Images Of Breast Tissue Research Articles

Detection and classification of masses in mammographic images in a multi-kernel approach

Background and ObjectiveAccording to the World Health Organization, breast cancer is the main cause of cancer death among adult women in the world. Although breast cancer occurs indiscriminately in countries with several degrees of social and economic development, among developing and underdevelopment countries mortality rates are still high due to low availability of early detection technologies. From the clinical point of view, mammography is still the most effective diagnostic technology, given the wide diffusion of the use and interpretation of these images. MethodsHerein this work we propose a method to detect and classify mammographic lesions using the regions of interest of images. Our proposal consists in decomposing each image using multi-resolution wavelets. Zernike moments are extracted from each wavelet component. Using this approach, we can combine both texture and shape features, which can be applied both to the detection and classification of mammary lesions. We used 355 images of fatty breast tissue of IRMA database, with 233 normal instances (no lesion), 72 benign, and 83 malignant cases. ResultsClassification was performed by using SVM and ELM networks with modified kernels in order to optimize accuracy rates, reaching 94.11%. Considering both accuracy rates and training times, we defined the ration between average percentage accuracy and average training time in a reverse order. Our proposal was 50 times higher than the ratio obtained using state-of-the-art approaches. ConclusionsAs our proposed model can combine high accuracy rate with low learning time, whenever a new data is received, our work will be able to save a lot of time, hours, in learning process in relation to the best method of the state-of-the-art.

LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues

In computer-aided diagnosis one of the crucial steps to classify suspicious lesions is the extraction of features. Texture analysis methods have been used in the analysis and interpretation of medical images. In this work we present a method based on the association among curvelet transform, local binary patterns, feature selection by statistical analysis and distinct classification methods, in order to support the development of computer aided diagnosis system. The similar features were removed by the statistical analysis of variance (ANOVA). The understanding of the features was evaluated by applying the decision tree, random forest, support vector machine and polynomial (PL) classifiers, considering the metrics accuracy (AC) and area under the ROC curve (AUC): the rates were calculated on images of breast tissues with different physical properties (commonly observed in clinical practice). The datasets were the Digital Database for Screening Mammography, Breast Cancer Digital Repository and UCSB biosegmentation benchmark. The investigated groups were normal-abnormal and benign-malignant. The association of curvelet transform, local binary pattern and ANOVA with the PL classifier achieved higher AUC and AC values for all cases: the obtained rates were among 91% and 100%. These results are relevant, specially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed association is useful as an automated protocol for the diagnosis of breast tissues and may contribute to the diagnosis of breast tissues (mammographic and histopathological images).

High-frequency ultrasound imaging for breast cancer biopsy guidance.

Image-guided core needle biopsy is the current gold standard for breast cancer diagnosis. Microcalcifications, an important radiographic finding on mammography suggestive of early breast cancer such as ductal carcinoma in situ, are usually biopsied under stereotactic guidance. This procedure, however, is uncomfortable for patients and requires the use of ionizing radiation. It would be preferable to biopsy microcalcifications under ultrasound guidance since it is a faster procedure, more comfortable for the patient, and requires no radiation. However, microcalcifications cannot reliably be detected with the current standard ultrasound imaging systems. This study is motivated by the clinical need for real-time high-resolution ultrasound imaging of microcalcifications, so that biopsies can be accurately performed under ultrasound guidance. We have investigated how high-frequency ultrasound imaging can enable visualization of microstructures in ex vivo breast tissue biopsy samples. We generated B-mode images of breast tissue and applied the Nakagami filtering technique to help refine image output so that microcalcifications could be better assessed during ultrasound-guided core biopsies. We describe the preliminary clinical results of high-frequency ultrasound imaging of ex vivo breast biopsy tissue with microcalcifications and without Nakagami filtering and the correlation of these images with the pathology examination by hematoxylin and eosin stain and whole slide digital scanning.

Clinical Report on the First Prototype of a Photoacoustic Tomography System with Dual Illumination for Breast Cancer Imaging.

