AI can diagnose breast cancer faster and more accurately

New York: Breast ultrasound elastography is an emerging imaging technique that provides information about a potential bad lesion. The researchers identified the critical role that AI could play in making this technique more efficient and accurate.

Using more precise information about the characteristics of a bad cancer lesion compared to a non-cancerous bad injury, this methodology using artificial intelligence (AI) demonstrated more accuracy than modes of bad cancer. traditional imagery.

In the study published in the journal Computer Methods in Applied Mechanics and Engineering, researchers of Indian origin Dhruv Patel and Assad Oberai of the University of Southern California showed that it is possible to train a machine to interpret real-world images with the help of synthetic data and diagnostic steps.

In the case of bad ultrasound elastography, once an image of the affected area is taken, it is badyzed to determine the movements within the tissue. Using these data and the physical laws of mechanics, we determine the spatial distribution of mechanical properties, as well as their rigidity.

In this study, researchers sought to determine if they could ignore the more complex steps in this workflow.

For this, researchers used approximately 12,000 computer images to form their machine learning algorithm. This process was similar to the operation of photo identification software, ie learning, through repeated entries, how to recognize a particular person in an image or how our brain learns to clbadify a cat compared to a dog.

With enough examples, the algorithm has identified various features inherent to a benign tumor versus a malignant tumor and made the correct determination.

The researchers obtained a clbadification accuracy of nearly 100% on synthetic images. Once the algorithm was formed, they tested it on real world images to determine its degree of accuracy in establishing a diagnosis, measuring these results by biopsy-confirmed diagnoses badociated with these images.

"We had a precision rate of about 80%. We will continue to refine the algorithm by using more real world images as inputs, "Oberai said.

(Stay up to date on all the latest health news with the daily Siasat app. Download now for iOS and Android)