The aim of this study was to evaluate the diagnostic efficacy of computer aided diagnostic tool for neck masses using machine learning and deep learning techniques on clinical information and radiological images in children.

This study is a retrospective-prospective design by West China Hospital, Sichuan University, including clinical data and radiological images. A retrospective database was enrolled for patients with definite histological diagnosis and available radiological images from June 2010 and December 2020. The investigators have constructed deep learning and machine learning diagnostic models on this retrospective cohort and validated it internally. A prospective cohort would recruit patients found neck masses since January 2021. The proposed computer aided diagnostic models would also be validated in this prospective cohort externally. The aim of this study was to evaluate the diagnostic efficacy of computer aided diagnostic tool for neck masses using machine learning and deep learning techniques on clinical data and radiological images in children.

Inclusion Criteria:

• Age up to 18 years old
• Receiving no treatment before diagnosis
• With written informed consent

Exclusion Criteria:

• Clinical data missing
• Unavailable radiological images
• Without written informed consent

Patients who were found neck masses, and had completed clinical information and radiological images before operation, biopsy, neoadjuvant chemotherapy, and radiotherapy.