A new deep learning-based process can enhance the quality of medical images and improve clinical diagnoses and the quality of patient care.

The technique, known as “image fusion,” automatically detects information contained across a number of scans and combines them to produce a single high-quality image, researchers explained in the June issue of the International Journal of Cognitive Computing in Engineering.

“We have achieved state-of-the-art performance in terms of both visual quality and quantitative evaluation metrics,” Yi Li, with Qingdao University’s College of Data Science and Software Engineering in Qingdao, China, explained May 16.

The group was able to apply the process to MRI, CT, and SPECT images. Li and co-authors said they used successful fusion results to build an image training database, which was then harnessed to fuse medical images in batches.

The fused images, they noted, appear more natural, have sharper edges and higher resolutions.

“Experimental results indicate that the proposed method achieves state-of-the-art performance in terms of both visual quality and quantitative evaluation metrics.”

Read much more from the authors, including a highly technical breakdown of their process here.