Convolutional Neural Network Architectures to Solve a Problem of Tuberculosis Classification Using X-Ray Images of the Lungs

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Images</td><td class="align_center">Correct detection for the chest cage</td><td class="align_center">Correct detection for the spine</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">With pneumonia (500 images)</td><td class="align_center">100%</td><td class="align_center">75.2% (376 images)</td></tr><tr><td class="align_left">Without pneumonia (500 images)</td><td class="align_center">100%</td><td class="align_center">88.8% (444 images)</td></tr><tr><td class="align_left">Overall correct percentage of 1000 images</td><td class="align_center">100%</td><td class="align_center">82% (820 images)</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Results of the detection of the thorax and spine in 1000 images using MobileNet 1.0.</div>

Journal of Nanomaterials

tab3

Table 3

Table 3: Convolutional Neural Network Architectures to Solve a Problem of Tuberculosis Classification Using X-Ray Images of the Lungs 