A research team led by Prof. LI Hai from Hefei Institutes of Physical Science, Chinese Academy of Sciences, has developed an explainable artificial intelligence (AI) approach to assess the risk of central lymph node metastasis in patients with papillary thyroid carcinoma (PTC) before surgery.
By combining information from different types of ultrasound images with clinical data, the approach not only estimates the risk of lymph node metastasis but also shows the imaging features behind its prediction, helping radiologists better understand the results.
The study was published in Journal of Imaging Informatics in Medicine.
PTC is the most common type of thyroid cancer and generally has a favorable prognosis. However, it can spread to nearby lymph nodes, making early assessment important for treatment planning. Because central lymph nodes can be difficult to detect with conventional ultrasound, the researchers combined information from different ultrasound techniques with clinical data to improve preoperative prediction.
In this study, the team analyzed ultrasound images and clinical information from 428 patients with 508 PTC nodules at four hospitals. The resulting machine-learning model showed good performance in an independent external test, achieving an AUC of 0.844.
Unlike models that provide only a risk score, the new approach also identifies the imaging features that contribute to each prediction, allowing radiologists to review the evidence behind the AI assessment.
The researchers further tested the system with six radiologists of different experience levels. With the support of explainable AI, the radiologists achieved higher diagnostic accuracy and showed greater agreement in their assessments.
"The value of medical AI lies not only in predicting risk, but also in making the evidence behind each prediction visible and open to clinical scrutiny," said Prof. LI Hai. "By connecting multimodal imaging with radiologists' expertise, explainable AI can support more transparent and collaborative clinical decision-making."
Clinical validation workflow for the explainable AI system combining multimodal ultrasound to predict central lymph node metastasis in papillary thyroid carcinoma (Image by WANG Tengfei)
