The results of PA analysis obtained by machine learning techniques in the second analysis were combined with the results of the initial examination based on ultrasound images normally used in hospitals. Again, it was confirmed that the malignant thyroid nodules could be distinguished with a sensitivity of 83% and a specificity of 93%.
Going a step further, when the researchers kept the sensitivity at 100% in the third analysis, the specificity reached 55%. This was about three times higher than the specificity of 17.3% (sensitivity of 98%) of the initial examination of thyroid nodules using the conventional ultrasound.
As a result, the probability of correctly diagnosing benign, non-malignant nodules increased more than three times, which shows that overdiagnosis and unnecessary biopsies and repeated tests can be dramatically reduced, and thereby cut down on excessive medical costs.
"This study is significant in that it is the first to acquire photoacoustic images of thyroid nodules and classify malignant nodules using machine learning," remarked Professor Chulhong Kim of POSTECH. "In addition to minimizing unnecessary biopsies in thyroid cancer patients, this technique can also be applied to a variety of other cancers, including breast cancer."
"The ultrasonic device based on photoacoustic imaging will be helpful in effectively diagnosing thyroid cancer commonly found during health checkups and in reducing the number of biopsies," explained Professor Dong-Jun Lim of Seoul St. Mary's Hospital. "It can be developed into a medical device that can be readily used on thyroid nodule patients."
This research was conducted with the support from the National Research Foundation of Korea, the Key Research Institutes in Universities' Medical Device Innovation Center (MDIC) of the Ministry of Education, the Graduate School of Artificial Intelligence support of the Ministry of Science and ICT, and the BK21 FOUR Project.
Back to HCB News
