Investigating the feasibility of classifying breast microcalcifications using photon-counting spectral mammography: A simulation study

Ghammraoui, Bahaa; Glick, Stephen J.

doi:10.1002/mp.12230

Cited by 15 publications

(11 citation statements)

References 34 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main advantages of PCDs relative to energy‐integrating detectors (EIDs) include rejection of electronic noise, which is important at low exposures, and single‐shot multi‐energy imaging. This latter technique uses a PCD to count detected photons into two or more energy bins, which can be used to estimate volumetric breast density, 3 classify breast calcifications, 4 and remove the source of motion artifacts in contrast‐enhanced breast imaging 2,5 . While such multi‐energy applications are the more exciting prospects of PCDs, PCDs should also be expected to provide image quality equal to or superior to EIDs in standard screening and diagnostic mammography.…”

Section: Introductionmentioning

confidence: 99%

The detective quantum efficiency of cadmium telluride photon‐counting x‐ray detectors in breast imaging applications

Day

Tanguay

2021

Medical Physics

View full text Add to dashboard Cite

Purpose In breast imaging applications, cadmium telluride (CdTe) photon counting x‐ray detectors (PCDs) may reduce radiation dose and enable single‐shot multi‐energy x‐ray imaging. The purpose of this work is to determine the upper limits of the detective quantum efficiency (DQE) of CdTe PCDs for x‐ray mammography and to compare them with the published DQEs of energy‐integrating detectors (EIDs) and other PCDs. Methods We calibrated and validated a Monte Carlo (MC) model of the DQE of CdTe PCDs using an XCounter CdTe PCD. Our model accounted for charge sharing, electronic noise, and charge summation logic. We used a 28 kVp Mo/Mo spectrum hardened by 3.9 cm of Lucite to optimize the detector thickness and energy threshold for pixel sizes of 50, 85, and 100 μ${{\mu}}$m with and without inter‐pixel charge summation logic. The figure of merit used for optimization was the integral of the DQE, which is equivalent to the detectability index for a delta function task function, which represents a high‐frequency task. Results For an electronic noise level equal to that of the XCounter, the optimal DQE(0) without charge summing was 0.74. Charge summing for charge‐sharing correction reduced DQE(0) by 14% due to an increase in electronic noise. Reducing the electronic noise to ∼0.5 keV per pixel in combination with charge summing resulted in DQE(0) ≈$ \approx $0.78 for 85 μ${{\mu}}$m pixels, which is approximately equal to that of a‐Se and slot‐scanning silicon‐strip PCDs. At higher spatial frequencies, and for matched pixel sizes, the DQE was inferior to that of a‐Se EIDs and superior to that of slot‐scanning silicon‐strip PCDs in the scan direction but inferior in the slit direction. Conclusions (1) CdTe PCDs have the potential to provide a zero‐frequency DQE equal to that of a‐Se EIDs and slot‐scanning silicon‐strip PCDs, but this will require electronic noise levels ∼0.5 keV per pixel. (2) At mid‐to‐high spatial frequencies the DQE of CdTe PCDs may be (a) inferior to that of a‐Se EIDs and slot‐scanning silicon‐strip PCDs in the slit direction, and (b) superior to slot‐scanning silicon‐strip PCDs in the scan direction.

show abstract

Section: Introductionmentioning

confidence: 99%

The detective quantum efficiency of cadmium telluride photon‐counting x‐ray detectors in breast imaging applications

Day

Tanguay

2021

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Thus, the CNN approach for classification of solid masses and cysts using dual‐energy mammography appears feasible and should be investigated further with clinical data. Results from this and other studies 10,15–18 should motivate further development of spectral mammography systems.…”

Section: Discussionmentioning

confidence: 67%

Using convolutional neural networks to discriminate between cysts and masses in Monte Carlo‐simulated dual‐energy mammography

Makeev

Toner

Qian³

et al. 2021

Medical Physics

Self Cite

View full text Add to dashboard Cite

Purpose A substantial percentage of recalls (up to 20%) in screening mammography is attributed to extended round lesions. Benign fluid‐filled breast cysts often appear similar to solid tumors in conventional mammograms. Spectral imaging (dual‐energy or photon‐counting mammography) has been shown to discriminate between cysts and solid masses with clinically acceptable accuracy. This work explores the feasibility of using convolutional neural networks (CNNs) for this task. Methods A series of Monte Carlo experiments was conducted with digital breast phantoms and embedded synthetic lesions to produce realistic dual‐energy images of both lesion types. We considered such factors as nonuniform anthropomorphic background, size of the mass, breast compression thickness, and variability in lesion x‐ray attenuation. These data then were used to train a deep neural network (ResNet‐18) to learn the differences in x‐ray attenuation of cysts and masses. Results Our simulation results showed that the CNN‐based classifier could reliably discriminate between cystic and solid mass round lesions in dual‐energy images with an area under the receiver operating characteristic curve (ROC AUC) of 0.98 or greater. Conclusions The proposed approach showed promising performance and ease of implementation, and could be applied to novel photon‐counting detector‐based spectral mammography systems.

show abstract

“…Oncology / Breast, chest: [41,68,76,109,[158][159][160][161][162][163][164] Urology / Abdomen: [53,[165][166][167][168] Orthopaedics / Musculoskeletal: [169][170][171] Normal tissue characterization Measurement of breast density and bone mineral density. Calculation of proton stopping power.…”

Section: Molecular Imagingmentioning

confidence: 99%

“…A pilot study reported a specificity of approximately 50% at a sensitivity level of 1% for discriminating between solids and cysts [41]. Related to cyst-tumour differentiation is differentiation between benign and malignant micro calcifications in the breast, which is initially promising, at least for larger clusters of calcifications [164].…”

Section: Characterization Of Lesions and Abnormalities Without Contra...mentioning

confidence: 99%

Spectral and dual-energy X-ray imaging for medical applications

Fredenberg

2018

Nuclear Instruments and Methods in Physics Research Section A:

View full text Add to dashboard Cite

show abstract

Investigating the feasibility of classifying breast microcalcifications using photon-counting spectral mammography: A simulation study

Cited by 15 publications

References 34 publications

The detective quantum efficiency of cadmium telluride photon‐counting x‐ray detectors in breast imaging applications

The detective quantum efficiency of cadmium telluride photon‐counting x‐ray detectors in breast imaging applications

Using convolutional neural networks to discriminate between cysts and masses in Monte Carlo‐simulated dual‐energy mammography

Spectral and dual-energy X-ray imaging for medical applications

Contact Info

Product

Resources

About