.8, 1.2] pixels), while moderate with respect to AOM{sub cluster} (0.64 [0.55, 0.71] and 0.59 [0.52, 0.66]). The proposed segmentation method outperformed (0.80 ± 0.04) statistically significantly (Mann-Whitney U-test, p < 0.05) the B-spline active rays segmentation method (0.69 ± 0.04), suggesting the significance of the proposed semiautomated method. Conclusions: Results indicate a reliable semiautomated segmentation method for MC clusters offered by deformable models, which could be utilized in MC cluster quantitative image analysis.« less

The purpose of the present study was to evaluate the visibility and the image quality of the biliary and pancreatic duct system on magnetic resonance cholangiopancreatography (MRCP) images based on two breath-hold (BH) methods using array spatial sensitivity technique: a single-shot fast spin-echo (SS-FSE) sequence and a three-dimensional single slab fast spin-echo (3D-FSE) sequence.In the present prospective comparative study, 47 patients (22 male and 25 female, mean age=50 years, age range=22-82 years) that were referred for MRCP during a 12-month period are included. All of them were referred with suspected pancreaticobiliary disease. All patients underwent MRCP with both a SS-FSE BH sequence and a 3D-FSE BH sequence. Qualitative evaluation regarding the depiction of three segments of the pancreaticobiliary tree and the frequency of artifacts was performed. Two radiologists graded each sequence of the obtained studies in a blinded fashion. Quantitative evaluation including calculation of relative signal intensity (rSI) and relative contrast (RC) ratios at seven segments of the pancreaticobiliary tree between fluid-filled ductal structures and organ parenchyma at the same ductal segments was performed. In order to evaluate the parameters' differences of the two sequences, either in qualitative or in quantitative analysis, the Wilcoxon paired signed-rank test was performed.On quantitative evaluation, both rSI and RC ratios of all segments of the pancreaticobiliary tree at SS-FSE BH sequence were higher than those at 3D-FSE BH sequences. This finding was statistically significant (P.01). On qualitative evaluation, the two radiologists found intrahepatic ducts and pancreatic ducts to be better visualized with SS-FSE BH than with 3D-FSE BH sequence. This finding was statistically significant (P.02). One of them found extrahepatic ducts to be significantly better visualized with SS-FSE BH sequence. Moreover, the frequency of artifacts was lower in the SS-FSE sequence, a finding that was of statistical significance. Interobserver agreement analysis found at least substantial agreement (κ0.60) between the two radiologists.The SS-FSE sequence is performed faster and significantly improves image quality; thus, it should be included into the routine MRCP sequence protocol at 3.0 T. Furthermore, we recommended SS-FSE BH MRCP examination to be applied to uncooperative patients or patients in emergency because of its short acquisition time (1 s).

Accurate segmentation of microcalcifications in mammography is crucial for the quantification of morphologic properties by features incorporated in computer-aided diagnosis schemes. A novel segmentation method is proposed implementing active rays (polar-transformed active contours) on B-spline wavelet representation to identify microcalcification contour point estimates in a coarse-to-fine strategy at two levels of analysis. An iterative region growing method is used to delineate the final microcalcification contour curve, with pixel aggregation constrained by the microcalcification contour point estimates. A radial gradient-based method was also implemented for comparative purposes. The methods were tested on a dataset consisting of 149 mainly pleomorphic microcalcification clusters originating from 130 mammograms of the DDSM database. Segmentation accuracy of both methods was evaluated by three radiologists, based on a five-point rating scale. The radiologists’ average accuracy ratings were 3.96 ± 0.77 , 3.97 ± 0.80 , and 3.83 ± 0.89 for the proposed method, and 2.91 ± 0.86 , 2.10 ± 0.94 , and 2.56 ± 0.76 for the radial gradient-based method, respectively, while the differences in accuracy ratings between the two segmentation methods were statistically significant (Wilcoxon signed-ranks test, p 0.05 ). The effect of the two segmentation methods in the classification of benign from malignant microcalcification clusters was also investigated. A least square minimum distance classifier was employed based on cluster features reflecting three morphological properties of individual microcalcifications (area, length, and relative contrast). Classification performance was evaluated by means of the area under ROC curve ( A z ) . The area and length morphologic features demonstrated a statistically significant (Mann-Whitney U-test, p 0.05 ) higher patient-based classification performance when extracted from microcalcifications segmented by the proposed method ( 0.82 ± 0.06 and 0.86 ± 0.05 , respectively), as compared to segmentation by the radial gradient-based method ( 0.71 ± 0.08 and 0.75 ± 0.08 ). The proposed method demonstrates improved segmentation accuracy, fulfilling human visual criteria, and enhances the ability of morphologic features to characterize microcalcification clusters.

