A deep learning classifier for digital breast tomosynthesis

Digital Breast Tomosynthesis

Digital Breast Tomosynthesis (DBT)

DBT is a three-dimensional (3D) breast imaging technology that uses a rotating X-ray source to acquire multiple image slices at several angles. The X-ray source rotates around the breast in an arc. Serial exposures are taken every few degrees in the arc rotation. These images are then reconstituted by software to produce a 3Dimage of the breast, similar to CAT scanning. It has been suggested th...

Detection of soft tissue densities from digital breast tomosynthesis: comparison of conventional and deep learning approaches

Computer-aided detection (CAD) has been used in screening mammography for many years and is likely to be utilized for digital breast tomosynthesis (DBT). Higher detection performance is desirable as it may have an impact on radiologist’s decisions and clinical outcomes. Recently the algorithms based on deep convolutional architectures have been shown to achieve state of the art performance in o...

Digital Breast Tomosynthesis - 06/13

Digital breast tomosynthesis (DBT) is being developed as an approach to generate images that may improve the sensitivity and specificity of mammography. Current radiographic approaches to mammography produce two-dimensional (2D) images. These 2D systems can have limitations due to overlapping tissue in the breast that may hide lesions (cancers) or cause benign masses to appear suspicious. DBT, ...

A Review of Digital Breast Tomosynthesis

While the principle of tomosynthesis has been known for almost a century, digital breast tomosynthesis (DBT) is a novel technology that owes its rapid development to the introduction of full-field digital mammography (FFDM). This review article covers the principles and design considerations of DBT, including system geometry. Further, the article provides an in-depth introduction to DBT dosimet...