Abdominal organ segmentation using texture transforms and a Hopfield neural network

Abstract

Abdominal organ segmentation is highly desirable but difficult, due to large differences between patients and to overlapping grey-scale values of the various tissue types. The first step in automating this process is to cluster together the pixels within each organ or tissue type. We propose to form images based on second-order statistical texture transforms (Haralick transforms) of a CT or MRI scan. The original scan plus the suite of texture transforms are then input into a Hopfield neural network (HNN). The network is constructed to solve an optimization problem, where the best solution is the minima of a Lyapunov energy function. On a sample abdominal CT scan, this process successfully clustered 79-100% of the pixels of seven abdominal organs. It is envisioned that this is the first step to automate segmentation. Active contouring (e.g., SNAKE's) or a back-propagation neural network can then be used to assign names to the clusters and fill in the incorrectly clustered pixels.

Massive Regional Texture Extraction for Aerial and Natural Images

“…Segmentation [2] is usually a process of partitioning a digital image into multiple segments the major objective of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze the medical images [3]. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.)…”

Liver Segmentation and Volume Estimation from Preoperative CT Images in Hepatic Surgical Planning: Application of a Semiautomatic Method Based on 3D Level Sets

“…Other approaches try to overcome the problem of liver's gray-level estimation by learning graylevel features corresponding to the liver from different CT images with methods based on neural networks. Tsai and Tanahashi (Tsai & Tanahashi, 1994) , Koss et al (Koss et al, 1999) and Lee et al (Lee & Chung, 2000;Lee et al, 2003) presented examples of automatic detection and labeling of abdominal organs with neural networks. A common difficulty of this kind of methods is that they usually need a big and highly varied training set to learn the variability among different patients.…”

Performance Analysis of Distance Transform Based Inter-Slice Similarity Information on Segmentation of Medical Image Series

“…There are mainly two approaches for segmenting a series of medical images: 1) Three dimensional (3-D) approaches which use 3-D information provided by volumetric data constructed by integration of image slices; [2] 2) Slice-by-slice (or iterative 2-D) approaches which perform segmentation on a single image but use adjacent slice information in some manner [3,4,6]. Although, organs of interest are three-dimensional in nature, the use of first approach (i.e.…”

“…liver, kidneys, spleen etc.) through the image series [3]. These organs have small size in the initial slices where they begin to appear, slightly expand in the successive ones and finally disappear with a gradual decrease in size o appearance [4].…”