CAD system makes breast MRI more effective, efficient

A computer-aided detection (CAD) system is helping radiologists to more quickly and accurately determine the sizes and locations of cancers found on breast MRI—information that could change patients’ treatment, a new study shows.

The study, undertaken at Clinica Girona in Girona, Spain, compared the CAD system to breast imaging software that comes standard with MRI machines, said Joan C. Vilanova, MD, director of the department of magnetic resonance and lead author of the study. Thirty-six patients with known breast cancer underwent an MRI examination using the standard software and the CAD system.

The CAD system in conjunction with the MRI examination allowed the radiologist to more accurately determine the size of the cancer lesions, Dr. Vilanova said; the size correlated more closely to what was seen under the microscope, he added. “The quality of the final (postprocessed) CAD system images was better than the standard software images in 83% of the cases,” said Dr. Vilanova. In addition, it took radiologists an average 12 minutes to analyze and interpret the CAD system images compared to 19 minutes for the standard MRI software images. A breast MRI study generates more than 1,000 images per examination, according to Dr. Vilanova.

Both systems detected additional lesions in 10 patients; eight of those patients were scheduled to undergo a lumpectomy before the MRI examination was done; their treatment was changed to a mastectomy. “Cancerous lesions would have been left within the breast if breast MRI had not been performed,” Dr. Vilanova said.

“The CAD system has allowed us and our clinicians to have more confidence in our ability to evaluate breast MRI,” Dr. Vilanova said. “In fact, the number of breast MRI examinations has increased by 50% in the last nine months,” he added.

The study was presented at the American Roentgen Ray Society Annual Meeting in New Orleans, LA.

Comments

The opinions expressed here are the views of the writer and do not necessarily reflect the views and opinions of News Medical.
Post a new comment
Post

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.

You might also like...
Study shows AI can predict prognosis in triple-negative breast cancer