Algorithm fusion to improve detection of lung cancer on chest radiographs

Abstract

Purpose -The purpose of this paper is to show an efficient method for the detection of signs of early lung cancer. Various image processing algorithms are presented for different types of lesions, and a scheme is proposed for the combination of results. Design/methodology/approach -A computer aided detection (CAD) scheme was developed for detection of lung cancer. It enables different lesion enhancer algorithms, sensitive to specific lesion subtypes, to be used simultaneously. Three image processing algorithms are presented for the detection of small nodules, large ones, and infiltrated areas. The outputs are merged, the false detection rate is reduced with four separated support vector machine (SVM) classifiers. The classifier input comes from a feature selection algorithm selecting from various textural and geometric features. A total of 761 images were used for testing, including the database of the Japanese Society of Radiological Technology (JSRT). Findings -The fusion of algorithms reduced false positives on average by 0.6 per image, while the sensitivity remained 80%. On the JSRT database the system managed to find 60.2% of lesions at an average of 2.0 false positives per image. The effect of using different result evaluation criteria was tested and a difference as high as 4 percentage points in sensitivity was measured. The system was compared to other published methods.Originality/value -This study proves the usefulness of lesion enhancement decomposition, while proposing a scheme for the fusion of algorithms. Furthermore, a new algorithm is introduced for the detection of infiltrated areas, possible signs of lung cancer, neglected by previous solutions. * Marczibányi tér 5.,

Artificial intelligence for closed-loop ventilation therapy with hemodynamic control using the open lung concept

“…• diagnostic system of pigmented skin lesions (Korotkov and Garcia, 2012); • medical imaging system for myocardial perfusion (Ohlsson, 2004) or for lung cancer detection (Orbán and Horváth, 2012); • laboratory information system for pulmonary function tests (Snow et al, 1988); • machine learning system for interpreting ECG signals (Bratko et al, 1989); and • medical expert system such as "MYCIN" in diagnosing patients with infectious blood caused by bacteremia or meningitis (Buchanan and Shortliffe, 1984).…”

Digital chest tomosynthesis: The main steps to a computer assisted lung diagnostic system

“…Computer aided detection (CADe) of lung nodules is an extensively studied field both for CXR [4] and CT [5]. Although there are many CADs for CXR, as the sensitivity of a CXR is relatively low, the importance of adding CAD functionality to a CXR system is questionable.…”

An X-ray CAD system with ribcage suppression for improved detection of lung lesions

“…In the sequel we give a brief description of these methods, while a more detailed presentation can be found in [13].…”

“…Keeping negative samples only from healthy images improved classifier performance on independent test data. Exact thresholds used for training data generation are described in [13]. As 30 times more negative samples were available than positive ones, we used a cost-sensitive version of the SVM.…”

“…Only a few of the recently published ones are [6][7][8][9][10][11][12]. A brief description of them can be found in [13]. The most important problem of existing CADe systems is the low positive predictive value.…”