바로가기  >

Abstract
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.

(위쪽 row부터: Low-energy DBT, High-energy DBT, Water-based, Protein-based, and Lipid-based 영상, 왼쪽 column부터: Double dose 조건의 reference 이중에너지 DBT 결과, 제안된 방법으로 얻은 결과, 그리고 한쪽 에너지 정보로만 합성한 네트워크 결과)

본 영상은 돼지고기에 다양한 모사 물질 (콩, 곡물, 석회 등)을 넣어 만든 팬텀을 촬영한 것으로 제안된 방식에서 기준 영상과 유사한 영상 품질 및 물질 분별력을 갖춘 것을 보여주고 있음.

Affiliations

Hyeongseok Kim 1, Hoyeon Lee 2, Seoyoung Lee 3, Young-Wook Choi 4, Young Jin Choi 4, Kee Hyun Kim 4, Wontaek Seo 5, Choul Woo Shin 5, Seungryong Cho 1 3 6 7
1KAIST Institute for Artificial Intelligence, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.
2Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA.
3Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.
4Korea Electrotechnology Research Institute (KERI), Ansan, South Korea.
5DRTECH, Seongnam, South Korea.
6KAIST Institute for Health Science and Technology, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.
7KAIST Institute for IT Convergence, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.