AI Model May Aid in Screening, Staging, and Treatment Planning for Thyroid Cancer

Get Permission

A new study has found that an artificial intelligence (AI) model incorporating multiple methods of machine learning accurately detects thyroid cancer and predicts pathological and genomic outcomes through analysis of routine ultrasound images. The AI model could present a low-cost, noninvasive option for screening, staging, and personalized treatment planning for the disease. Findings from the study were presented by Chan et al at the 2022 Multidisciplinary Head and Neck Cancers Symposium (Abstract 10).

"Thyroid cancer is one of the most rapidly increasing cancers in the United States, largely due to increased detection and improved diagnostics. We have developed an AI platform that would examine ultrasound images and predict with high accuracy whether a potentially problematic thyroid nodule is, in fact, cancerous. If it is cancerous, we can further predict the tumor stage, the nodal stage, and the presence or absence of BRAF mutation," said senior author Annie Chan, MD, Director of the Head and Neck Radiation Oncology Research Program at the Massachusetts General Cancer Center. "If caught early, this disease is highly treatable, and patients generally can expect to live a long time after treatment."

Creation and Performance of the Platform

To train and validate the AI platform, researchers obtained 1,346 thyroid nodule images through routine diagnostic ultrasound from 784 patients. The ultrasound images were divided into two datasets: one for internal training and validation and one for external validation. Malignancy was confirmed with samples obtained from fine-needle biopsy. Pathological staging and mutational status were confirmed with operative reports and genomic sequencing, respectively.

Unlike the conventional AI approach, researchers combined multiple AI methods for the model, including radiomics, which extracts a large number of quantitative features from the images; topologic data analysis (TDA), which assesses the spatial relationship between data points in the images; deep learning, where algorithms run the data through multiple layers of an AI neural network to generate predictions; and machine learning (ML), in which an algorithm utilizes Thyroid Imaging Reporting and Data System (TI-RADS)-defined ultrasound properties as machine learning features.

“By integrating different AI methods, we were able to capture more data while minimizing noise. This allows us to achieve a high level of accuracy in making predictions,” said Dr. Chan.

A multimodal platform utilizing these four methods accurately predicted 98.7% of thyroid nodule malignancies in the internal dataset, significantly outperforming individual AI modalities used alone. By comparison, the individual radiomics model predicted 89% of malignancies (P < .001 compared to the multimodal platform), the deep-learning model achieved 87% accuracy (P = .002), and TDA and (ML)TI-RADS were accurate for 81% and 80% of the samples, respectively (both P < .001). On the external validation dataset, the model was 93% accurate for malignancy prediction.

A multimodal model comprising radiomics, TDA and (ML)TI-RADS also was able to distinguish pathological stage (93% accuracy for T stage, 89% for N stage, and 98% for extrathyroidal extension). Additionally, the model identified BRAF V600E mutation with 96% accuracy.

Disclosure: For full disclosures of the study authors, visit

The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.