My and Dr. Chen’s journal paper submission to the journal of Medical Physics is accepted for the publication.
Title of the study: 3D Automatic Anatomy Segmentation Based on Iterative Graph Cut ASM
In this work, we studied the feasibility of developing an automatic anatomy segmentation (AAS) system in clinical radiology and demonstrated its operation on clinical 3D images. The AAS system we are developing consists of two main parts: object recognition, and object delineation. As for recognition, a hierarchical 3D scale-based multi-object method is used for the multi-object recognition task, which incorporates intensity weighted ball-scale (b-scale) information into the active shape model (ASM). For object delineation, an iterative graph-cut-ASM (IGCASM) algorithm is proposed which effectively combines the rich statistical shape information embodied in ASM with the globally optimal delineation capability of the GC method. The presented IGCASM algorithm is a 3D generalization of the 2D GC-ASM method that we proposed previously (see our SPIE 2010 paper). The proposed methods are tested on two datasets comprised of images obtained from 20 patients (10 male and 10 female) of clinical abdominal CT scans, and 11 foot MRI scans. The test is for 4 organs (liver, left and right kidney, and spleen) segmentation, 5 foot bones (calcaneus, tibia, cuboid, talus, and navicular). The recognition and delineation accuracies were evaluated separately. The recognition accuracy was evaluated in terms of translation, rotation and scale (size) error. The delineation accuracy was evaluated in terms of true and false positive volume fractions (TPVF, FPVF). The efficiency of the delineation method was also evaluated on an Intel Pentium IV PC with a 3.4 GHZ CPU machine. The experimental results showed the feasibility and efficacy of the proposed automatic anatomy segmentation system: (a) the incorporation of shape priors into the GC framework is feasible in 3D as demonstrated previously for 2D images; (b) Our results in 3D confirm the accuracy behavior observed in 2D. The hybrid strategy IGCASM seems to be more robust and accurate than ASM and GC individually; (c) Delineations within body regions and foot bones of clinical importance can be accomplished quite rapidly within 1.5 min.
X.Chen*, U.Bagci, 3D Automatic Anatomy Segmentation Based on Iterative Graph Cut ASM, Medical Physics, Accepted for publication. (* indicates equal contribution)