Photoacoustic tomography is a recently developed imaging modality that can provide high spatial-resolution images of hemoglobin distribution in tissues such as the breast. Because breast cancer is an angiogenesis-dependent type of malignancy, we evaluated the clinical acceptability of breast tissue images produced using our first prototype photoacoustic mammography (PAM) system in patients with known cancer. Post-excisionally, histological sections of the tumors were stained immunohistochemically (IHC) for CD31 (an endothelial marker) and carbonic anhydrase IX (CAIX) (a marker of hypoxia). Whole-slide scanning and image analyses were used to evaluate the tumor microvessel distribution pattern and to calculate the total vascular perimeter (TVP)/area for each lesion. In this clinical study, 42 lesions were primarily scanned using PAM preoperatively, three of which were reported to be benign and were excluded from statistical analysis. Images were produced for 29 out of 39 cancers (visibility rate = 74.4%) at the median depth of 26.5 (3.25–51.2) mm. Age, menopausal status, body mass index, history of neoadjuvant treatment, clinical stage and histological tumor angiogenesis markers did not seem to affect the visibility. The oxygen saturation level in all of the measured lesions was lower than in the subcutaneous counterpart vessels (Wilcoxon test, p value<0.001), as well as in the counterpart contralateral normal breast region of interest (ROI) (Wilcoxon test, p value = 0.001). Although the oxygen saturation level was not statistically significant between CAIX-positive vs. -negative cases, lesional TVP/area showed a positive correlation with the oxygen saturation level only in the group that had received therapy before PAM. In conclusion, the vascular and oxygenation data obtained by PAM have great potential for identifying functional features of breast tumors.

Viscosity-compensated shear speed imaging with acoustic radiation force

Shear wave elastography imaging (SWEI) with ultrasound uses an applied acoustic radiation force to obtain quantitative images of liver, breast, prostate, and other soft tissues. In SWEI, shear velocity waveforms are collected along a line, and then, the shear speed is estimated either with a k-space or a correlation-based method. Although these yield effective estimates in elastic media, both methods consistently overestimate the shear speed in viscoelastic soft tissue because neither considers the shear viscosity. To address this problem, we have created a new shear speed estimation approach that also accounts for the effect of shear viscosity. The new approach is evaluated in a computational model that calculates the three-dimensional (3D) intensity field generated by a linear array transducer in FOCUS (http://www.egr.msu.edu/~fultras-web) and then simulates the shear wave velocities in a viscoelastic medium with a 3D finite difference model. In the viscoelastic shear wave simulation model, the shear speed constant is 1.5 m/s, and the shear viscosity is 1 Pa·s. Correlation-based shear speed estimates are compared to the viscosity-compensated estimates, and the results show that the viscosity-compensated approach consistently achieves improved shear speed estimates relative to the correlation-based method. [Work supported in part by NIH Grant Nos. R01EB012079 and R01DK092255.]

High resolution functional photoacoustic tomography of breast cancer.

To evaluate the feasibility of functional photoacoustic tomography (fPAT) for high resolution detection and characterization of breast cancer and to demonstrate for the first time quantitative hemoglobin concentration and oxygen saturation images of breasts that were formed with model-based reconstruction of tomographic photoacoustic data. The study was HIPAA compliant and was approved by the university institutional review board. Written informed consents were obtained from all the participants. Ten cases, including six cancer and four healthy (mean age = 50 yr; age range = 41-66 yr), were examined. Functional images of breast tissue including absolute total hemoglobin concentration (HbT) and oxygen saturation (StO2%) were obtained by fPAT and cross validated with magnetic resonance imaging (MRI) readings and/or histopathology. HbT and StO2% maps from all six pathology-confirmed cancer cases (60%) show clear detection of tumor, while MR images indicate clear detection of tumor for five of six cancer cases; one small tumor was read as near-complete-resolution by MRI. The average HbT and StO2% value of suspicious lesion area for the cancer cases was 61.6 ± 18.9 μM/l and 67.5% ± 5.2% compared to 25.6 ± 7.4 μM/l and 65.2% ± 3.8% for background normal tissue. fPAT has the potential to be a significant add-on in breast cancer detection and characterization as it provides submillimeter resolution functional images of breast lesions.

Feature extraction employing fuzzy-morphological decomposition for detection and classification of mass on mammograms.

Mathematical Morphology is a theory of nonlinear processing extensively used in digital image processing. The computation effort, however, associated to Mathematical Morphology is usually large mainly because of high occurrence of conditional branches, due to use of intersection and union set operations. In terms of processing, it means the occurrence of maximum and minimum calculation. Mathematical Morphology, despite a relative large computational cost, is suitable to biomedical images applications, where both form and texture are essential in order to study anatomical deformities. We use detection and classification of mass in mammograms as a case study. The reason is that breast cancer is the leading cause of adult women by cancer worldwide. We propose a method inspired by series of wavelets for fuzzy-morphological decomposition in regions of interest on mammograms. Our decomposition employs nonlinear low-pass and high-pass filters based on openings and closings operations, which employ fuzzy-approximations. They replace conditional branches by arithmetic operators of subtraction and multiplication, computationally more efficient. We used 355 images of fatty breast tissue of IRMA database, with 233 normal instances, 66 benign, and 56 malignant cases. Classification was performed using SVM and ELM networks with modified kernels, in order to optimize accuracy rates, reaching 93.18%.

