Feature Selection for Automatic Tuberculosis Screening in Frontal Chest Radiographs.

To detect pulmonary abnormalities such as Tuberculosis (TB), an automatic analysis and classification of chest radiographs can be used as a reliable alternative to more sophisticated and technologically demanding methods (e.g. culture or sputum smear analysis).

Edge map analysis in chest X-rays for automatic pulmonary abnormality screening.

Purpose: Our particular motivator is the need for screening HIV+ populations in resource-constrained regions for the evidence of tuberculosis, using posteroanterior chest radiographs (CXRs).

Method: The proposed method is motivated by the observation that abnormal CXRs tend to exhibit corrupted and/or deformed thoracic edge maps. We study histograms of thoracic edges for all possible orientations of gradients in the range [Formula: see text] at different numbers of bins and different pyramid levels, using five different regions-of-interest selection.

Combination of texture and shape features to detect pulmonary abnormalities in digital chest X-rays.

Purpose: To improve detection of pulmonary and pleural abnormalities caused by pneumonia or tuberculosis (TB) in digital chest X-rays (CXRs).

Methods: A method was developed and tested by combining shape and texture features to classify CXRs into two categories: TB and non-TB cases. Based on observation that radiologist interpretation is typically comparative: between left and right lung fields, the algorithm uses shape features to describe the overall geometrical characteristics of the lung fields and texture features to represent image characteristics inside them.

Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition.

For training supervised classifiers to recognize different patterns, large data collections with accurate labels are necessary. In this paper, we propose a generic, semi-automatic labeling technique for large handwritten character collections. In order to speed up the creation of a large scale ground truth, the method combines unsupervised clustering and minimal expert knowledge.