Introduction It is commonly accepted that differentiation between glioblastoma multiforme (GBM) and solitary metastases (MET), relying on conventional Magnetic Resonance Imaging (MRI), in daily clinical practice, remains controversial. Purpose In the frame of such differentiation by means of quantitative image analysis of advanced MR techniques, such as Diffusion Tensor Imaging (DTI), the initial step of tumor segmentation is essential. Materials and methods In this study a proposed state-of-the-art segmentation technique was implemented, based on isotropic (p) and anisotropic (q) maps, derived from diffusion tensor decomposition. The unsupervised k-medians clustering of the 2D (p,q) histogram ( k = 16, account for 16 different types of brain tissues) results in whole brain segmented maps, where brain tumor lesions present distinctive boundaries. The technique has been tested on a case sample of 10 GBM and 10 MET patients, who underwent preoperative DTI scans at 3Tesla. Results Initial pilot evaluation of the produced brain color maps, by expert observers, demonstrated a potential role of specific tissue segments in precise determination of tumor’s margins, including intratumoral/peritumoral regions. In addition, due to its automated character, the technique is expected to deal with observer variabilities, introduced by manual ROI sampling of the above mentioned tumor regions, representing the current clinical standard. Conclusion The technique implemented lends itself to 3D tumor modeling and is expected to contribute in GMB and metastases differentiation, by means of 3D surface quantitative descriptors, complemented by 3D whole tumor texture analysis.

The aim of the present study is to investigate means for the reduction or even elimination of enhancement kinetic curve errors due to breast motion in order to avoid pitfalls and to increase the sensitivity and specificity of the method.115 women underwent breast Magnetic Resonance Imaging (MRI). All patients were properly immobilized in a dedicated bilateral phased array coil. A magnetic resonance unit 3-Tesla (Signa, GE Healthcare) was used. The following sequences were applied: (I) axial Τ2-TSE, (II) axial STIR and (III) Vibrant axial T1-weighted fat saturation (six phases). Kinetic curves were derived semi-automatically using the software of the system and manually by positioning the regions of interest (ROI) from stable reference points in all the phases.376 abnormalities in 115 patients were investigated. In 81 (21.5%) cases, a change of the enhancement kinetic curve type was found when the two different methods were used. In cases of large fatty breasts, a change of the enhancement kinetic curve type in 13 lesions was found. In cases of small and dense breasts, only in 4 lesions the kinetic curve type changed, whereas in cases of small and fatty breasts, the kinetic curve type changed in 64 lesions (50 were observed in left breasts and 14 in right breasts).The derivation of enhancement kinetic curves should be performed by controlling and verifying that the ROIs lay at the same location of the lesion in all the phases of the dynamic study.

Breast cancer is the second leading cause of cancer deaths in women today (after lung cancer) and is the most frequently diagnosed cancer among women, excluding skin cancers. According to the American Cancer Society, an estimated of 230,480 new cancer cases are expected to be diagnosed in 2011; about 2,140 new cases are expected in men. In addition to invasive breast cancer, 57,650 new cases of in situ breast cancer are expected to occur among women in 2011. Of these, approximately 85% will be ductal carcinoma in situ (DCIS). An estimated 39,970 breast cancer deaths (39,520 women, 450 men) are expected in 2011. Death rates for breast cancer have steadily decreased in women since 1990, with larger decreases in women younger than 50 (a decrease of 3.2% per year) than in those 50 and older (2.0% per year), representing progress in both earlier detection and improved treatment.

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 contrast-enhanced 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.

The purpose of this study is size-adapted segmentation of individual microcalcifications in mammography, based on microcalcification scale-space signature estimation, enabling robust scale selection for initialization of multiscale active contours. Segmentation accuracy was evaluated by the area overlap measure, by comparing the proposed method and two recently proposed ones to expert manual delineations. The method achieved area overlap of 0.61+/-0.15 outperforming statistically (p0.001) the other two methods (0.53+/-0.18, 0.42+/-0.16). Only the proposed method performed equally for both small (460 microm) and large (/= 460 microm) microcalcifications. Results indicate an accurate method, which could be utilized in computer-aided diagnosis schemes of microcalcification clusters.

