Abstract
Non-invasive assessment of the risk of lymph node metastasis (LNM) in patients with papillary thyroid carcinoma (PTC) is of great value for the treatment option selection. The purpose of this paper is to develop a transfer learning radiomics (TLR) model for preoperative prediction of LNM in PTC patients in a multicenter, cross-machine, multi-operator scenario. Here we report the TLR model produces a stable LNM prediction. In the experiments of cross-validation and independent testing of the main cohort according to diagnostic time, machine, and operator, the TLR achieves an average area under the curve (AUC) of 0.90. In the other two independent cohorts, TLR also achieves 0.93 AUC, and this performance is statistically better than the other three methods according to Delong test. Decision curve analysis also proves that the TLR model brings more benefit to PTC patients than other methods.
Highlights
Non-invasive assessment of the risk of lymph node metastasis (LNM) in patients with papillary thyroid carcinoma (PTC) is of great value for the treatment option selection
The potential risk of LNM of PTC has led to a large number of PTC patients received treatment such as total thyroidectomy and lymph node dissection (LND), resulting in widespread overtreatment[10]
PTC is generally an indolent tumor, LNM will occur in an early stage
Summary
Non-invasive assessment of the risk of lymph node metastasis (LNM) in patients with papillary thyroid carcinoma (PTC) is of great value for the treatment option selection. In the experiments of cross-validation and independent testing of the main cohort according to diagnostic time, machine, and operator, the TLR achieves an average area under the curve (AUC) of 0.90. The incidence of thyroid cancer has continued to increase in many countries since the 1980s This is mainly due to the increase of the papillary thyroid carcinoma (PTC) detection rate through the improvement in detection and diagnosis[2]. Radiomics-based methods were proposed for LNM prediction in PTC patients by converting ultrasound images into mineable data[21,22]. Whether based on clinical statistics or radiomics, since the completeness of the extracted image features is difficult to guarantee, the LNM prediction performance was not ideal with the area under the receiver operating characteristic (ROC) curve (AUC) on independent testing set approximately ranged from 0.67 to 0.78
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
