방사선의학 웹진

바로가기  >

그림 1. 제안 방법에서 특징 정보 추출에 활용한 영상에 따른 FROC 분류 성능 비교. 단면영상과 투영영상 모두에서 특징 정보를 추출할 때(projection views+reconstructed volume) 분류 성능이 향상됨을 보임.

그림 2. 제안 boosting 기반 분류 방법에서 각 특징 정보가 선택된 비율. 단면영상과 투영영상에서 추출된 특징 정보가 모두 활용되기 때문에 두 영상 특성이 상보적임을 보임.​

그림 3. 기존 정보 융합 분류 방법들과 제안 방법의 FROC 분류 성능 비교. 제안 방법이 기존 정보 융합 방법(decision-level fusion, feature-level fusion)보다 두 영상에서 추출된 다양한 특징 정보를 효과적으로 융합함을 보임.

그림 4. 제안 방법의 false positive (FP) 감소 효과 예시. (a, c, e, g) 자동 병변 검출을 통해 생성된 병변 의심 영역이 그려진 단면영상 (실제 병변은 흰색 화살표로 표시함), (b, d, f, h) 제안 방법을 통해 FP가 감소된 단면영상.​​

​

Abstract
In digital breast tomosynthesis (DBT), image characteristics of projection views and reconstructed volume are different and both have the advantage of detecting breast masses, e.g. reconstructed volume mitigates a tissue overlap, while projection views have less reconstruction blur artifacts. In this paper, an improved mass detection is proposed by using combined feature representations from projection views and reconstructed volume in the DBT. To take advantage of complementary effects on different image characteristics of both data, combined feature representations are extracted from both projection views and reconstructed volume concurrently. An indirect region-of-interest segmentation in projection views, which projects volume-of-interest in reconstructed volume into the corresponding projection views, is proposed to extract combined feature representations. In addition, a boosting based classification with feature selection has been employed for selecting effective feature representations among a large number of combined feature representations, and for reducing false positives. Experiments have been conducted on a clinical data set that contains malignant masses. Experimental results demonstrate that the proposed mass detection can achieve high sensitivity with a small number of false positives. In addition, the experimental results demonstrate that the selected feature representations for classifying masses complementarily come from both projection views and reconstructed volume.​

Author information

Kim DH1, Kim ST, Ro YM.​
1School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST) 291, Daehak-ro, Yuseong-gu, Daejeon, 305-701, Korea.