Breast cancer is the most common cancer in women worldwide. Mammography is currently the most effective modality in detecting breast cancer, challenged by the presence of dense breast parenchyma with relatively low specificity in distinguishing malignant from benign lesions. Breast ultrasound and Magnetic Resonance Imaging (MRI) are significant adjuncts to mammography providing additional diagnostic information. Various Computer-Aided Diagnosis (CADx) schemes have been proposed across modalities, acting as clinical tools that provide a “second opinion” to assist radiologists in the diagnostic task of lesion characterization by means of quantitative image feature extraction and classification methods. The advent of multimodality imaging broadens the role of CADx, in terms of complementary tissue properties analyzed. In this chapter, major stages of CADx schemes in breast imaging are reviewed, while challenges and trends are discussed and highlighted by corresponding application examples of CADx methodologies for microcalcification clusters in mammography and masses in Dynamic Contrast-Enhanced MRI.

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 Lawspsila 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 (Az) of 0.989. Results suggest that MCspsila ST texture analysis can contribute to computer-aided diagnosis of breast cancer.

The statistical nature of SPECT imaging, due to Poisson noise effect, results in degradation of image quality, especially in case of lesions of small signal-to-noise (SNR) ratio (small size, reduced activity). In this paper, the performance of a platelet de-noising method applied, by means of a pre- processing step, on myocardial perfusion SPECT imaging is evaluated. A cardiac phantom, containing two different size cold lesions, was utilized to evaluate the platelet de-noising method performance and compare it with the performance of the Butterworth filtering method, applied on raw data in pre-processing fashion, as well as on reconstructed data, representing the clinical routine. Two experiments were conducted to simulate conditions with and without scatter irradiation from myocardial surrounding tissue. Noise, lesion contrast, SNR and lesion contrast-to-noise ratio (CNR) metrics for both lesions were computed for the three de-noising methods. Results demonstrate sufficient reduction of noise for platelet method yielding increased SNR and lesion CNR values as compared to Butterworth filtering method, applied on pre- and post-processed data, for both lesions. However, no statistically significant differences were demonstrated for all metrics considered (p>0.05). In conclusion, platelet de-noising prior to reconstruction has the potential to provide an efficient means of improving image quality in myocardial perfusion SPECT phantom.

Purpose: The purpose of this study is to evaluate the ability of Proton Density (PD)‐BLADE sequences in reducing or even eliminating motion and pulsatile flow artifacts in knee MRI examinations. Methods: Eighty consecutive patients, who had been routinely scanned for knee examination, participated in the study. The following pairs of sequences with and without BLADE were compared: a) PD Turbo Spin Echo (TSE) Sagittal (SAG) Fat Saturation (FS) in thirty five patients, b) PD TSE Coronal (COR) FS in nineteen patients, c) T2 TSE AXIAL in thirteen patients and d) PD TSE SAG in thirteen patients. Both qualitative and quantitative analyses were performed based on the signal‐to‐noise ratio (SNR), contrast‐to‐noise ratio (CNR), and relative contrast (ReCon) measures of normal anatomic structures. The qualitative analysis was performed by experienced radiologists. Also, the presence of image motion and pulsation artifacts was evaluated. Results: Based on the results of the SNR, CRN and ReCon for the different sequences and anatomical structures, the BLADE sequences were significantly superior in nineteen cases, whereas the corresponding conventional sequences were significantly superior in six only cases. The BLADE sequences eliminated motion artifacts in all the cases. However, motion artifacts were shown in: a) six PD TSE SAG FS, b) three PD TSE COR FS, c) three PD TSE SAG, and d) two T2 TSE AXIAL conventional sequences. In our results, it was found that in PD FS sequences (Sagittal and Coronal) the differences between the BLADE and conventional sequences regarding the elimination of motion and pulsatile flow artifacts were statistically significant. In all the comparisons, the PD FS BLADE sequences (coronal and sagittal) were significantly superior to the corresponding conventional sequences regarding the classification of their image quality. Conclusion: This technique appears to be capable to potentially eliminate motion and pulsatile flow artifacts in knee MR images.

Morphology of individual microcalcifications is an important clinical factor in microcalcification clusters diagnosis. Accurate segmentation remains a difficult task due to microcalcifications small size, low contrast, fuzzy nature and low distinguishability from surrounding tissue. A novel application of active rays (polar transformed active contours) on B-spline wavelet representation is employed, to provide initial estimates of microcalcification boundary. Then, a region growing method is used with pixel aggregation constrained by the microcalcification boundary estimates, to obtain the final microcalcification boundary. The method was tested on dataset of 49 microcalcification clusters (30 benign, 19 malignant), originating from the DDSM database. An observer study was conducted to evaluate segmentation accuracy of the proposed method, on a 5-point rating scale (from 5:excellent to 1:very poor). The average accuracy rating was 3.98±0.81 when multiscale active rays were combined to region growing and 2.93±0.92 when combined to linear polynomial fitting, while the difference in rating of segmentation accuracy was statistically significant (p < 0.05).