Detection of clustered microcalcifications using spatial point process modeling

Jing, Hao; Yang, Yongyi; Nishikawa, Robert M.

doi:10.1088/0031-9155/56/1/001

Cited by 47 publications

(38 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As a result, an unfocused transmit sequence was used on a Verasonics system (Verasonics, Redmond, WA) in order to acquire ultrasound RF frames at 2000 fps using a 2.5-MHz ATL P4-2 phased array. Such a high frame rate can be achieved by emitting unfocused circular ultrasound waves using a virtual focus located 10.2 mm behind the array (Figure 1-1) [15]. This allowed us to reach a high framerate while being able to get a full view of the heart for each transmit for the purpose of EWI.…”

Section: Methodsmentioning

confidence: 99%

“…Using incremental strain estimation in the axial direction, EWI tracks the electromechanical wave (EW) which refers to the spatial propagation of the electromechanical activation through the heart. Previous studies have shown that the EW propagation is highly correlated with the underlying electrical activation sequence in all four chambers of the heart in normal canine hearts during sinus rhythm and various pacing protocols in silico and in vivo [15,21–23]. EWI has also been shown capable of localizing regions of ischemia in a large animal model during intermediate levels of occlusion of the left anterior descending artery (LAD) [13], but not yet for detection and monitoring of MI.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Electromechanical wave imaging and electromechanical wave velocity estimation in a large animal model of myocardial infarction

et al. 2017

View full text Add to dashboard Cite

Background Echocardiography is often used in the clinic for detection and characterization of myocardial infarction. Electromechanical wave imaging (EWI) is a non-invasive ultrasound-based imaging technique based on time-domain incremental motion and strain estimation that can evaluate changes in contractility in the heart. In this study, electromechanical activation is assessed in infarcted heart to determine whether EWI is capable of detecting and monitoring infarct formation. Additionally, methods for estimating electromechanical wave (EW) velocity are presented, and changes in the EW propagation velocity after infarct formation are studied. Methods and Results Five (n=5) adult mongrels were used in this study. Successful infarct formation was achieved in three animals by ligation of the left anterior descending (LAD) coronary artery. Dogs were survived for a few days after LAD ligation and monitored daily with EWI. At the end of the survival period, dogs were sacrificed and TTC (Tetrazolium chloride) staining confirmed the formation and location of the infarct. In all three dogs, as soon as day 1 EWI was capable of detecting late-activated and non-activated regions, which grew over the next few days. On final day images, the extent of these regions corresponded to the location of infarct as confirmed by staining. EW velocities in border zones of infarct were significantly lower post-infarct formation when compared to baseline, whereas velocities in healthy tissues were not. Conclusions These results indicate that EWI and EW velocity might help with the detection of infarcts and their border zones, which may be useful for characterizing arrhythmogenic substrate.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Electromechanical wave imaging and electromechanical wave velocity estimation in a large animal model of myocardial infarction

et al. 2017

View full text Add to dashboard Cite

show abstract

“…40 To speed up the FROC analysis, in the experiments, we first applied a prescouting step as in Ref. 11, during which only the most suspicious regions in a mammogram image were identified for further consideration. This was based on the fact that the spatial extent of clustered MCs is typically limited (<1 cm 2 in area), while a whole mammogram image can be rather large in size.…”

Section: D4 Performance Evaluation Using Free-response Receiver Omentioning

confidence: 99%

“…5,6 In contrast, stochastic modeling methods are designed to exploit the statistical difference between MCs and their surroundings, which include, for example, higher-order statistics, 7 Markov random field, 8,9 Gaussian mixture models, 10 and spatial point process models. 11 Different from these approaches, machine learning methods treat the MC detection as a twoclass classification problem, wherein a decision function is determined with supervised learning from data examples in mammogram images. [12][13][14][15][16][17] Such methods include, for example, neural network, 12,13 boosted learning, 14 relevant vector machine (RVM), 15 and support vector machine (SVM).…”

