FEATURE PROCESSING FOR LUNG NODULES IN COMPUTER ASSISTED DIAGNOSIS
摘要
Feature processing is provided for lung nodules in computer-assisted diagnosis. A feature that may better distinguish nodules from background is extracted (22) using a Hough transform. Rather than relying on a specific boundary shape, the Hough transform accumulates (26) evidence associated with a region, such as a ring region. The accumulated evidence provides a feature score without requiring a nodule to fit a specific shape. In another approach, a background level is determined (36) from extracted features. Rather than attempting to normalize an image prior to extraction, the features are normalized (38). The feature normalization and generalized Hough transform extraction may be used together or alone.
申请公布号
WO2009020574(A3)
申请公布日期
2009.03.26
申请号
WO2008US09361
申请日期
2008.08.04
申请人
SIEMENS MEDICAL SOLUTIONS USA, INC.;HONG, LIN;ALVINO, CHRISTOPHER, V.;SHEN, HONG