An artificial intelligence (AI) model that uses both lateral and frontal chest x-ray views performs better for classifying adenopathy, said researchers from Johns Hopkins University at the Conference on Machine Intelligence in Medical Imaging on September 20, 2021, wrote Ridley.

“This is actually analogous to the common practice of radiologists who use both projections — frontal and lateral — to glean synergistic diagnostic details,” said presenter Ishan Mazumdar, a second-year medical student, quoted Ridley.

Though promising, Ridley noted that Mazumdar acknowledged, “…the ground truth for adenopathy is difficult to establish and subject to interobserver variability, and the optimal method of combining frontal and lateral chest x-rays isn’t yet known, he said.” The next phase of work will explore different deep-learning methods for generating combined frontal and lateral predictions, according to Ridley.

Source:

Ridley, Erik. In chest x-ray AI, two views are better than one. AuntMinnie.com September 21, 2021. Accessed September 27, 2021, at https://www.auntminnie.com/index.aspx?sec=sup&sub=aic&pag=dis&ItemID=133539