Section: Introductionmentioning

confidence: 99%

Improving the accuracy in detection of clustered microcalcifications with a context-sensitive classification model

2015

Self Cite

View full text Add to dashboard Cite

Purpose: In computer-aided detection of microcalcifications (MCs), the detection accuracy is often compromised by frequent occurrence of false positives (FPs), which can be attributed to a number of factors, including imaging noise, inhomogeneity in tissue background, linear structures, and artifacts in mammograms. In this study, the authors investigated a unified classification approach for combating the adverse effects of these heterogeneous factors for accurate MC detection. Methods: To accommodate FPs caused by different factors in a mammogram image, the authors developed a classification model to which the input features were adapted according to the image context at a detection location. For this purpose, the input features were defined in two groups, of which one group was derived from the image intensity pattern in a local neighborhood of a detection location, and the other group was used to characterize how a MC is different from its structural background. Owing to the distinctive effect of linear structures in the detector response, the authors introduced a dummy variable into the unified classifier model, which allowed the input features to be adapted according to the image context at a detection location (i.e., presence or absence of linear structures). To suppress the effect of inhomogeneity in tissue background, the input features were extracted from different domains aimed for enhancing MCs in a mammogram image. To demonstrate the flexibility of the proposed approach, the authors implemented the unified classifier model by two widely used machine learning algorithms, namely, a support vector machine (SVM) classifier and an Adaboost classifier. In the experiment, the proposed approach was tested for two representative MC detectors in the literature [difference-of-Gaussians (DoG) detector and SVM detector]. The detection performance was assessed using free-response receiver operating characteristic (FROC) analysis on a set of 141 screen-film mammogram (SFM) images (66 cases) and a set of 188 full-field digital mammogram (FFDM) images (95 cases). Results: The FROC analysis results show that the proposed unified classification approach can significantly improve the detection accuracy of two MC detectors on both SFM and FFDM images. Despite the difference in performance between the two detectors, the unified classifiers can reduce their FP rate to a similar level in the output of the two detectors. In particular, with true-positive rate at 85%, the FP rate on SFM images for the DoG detector was reduced from 1.16 to 0.33 clusters/image (unified SVM) and 0.36 clusters/image (unified Adaboost), respectively; similarly, for the SVM detector, the FP rate was reduced from 0.45 clusters/image to 0.30 clusters/image (unified SVM) and 0.25 clusters/image (unified Adaboost), respectively. Similar FP reduction results were also achieved on FFDM images for the two MC detectors. Conclusions: The proposed unified classification approach can be effective for discriminating MCs from FPs caused by different factors (su...

show abstract

“…Jing et al [4] investigated the spatial distribution of MC clusters in mammograms. They modeled MCs and background noise by gamma and Gaussian distribution, respectively.…”

Section: Introductionmentioning

confidence: 99%

Detection of microcalcification clusters in digitized X-ray mammograms using unsharp masking and image statistics

Kus

Karagöz²

2013

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

A fully automated method for detecting microcalcification (MC) clusters in regions of interest (ROIs) extracted from digitized X-ray mammograms is proposed. In the first stage, an unsharp masking is used to perform the contrast enhancement of the MCs. In the second stage, the ROIs are decomposed into a 2-level contourlet representation and the reconstruction is obtained by eliminating the low-frequency subband in the second level. In the third stage, In particular, a true positive rate of about 94% is achieved at the rate of 0.06 false positives per image.

show abstract

Detection of clustered microcalcifications using spatial point process modeling

Cited by 47 publications

References 31 publications

Electromechanical wave imaging and electromechanical wave velocity estimation in a large animal model of myocardial infarction

Electromechanical wave imaging and electromechanical wave velocity estimation in a large animal model of myocardial infarction

Improving the accuracy in detection of clustered microcalcifications with a context-sensitive classification model

Detection of microcalcification clusters in digitized X-ray mammograms using unsharp masking and image statistics

Contact Info

Product

Resources

About