Mammographic quantitative image analysis and biologic image composition for breast lesion characterization and classification

A feasibility study on deep-neural-network-based dose-neutral dual-energy digital breast tomosynthesis

BACKGROUND

Diagnostic performance based on x-ray breast imaging is subject to breast density. Although digital breast tomosynthesis (DBT) is reported to outperform conventional mammography in denser breasts, mass detection and malignancy characterization are often considered challenging yet.

PURPOSE

As an improved diagnostic solution to the dense breast cases, we propose a dual-energy DBT imaging technique that enables breast compositional imaging at comparable scanning time and patient dose compared to the conventional single-energy DBT.

METHODS

The proposed dual-energy DBT acquires projection data by alternating two different energy spectra. Then, we synthesize unmeasured projection data using a deep neural network that exploits the measured projection data and adjacent projection data obtained under the other x-ray energy spectrum. For material decomposition, we estimate partial path lengths of an x-ray through water, lipid, and protein from the measured and the synthesized projection data with the object thickness information. After material decomposition in the projection domain, we reconstruct material-selective DBT images. The deep neural network is trained with the numerical breast phantoms. A pork meat phantom is scanned with a prototype dual-energy DBT system to demonstrate the feasibility of the proposed imaging method.

RESULTS

The developed deep neural network successfully synthesized missing projections. Material-selective images reconstructed from the synthesized data present comparable compositional contrast of the cancerous masses compared with those from the fully measured data.

CONCLUSIONS

The proposed dual-energy DBT scheme is expected to substantially contribute to enhancing mass malignancy detection accuracy particularly in dense breasts.

Pterygium and Ocular Surface Squamous Neoplasia: Optical Biopsy Using a Novel Autofluorescence Multispectral Imaging Technique

In this study, differentiation of pterygium vs. ocular surface squamous neoplasia based on multispectral autofluorescence imaging technique was investigated. Fifty (N = 50) patients with histopathological diagnosis of pterygium (PTG) and/or ocular surface squamous neoplasia (OSSN) were recruited. Fixed unstained biopsy specimens were imaged by multispectral microscopy. Tissue autofluorescence images were obtained with a custom-built fluorescent microscope with 59 spectral channels, each with specific excitation and emission wavelength ranges, suitable for the most abundant tissue fluorophores such as elastin, flavins, porphyrin, and lipofuscin. Images were analyzed using a new classification framework called fused-classification, designed to minimize interpatient variability, as an established support vector machine learning method. Normal, PTG, and OSSN regions were automatically detected and delineated, with accuracy evaluated against expert assessment by a specialist in OSSN pathology. Signals from spectral channels yielding signals from elastin, flavins, porphyrin, and lipofuscin were significantly different between regions classified as normal, PTG, and OSSN (p < 0.01). Differential diagnosis of PTG/OSSN and normal tissue had accuracy, sensitivity, and specificity of 88 ± 6%, 84 ± 10% and 91 ± 6%, respectively. Our automated diagnostic method generated maps of the reasonably well circumscribed normal/PTG and OSSN interface. PTG and OSSN margins identified by our automated analysis were in close agreement with the margins found in the H&E sections. Such a map can be rapidly generated on a real time basis and potentially used for intraoperative assessment.

Dual-energy three-compartment breast imaging for compositional biomarkers to improve detection of malignant lesions

Background

While breast imaging such as full-field digital mammography and digital breast tomosynthesis have helped to reduced breast cancer mortality, issues with low specificity exist resulting in unnecessary biopsies. The fundamental information used in diagnostic decisions are primarily based in lesion morphology. We explore a dual-energy compositional breast imaging technique known as three-compartment breast (3CB) to show how the addition of compositional information improves malignancy detection.

Methods

Women who presented with Breast Imaging-Reporting and Data System (BI-RADS) diagnostic categories 4 or 5 and who were scheduled for breast biopsies were consecutively recruited for both standard mammography and 3CB imaging. Computer-aided detection (CAD) software was used to assign a morphology-based prediction of malignancy for all biopsied lesions. Compositional signatures for all lesions were calculated using 3CB imaging and a neural network evaluated CAD predictions with composition to predict a new probability of malignancy. CAD and neural network predictions were compared to the biopsy pathology.

Results

The addition of 3CB compositional information to CAD improves malignancy predictions resulting in an area under the receiver operating characteristic curve (AUC) of 0.81 (confidence interval (CI) of 0.74–0.88) on a held-out test set, while CAD software alone achieves an AUC of 0.69 (CI 0.60–0.78). We also identify that invasive breast cancers have a unique compositional signature characterized by reduced lipid content and increased water and protein content when compared to surrounding tissues.

Conclusion

Clinically, 3CB may potentially provide increased accuracy in predicting malignancy and a feasible avenue to explore compositional breast imaging biomarkers.

Leong et al. use a dual-energy mammography technique termed three-compartment breast imaging to study breast composition and detect malignant lesions. Combining compositional information with morphology-based computer-aided diagnosis improves breast cancer detection.

