Initial experience of a deep learning application for the differentiation of Kikuchi-Fujimoto’s disease from tuberculous lymphadenitis on neck CECT

Abstract

Neck contrast-enhanced CT (CECT) is a routine tool used to evaluate patients with cervical lymphadenopathy. This study aimed to evaluate the ability of convolutional neural networks (CNNs) to classify Kikuchi-Fujimoto’s disease (KD) and cervical tuberculous lymphadenitis (CTL) on neck CECT in patients with benign cervical lymphadenopathy. A retrospective analysis of consecutive patients with biopsy-confirmed KD and CTL in a single center, from January 2012 to June 2020 was performed. This study included 198 patients of whom 125 patients (mean age, 25.1 years ± 8.7, 31 men) had KD and 73 patients (mean age, 41.0 years ± 16.8, 34 men) had CTL. A neuroradiologist manually labelled the enlarged lymph nodes on the CECT images. Using these labels as the reference standard, a CNN was developed to classify the findings as KD or CTL. The CT images were divided into training (70%), validation (10%), and test (20%) subsets. The Cut&Remain method was applied to improve performance. For the test set, the best area under the receiver operating characteristic curve for classifying KD from CTL was 0.91. Our findings show that the differentiation of KD from CTL on neck CECT using a CNN is feasible with high diagnostic performance.