Automatic Segmentation of Lung Fields in Chest Radiographs

Abstract

Abstract. We present algorithms for the automatic delineation of lung fields in chest radiographs. We first develop a rule-based scheme that detects lung contours using a general framework for the detection of oriented edges and ridges. This algorithm is compared to several pixel classifiers using different combinations of features. We propose a hybrid system that combines both approaches. The performance of each system is compared with interobserver variability and results available from the literature. Our hybrid scheme turns out to be accurate and robust; the accuracy is 0.969 ± 0.00803, and above 94% for all 115 test images.

Computer aided diagnosis in chest radiography

“…Vittitoe et al [250,251] developed a pixel classifier for the identification of lung regions using Markov random field modeling. Van Ginneken and ter Haar Romeny proposed a hybrid method that combines a rule-based scheme with a pixel classifier [84,Chapter 3].…”

“…A rule-based scheme is a sequence of steps, tests and rules. Most algorithms for the segmentation of lung fields fall in this category [198,269,270,65,4,6,7,32,82,84]. Techniques employed are (local) thresholding, region growing, edge detection, ridge detection, morphologi-RB PC PA / lateral evaluation remarks Toriwaki [233,232] × PA none describes a complete analysis system Harlow [102] × PA none Chien [37,38] × PA none only right lung, result used to detect abnormalities Hasegawa [103] × PA none Pietka [198] × PA none McNitt-Gray [179,178] × PA 16 Q uses 5 anatomical classes Duryea [65] × PA 802 Q Xu [269] × PA 1000 R outer rib cage only Xu [270] × PA 300 R diaphragm edges only Armato [7] × PA 600 R costophrenic angles only Armato [4] × lateral 200 Q Armato [6] × PA 600 R Carrascal [32] × both 65 RQ Vittitoe [250] × PA 99 Q Tsujii [235] × PA 71 Q Wilson, Brown [265,28] × PA none describes a complete analysis system Vittitoe [251] × PA 115 Q uses 6 anatomical classes Van Ginneken [82,84] (Chapter 3)…”

“…Although this may seem to be a restriction of the applicability of the method, in practice a computerized analysis of a chest image will usually segment the lung fields before attempting to delineate the ribs. In this paper, we used the lung fields segmented by the method described in Chapter 3 and in [82,84].…”

A computer-aided diagnosis approach for emphysema recognition in chest radiography

“…They include rule-based schemes [11][12][13][14][15][16], methods based on pixel classification [17][18][19][20], hybrid approaches [21], active shape models (ASM) and active appearance models (AAM) [22][23][24]. A comparison of several segmentation methods is provided by van Ginneken et al [23] using the images form JSRT dataset [25].…”

Lung Segmentation on Postero-anterior Digital Chest Radiographs Using Active Contours

“…Tsujii et al [14] classified the pixels of the DR using an adaptative-sized hybrid neural network. Van Ginneken et al [15] developed and compared several segmentation techniques: a matching approach, pixel classifiers based on several combinations of features, a rule-based scheme that detects lung contours using a general framework for the detection of oriented edges and ridges in images, and a hybrid scheme. Later, an active shape model was used by van Ginneken et al [16] to obtain the segmentation.…”