Breast cancers are detected by mammography. This study explored the use of a particular kind of mammography technique to obtain information about the composition of cancerous and non-cancerous breast tissue. This technique provided measures of lipid (fat), water, and protein content in addition to shape characteristics provided from standard mammography. Adding information about the composition of the tissue to its shape characteristics resulted in an increased ability to distinguish invasive cancerous tissue from unaffected surroundings. Invasive breast cancer tissues were also found to exhibit lower lipid, higher protein and higher water content when compared to other non-invasive, non-cancerous breast tissues in which cancer was suspected. Our findings highlight the added value of including the composition of breast tissue when deciding if biopsy of the suspicious tissue is warranted.

Novel automated non invasive detection of ocular surface squamous neoplasia using multispectral autofluorescence imaging

PURPOSE

Diagnosing Ocular surface squamous neoplasia (OSSN) using newly designed multispectral imaging technique.

METHODS

Eighteen patients with histopathological diagnosis of Ocular Surface Squamous Neoplasia (OSSN) were recruited. Their previously collected biopsy specimens of OSSN were reprocessed without staining to obtain auto fluorescence multispectral microscopy images. This technique involved a custom-built spectral imaging system with 38 spectral channels. Inter and intra-patient frameworks were deployed to automatically detect and delineate OSSN using machine learning methods. Different machine learning methods were evaluated, with K nearest neighbor and Support Vector Machine chosen as preferred classifiers for intra- and inter-patient frameworks, respectively. The performance of the technique was evaluated against a pathological assessment.

RESULTS

Quantitative analysis of the spectral images provided a strong multispectral signature of a relative difference between neoplastic and normal tissue both within each patient (at p < 0.0005) and between patients (at p < 0.001). Our fully automated diagnostic method based on machine learning produces maps of the relatively well circumscribed neoplastic-non neoplastic interface. Such maps can be rapidly generated in quasi-real time and used for intraoperative assessment. Generally, OSSN could be detected using multispectral analysis in all patients investigated here. The cancer margins detected by multispectral analysis were in close and reasonable agreement with the margins observed in the H&E sections in intra- and inter-patient classification, respectively.

CONCLUSIONS

This study shows the feasibility of using multispectral auto-fluorescence imaging to detect and find the boundary of human OSSN. Fully automated analysis of multispectral images based on machine learning methods provides a promising diagnostic tool for OSSN which can be translated to future clinical applications.

Combined Benefit of Quantitative Three-Compartment Breast Image Analysis and Mammography Radiomics in the Classification of Breast Masses in a Clinical Data Set

Purpose To investigate the combination of mammography radiomics and quantitative three-compartment breast (3CB) image analysis of dual-energy mammography to limit unnecessary benign breast biopsies. Materials and Methods For this prospective study, dual-energy craniocaudal and mediolateral oblique mammograms were obtained immediately before biopsy in 109 women (mean age, 51 years; range, 31-85 years) with Breast Imaging Reporting and Data System category 4 or 5 breast masses (35 invasive cancers, 74 benign) from 2013 through 2017. The three quantitative compartments of water, lipid, and protein thickness at each pixel were calculated from the attenuation at high and low energy by using a within-image phantom. Masses were automatically segmented and features were extracted from the low-energy mammograms and the quantitative compartment images. Tenfold cross-validations using a linear discriminant classifier with predefined feature signatures helped differentiate between malignant and benign masses by means of (a) water-lipid-protein composition images alone, (b) mammography radiomics alone, and (c) a combined image analysis of both. Positive predictive value of biopsy performed (PPV₃) at maximum sensitivity was the primary performance metric, and results were compared with those for conventional diagnostic digital mammography. Results The PPV₃ for conventional diagnostic digital mammography in our data set was 32.1% (35 of 109; 95% confidence interval [CI]: 23.9%, 41.3%), with a sensitivity of 100%. In comparison, combined mammography radiomics plus quantitative 3CB image analysis had PPV₃ of 49% (34 of 70; 95% CI: 36.5%, 58.9%; P < .001), with a sensitivity of 97% (34 of 35; 95% CI: 90.3%, 100%; P < .001) and 35.8% (39 of 109) fewer total biopsies (P < .001). Conclusion Quantitative three-compartment breast image analysis of breast masses combined with mammography radiomics has the potential to reduce unnecessary breast biopsies. © RSNA, 2018 Online supplemental material is available for this article.

Quantification of breast lesion compositions using low-dose spectral mammography: A feasibility study

PURPOSE

The positive predictive power for malignancy can potentially be improved, if the chemical compositions of suspicious breast lesions can be reliably measured in screening mammography. The purpose of this study is to investigate the feasibility of quantifying breast lesion composition, in terms of water and lipid contents, with spectral mammography.

