Machine Learning Assisted Doppler Features for Enhancing Thyroid Cancer Diagnosis: A Multi-cohort Study

AlZoubi, Alaa and Zhu, Yi-Cheng and Du, Hongbo and Jiang, Quan and zhang, Tao and Huang, Xu-Juan and Zang, Yuan and Shi, Xiu-Rong and Shan, Jun (2021) Machine Learning Assisted Doppler Features for Enhancing Thyroid Cancer Diagnosis: A Multi-cohort Study. Journal of Ultrasound in Medicine. ISSN 1550-9613

Preview

Text AlZoubi.pdf - Accepted Version Download (781kB) | Preview

Abstract

Background: This pilot study aims at exploiting machine learning techniques to extract colour Doppler Ultrasound (CDUS) features and to build an artificial neural network (ANN) model based on these CDUS features for improving the diagnostic performance of thyroid cancer classification. Methods: A total of 674 patients with 712 thyroid nodules (TNs) (512 from in-ternal dataset and 200 from external dataset) were randomly selected in this retrospective study. We used ANN to build a model (TDUS-Net) for classifying malignant and benign TNs using both the automatically extracted quantitative CDUS features (whole ratio, intranodular ratio, peripheral ratio, and number of vessels) and grey-scale Ultrasound (US) features defined by the ACR Thyroid Imaging Reporting and Data System (TI-RADS). Then, we compared the diagnostic performance of the model, the performance of another ANN model based on the grey-scale US features alone (TUS-Net), and that of radiologists. Results: The TDUS-Net (0.898, 95%CI: 0.868-0.922) achieved a higher area under the curve (AUC) than that of TUS-Net (0.881, 95%CI: 0.850-0.908) in the internal tests. Compared with radiologists, TDUS-Net (AUC: 0.925, 95% CI: 0.880-0.958) performed better than radiologists (AUC: 0.810, 95% CI: 0.749-0.862) in the external tests. Conclusions: Applying a machine learning model by combining both gray-scale US features and CDUS features can achieve comparable or even higher performance than radiologists in classifying thyroid nodules.

Actions (login required)

View Item