Tumor cell identification using features rules

Abstract

Advances in imaging techniques have led to large repositories of images. There is an increasing demand for automated systems that can analy ze complex medical images and extract meaningful information for mining patterns. Here, we describe a real-life image mining application to the problem of tumour cell counting. The quantitative analysis of tumour cells is fundamental to characterizing the activity of tumour cells. Existing approaches are mostly manual, time-consuming and subjective. Efforts to automate the process of cell counting have largely focused on using image processing techniques only. Our studies indicate that image processing alone is unable to give accurate results. In this paper, we examine the use of extracted features rules to aid in the process of tumor cell counting. We propose a robust local adaptive thresholding and dynamic water immersion algorithms to segment regions of interesting from background. Meaningful features are then extracted from the segmented regions. A number of base classifiers are built to generate features rules to help identify the tumor cell. Two voting strategies are implemented to combine the base classifiers into a meta-classifier. Experiment results indicate that this process of using extracted features rules to help identify tumor cell leads to better accuracy than pure image processing techniques alone.

Incorporating Domain Knowledge into Medical Image Mining

“…Direct application of water immersion method to the digitized medical images typically produces over-segmentation of the trivial regions. Instead, we propose a progressive water immersion algorithm with guidance of domain knowledge to cope with this situation [34]. Details of the algorithm follow.…”

Incorporating Domain Knowledge into Medical Image Mining

“…Direct application of water immersion method to the digitized medical images typically produces over-segmentation of the trivial regions. Instead, we propose a progressive water immersion algorithm with guidance of domain knowledge to cope with this situation [34]. Details of the algorithm follow.…”

Mining viewpoint patterns in image databases

“…Existing works adapted data mining algorithms such as association rule mining [10] [13], clustering [2] and classification techniques [3] [11] to generate patterns based on pixel level or object level features. While these approaches can discover hidden relationships among appearance features in t he images, they ignore the patterns relating to the spatial properties of objects in the images.…”

<title>Automatic identification of medical structures</title>

“…In spite of the difficulties there are some new developments in the field of medical image identification. Researchers have been working in several fields of application, such as: visualization and surgical planning 1-3 , planning radiotherapy procedures 4 , tumor identification, malformation and disfunctions [5][6][7][8][9][10][11][12] ; organ, tissue and cell classification [13][14][15] of images based on image content similarity (CBIR) systems 19 . All these works aim at the solution of a specific problem of the medical domain and contribute to the field of identification.…”

Incorporating Domain Knowledge into Medical Image Mining

“…Direct application of water immersion method to the digitized medical images typically produces over-segmentation of the trivial regions. Instead, we propose a progressive water immersion algorithm with guidance of domain knowledge to cope with this situation [34]. Details of the algorithm follow.…”

Mining viewpoint patterns in image databases

“…Existing works adapted data mining algorithms such as association rule mining [10] [13], clustering [2] and classification techniques [3] [11] to generate patterns based on pixel level or object level features. While these approaches can discover hidden relationships among appearance features in t he images, they ignore the patterns relating to the spatial properties of objects in the images.…”

<title>Automatic identification of medical structures</title>

“…In spite of the difficulties there are some new developments in the field of medical image identification. Researchers have been working in several fields of application, such as: visualization and surgical planning 1-3 , planning radiotherapy procedures 4 , tumor identification, malformation and disfunctions [5][6][7][8][9][10][11][12] ; organ, tissue and cell classification [13][14][15] of images based on image content similarity (CBIR) systems 19 . All these works aim at the solution of a specific problem of the medical domain and contribute to the field of identification.…”

Incorporating Domain Knowledge into Medical Image Mining

“…Direct application of water immersion method to the digitized medical images typically produces over-segmentation of the trivial regions. Instead, we propose a progressive water immersion algorithm with guidance of domain knowledge to cope with this situation [34]. Details of the algorithm follow.…”

Mining viewpoint patterns in image databases

“…Existing works adapted data mining algorithms such as association rule mining [10] [13], clustering [2] and classification techniques [3] [11] to generate patterns based on pixel level or object level features. While these approaches can discover hidden relationships among appearance features in t he images, they ignore the patterns relating to the spatial properties of objects in the images.…”

<title>Automatic identification of medical structures</title>

“…In spite of the difficulties there are some new developments in the field of medical image identification. Researchers have been working in several fields of application, such as: visualization and surgical planning 1-3 , planning radiotherapy procedures 4 , tumor identification, malformation and disfunctions [5][6][7][8][9][10][11][12] ; organ, tissue and cell classification [13][14][15] of images based on image content similarity (CBIR) systems 19 . All these works aim at the solution of a specific problem of the medical domain and contribute to the field of identification.…”