Fusing Heterogeneous Features From Stacked Sparse Autoencoder for Histopathological Image Analysis.

In the analysis of histopathological images, both holistic (e.g., architecture features) and local appearance features demonstrate excellent performance, while their accuracy may vary dramatically when providing different inputs. This motivates us to investigate how to fuse results from these features to enhance the accuracy. Particularly, we employ content-based image retrieval approaches to discover morphologically relevant images for image-guided diagnosis, using holistic and local features, both of which are generated from the cell detection results by a stacked sparse autoencoder. Because of the dramatically different characteristics and representations of these heterogeneous features (i.e., holistic and local), their results may not agree with each other, causing difficulties for traditional fusion methods. In this paper, we employ a graph-based query-specific fusion approach where multiple retrieval results (i.e., rank lists) are integrated and reordered based on a fused graph. The proposed method is capable of combining the strengths of local or holistic features adaptively for different inputs. We evaluate our method on a challenging clinical problem, i.e., histopathological image-guided diagnosis of intraductal breast lesions, and it achieves 91.67% classification accuracy on 120 breast tissue images from 40 patients.

Tomographic images of breast tissues obtained by Compton scattering: An analytical computational study

Abstract In this work, we studied by analytical simulation the potential of a Compton scatter technique for breast imaging application. A Compton scattering tomography system was computationally simulated in order to provide the projection data (scattering signal) for the image reconstructions. The simulated projections generated by the analytical proposed method were validated through comparison with those obtained by Monte Carlo simulation. Electron density images were obtained from the scattering signal using a reconstruction algorithm implemented for the system geometry. Finally, the quality of the reconstructed images was evaluated for different sample sizes, beam energies, and tissue compositions (glandularities).

A novel model for smart breast cancer detection in thermogram images.

Accuracy in feature extraction is an important factor in image classification and retrieval. In this paper, a breast tissue density classification and image retrieval model is introduced for breast cancer detection based on thermographic images. The new method of thermographic image analysis for automated detection of high tumor risk areas, based on two-directional two-dimensional principal component analysis technique for feature extraction, and a support vector machine for thermographic image retrievalwas tested on 400 images. The sensitivity and specificity of the model are 100% and 98%, respectively.

Differentiating the two main histologic categories of fibroadenoma tissue from normal breast tissue by using multiphoton microscopy.

Multiphoton microscopy has become a novel biological imaging technique that allows cellular and subcellular microstructure imaging based on two-photon excited fluorescence and second harmonic generation. In this work, we used multiphoton microscopy to obtain the high-contrast images of human normal breast tissue and two main histologic types of fibroadenoma (intracanalicular, pericanalicular). Moreover, quantitative image analysis was performed to characterize the changes of collagen morphology (collagen content, collagen orientation). The results show that multiphoton microscopy combined with quantitative method has the ability to identify the characteristics of fibroadenoma including changes of the duct architecture and collagen morphology in stroma. With the advancement of multiphoton microscopy, we believe that the technique has great potential to be a real-time histopathological diagnostic tool for intraoperative detection of fibroadenoma in the future.

PB.39. CT or not CT: a systematic review of the breast on CT of the chest and abdomen over 1 year - another screening tool?

Images of breast tissue are usually included on CT scans of the chest or abdomen. It is generally thought that CT has a low sensitivity for breast pathology. We tested this assumption to assess the importance of the breast as a review area on CT.

Non-rigid registration of medical images based on estimation of deformation states

