Lung Lobe Segmentation Based on HRCT Data Zhiqiong Wang; Xianfeng Meng; Yue Zhao ...
2010 International Conference on Biomedical Engineering and Computer Science,
2010-April
Conference Proceeding
Nowadays, the lung lobe segmentation is the most basic step in Lung CAD (Computer-aided diagnosis) and is playing an increasingly important role in the early diagnosis of lung diseases and the ...analysis of pulmonary functions. The key to achieving lung lobe segmentation is to detect and locate lung fissures. With the wide applications of HRCT (High-Resolution Computed Tomography), CT data with higher contrast can be got, thus making it possible to locate lung fissures more accurately. In this paper, a lung fissure extraction algorithm based on the two-dimensional chest HRCT data is proposed. First, A linear structure enhancement filter based on the Hessian matrix is designed to enhance the contrast of lung fissures; then, according to the idea of Canny operator, ridge of the image is extracted, which allows the location of the fissures to be determined accurately; finally, the Uniform Cost Method is applied to the detection of ridge of the fissures and the extraction of them are achieved. Experiments show that this algorithm can realize the extraction of lung fissures and achieve the lung lobe segmentation with good effects.
This paper proposes a general model for bidirectional associative memories that associate patterns between the X-space and the Y-space. The general model does not require the usual assumption that ...the interconnection weight from a neuron in the X-space to a neuron in the Y-space is the same as the one from the Y-space to the X-space. We start by defining a supporting function to measure how well a state supports another state in a general bidirectional associative memory (GBAM). We then use the supporting function to formulate the associative recalling process as a dynamic system, explore its stability and asymptotic stability conditions, and develop an algorithm for learning the asymptotic stability conditions using the Rosenblatt perceptron rule. The effectiveness of the proposed model for recognition of noisy patterns and the performance of the model in terms of storage capacity, attraction, and spurious memories are demonstrated by some outstanding experimental results.
This paper proposes a general model for bidirectional associative memories that associate patterns between the X-space and the Y-space. The general model does not require the usual assumption that ...the interconnection weight from a neuron in the X-space to a neuron in the Y-space is the same as the one from the Y-space to the X-space. We start by defining a supporting function to measure how well a state supports another state in a general bidirectional associative memory (GBAM). We then use the supporting function to formulate the associative recalling process as a dynamic system, explore its stability and asymptotic stability conditions, and develop an algorithm for learning the asymptotic stability conditions using the Rosenblatt perceptron rule. The effectiveness of the proposed model is demonstrated by several outstanding experimental results.
A general auto-associative memory model Xinhua Zhuang; Hongchi Shi; Yunxin Zhao
Proceedings of International Conference on Neural Networks (ICNN'96),
1996, Letnik:
1
Conference Proceeding
This paper attempts to establish a theory for a general auto-associative memory model. We start by defining a new concept called supporting function to replace the concept of energy function. The ...latter relies on an assumption of symmetric connection weights, which is used in the conventional Hopfield auto-associative memory, but not evidenced in any biological memories. We then formulate the information retrieval or recalling process as a dynamic system by making use of the supporting function, explore its stability and attraction conditions, and develop an algorithm for learning the attraction condition based upon Rosenblatt's perceptron rule. The effectiveness of the learning algorithm is evidenced by some outstanding experiment results.