Improving Performance of Computer-aided Detection Scheme by Combining Results From Two Machine Learning Classifiers

Abstract

Rationale and Objectives-Global data and local instance based machine learning methods and classifiers have been widely used to optimize computer-aided detection (CAD) schemes to classify between true-positive and false-positive detections. In this study the authors investigated the correlation between these two types of classifiers using a new independent testing dataset and assessed the potential improvement of a CAD scheme performance by combining the results of the two classifiers in detecting breast masses.Materials and Methods-The CAD scheme first used image filtering and a multi-layer topographic region growth algorithm to detect and segment suspicious mass regions. The scheme then used an image feature based classifier to classify these regions into true-positive and falsepositive regions. Two classifiers were used in this study. One was a global data based machine learning classifier, an artificial neural network (ANN), and the other one was a local instance based machine learning classifier, a k-nearest neighbor (KNN) algorithm. An independent image database involving 400 mammography examinations was used in this study. Among them, 200 were cancer cases and 200 were negative cases. The pre-optimized CAD scheme was applied twice to the database using the two different classifiers. The correlation between the two sets of classification results was analyzed. Three sets of CAD performances using the ANN, KNN, and average detection scores from both classifiers were assessed and compared using the free-response receiver operating characteristics (FROC) method. Results-The results showed that the ANN achieved higher performance than the KNN with a normalized area under the performance curve (AUC) of 0.891 versus 0.845. The correlation coefficients between the detection scores generated by the two classifiers were 0.436 and 0.161 for the true-positive and false-positive detections, respectively. The average detection scores of the two classifiers improved CAD performance and reliability by increasing AUC to 0.912 and reducing the standard error of the estimated AUC by 14.4%. The detection sensitivity was also increased from 75.8% (ANN) and 65.9% (KNN) to 80.3% at the false-positive detection rate of 0.3 per image.Conclusions-The study demonstrates that the global and local data based machine learning classifiers (ANN and KNN) generate low correlated detection results and combining the detection scores of these two classifiers can significantly improve overall CAD performance (p < 0.01) and reduce standard error in CAD performance assessment.

Multisource Data Fusion Framework for Land Use/Land Cover Classification Using Machine Vision

“…In the fourth step, these 30 texture features are combined with 5 multispectral datasets and a fused dataset is developed with the combination of two different sources of data [18]. Table 1 describes the optimized texture feature dataset while Table 2 describes the multispectral feature dataset.…”

A Feature Selection Method Base on GA for CBIR Mammography CAD

“…At present, those algorithms for masses segmentation can be divided into region based and edge based two main categories [17]. The typical approaches of the first kind are a multilayer topographic region-growing algorithm which proposed by Park et al [18]. In the edge-based methods, active-contour models [19] and dynamic programming techniques [17] have been used to mass segmentation.…”

“…Mass segmentation, which extract the mass contour from the lesion surrounding tissues and its results substantially affects the accuracy of subsequent computed image features (i.e., mass region size, the effective radius of the mass), is one of the most important steps in the computerized analysis of mammograms [14]. Over the past decades, many researchers have been interested in it and a number of groups have developed algorithms for automated segmentation of breast masses [17][18][19]. Despite of great research efforts, since the breast masses are usually embedded and hidden in varying densities of parenchyma structures, accurately segmenting the targeted suspicious remains a difficult task.…”

Discovering Mammography-based Machine Learning Classifiers for Breast Cancer Diagnosis

“…Machine Learning Classifier (MLC) approaches have been reported in the past few years for mammography images analysis and classification with different degrees of success [6,7,19,[21][22][23][24][25][26][27][28][29][30] (see discussion in Section 3). In this work we consider SVM and ANN based MLC.…”