Artificial intelligence could diagnose breast cancer better than doctors

0
25
AI may be better than a pathologist at diagnosing some cancers, UCLA research suggests


Artificial intelligence could diagnose breast cancer better than doctors after being trained to read MRI scans

  • Researchers at UCLA trained its AI system using 240 breast biopsy images
  • Its reading were compared against diagnoses made by 87 pathologists 
  • The machine was on par with doctors on all, but more accurate at deciphering between two types in particular
  • DCIS and atypical hyperplasia look similar but they are very different
  • DCIS requires radiation therapy and hormonal therapy and sometimes a mastectomy
  • Atypical hyperplasia is a precancerous lesion that should be removed but should not be followed by other treatment

A computer could be better than a doctor at diagnosing certain types of cancerous and precancerous breast lesions, new research suggests.  

Researchers at the University of California, Los Angeles, trained an artificial intelligence system using 240 biopsy images, and tested it against 87 pathologists. 

The machine performed more or less as well as doctors at detecting and classifying all of the breast biopsies.

However, it was better at making one crucial distinction: telling the difference between DCIS (ductal carcinoma in situ), a type of cancer, and atypical hyperplasia, a high-risk lesion that has very similar hallmarks but does is not cancerous and does not require the same level of treatment. 

AI may be better than a pathologist at diagnosing some cancers, UCLA research suggests

‘Medical images of breast biopsies contain a great deal of complex data and interpreting them can be very subjective,’ said Dr Joann Elmore, lead author of the study published in the JAMA Network Open journal. 

‘Distinguishing breast atypia from ductal carcinoma in situ (DCIS) is important clinically but very challenging for pathologists. 

‘Sometimes, doctors do not even agree with their previous diagnosis when they are shown the same case a year later.’ 

The first step is the same for both DCIS and atypical hyperplasia: the lesions need to be removed. 

But the next steps differ greatly.  

People diagnosed with DCIS will need a lumpectomy, often followed by radiation therapy or a hormonal therapy like tamoxifen. If the cancer is invasive, it may warrant a mastectomy. 

Atypical hyperplasia, however, is a high risk lesion that affects the breast, signaling a risk of breast cancer. Doctors would recommend removing the cells but that would be it.

Dr Marilin Rosa, a pathologist at Moffitt Cancer Center who was not involved in the study, told DailyMail.com the current methods for telling the difference between the two are imperfect. 

‘The man issue for us is distinguishing between atypical hyperplasia and low-grade DCIS. Atypical hyperplasia has been defined as an entity that has some but not all of the fissures of DCIS,’ Dr Rosa said. 

‘It looks like low-grade DCIS but it’s not.’

To tell them apart, doctors measure the lesion. If it is less than 2mm, it is deemed atypical hyperplasia. If it is more, it is deemed DCIS. 

It seems to work most of the time, but it is imprecise. 

‘The problem is you create a sampling issue with the biopsy. You only have one millimeter of the lesion, and you don’t know what is left behind,’ Dr Rosa said. 

‘You don’t want to give treatment to someone who does not need it,’ she added.

That is why Dr Elmore, professor at the University of California, Los Angeles, found the results to be so encouraging. 

‘It is critical to get a correct diagnosis from the beginning so that we can guide patients to the most effective treatments.’ 

With further improvements, researchers hope AI could be a vital tool in aiding pathologists, and are looking at how it could be used to diagnose melanoma next.  



Source link

LEAVE A REPLY

Please enter your comment!
Please enter your name here