Thyroid Cancer Now Diagnosed Using AI Photoacoustic / Ultrasound Imaging


[ad_1]

A schematic diagram of the acquisition of the photoacoustic signal generated when laser light is irradiated to a malignant thyroid nodule with an ultrasonic sensor. Credit: POSTECH

A lump in the thyroid gland is called a thyroid nodule, and 5-10% of all thyroid nodules are diagnosed as thyroid cancer. Thyroid cancer has a good prognosis, a high survival rate, and a low recurrence rate, so early diagnosis and treatment is crucial. Recently, a joint research team in Korea proposed a new, non-invasive method to distinguish thyroid nodules from cancer by combining photoacoustic (PA) and ultrasound imaging technology with artificial intelligence.

Joint research team, consisting of Professor Chulhong Kim and Dr Byullee Park from POSTECH Electrical Engineering Department, Convergence Computer Engineering Department and Mechanical Engineering Department, Professor Dong-Jun Lim and Professor Jeonghoon Ha from Seoul Catholic Hospital St. Mary Korea University and Professor Jeesu Kim from Pusan ​​National University conducted research to acquire PA images of patients with malignant and benign nodules and analyzed them with artificial intelligence. In recognition of their importance, the results of this study have been published in Research against cancer.

Currently, the diagnosis of a thyroid nodule is made using a fine needle aspiration biopsy (FNAB) using an ultrasound image. But about 20% of FNABs are inaccurate, leading to repetitive and unnecessary biopsies.

To overcome this problem, the joint research team explored the use of PA imaging to obtain an ultrasound signal generated by light. When light (laser) is irradiated on the patient’s thyroid nodule, an ultrasound signal called the PA signal is generated from the thyroid gland and the nodule. By acquiring and processing this signal, PA images of the gland and the nodule are collected. At this point, if multispectral PA signals are obtained, information about the oxygen saturation of the thyroid gland and thyroid nodule can be calculated.

The researchers focused on the fact that the oxygen saturation of malignant nodules is lower than that of normal nodules and acquired PA images of patients with malignant thyroid nodules (23 patients) and those with benign nodules (29 patients). ). By performing multispectral PA imaging in vivo on the patient’s thyroid nodules, the researchers calculated several parameters, including the level of hemoglobin oxygen saturation in the nodule area. This was analyzed using machine learning techniques to successfully and automatically classify whether the thyroid nodule was malignant or benign. In the initial classification, the sensitivity to classify malignancy as malignant was 78% and the specificity to classify benign as benign was 93%.

The results of the 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 malignant thyroid nodules could be distinguished with a sensitivity of 83% and specificity of 93%.

To take it 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% (98% sensitivity) of the initial thyroid nodule examination using conventional ultrasound.

As a result, the likelihood of correctly diagnosing both benign and non-malignant nodules has increased more than three times, showing that overdiagnosis, unnecessary biopsies and repeated testing can be significantly reduced, thereby reducing 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,” said Professor Chulhong Kim of POSTECH. “In addition to minimizing unnecessary biopsies in patients with thyroid cancer, this technique can also be applied to a variety of other cancers, including breast cancer.”

“The ultrasound machine based on photoacoustic imaging will be useful in effectively diagnosing thyroid cancer commonly encountered during check-ups and in reducing the number of biopsies,” said Professor Dong-Jun Lim of the hospital. St. Mary of Seoul. “It can be developed into a medical device that can be easily used on patients with thyroid nodules.”


Ultrasound guidelines identify children who should be biopsied for thyroid cancer


More information:
Jeesu Kim et al, Multiparametric photoacoustic analysis of human thyroid cancers in vivo, Research against cancer (2021). DOI: 10.1158 / 008-5472.CAN-20-3334

Provided by Pohang University of Science and Technology

Quote: Thyroid cancer now diagnosed with IA photoacoustic / ultrasound imaging (2021, July 9) retrieved July 9, 2021 from https://medicalxpress.com/news/2021-07-thyroid-cancer-ai-photoacousticultrasound-imaging .html

This document is subject to copyright. Other than fair use for private study or research purposes, no part may be reproduced without written permission. The content is provided for information only.

[ad_2]

Comments are closed.