Segmentation of liver and spleen based on computational anatomy models Chunhua Dong a , Yen-wei Chen a,c,n , Amir Hossein Foruzan b , Lanfen Lin c , Xian-hua Han a , Tomoko Tateyama a , Xing Wu a , Gang Xu a , Huiyan Jiang d a Graduate School of Information Science and Engineering, Ritsumeikan University, Noji-higashi 1-1-1, Kusatsu, Japan b Biomedical Engineering Department, Faculty of Engineering, Shahed University, Tehran, Iran c College of Computer Science and Technology, Zhejiang University, Zhejiang, China d College of Software, Northeastern University, Shenyang, China article info Article history: Received 17 December 2014 Accepted 9 October 2015 Keywords: Multiple organs segmentation Template matching Organ bounding box Iterative probabilistic atlas Computational anatomy model abstract Accurate segmentation of abdominal organs is a key step in developing a computer-aided diagnosis (CAD) system. Probabilistic atlas based on human anatomical structure, used as a priori information in a Bayes framework, has been widely used for organ segmentation. How to register the probabilistic atlas to the patient volume is the main challenge. Additionally, there is the disadvantage that the conventional probabilistic atlas may cause a bias toward the specific patient study because of the single reference. Taking these into consideration, a template matching framework based on an iterative probabilistic atlas for liver and spleen segmentation is presented in this paper. First, a bounding box based on human anatomical localization, which refers to the statistical geometric location of the organ, is detected for the candidate organ. Then, the probabilistic atlas is used as a template to find the organ in this bounding box by using template matching technology. We applied our method to 60 datasets including normal and pathological cases. For the liver, the Dice/Tanimoto volume overlaps were 0.930/0.870, the root-mean- squared error (RMSE) was 2.906 mm. For the spleen, quantification led to 0.922 Dice/0.857 Tanimoto overlaps, 1.992 mm RMSE. The algorithm is robust in segmenting normal and abnormal spleens and livers, such as the presence of tumors and large morphological changes. Comparing our method with conventional and recently developed atlas-based methods, our results show an improvement in the segmentation accuracy for multi-organs (p o0:00001). & 2015 Elsevier Ltd. All rights reserved. 1. Introduction Organ segmentation refers to the process of separating the organ of interest from its surroundings for clinical medical images. Manual segmentation of organ structures by an expert is a labor- ious and time-consuming task. Therefore, automatic or semi- automatic organ segmentation methods have been developed to provide a reproducible, accurate and robust alternative. In order to segment the organs from their medical images, a variety of sophisticated methods of segmenting organs have been proposed [1–4]. This methodological explosion reflects the difficulty of organ segmentation for clinical applications. These methods can be summarized as classification-based [5–7], region-based [8,9], contour-based [10,11], graph cut-based [12,13] and random walks- based [14,15] segmentations. However, these segmentation methods depend solely on gradient or intensity analysis, and omit the use of anatomical information. Hence, their performance is insufficient when the image contains noise or the contrast between object and background is low. Recently, significant effort has been focused on the develop- ment of anatomical model-based methods, such as probabilistic atlas [16–24] and statistical shape model [25,26] for organ seg- mentation. In anatomical model based methods, the anatomical model can be used as a priori location and shape information of organs. These methods are robust against noise, but they are sensitive to initialization of their parameters, such as pose and initial contour. Our research focused on the probabilistic atlas- based segmentation method. Most of the work has involved the construction of atlases for organ segmentation [27–31]. Probabil- istic atlas-based organ segmentation, however, poses a number of challenges. Accurate mapping of the probabilistic atlas onto the Contents lists available at ScienceDirect journal homepage: www.elsevier.com/locate/cbm Computers in Biology and Medicine http://dx.doi.org/10.1016/j.compbiomed.2015.10.007 0010-4825/& 2015 Elsevier Ltd. All rights reserved. n Corresponding author at: Graduate School of Information Science and Engi- neering, Ritsumeikan University, Noji-higashi 1-1-1, Kusatsu, Japan E-mail addresses: dongchunhua89@gmail.com (C. Dong), chen@is.ritsumei.ac.jp (Y.-w. Chen). Computers in Biology and Medicine 67 (2015) 146–160