Researchers at Pohang University of Science and Technology in South Korea report that they have developed a technique for the minimally invasive diagnosis of thyroid cancer. The method combines multispectral photoacoustic imaging and machine learning, and is conceived as a substitute for invasive and occasionally inaccurate fine-needle aspiration biopsies. The new technique involves analyzing the unique photoacoustic signatures of malignant thyroid nodules and then training the system to recognize them.
The vast majority of thyroid nodules are benign, but since they are not between 5 and 10%, it is recommended that they be checked. Doctors currently use a fine needle to get a biopsy of the nodule. This is invasive and will need to be repeated in approximately 20% of cases, as the results are unreliable.
Alternatively, these researchers have developed a non-invasive technique, based on the photoacoustic effect, where light absorbed by a sample produces sound waves. The researchers developed their system based on the premise that oxygen saturation in malignant thyroid nodules is lower than in benign nodules and that photoacoustic imaging could help detect these differences non-invasively.
In practice, this would mean illuminating a patient’s thyroid nodule using a laser and then recording the resulting ultrasound signal. The researchers analyzed these data from patients with malignant and benign thyroid nodules using machine learning. This led them to be able to train their system to identify malignant nodules.
To date, they have been able to detect malignant nodules with a reasonable level of accuracy, with a sensitivity of 83% and a specificity of 93%, when combining the machine learning approach with conventional ultrasound assessments.
“This study is significant as it is the first to acquire photoacoustic images of thyroid nodules and classify malignant nodules through machine learning,” Chulhong Kim, a researcher involved in the study, said in a Pohang press release. “In addition to minimizing unnecessary biopsies in patients with thyroid cancer, this technique can also be applied to other cancers, including breast cancer.”
“The ultrasound device based on photoacoustic imaging will be useful to effectively diagnose thyroid cancer that is commonly found during health checkups and to reduce the number of biopsies,” added Dong-Jun Lim, another researcher involved in the project. “It can be turned into a medical device that can be easily used in patients with thyroid nodules.”
Study the magazine Cancer research: Multiparametric photoacoustic analysis of human thyroid cancers Live