![ge networx software ge networx software](http://www.increa.com/reverse/nx-8e/P003-cable.jpg)
Lee et al ( 15) proposed an automated detection of the tip locations of peripherally inserted central catheters using convolutional neural networks. Hwang et al ( 13) and Lakhani and Sundaram ( 14) sequentially reported that deep learning with DCNNs can classify digital chest radiographs with tuberculosis with an area under the receiver operating characteristic curve of 0.99 (95% confidence interval : 0.96, 1.00). DCNNs have shown promising results for chest radiograph interpretation.
![ge networx software ge networx software](http://static.interlogix.com/products/112024_NetworX.jpg)
Recently there have been improvements in image classification achieved by machine-learning methods, which includes the implementation of deep convolutional neural networks (DCNNs) ( 12).
Ge networx software software#
Xu et al ( 11) reported that most of false-positives generated by their CAD software were easily recognized as a normal anatomic structure and would therefore be easily dismissed by radiologists. However, the cancer-detection rate was not substantially improved because they were unable to sufficiently differentiate true-positive markings from false-positive markings. de Hoop et al ( 10) showed that the sensitivity of their CAD in 2010 was comparable to that of expert radiologists in detecting lung cancers. In 2004, Kakeda et al ( 9) tested their CAD and reported that it was beneficial in analyzing radiographs with nodules but had an average false-positive rate of 3.15 per image. To improve the efficacy of chest radiography for nodule detection, computer-aided detection (CAD) software has been developed and evaluated. Lesion characteristics including size, density, and location make the detection of lung nodules more challenging on chest radiographs ( 6– 8). This oversight can be due to a lack of perception of the nodule, the decision to ignore a subtle density, and the satisfaction of search when another abnormality is identified ( 3– 5). Misdiagnoses of lung cancer can occur for many reasons. Some authors showed that up to 90% of “missed” lung cancer nodules can be found when the baseline chest radiograph is re-reviewed with the benefit of the follow-up examination showing the mass that has grown in size ( 2). Chest radiography is the most common radiologic examination, despite its inferiority to low-dose CT, for lung cancer screening ( 1).