A unified framework for automatic non-rigid 3D–3D and 3D–2D registration of medical images with static and dynamic deformations is proposed in this paper. The problem of non-rigid image registration is approached as a classical state estimation problem using a generic deformation model for the soft tissue. The registration technique employs a dynamic linear elastic continuum mechanics model of the tissue deformation, which is discretized using the finite element method. In the proposed method, the registration is achieved through a Kalman-like filtering process, which incorporates information from the deformation model and a vector of observation prediction errors computed from an intensity-based similarity/distance metric between images. With this formulation, single and multiple-modality, 3D–3D and 3D–2D image registration problems can all be treated within the same framework. The performance of the proposed registration technique was evaluated in a number of different registration scenarios. First, 3D magnetic resonance (MR) images of uncompressed and compressed breast tissue were co-registered. 3D MR images of the uncompressed breast tissue were also registered to a sequence of simulated 2D interventional MR images of the compressed breast. Finally, the registration algorithm was employed to dynamically track a target sub-volume inside the breast tissue during the process of the biopsy needle insertion based on registering pre-insertion 3D MR images to a sequence of real-time simulated 2D interventional MR images. Registration results indicate that the proposed method can be effectively employed for the registration of medical images in image-guided procedures, such as breast biopsy in which the tissue undergoes static and dynamic deformations.

In vitro selection of DNA aptamers for metastatic breast cancer cell recognition and tissue imaging.

Cancer is a major public health issue, with metastatic cancer accounting for the overwhelming majority of cancer deaths. Early diagnosis and appropriate treatment of metastatic cancer may largely prolong the survival rate and improve the quality of life for patients. In this study, we have identified a panel of DNA aptamers specifically binding to MDA-MB-231 cells derived from metastatic site-pleural effusion, with high affinity after 15 rounds of selections using the cell-based systematic evolution of ligands by exponential enrichment (SELEX) method. The selected aptamers were subjected to flow cytometry and laser confocal fluorescence microscopy to evaluate their binding affinity and selectivity. The aptamer LXL-1 with the highest abundance in the enriched library demonstrated a low K(d) value and excellent selectivity for the recognition of the metastatic breast cancer cells. Tissue imaging results showed that truncated aptamer sequence LXL-1-A was highly specific to the corresponding tumor tissue and displayed 76% detection rate against breast cancer tissue with metastasis in regional lymph nodes. Therefore, on the basis of its excellent targeting properties and functional versatility, LXL-1-A holds great potential to be used as a molecular imaging probe for the detection of breast cancer metastasis. Our result clearly demonstrates that metastatic-cell-based SELEX can be used to generate DNA ligands specifically recognizing metastatic cancer cells, which is of great significance for metastatic cancer diagnosis and treatment.

A Nonlinear Microwave Breast Cancer Imaging Approach Through Realistic Body–Breast Modeling

A nonlinear microwave tomography approach which suggests monitoring of differences inside the breast with respect to a reference breast model that adequately represents the healthy breast is presented. This approach simplifies the breast cancer imaging problem through realistic modeling of the body-breast configuration and does not require the imaging of the entire breast tissues. The tumor is considered as a buried object inside the breast which is assumed to be located on the interface of two-half spaces media composed of air or a coupling liquid and the chest wall or the base of the bed on which patient lies in a prone position. Then, the tumor, as well as the deviations of the actual breast from the breast model, is imaged by using the contrast source inversion method at a single frequency. The Green's function of the inhomogeneous background required in the application of the inversion algorithm is obtained through the buried object approach and accelerated by an adaptation of the discrete complex images method. Through the simulations it has been shown that, the proposed modeling and nonlinear inversion algorithm is capable of reconstructing tumors as small as 4 mm in radius for 3-D scenarios.

The effect of crosstalk in a circular transducer array on ultrasound transmission tomography of breast

Various types of undesirable crosstalk can occur in ultrasonic arrays consisting of a number of elementary piezoelectric transducers. Crosstalk is a result of deficiency in electrical or mechanical isolation between array elements. It is a function of proximity between piezoelectric transducers of the array or between connections. Small piezoceramic transducers tightly located inside of a circle (cylinder or sphere in 3-D systems) are mostly used for in vivo ultrasound tomography imaging of breast tissue. This means that proper switching of transducers makes it possible to quickly acquire tomographic transmission and reflection data for all directions around the object. A problem with such arrangements is the occurrence of crosstalk, which introduce specific errors to measurement data. Transmission and reflection tomographic images reconstructed based on ultrasonic measurements with crosstalk are distorted in a characteristic way. This work analyzes the effect of crosstalk in a circular transducer array on ultrasound transmission tomography imaging—especially, when used for examination of breast tissue.

Comparison of sound speed measurements on two different ultrasound tomography devices.