METHODS

Phantom and tissue samples were imaged with a spectral mammography system based on silicon-strip photon-counting detectors. Dual-energy calibration was performed for material decomposition, using plastic water and adipose-equivalent phantoms as the basis materials. The step wedge calibration phantom consisted of 20 calibration configurations, which ranged from 2 to 8 cm in thickness and from 0% to 100% in plastic water density. A nonlinear rational fitting function was used in dual-energy calibration of the imaging system. Breast lesion phantoms, made from various combinations of plastic water and adipose-equivalent disks, were embedded in a breast mammography phantom with a heterogeneous background pattern. Lesion phantoms with water densities ranging from 0% to 100% were placed at different locations of the heterogeneous background phantom. The water density in the lesion phantoms was measured using dual-energy material decomposition. The thickness and density of the background phantom were varied to test the accuracy of the decomposition technique in different configurations. In addition, an in vitro study was also performed using mixtures of lean and fat bovine tissue of 25%, 50%, and 80% lean weight percentages as the background. Lesions were simulated by using breast lesion phantoms, as well as small bovine tissue samples, composed of carefully weighed lean and fat bovine tissues. The water densities in tissue samples were measured using spectral mammography and compared to measurement using chemical decomposition of the tissue.

RESULTS

The thickness of measured and known water contents was compared for various lesion configurations. There was a good linear correlation between the measured and the known values. The root-mean-square errors in water thickness measurements were 0.3 and 0.2 mm for the plastic phantom and bovine tissue backgrounds, respectively.

CONCLUSIONS

The results indicate that spectral mammography can be used to accurately characterize breast lesion composition in terms of their equivalent water and lipid contents.

Postmortem validation of breast density using dual-energy mammography

PURPOSE

Mammographic density has been shown to be an indicator of breast cancer risk and also reduces the sensitivity of screening mammography. Currently, there is no accepted standard for measuring breast density. Dual energy mammography has been proposed as a technique for accurate measurement of breast density. The purpose of this study is to validate its accuracy in postmortem breasts and compare it with other existing techniques.

METHODS

Forty postmortem breasts were imaged using a dual energy mammography system. Glandular and adipose equivalent phantoms of uniform thickness were used to calibrate a dual energy basis decomposition algorithm. Dual energy decomposition was applied after scatter correction to calculate breast density. Breast density was also estimated using radiologist reader assessment, standard histogram thresholding and a fuzzy C-mean algorithm. Chemical analysis was used as the reference standard to assess the accuracy of different techniques to measure breast composition.

RESULTS

Breast density measurements using radiologist reader assessment, standard histogram thresholding, fuzzy C-mean algorithm, and dual energy were in good agreement with the measured fibroglandular volume fraction using chemical analysis. The standard error estimates using radiologist reader assessment, standard histogram thresholding, fuzzy C-mean, and dual energy were 9.9%, 8.6%, 7.2%, and 4.7%, respectively.

CONCLUSIONS

The results indicate that dual energy mammography can be used to accurately measure breast density. The variability in breast density estimation using dual energy mammography was lower than reader assessment rankings, standard histogram thresholding, and fuzzy C-mean algorithm. Improved quantification of breast density is expected to further enhance its utility as a risk factor for breast cancer.

Breast tissue decomposition with spectral distortion correction: a postmortem study

PURPOSE

To investigate the feasibility of an accurate measurement of water, lipid, and protein composition of breast tissue using a photon-counting spectral computed tomography (CT) with spectral distortion corrections.

METHODS

Thirty-eight postmortem breasts were imaged with a cadmium-zinc-telluride-based photon-counting spectral CT system at 100 kV. The energy-resolving capability of the photon-counting detector was used to separate photons into low and high energy bins with a splitting energy of 42 keV. The estimated mean glandular dose for each breast ranged from 1.8 to 2.2 mGy. Two spectral distortion correction techniques were implemented, respectively, on the raw images to correct the nonlinear detector response due to pulse pileup and charge-sharing artifacts. Dual energy decomposition was then used to characterize each breast in terms of water, lipid, and protein content. In the meantime, the breasts were chemically decomposed into their respective water, lipid, and protein components to provide a gold standard for comparison with dual energy decomposition results.

RESULTS

The accuracy of the tissue compositional measurement with spectral CT was determined by comparing to the reference standard from chemical analysis. The averaged root-mean-square error in percentage composition was reduced from 15.5% to 2.8% after spectral distortion corrections.

CONCLUSIONS

The results indicate that spectral CT can be used to quantify the water, lipid, and protein content in breast tissue. The accuracy of the compositional analysis depends on the applied spectral distortion correction technique.

Dual-energy contrast-enhanced spectral mammography (CESM)

Dual-energy contrast-enhanced mammography is one of the latest developments in breast care. Imaging with contrast agents in breast cancer was already known from previous magnetic resonance imaging and computed tomography studies. However, high costs, limited availability-or high radiation dose-led to the development of contrast-enhanced spectral mammography (CESM). We reviewed the current literature, present our experience, discuss the advantages and drawbacks of CESM and look at the future of this innovative technique.