Ultrasound tomography (UST) employs sound waves to produce three-dimensional images of breast tissue and precisely measures the sound speed of breast tissue composition. High breast density is a strong breast cancer risk factor and sound speed is directly proportional to breast density. UST provides a quantitative measure of breast density based on three-dimensional imaging without compression, thereby overcoming the shortcomings of many other imaging modalities. The quantitative nature of the UST breast density measures are tied to an external standard, so sound speed measurement in breast tissue should be independent of specific hardware. The work presented here compares breast sound speed measurement obtained with two different UST devices. The Computerized Ultrasound Risk Evaluation (CURE) system located at the Karmanos Cancer Institute in Detroit, Michigan was recently replaced with the SoftVue ultrasound tomographic device. Ongoing clinical trials have used images generated from both sets of hardware, so maintaining consistency in sound speed measurements is important. During an overlap period when both systems were in the same exam room, a total of 12 patients had one or both of their breasts imaged on both systems on the same day. There were 22 sound speed scans analyzed from each system and the average breast sound speeds were compared. Images were either reconstructed using saved raw data (for both CURE and SoftVue) or were created during the image acquisition (saved in DICOM format for SoftVue scans only). The sound speed measurements from each system were strongly and positively correlated with each other. The average difference in sound speed between the two sets of data was on the order of 1-2 m/s and this result was not statistically significant. The only sets of images that showed a statistical difference were the DICOM images created during the SoftVue scan compared to the SoftVue images reconstructed from the raw data. However, the discrepancy between the sound speed values could be easily handled by uniformly increasing the DICOM sound speed by approximately 0.5 m/s. These results suggest that there is no fundamental difference in sound speed measurement for the two systems and support combining data generated with these instruments in future studies.

Microwave radar imaging of heterogeneous breast tissue integrating a priori information.

Conventional radar-based image reconstruction techniques fail when they are applied to heterogeneous breast tissue, since the underlying in-breast relative permittivity is unknown or assumed to be constant. This results in a systematic error during the process of image formation. A recent trend in microwave biomedical imaging is to extract the relative permittivity from the object under test to improve the image reconstruction quality and thereby to enhance the diagnostic assessment. In this paper, we present a novel radar-based methodology for microwave breast cancer detection in heterogeneous breast tissue integrating a 3D map of relative permittivity as a priori information. This leads to a novel image reconstruction formulation where the delay-and-sum focusing takes place in time rather than range domain. Results are shown for a heterogeneous dense (class-4) and a scattered fibroglandular (class-2) numerical breast phantom using Bristol's 31-element array configuration.

Study of the Reduced Field-of-View Diffusion-Weighted Imaging of the Breast

BackgroundThis study aimed to compare the imaging quality, apparent diffusion coefficient (ADC) values, and application values between reduced field-of-view diffusion-weighted imaging (rFOV DWI) and single-shot echo-planar–imaging diffusion-weighted imaging (SS-EPI DWI) of breast tissue. Patients and MethodsFor 87 cases (75 with normal breast tissue, 12 with mammary cancer), breasts were scanned with SS-EPI DWI and rFOV DWI (b values, 800 s/mm2). Image quality and ADC values of breast tissue images were compared between SS-EPI DWI and rFOV DWI. ResultsThe average image quality score for the 87 cases was 4.73 in rFOV DWI and 3.62 in SS-EPI DWI. The difference was statistically significant (P < .01). The resolution of rFOV DWI was 2.25 mm × 1.23 mm, which was higher than the resolution of SS-EPI DWI (2.25 mm × 2.25 mm). The mean ADC value of 75 cases with normal breast tissue was 1.696 × 10-3 mm2/s by rFOV DWI and 1.832 × 10-3 mm2/s by SS-EPI DWI, and the difference was statistically significant (P < .01). The mean ADC value for the 12 cases with breast cancer was 1.065 × 10-3 mm2/s by rFOV DWI and 1.192 × 10-3 mm2/s by SS-EPI DWI, which was a statistically significant difference (P < .05). ConclusionrFOV DWI presented images with higher resolution and less distortion than SS-EPI DWI, and this difference may be helpful in disease diagnosis.

A mass classification and image retrieval model for mammograms

In this paper, a breast tissue density classification and image retrieval model is studied and a model for the data reduction is presented. This model is based on two-directional two-dimensional principal component analysis ((2D)2PCA) technique, and a support vector machine (SVM) with the radial basis function (RBF) for mammographic images classification and retrieval. The model is formed based on breast density, according to the categories defined by the breast imaging-reporting and data system (BIRADS) which is a standard on the assessment of mammographic images and is tested on the Mammographic Image Analysis Society (MIAS) database. The five-fold cross-validation has been used for the parameters selection in SVM to avoid the over-fitting error in the data classification. The average precision rates of the model are in the range from 87·34% to 99·12%.